Skip to content

P
Python-100-Days
Commit 43c147da authored by softpo's avatar softpo
Browse files
Options

'pandas使用'

parent aa359771
Hide whitespace changes
Inline Side-by-side
Showing with 10313 additions and 0 deletions
Day76-90/02.Pandas的应用.md
View file @ 43c147da
## Pandas的应用 ## Pandas的应用
### 1、pandas入门
### 2、pandas索引
### 3、pandas数据清洗之空数据
[数据挖掘之空数据处理（有史以来最全面）]: https://blog.csdn.net/Soft_Po/article/details/89302887
### 4、pandas多层索引
### 5、pandas多层索引计算
### 6、pandas数据集成concat
### 7、pandas数据集成merge
### 8、pandas分组聚合操作
### 9、pandas数据集成实战
### 10、美国大选项目
[2012美国大选政治献金项目数据分析（有史以来最全面）]: https://blog.csdn.net/Soft_Po/article/details/89283382
\ No newline at end of file
Day76-90/code/1-pandas入门.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"Math 120\n",
"Python 136\n",
"En 128\n",
"Chinese 99\n",
"dtype: int64"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 创建\n",
"# Series是一维的数据\n",
"s = Series(data = [120,136,128,99],index = ['Math','Python','En','Chinese'])\n",
"s"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(4,)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([120, 136, 128, 99], dtype=int64)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"v = s.values\n",
"v"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"numpy.ndarray"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(v)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"120.75"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.mean()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"136"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.max()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"15.903353943953666"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.std()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"Math 14400\n",
"Python 18496\n",
"En 16384\n",
"Chinese 9801\n",
"dtype: int64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.pow(2)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>a</th>\n",
" <td>113</td>\n",
" <td>116</td>\n",
" <td>75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>b</th>\n",
" <td>19</td>\n",
" <td>145</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>c</th>\n",
" <td>57</td>\n",
" <td>107</td>\n",
" <td>113</td>\n",
" </tr>\n",
" <tr>\n",
" <th>d</th>\n",
" <td>95</td>\n",
" <td>3</td>\n",
" <td>66</td>\n",
" </tr>\n",
" <tr>\n",
" <th>e</th>\n",
" <td>28</td>\n",
" <td>121</td>\n",
" <td>120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>f</th>\n",
" <td>141</td>\n",
" <td>85</td>\n",
" <td>132</td>\n",
" </tr>\n",
" <tr>\n",
" <th>h</th>\n",
" <td>124</td>\n",
" <td>39</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>i</th>\n",
" <td>80</td>\n",
" <td>35</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>j</th>\n",
" <td>68</td>\n",
" <td>99</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>k</th>\n",
" <td>74</td>\n",
" <td>12</td>\n",
" <td>11</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"a 113 116 75\n",
"b 19 145 23\n",
"c 57 107 113\n",
"d 95 3 66\n",
"e 28 121 120\n",
"f 141 85 132\n",
"h 124 39 10\n",
"i 80 35 17\n",
"j 68 99 31\n",
"k 74 12 11"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# DataFrame是二维的数据\n",
"# excel就非诚相似\n",
"# 所有进行数据分析，数据挖掘的工具最基础的结果：行和列，行表示样本，列表示的是属性\n",
"df = DataFrame(data = np.random.randint(0,150,size = (10,3)),index = list('abcdefhijk'),columns=['Python','En','Math'])\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"(10, 3)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[113, 116, 75],\n",
" [ 19, 145, 23],\n",
" [ 57, 107, 113],\n",
" [ 95, 3, 66],\n",
" [ 28, 121, 120],\n",
" [141, 85, 132],\n",
" [124, 39, 10],\n",
" [ 80, 35, 17],\n",
" [ 68, 99, 31],\n",
" [ 74, 12, 11]])"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"v = df.values\n",
"v"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Python 79.9\n",
"En 76.2\n",
"Math 59.8\n",
"dtype: float64"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.mean()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Python 141\n",
"En 145\n",
"Math 132\n",
"dtype: int32"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.max()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>a</th>\n",
" <td>113</td>\n",
" <td>116</td>\n",
" <td>75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>b</th>\n",
" <td>19</td>\n",
" <td>145</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>c</th>\n",
" <td>57</td>\n",
" <td>107</td>\n",
" <td>113</td>\n",
" </tr>\n",
" <tr>\n",
" <th>d</th>\n",
" <td>95</td>\n",
" <td>3</td>\n",
" <td>66</td>\n",
" </tr>\n",
" <tr>\n",
" <th>e</th>\n",
" <td>28</td>\n",
" <td>121</td>\n",
" <td>120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>f</th>\n",
" <td>141</td>\n",
" <td>85</td>\n",
" <td>132</td>\n",
" </tr>\n",
" <tr>\n",
" <th>h</th>\n",
" <td>124</td>\n",
" <td>39</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>i</th>\n",
" <td>80</td>\n",
" <td>35</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>j</th>\n",
" <td>68</td>\n",
" <td>99</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>k</th>\n",
" <td>74</td>\n",
" <td>12</td>\n",
" <td>11</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"a 113 116 75\n",
"b 19 145 23\n",
"c 57 107 113\n",
"d 95 3 66\n",
"e 28 121 120\n",
"f 141 85 132\n",
"h 124 39 10\n",
"i 80 35 17\n",
"j 68 99 31\n",
"k 74 12 11"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Python 79.9\n",
"En 76.2\n",
"Math 59.8\n",
"dtype: float64"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.mean(axis = 0)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"a 101.333333\n",
"b 62.333333\n",
"c 92.333333\n",
"d 54.666667\n",
"e 89.666667\n",
"f 119.333333\n",
"h 57.666667\n",
"i 44.000000\n",
"j 66.000000\n",
"k 32.333333\n",
"dtype: float64"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.mean(axis = 1)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/2-pandas-索引.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"import pandas as pd\n",
"\n",
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"11 111\n",
"12 113\n",
"13 103\n",
"14 147\n",
"15 63\n",
"16 11\n",
"17 130\n",
"18 38\n",
"19 17\n",
"20 32\n",
"21 112\n",
"22 75\n",
"23 68\n",
"24 124\n",
"25 138\n",
"26 56\n",
"27 1\n",
"28 88\n",
"29 113\n",
"30 63\n",
"31 42\n",
"32 65\n",
"33 104\n",
"34 105\n",
"35 0\n",
"36 95\n",
"37 119\n",
"38 86\n",
"39 124\n",
" ... \n",
"80 127\n",
"81 139\n",
"82 110\n",
"83 65\n",
"84 127\n",
"85 108\n",
"86 33\n",
"87 91\n",
"88 134\n",
"89 65\n",
"90 110\n",
"91 144\n",
"92 40\n",
"93 3\n",
"94 3\n",
"95 59\n",
"96 97\n",
"97 64\n",
"98 126\n",
"99 94\n",
"100 20\n",
"101 107\n",
"102 59\n",
"103 146\n",
"104 83\n",
"105 59\n",
"106 25\n",
"107 0\n",
"108 78\n",
"109 93\n",
"Name: Python, Length: 100, dtype: int16"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s = Series(np.random.randint(0,150,size = 100),index = np.arange(10,110),dtype=np.int16,name = 'Python')\n",
"s"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [
{
"ename": "KeyError",
"evalue": "0",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-4-b1a877195018>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;31m# 索引操作\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0ms\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 866\u001b[0m \u001b[0mkey\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 867\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 868\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 869\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 870\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_scalar\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_value\u001b[1;34m(self, series, key)\u001b[0m\n\u001b[0;32m 4373\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4374\u001b[0m return self._engine.get_value(s, k,\n\u001b[1;32m-> 4375\u001b[1;33m tz=getattr(series.dtype, 'tz', None))\n\u001b[0m\u001b[0;32m 4376\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4377\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m0\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mholds_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mis_boolean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.Int64HashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.Int64HashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: 0"
]
}
],
"source": [
"# 索引操作\n",
"s[0]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"34"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s[10]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"20 32\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s[[10,20]]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"20 32\n",
"21 112\n",
"22 75\n",
"23 68\n",
"24 124\n",
"25 138\n",
"26 56\n",
"27 1\n",
"28 88\n",
"29 113\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 切片操作\n",
"s[10:20]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"12 113\n",
"14 147\n",
"16 11\n",
"18 38\n",
"20 32\n",
"22 75\n",
"24 124\n",
"26 56\n",
"28 88\n",
"30 63\n",
"32 65\n",
"34 105\n",
"36 95\n",
"38 86\n",
"40 6\n",
"42 57\n",
"44 72\n",
"46 43\n",
"48 87\n",
"50 83\n",
"52 99\n",
"54 132\n",
"56 17\n",
"58 116\n",
"60 33\n",
"62 51\n",
"64 80\n",
"66 121\n",
"68 81\n",
"70 0\n",
"72 50\n",
"74 31\n",
"76 114\n",
"78 60\n",
"80 127\n",
"82 110\n",
"84 127\n",
"86 33\n",
"88 134\n",
"90 110\n",
"92 40\n",
"94 3\n",
"96 97\n",
"98 126\n",
"100 20\n",
"102 59\n",
"104 83\n",
"106 25\n",
"108 78\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s[::2]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"109 93\n",
"107 0\n",
"105 59\n",
"103 146\n",
"101 107\n",
"99 94\n",
"97 64\n",
"95 59\n",
"93 3\n",
"91 144\n",
"89 65\n",
"87 91\n",
"85 108\n",
"83 65\n",
"81 139\n",
"79 14\n",
"77 96\n",
"75 76\n",
"73 29\n",
"71 68\n",
"69 4\n",
"67 57\n",
"65 58\n",
"63 106\n",
"61 42\n",
"59 135\n",
"57 56\n",
"55 12\n",
"53 135\n",
"51 74\n",
"49 129\n",
"47 110\n",
"45 1\n",
"43 90\n",
"41 120\n",
"39 124\n",
"37 119\n",
"35 0\n",
"33 104\n",
"31 42\n",
"29 113\n",
"27 1\n",
"25 138\n",
"23 68\n",
"21 112\n",
"19 17\n",
"17 130\n",
"15 63\n",
"13 103\n",
"11 111\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s[::-2]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"34"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 可以使用pandas为开发者提供方法，去进行检索\n",
"s.loc[10]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"20 32\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.loc[[10,20]]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"11 111\n",
"12 113\n",
"13 103\n",
"14 147\n",
"15 63\n",
"16 11\n",
"17 130\n",
"18 38\n",
"19 17\n",
"20 32\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.loc[10:20]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"12 113\n",
"14 147\n",
"16 11\n",
"18 38\n",
"20 32\n",
"22 75\n",
"24 124\n",
"26 56\n",
"28 88\n",
"30 63\n",
"32 65\n",
"34 105\n",
"36 95\n",
"38 86\n",
"40 6\n",
"42 57\n",
"44 72\n",
"46 43\n",
"48 87\n",
"50 83\n",
"52 99\n",
"54 132\n",
"56 17\n",
"58 116\n",
"60 33\n",
"62 51\n",
"64 80\n",
"66 121\n",
"68 81\n",
"70 0\n",
"72 50\n",
"74 31\n",
"76 114\n",
"78 60\n",
"80 127\n",
"82 110\n",
"84 127\n",
"86 33\n",
"88 134\n",
"90 110\n",
"92 40\n",
"94 3\n",
"96 97\n",
"98 126\n",
"100 20\n",
"102 59\n",
"104 83\n",
"106 25\n",
"108 78\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.loc[::2]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"109 93\n",
"107 0\n",
"105 59\n",
"103 146\n",
"101 107\n",
"99 94\n",
"97 64\n",
"95 59\n",
"93 3\n",
"91 144\n",
"89 65\n",
"87 91\n",
"85 108\n",
"83 65\n",
"81 139\n",
"79 14\n",
"77 96\n",
"75 76\n",
"73 29\n",
"71 68\n",
"69 4\n",
"67 57\n",
"65 58\n",
"63 106\n",
"61 42\n",
"59 135\n",
"57 56\n",
"55 12\n",
"53 135\n",
"51 74\n",
"49 129\n",
"47 110\n",
"45 1\n",
"43 90\n",
"41 120\n",
"39 124\n",
"37 119\n",
"35 0\n",
"33 104\n",
"31 42\n",
"29 113\n",
"27 1\n",
"25 138\n",
"23 68\n",
"21 112\n",
"19 17\n",
"17 130\n",
"15 63\n",
"13 103\n",
"11 111\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.loc[::-2]"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Int64Index([ 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22,\n",
" 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35,\n",
" 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48,\n",
" 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61,\n",
" 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74,\n",
" 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87,\n",
" 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100,\n",
" 101, 102, 103, 104, 105, 106, 107, 108, 109],\n",
" dtype='int64')"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.index"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"34"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# iloc 索引从0开始，数字化自然索引\n",
"s.iloc[0]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"20 32\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.iloc[[0,10]]"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"10 34\n",
"11 111\n",
"12 113\n",
"13 103\n",
"14 147\n",
"15 63\n",
"16 11\n",
"17 130\n",
"18 38\n",
"19 17\n",
"20 32\n",
"21 112\n",
"22 75\n",
"23 68\n",
"24 124\n",
"25 138\n",
"26 56\n",
"27 1\n",
"28 88\n",
"29 113\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.iloc[0:20]"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"109 93\n",
"107 0\n",
"105 59\n",
"103 146\n",
"101 107\n",
"99 94\n",
"97 64\n",
"95 59\n",
"93 3\n",
"91 144\n",
"89 65\n",
"87 91\n",
"85 108\n",
"83 65\n",
"81 139\n",
"79 14\n",
"77 96\n",
"75 76\n",
"73 29\n",
"71 68\n",
"69 4\n",
"67 57\n",
"65 58\n",
"63 106\n",
"61 42\n",
"59 135\n",
"57 56\n",
"55 12\n",
"53 135\n",
"51 74\n",
"49 129\n",
"47 110\n",
"45 1\n",
"43 90\n",
"41 120\n",
"39 124\n",
"37 119\n",
"35 0\n",
"33 104\n",
"31 42\n",
"29 113\n",
"27 1\n",
"25 138\n",
"23 68\n",
"21 112\n",
"19 17\n",
"17 130\n",
"15 63\n",
"13 103\n",
"11 111\n",
"Name: Python, dtype: int16"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s.iloc[::-2]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89</td>\n",
" <td>97</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>64</td>\n",
" <td>26</td>\n",
" <td>109</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>48</td>\n",
" <td>46</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>16</td>\n",
" <td>49</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>J</th>\n",
" <td>122</td>\n",
" <td>126</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>K</th>\n",
" <td>60</td>\n",
" <td>136</td>\n",
" <td>62</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"B 135 65 135\n",
"C 13 79 146\n",
"D 47 24 145\n",
"E 89 97 16\n",
"F 64 26 109\n",
"H 48 46 111\n",
"I 16 49 97\n",
"J 122 126 100\n",
"K 60 136 62"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# DataFrame是二维，索引大同小异，\n",
"df = DataFrame(data = np.random.randint(0,150,size= (10,3)),index=list('ABCDEFHIJK'),columns=['Python','En','Math'])\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": true
},
"outputs": [
{
"ename": "KeyError",
"evalue": "'A'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2656\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2657\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: 'A'",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-22-c31f9b0c4302>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'A'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 2925\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnlevels\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2926\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2927\u001b[1;33m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2928\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2929\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mindexer\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2657\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2659\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2660\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2661\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msize\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: 'A'"
]
}
],
"source": [
"df['A']"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"A 103\n",
"B 135\n",
"C 13\n",
"D 47\n",
"E 89\n",
"F 64\n",
"H 48\n",
"I 16\n",
"J 122\n",
"K 60\n",
"Name: Python, dtype: int32"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['Python']"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>64</td>\n",
" <td>26</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>48</td>\n",
" <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>16</td>\n",
" <td>49</td>\n",
" </tr>\n",
" <tr>\n",
" <th>J</th>\n",
" <td>122</td>\n",
" <td>126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>K</th>\n",
" <td>60</td>\n",
" <td>136</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En\n",
"A 103 56\n",
"B 135 65\n",
"C 13 79\n",
"D 47 24\n",
"E 89 97\n",
"F 64 26\n",
"H 48 46\n",
"I 16 49\n",
"J 122 126\n",
"K 60 136"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[['Python','En']]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: [Python, En, Math]\n",
"Index: []"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['Python':'Math']"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"B 135 65 135\n",
"C 13 79 146\n",
"D 47 24 145"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['A':'D']"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": true
},
"outputs": [
{
"ename": "KeyError",
"evalue": "'Python'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2656\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2657\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: 'Python'",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-27-8027bd5615fd>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Python'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1498\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1499\u001b[0m \u001b[0mmaybe_callable\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1500\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_axis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmaybe_callable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1501\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1502\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_is_scalar_access\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_getitem_axis\u001b[1;34m(self, key, axis)\u001b[0m\n\u001b[0;32m 1911\u001b[0m \u001b[1;31m# fall thru to straight lookup\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1912\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_validate_key\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1913\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_label\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1914\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1915\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_get_label\u001b[1;34m(self, label, axis)\u001b[0m\n\u001b[0;32m 139\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mIndexingError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'no slices here, handle elsewhere'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 140\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 141\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_xs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 142\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 143\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_get_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36mxs\u001b[1;34m(self, key, axis, level, drop_level)\u001b[0m\n\u001b[0;32m 3583\u001b[0m drop_level=drop_level)\n\u001b[0;32m 3584\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3585\u001b[1;33m \u001b[0mloc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3586\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3587\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2657\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2659\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2660\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2661\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msize\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: 'Python'"
]
}
],
"source": [
"df.loc['Python']"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Python 103\n",
"En 56\n",
"Math 98\n",
"Name: A, dtype: int32"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc['A']"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>48</td>\n",
" <td>46</td>\n",
" <td>111</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"H 48 46 111"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[['A','H']]"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89</td>\n",
" <td>97</td>\n",
" <td>16</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"B 135 65 135\n",
"C 13 79 146\n",
"D 47 24 145\n",
"E 89 97 16"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc['A':'E']"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89</td>\n",
" <td>97</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>48</td>\n",
" <td>46</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>J</th>\n",
" <td>122</td>\n",
" <td>126</td>\n",
" <td>100</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"C 13 79 146\n",
"E 89 97 16\n",
"H 48 46 111\n",
"J 122 126 100"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[::2]"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>K</th>\n",
" <td>60</td>\n",
" <td>136</td>\n",
" <td>62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>16</td>\n",
" <td>49</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>64</td>\n",
" <td>26</td>\n",
" <td>109</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"K 60 136 62\n",
"I 16 49 97\n",
"F 64 26 109\n",
"D 47 24 145\n",
"B 135 65 135"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[::-2]"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": true
},
"outputs": [
{
"ename": "TypeError",
"evalue": "Cannot index by location index with a non-integer key",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-33-3cf21a555a1f>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0miloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'A'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1498\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1499\u001b[0m \u001b[0mmaybe_callable\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1500\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_axis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmaybe_callable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1501\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1502\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_is_scalar_access\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_getitem_axis\u001b[1;34m(self, key, axis)\u001b[0m\n\u001b[0;32m 2224\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2225\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2226\u001b[1;33m raise TypeError(\"Cannot index by location index with a \"\n\u001b[0m\u001b[0;32m 2227\u001b[0m \"non-integer key\")\n\u001b[0;32m 2228\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mTypeError\u001b[0m: Cannot index by location index with a non-integer key"
]
}
],
"source": [
"df.iloc['A']"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Python 103\n",
"En 56\n",
"Math 98\n",
"Name: A, dtype: int32"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[0]"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>64</td>\n",
" <td>26</td>\n",
" <td>109</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"F 64 26 109"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[[0,5]]"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89</td>\n",
" <td>97</td>\n",
" <td>16</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"B 135 65 135\n",
"C 13 79 146\n",
"D 47 24 145\n",
"E 89 97 16"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[0:5]"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>K</th>\n",
" <td>60</td>\n",
" <td>136</td>\n",
" <td>62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>16</td>\n",
" <td>49</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>64</td>\n",
" <td>26</td>\n",
" <td>109</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"K 60 136 62\n",
"I 16 49 97\n",
"F 64 26 109\n",
"D 47 24 145\n",
"B 135 65 135"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[::-2]"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>103</td>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>65</td>\n",
" <td>135</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>13</td>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>47</td>\n",
" <td>24</td>\n",
" <td>145</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89</td>\n",
" <td>97</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>64</td>\n",
" <td>26</td>\n",
" <td>109</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>48</td>\n",
" <td>46</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>16</td>\n",
" <td>49</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>J</th>\n",
" <td>122</td>\n",
" <td>126</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>K</th>\n",
" <td>60</td>\n",
" <td>136</td>\n",
" <td>62</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 103 56 98\n",
"B 135 65 135\n",
"C 13 79 146\n",
"D 47 24 145\n",
"E 89 97 16\n",
"F 64 26 109\n",
"H 48 46 111\n",
"I 16 49 97\n",
"J 122 126 100\n",
"K 60 136 62"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>56</td>\n",
" <td>98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>79</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>97</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>46</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>J</th>\n",
" <td>126</td>\n",
" <td>100</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" En Math\n",
"A 56 98\n",
"C 79 146\n",
"E 97 16\n",
"H 46 111\n",
"J 126 100"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[::2,1:]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/3-pandas数据清洗之空数据.ipynb 0 → 100644
View file @ 43c147da
This source diff could not be displayed because it is too large. You can view the blob instead.
Day76-90/code/4-pandas多层索引.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"import pandas as pd\n",
"# 数据分析BI-------->人工智能AI\n",
"# 数据分析和数据挖掘一个意思，\n",
"# 工具和软件：Excel 免费版\n",
"# SPSS（一人一年10000）、SAS（一人一年5000）、Matlab 收费\n",
"# R、Python（全方位语言，流行） 免费\n",
"# Python + numpy + scipy + pandas + matplotlib + seaborn + pyEcharts + sklearn + kereas（Tensorflow）+…… \n",
"# 代码，自动化（数据输入----输出结果）\n",
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/plain": [
"a 63\n",
"b 107\n",
"c 16\n",
"d 35\n",
"e 140\n",
"f 83\n",
"dtype: int32"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 多层索引，行列\n",
"# 单层索引\n",
"s = Series(np.random.randint(0,150,size = 6),index=list('abcdef'))\n",
"s"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"张三 期中 114\n",
" 期末 131\n",
"李四 期中 3\n",
" 期末 63\n",
"王五 期中 107\n",
" 期末 34\n",
"dtype: int32"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 多层索引，两层，三层以上（规则一样）\n",
"s2 = Series(np.random.randint(0,150,size = 6),index = pd.MultiIndex.from_product([['张三','李四','王五'],['期中','期末']]))\n",
"s2"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">张三</th>\n",
" <th>期中</th>\n",
" <td>73</td>\n",
" <td>5</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>37</td>\n",
" <td>36</td>\n",
" <td>56</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">李四</th>\n",
" <th>期中</th>\n",
" <td>149</td>\n",
" <td>81</td>\n",
" <td>142</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>71</td>\n",
" <td>138</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">王五</th>\n",
" <th>期中</th>\n",
" <td>11</td>\n",
" <td>94</td>\n",
" <td>103</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>25</td>\n",
" <td>121</td>\n",
" <td>83</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"张三 期中 73 5 25\n",
" 期末 37 36 56\n",
"李四 期中 149 81 142\n",
" 期末 71 138 0\n",
"王五 期中 11 94 103\n",
" 期末 25 121 83"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = DataFrame(np.random.randint(0,150,size = (6,3)),columns=['Python','En','Math'],index =pd.MultiIndex.from_product([['张三','李四','王五'],['期中','期末']]) )\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">张三</th>\n",
" <th rowspan=\"2\" valign=\"top\">期中</th>\n",
" <th>A</th>\n",
" <td>15</td>\n",
" <td>31</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>82</td>\n",
" <td>56</td>\n",
" <td>123</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">期末</th>\n",
" <th>A</th>\n",
" <td>14</td>\n",
" <td>2</td>\n",
" <td>78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>69</td>\n",
" <td>50</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">李四</th>\n",
" <th rowspan=\"2\" valign=\"top\">期中</th>\n",
" <th>A</th>\n",
" <td>91</td>\n",
" <td>87</td>\n",
" <td>143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>120</td>\n",
" <td>118</td>\n",
" <td>39</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">期末</th>\n",
" <th>A</th>\n",
" <td>56</td>\n",
" <td>76</td>\n",
" <td>55</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>11</td>\n",
" <td>105</td>\n",
" <td>121</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">王五</th>\n",
" <th rowspan=\"2\" valign=\"top\">期中</th>\n",
" <th>A</th>\n",
" <td>147</td>\n",
" <td>78</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>128</td>\n",
" <td>126</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">期末</th>\n",
" <th>A</th>\n",
" <td>49</td>\n",
" <td>45</td>\n",
" <td>114</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>121</td>\n",
" <td>26</td>\n",
" <td>77</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"张三 期中 A 15 31 17\n",
" B 82 56 123\n",
" 期末 A 14 2 78\n",
" B 69 50 17\n",
"李四 期中 A 91 87 143\n",
" B 120 118 39\n",
" 期末 A 56 76 55\n",
" B 11 105 121\n",
"王五 期中 A 147 78 1\n",
" B 128 126 146\n",
" 期末 A 49 45 114\n",
" B 121 26 77"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 三层索引\n",
"df3 = DataFrame(np.random.randint(0,150,size = (12,3)),columns=['Python','En','Math'],index =pd.MultiIndex.from_product([['张三','李四','王五'],['期中','期末'],['A','B']]) )\n",
"\n",
"df3"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"73"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 先获取列后获取行\n",
"df['Python']['张三']['期中']"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"df2 = df.copy()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">张三</th>\n",
" <th>期中</th>\n",
" <td>73</td>\n",
" <td>5</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>37</td>\n",
" <td>36</td>\n",
" <td>56</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">李四</th>\n",
" <th>期中</th>\n",
" <td>149</td>\n",
" <td>81</td>\n",
" <td>142</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>71</td>\n",
" <td>138</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">王五</th>\n",
" <th>期中</th>\n",
" <td>11</td>\n",
" <td>94</td>\n",
" <td>103</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>25</td>\n",
" <td>121</td>\n",
" <td>83</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"张三 期中 73 5 25\n",
" 期末 37 36 56\n",
"李四 期中 149 81 142\n",
" 期末 71 138 0\n",
"王五 期中 11 94 103\n",
" 期末 25 121 83"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.sort_index()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"73"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 先获取行，后获取列\n",
"df.loc['张三'].loc['期中']['Python']"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">张三</th>\n",
" <th>期中</th>\n",
" <td>73</td>\n",
" <td>5</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>37</td>\n",
" <td>36</td>\n",
" <td>56</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"张三 期中 73 5 25\n",
" 期末 37 36 56"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[[0,1]]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/5-pandas多层索引计算.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"import pandas as pd\n",
"\n",
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">Python</th>\n",
" <th colspan=\"2\" halign=\"left\">En</th>\n",
" <th colspan=\"2\" halign=\"left\">Math</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>131</td>\n",
" <td>101</td>\n",
" <td>1</td>\n",
" <td>73</td>\n",
" <td>15</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>62</td>\n",
" <td>34</td>\n",
" <td>53</td>\n",
" <td>101</td>\n",
" <td>24</td>\n",
" <td>57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>24</td>\n",
" <td>76</td>\n",
" <td>36</td>\n",
" <td>117</td>\n",
" <td>123</td>\n",
" <td>105</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>112</td>\n",
" <td>46</td>\n",
" <td>79</td>\n",
" <td>42</td>\n",
" <td>46</td>\n",
" <td>122</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>66</td>\n",
" <td>113</td>\n",
" <td>104</td>\n",
" <td>45</td>\n",
" <td>10</td>\n",
" <td>108</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>111</td>\n",
" <td>108</td>\n",
" <td>4</td>\n",
" <td>41</td>\n",
" <td>132</td>\n",
" <td>21</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math \n",
" 期中 期末 期中 期末 期中 期末\n",
"A 131 101 1 73 15 17\n",
"B 62 34 53 101 24 57\n",
"C 24 76 36 117 123 105\n",
"D 112 46 79 42 46 122\n",
"E 66 113 104 45 10 108\n",
"F 111 108 4 41 132 21"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 多层列索引\n",
"df = DataFrame(np.random.randint(0,150,size = (6,6)),index = list('ABCDEF'),\n",
" columns=pd.MultiIndex.from_product([['Python','En','Math'],['期中','期末']]))\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"Python 期中 84.3\n",
" 期末 79.7\n",
"En 期中 46.2\n",
" 期末 69.8\n",
"Math 期中 58.3\n",
" 期末 71.7\n",
"dtype: float64"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# round保留2位小数\n",
"df.mean().round(1)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">Python</th>\n",
" <th colspan=\"2\" halign=\"left\">En</th>\n",
" <th colspan=\"2\" halign=\"left\">Math</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>131</td>\n",
" <td>101</td>\n",
" <td>1</td>\n",
" <td>73</td>\n",
" <td>15</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>62</td>\n",
" <td>34</td>\n",
" <td>53</td>\n",
" <td>101</td>\n",
" <td>24</td>\n",
" <td>57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>24</td>\n",
" <td>76</td>\n",
" <td>36</td>\n",
" <td>117</td>\n",
" <td>123</td>\n",
" <td>105</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>112</td>\n",
" <td>46</td>\n",
" <td>79</td>\n",
" <td>42</td>\n",
" <td>46</td>\n",
" <td>122</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>66</td>\n",
" <td>113</td>\n",
" <td>104</td>\n",
" <td>45</td>\n",
" <td>10</td>\n",
" <td>108</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>111</td>\n",
" <td>108</td>\n",
" <td>4</td>\n",
" <td>41</td>\n",
" <td>132</td>\n",
" <td>21</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math \n",
" 期中 期末 期中 期末 期中 期末\n",
"A 131 101 1 73 15 17\n",
"B 62 34 53 101 24 57\n",
"C 24 76 36 117 123 105\n",
"D 112 46 79 42 46 122\n",
"E 66 113 104 45 10 108\n",
"F 111 108 4 41 132 21"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>116.0</td>\n",
" <td>37.0</td>\n",
" <td>16.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>48.0</td>\n",
" <td>77.0</td>\n",
" <td>40.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>50.0</td>\n",
" <td>76.5</td>\n",
" <td>114.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>79.0</td>\n",
" <td>60.5</td>\n",
" <td>84.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>89.5</td>\n",
" <td>74.5</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>109.5</td>\n",
" <td>22.5</td>\n",
" <td>76.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math\n",
"A 116.0 37.0 16.0\n",
"B 48.0 77.0 40.5\n",
"C 50.0 76.5 114.0\n",
"D 79.0 60.5 84.0\n",
"E 89.5 74.5 59.0\n",
"F 109.5 22.5 76.5"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# axis = 0代表行\n",
"# axis = 1代表列\n",
"df.mean(axis = 1,level = 0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>49.0</td>\n",
" <td>63.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>46.3</td>\n",
" <td>64.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>61.0</td>\n",
" <td>99.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>79.0</td>\n",
" <td>70.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>60.0</td>\n",
" <td>88.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>82.3</td>\n",
" <td>56.7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 期中 期末\n",
"A 49.0 63.7\n",
"B 46.3 64.0\n",
"C 61.0 99.3\n",
"D 79.0 70.0\n",
"E 60.0 88.7\n",
"F 82.3 56.7"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.mean(axis = 1,level = 1).round(1)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">Python</th>\n",
" <th colspan=\"2\" halign=\"left\">En</th>\n",
" <th colspan=\"2\" halign=\"left\">Math</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>131</td>\n",
" <td>101</td>\n",
" <td>1</td>\n",
" <td>73</td>\n",
" <td>15</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>62</td>\n",
" <td>34</td>\n",
" <td>53</td>\n",
" <td>101</td>\n",
" <td>24</td>\n",
" <td>57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>24</td>\n",
" <td>76</td>\n",
" <td>36</td>\n",
" <td>117</td>\n",
" <td>123</td>\n",
" <td>105</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>112</td>\n",
" <td>46</td>\n",
" <td>79</td>\n",
" <td>42</td>\n",
" <td>46</td>\n",
" <td>122</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>66</td>\n",
" <td>113</td>\n",
" <td>104</td>\n",
" <td>45</td>\n",
" <td>10</td>\n",
" <td>108</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>111</td>\n",
" <td>108</td>\n",
" <td>4</td>\n",
" <td>41</td>\n",
" <td>132</td>\n",
" <td>21</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python En Math \n",
" 期中 期末 期中 期末 期中 期末\n",
"A 131 101 1 73 15 17\n",
"B 62 34 53 101 24 57\n",
"C 24 76 36 117 123 105\n",
"D 112 46 79 42 46 122\n",
"E 66 113 104 45 10 108\n",
"F 111 108 4 41 132 21"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>En</th>\n",
" <th>Math</th>\n",
" <th>Python</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">A</th>\n",
" <th>期中</th>\n",
" <td>1</td>\n",
" <td>15</td>\n",
" <td>131</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>73</td>\n",
" <td>17</td>\n",
" <td>101</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">B</th>\n",
" <th>期中</th>\n",
" <td>53</td>\n",
" <td>24</td>\n",
" <td>62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>101</td>\n",
" <td>57</td>\n",
" <td>34</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">C</th>\n",
" <th>期中</th>\n",
" <td>36</td>\n",
" <td>123</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>117</td>\n",
" <td>105</td>\n",
" <td>76</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">D</th>\n",
" <th>期中</th>\n",
" <td>79</td>\n",
" <td>46</td>\n",
" <td>112</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>42</td>\n",
" <td>122</td>\n",
" <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">E</th>\n",
" <th>期中</th>\n",
" <td>104</td>\n",
" <td>10</td>\n",
" <td>66</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>45</td>\n",
" <td>108</td>\n",
" <td>113</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">F</th>\n",
" <th>期中</th>\n",
" <td>4</td>\n",
" <td>132</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>41</td>\n",
" <td>21</td>\n",
" <td>108</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" En Math Python\n",
"A 期中 1 15 131\n",
" 期末 73 17 101\n",
"B 期中 53 24 62\n",
" 期末 101 57 34\n",
"C 期中 36 123 24\n",
" 期末 117 105 76\n",
"D 期中 79 46 112\n",
" 期末 42 122 46\n",
"E 期中 104 10 66\n",
" 期末 45 108 113\n",
"F 期中 4 132 111\n",
" 期末 41 21 108"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 行和列的多层索引，进行转换\n",
"# Stack the prescribed level(s) from columns to index.\n",
"# 从列变成行\n",
"df2 = df.stack(level = 1)\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"6\" halign=\"left\">En</th>\n",
" <th colspan=\"6\" halign=\"left\">Math</th>\n",
" <th colspan=\"6\" halign=\"left\">Python</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" <th>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>期中</th>\n",
" <td>1</td>\n",
" <td>53</td>\n",
" <td>36</td>\n",
" <td>79</td>\n",
" <td>104</td>\n",
" <td>4</td>\n",
" <td>15</td>\n",
" <td>24</td>\n",
" <td>123</td>\n",
" <td>46</td>\n",
" <td>10</td>\n",
" <td>132</td>\n",
" <td>131</td>\n",
" <td>62</td>\n",
" <td>24</td>\n",
" <td>112</td>\n",
" <td>66</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>73</td>\n",
" <td>101</td>\n",
" <td>117</td>\n",
" <td>42</td>\n",
" <td>45</td>\n",
" <td>41</td>\n",
" <td>17</td>\n",
" <td>57</td>\n",
" <td>105</td>\n",
" <td>122</td>\n",
" <td>108</td>\n",
" <td>21</td>\n",
" <td>101</td>\n",
" <td>34</td>\n",
" <td>76</td>\n",
" <td>46</td>\n",
" <td>113</td>\n",
" <td>108</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" En Math Python \n",
" A B C D E F A B C D E F A B C D E F\n",
"期中 1 53 36 79 104 4 15 24 123 46 10 132 131 62 24 112 66 111\n",
"期末 73 101 117 42 45 41 17 57 105 122 108 21 101 34 76 46 113 108"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 从行变成列\n",
"df2.unstack(level= 0 )"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">En</th>\n",
" <th colspan=\"2\" halign=\"left\">Math</th>\n",
" <th colspan=\"2\" halign=\"left\">Python</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" <th>期中</th>\n",
" <th>期末</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>1</td>\n",
" <td>73</td>\n",
" <td>15</td>\n",
" <td>17</td>\n",
" <td>131</td>\n",
" <td>101</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>53</td>\n",
" <td>101</td>\n",
" <td>24</td>\n",
" <td>57</td>\n",
" <td>62</td>\n",
" <td>34</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>36</td>\n",
" <td>117</td>\n",
" <td>123</td>\n",
" <td>105</td>\n",
" <td>24</td>\n",
" <td>76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>79</td>\n",
" <td>42</td>\n",
" <td>46</td>\n",
" <td>122</td>\n",
" <td>112</td>\n",
" <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>104</td>\n",
" <td>45</td>\n",
" <td>10</td>\n",
" <td>108</td>\n",
" <td>66</td>\n",
" <td>113</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>4</td>\n",
" <td>41</td>\n",
" <td>132</td>\n",
" <td>21</td>\n",
" <td>111</td>\n",
" <td>108</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" En Math Python \n",
" 期中 期末 期中 期末 期中 期末\n",
"A 1 73 15 17 131 101\n",
"B 53 101 24 57 62 34\n",
"C 36 117 123 105 24 76\n",
"D 79 42 46 122 112 46\n",
"E 104 45 10 108 66 113\n",
"F 4 41 132 21 111 108"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.unstack(level = 1)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/6-pandas数据集成.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"import pandas as pd\n",
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 数据分析数据挖掘\n",
"# 有数据情况下：\n",
"# 数据预处理\n",
"# 数据清洗（空数据，异常值）\n",
"# 数据集成（多个数据合并到一起，级联）数据可能存放在多个表中\n",
"# 数据转化\n",
"# 数据规约（属性减少（不重要的属性删除），数据减少去重操作）"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 5, 12, 67, 29, 46, 103, 53, 53, 139, 87],\n",
" [126, 33, 55, 104, 45, 70, 96, 133, 116, 43],\n",
" [ 84, 45, 17, 42, 19, 11, 125, 43, 54, 39],\n",
" [ 97, 68, 99, 90, 28, 60, 135, 84, 111, 63],\n",
" [114, 56, 30, 81, 48, 73, 119, 65, 20, 22]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"array([[115, 128, 122, 127, 4, 135, 26, 25, 131, 139],\n",
" [ 66, 119, 37, 136, 101, 40, 102, 127, 148, 127],\n",
" [ 89, 80, 140, 133, 51, 142, 47, 27, 54, 23],\n",
" [ 64, 127, 33, 128, 60, 106, 67, 94, 110, 76],\n",
" [ 6, 21, 23, 96, 10, 62, 26, 79, 149, 43],\n",
" [116, 143, 132, 118, 68, 21, 57, 133, 124, 124]])"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# 首先看numpy数组的集成\n",
"nd1 = np.random.randint(0,150,size = (5,10))\n",
"\n",
"nd2 = np.random.randint(0,150,size = (6,10))\n",
"display(nd1,nd2)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 5, 12, 67, 29, 46, 103, 53, 53, 139, 87],\n",
" [126, 33, 55, 104, 45, 70, 96, 133, 116, 43],\n",
" [ 84, 45, 17, 42, 19, 11, 125, 43, 54, 39],\n",
" [ 97, 68, 99, 90, 28, 60, 135, 84, 111, 63],\n",
" [114, 56, 30, 81, 48, 73, 119, 65, 20, 22],\n",
" [115, 128, 122, 127, 4, 135, 26, 25, 131, 139],\n",
" [ 66, 119, 37, 136, 101, 40, 102, 127, 148, 127],\n",
" [ 89, 80, 140, 133, 51, 142, 47, 27, 54, 23],\n",
" [ 64, 127, 33, 128, 60, 106, 67, 94, 110, 76],\n",
" [ 6, 21, 23, 96, 10, 62, 26, 79, 149, 43],\n",
" [116, 143, 132, 118, 68, 21, 57, 133, 124, 124]])"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 原来数据一个5行，一个是6行，级联之后变成了11行\n",
"nd3 = np.concatenate([nd1,nd2],axis = 0)\n",
"nd3"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[110, 38, 144, 92, 38, 2, 67, 2, 103, 81],\n",
" [ 56, 61, 61, 22, 108, 145, 95, 44, 40, 100],\n",
" [ 65, 74, 85, 123, 47, 117, 35, 55, 120, 20],\n",
" [ 15, 9, 4, 84, 71, 133, 140, 13, 71, 91],\n",
" [ 94, 31, 41, 5, 7, 32, 50, 24, 18, 120]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"array([[ 65, 149, 86, 138, 98],\n",
" [136, 49, 102, 45, 140],\n",
" [ 13, 124, 94, 81, 73],\n",
" [ 82, 38, 0, 75, 94],\n",
" [146, 28, 143, 61, 49]])"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"nd1 = np.random.randint(0,150,size = (5,10))\n",
"\n",
"nd2 = np.random.randint(0,150,size = (5,5))\n",
"display(nd1,nd2)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[110, 38, 144, 92, 38, 2, 67, 2, 103, 81, 65, 149, 86,\n",
" 138, 98],\n",
" [ 56, 61, 61, 22, 108, 145, 95, 44, 40, 100, 136, 49, 102,\n",
" 45, 140],\n",
" [ 65, 74, 85, 123, 47, 117, 35, 55, 120, 20, 13, 124, 94,\n",
" 81, 73],\n",
" [ 15, 9, 4, 84, 71, 133, 140, 13, 71, 91, 82, 38, 0,\n",
" 75, 94],\n",
" [ 94, 31, 41, 5, 7, 32, 50, 24, 18, 120, 146, 28, 143,\n",
" 61, 49]])"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# axis = 0行级联（第一维度的级联），axis = 1（第二个维度的级联，列的级联）\n",
"np.concatenate((nd1,nd2),axis = 1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# pandas级联操作，pandas基于numpy\n",
"# pandas的级联类似"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>113</td>\n",
" <td>53</td>\n",
" <td>80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>40</td>\n",
" <td>52</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>144</td>\n",
" <td>18</td>\n",
" <td>64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 113 53 80\n",
"B 135 40 52\n",
"C 144 18 64"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>126</td>\n",
" <td>118</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>147</td>\n",
" <td>81</td>\n",
" <td>27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>87</td>\n",
" <td>63</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>35</td>\n",
" <td>95</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>130</td>\n",
" <td>117</td>\n",
" <td>91</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>124</td>\n",
" <td>98</td>\n",
" <td>122</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"D 126 118 146\n",
"E 147 81 27\n",
"F 87 63 1\n",
"G 35 95 33\n",
"H 130 117 91\n",
"I 124 98 122"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df1 = DataFrame(np.random.randint(0,150,size = (3,3)),index = list('ABC'),columns=['Python','Math','En'])\n",
"\n",
"df2 = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('DEFGHI'),columns=['Python','Math','En'])\n",
"\n",
"display(df1,df2)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>113</td>\n",
" <td>53</td>\n",
" <td>80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>40</td>\n",
" <td>52</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>144</td>\n",
" <td>18</td>\n",
" <td>64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>126</td>\n",
" <td>118</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>147</td>\n",
" <td>81</td>\n",
" <td>27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>87</td>\n",
" <td>63</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>35</td>\n",
" <td>95</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>130</td>\n",
" <td>117</td>\n",
" <td>91</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>124</td>\n",
" <td>98</td>\n",
" <td>122</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 113 53 80\n",
"B 135 40 52\n",
"C 144 18 64\n",
"D 126 118 146\n",
"E 147 81 27\n",
"F 87 63 1\n",
"G 35 95 33\n",
"H 130 117 91\n",
"I 124 98 122"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# pandas汇总数据，数据集成\n",
"df1.append(df2)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>113</td>\n",
" <td>53</td>\n",
" <td>80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135</td>\n",
" <td>40</td>\n",
" <td>52</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>144</td>\n",
" <td>18</td>\n",
" <td>64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>126</td>\n",
" <td>118</td>\n",
" <td>146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>147</td>\n",
" <td>81</td>\n",
" <td>27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>87</td>\n",
" <td>63</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>35</td>\n",
" <td>95</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>130</td>\n",
" <td>117</td>\n",
" <td>91</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>124</td>\n",
" <td>98</td>\n",
" <td>122</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 113 53 80\n",
"B 135 40 52\n",
"C 144 18 64\n",
"D 126 118 146\n",
"E 147 81 27\n",
"F 87 63 1\n",
"G 35 95 33\n",
"H 130 117 91\n",
"I 124 98 122"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.concat([df1,df2])"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"d:\\python36\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version\n",
"of pandas will change to not sort by default.\n",
"\n",
"To accept the future behavior, pass 'sort=False'.\n",
"\n",
"To retain the current behavior and silence the warning, pass 'sort=True'.\n",
"\n",
" \"\"\"Entry point for launching an IPython kernel.\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>113.0</td>\n",
" <td>53.0</td>\n",
" <td>80.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>135.0</td>\n",
" <td>40.0</td>\n",
" <td>52.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>144.0</td>\n",
" <td>18.0</td>\n",
" <td>64.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>126.0</td>\n",
" <td>118.0</td>\n",
" <td>146.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>147.0</td>\n",
" <td>81.0</td>\n",
" <td>27.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>87.0</td>\n",
" <td>63.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>35.0</td>\n",
" <td>95.0</td>\n",
" <td>33.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>H</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>130.0</td>\n",
" <td>117.0</td>\n",
" <td>91.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>124.0</td>\n",
" <td>98.0</td>\n",
" <td>122.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En Python Math En\n",
"A 113.0 53.0 80.0 NaN NaN NaN\n",
"B 135.0 40.0 52.0 NaN NaN NaN\n",
"C 144.0 18.0 64.0 NaN NaN NaN\n",
"D NaN NaN NaN 126.0 118.0 146.0\n",
"E NaN NaN NaN 147.0 81.0 27.0\n",
"F NaN NaN NaN 87.0 63.0 1.0\n",
"G NaN NaN NaN 35.0 95.0 33.0\n",
"H NaN NaN NaN 130.0 117.0 91.0\n",
"I NaN NaN NaN 124.0 98.0 122.0"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.concat([df1,df2],axis = 1,ignore_index = False)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>22</td>\n",
" <td>58</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>99</td>\n",
" <td>57</td>\n",
" <td>35</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>51</td>\n",
" <td>28</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>5</td>\n",
" <td>60</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>137</td>\n",
" <td>23</td>\n",
" <td>121</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>49</td>\n",
" <td>78</td>\n",
" <td>115</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 22 58 13\n",
"B 99 57 35\n",
"C 51 28 24\n",
"E 5 60 111\n",
"F 137 23 121\n",
"G 49 78 115"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>118</td>\n",
" <td>113</td>\n",
" <td>81</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>51</td>\n",
" <td>22</td>\n",
" <td>126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>0</td>\n",
" <td>115</td>\n",
" <td>128</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>100</td>\n",
" <td>130</td>\n",
" <td>94</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>49</td>\n",
" <td>93</td>\n",
" <td>140</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>70</td>\n",
" <td>59</td>\n",
" <td>94</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 118 113 81\n",
"B 51 22 126\n",
"C 0 115 128\n",
"E 100 130 94\n",
"F 49 93 140\n",
"G 70 59 94"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# 期中\n",
"df1 = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('ABCEFG'),columns=['Python','Math','En'])\n",
"\n",
"# 期末\n",
"df2 = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('ABCEFG'),columns=['Python','Math','En'])\n",
"\n",
"display(df1,df2)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"6\" valign=\"top\">期中</th>\n",
" <th>A</th>\n",
" <td>22</td>\n",
" <td>58</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>99</td>\n",
" <td>57</td>\n",
" <td>35</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>51</td>\n",
" <td>28</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>5</td>\n",
" <td>60</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>137</td>\n",
" <td>23</td>\n",
" <td>121</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>49</td>\n",
" <td>78</td>\n",
" <td>115</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"6\" valign=\"top\">期末</th>\n",
" <th>A</th>\n",
" <td>118</td>\n",
" <td>113</td>\n",
" <td>81</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>51</td>\n",
" <td>22</td>\n",
" <td>126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>0</td>\n",
" <td>115</td>\n",
" <td>128</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>100</td>\n",
" <td>130</td>\n",
" <td>94</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>49</td>\n",
" <td>93</td>\n",
" <td>140</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>70</td>\n",
" <td>59</td>\n",
" <td>94</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"期中 A 22 58 13\n",
" B 99 57 35\n",
" C 51 28 24\n",
" E 5 60 111\n",
" F 137 23 121\n",
" G 49 78 115\n",
"期末 A 118 113 81\n",
" B 51 22 126\n",
" C 0 115 128\n",
" E 100 130 94\n",
" F 49 93 140\n",
" G 70 59 94"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df3 = pd.concat([df1,df2],axis = 0,keys = ['期中','期末'])\n",
"df3"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">A</th>\n",
" <th>期中</th>\n",
" <td>22</td>\n",
" <td>58</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>118</td>\n",
" <td>113</td>\n",
" <td>81</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">B</th>\n",
" <th>期中</th>\n",
" <td>99</td>\n",
" <td>57</td>\n",
" <td>35</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>51</td>\n",
" <td>22</td>\n",
" <td>126</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">C</th>\n",
" <th>期中</th>\n",
" <td>51</td>\n",
" <td>28</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>0</td>\n",
" <td>115</td>\n",
" <td>128</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">E</th>\n",
" <th>期中</th>\n",
" <td>5</td>\n",
" <td>60</td>\n",
" <td>111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>100</td>\n",
" <td>130</td>\n",
" <td>94</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">F</th>\n",
" <th>期中</th>\n",
" <td>137</td>\n",
" <td>23</td>\n",
" <td>121</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>49</td>\n",
" <td>93</td>\n",
" <td>140</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">G</th>\n",
" <th>期中</th>\n",
" <td>49</td>\n",
" <td>78</td>\n",
" <td>115</td>\n",
" </tr>\n",
" <tr>\n",
" <th>期末</th>\n",
" <td>70</td>\n",
" <td>59</td>\n",
" <td>94</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 期中 22 58 13\n",
" 期末 118 113 81\n",
"B 期中 99 57 35\n",
" 期末 51 22 126\n",
"C 期中 51 28 24\n",
" 期末 0 115 128\n",
"E 期中 5 60 111\n",
" 期末 100 130 94\n",
"F 期中 137 23 121\n",
" 期末 49 93 140\n",
"G 期中 49 78 115\n",
" 期末 70 59 94"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df3.unstack(level = 0).stack()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/7-pandas数据集成merge.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"import pandas as pd\n",
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 上一讲，append，concat数据集成方法\n",
"# merge融合，根据某一共同属性进行级联，高级用法"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>name</th>\n",
" <th>sex</th>\n",
" <th>id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A</td>\n",
" <td>男</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>B</td>\n",
" <td>女</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>C</td>\n",
" <td>女</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>D</td>\n",
" <td>女</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>E</td>\n",
" <td>男</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>F</td>\n",
" <td>男</td>\n",
" <td>6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" name sex id\n",
"0 A 男 1\n",
"1 B 女 2\n",
"2 C 女 3\n",
"3 D 女 4\n",
"4 E 男 5\n",
"5 F 男 6"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1 = DataFrame({'name':['A','B','C','D','E','F'],\n",
" 'sex':['男','女','女','女','男','男'],\n",
" 'id':[1,2,3,4,5,6]})\n",
"df1"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>salary</th>\n",
" <th>id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>22</td>\n",
" <td>12000</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>25</td>\n",
" <td>15000</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>27</td>\n",
" <td>20000</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>21</td>\n",
" <td>30000</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>18</td>\n",
" <td>10000</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>29</td>\n",
" <td>8000</td>\n",
" <td>7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age salary id\n",
"0 22 12000 1\n",
"1 25 15000 2\n",
"2 27 20000 3\n",
"3 21 30000 4\n",
"4 18 10000 5\n",
"5 29 8000 7"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2 = DataFrame({'age':[22,25,27,21,18,29],'salary':[12000,15000,20000,30000,10000,8000],'id':[1,2,3,4,5,7]})\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"d:\\python36\\lib\\site-packages\\pandas\\core\\frame.py:6692: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version\n",
"of pandas will change to not sort by default.\n",
"\n",
"To accept the future behavior, pass 'sort=False'.\n",
"\n",
"To retain the current behavior and silence the warning, pass 'sort=True'.\n",
"\n",
" sort=sort)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>id</th>\n",
" <th>name</th>\n",
" <th>salary</th>\n",
" <th>sex</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>男</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>B</td>\n",
" <td>NaN</td>\n",
" <td>女</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>3</td>\n",
" <td>C</td>\n",
" <td>NaN</td>\n",
" <td>女</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>NaN</td>\n",
" <td>4</td>\n",
" <td>D</td>\n",
" <td>NaN</td>\n",
" <td>女</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NaN</td>\n",
" <td>5</td>\n",
" <td>E</td>\n",
" <td>NaN</td>\n",
" <td>男</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>NaN</td>\n",
" <td>6</td>\n",
" <td>F</td>\n",
" <td>NaN</td>\n",
" <td>男</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>22.0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>12000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>25.0</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>15000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>27.0</td>\n",
" <td>3</td>\n",
" <td>NaN</td>\n",
" <td>20000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>21.0</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>30000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>18.0</td>\n",
" <td>5</td>\n",
" <td>NaN</td>\n",
" <td>10000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>29.0</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>8000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age id name salary sex\n",
"0 NaN 1 A NaN 男\n",
"1 NaN 2 B NaN 女\n",
"2 NaN 3 C NaN 女\n",
"3 NaN 4 D NaN 女\n",
"4 NaN 5 E NaN 男\n",
"5 NaN 6 F NaN 男\n",
"0 22.0 1 NaN 12000.0 NaN\n",
"1 25.0 2 NaN 15000.0 NaN\n",
"2 27.0 3 NaN 20000.0 NaN\n",
"3 21.0 4 NaN 30000.0 NaN\n",
"4 18.0 5 NaN 10000.0 NaN\n",
"5 29.0 7 NaN 8000.0 NaN"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1.append(df2)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>name</th>\n",
" <th>sex</th>\n",
" <th>id</th>\n",
" <th>age</th>\n",
" <th>salary</th>\n",
" <th>id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A</td>\n",
" <td>男</td>\n",
" <td>1</td>\n",
" <td>22</td>\n",
" <td>12000</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>B</td>\n",
" <td>女</td>\n",
" <td>2</td>\n",
" <td>25</td>\n",
" <td>15000</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>C</td>\n",
" <td>女</td>\n",
" <td>3</td>\n",
" <td>27</td>\n",
" <td>20000</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>D</td>\n",
" <td>女</td>\n",
" <td>4</td>\n",
" <td>21</td>\n",
" <td>30000</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>E</td>\n",
" <td>男</td>\n",
" <td>5</td>\n",
" <td>18</td>\n",
" <td>10000</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>F</td>\n",
" <td>男</td>\n",
" <td>6</td>\n",
" <td>29</td>\n",
" <td>8000</td>\n",
" <td>7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" name sex id age salary id\n",
"0 A 男 1 22 12000 1\n",
"1 B 女 2 25 15000 2\n",
"2 C 女 3 27 20000 3\n",
"3 D 女 4 21 30000 4\n",
"4 E 男 5 18 10000 5\n",
"5 F 男 6 29 8000 7"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.concat([df1,df2],axis = 1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>name</th>\n",
" <th>sex</th>\n",
" <th>id</th>\n",
" <th>age</th>\n",
" <th>salary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A</td>\n",
" <td>男</td>\n",
" <td>1</td>\n",
" <td>22</td>\n",
" <td>12000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>B</td>\n",
" <td>女</td>\n",
" <td>2</td>\n",
" <td>25</td>\n",
" <td>15000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>C</td>\n",
" <td>女</td>\n",
" <td>3</td>\n",
" <td>27</td>\n",
" <td>20000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>D</td>\n",
" <td>女</td>\n",
" <td>4</td>\n",
" <td>21</td>\n",
" <td>30000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>E</td>\n",
" <td>男</td>\n",
" <td>5</td>\n",
" <td>18</td>\n",
" <td>10000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" name sex id age salary\n",
"0 A 男 1 22 12000\n",
"1 B 女 2 25 15000\n",
"2 C 女 3 27 20000\n",
"3 D 女 4 21 30000\n",
"4 E 男 5 18 10000"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1.merge(df2)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>name</th>\n",
" <th>sex</th>\n",
" <th>id</th>\n",
" <th>age</th>\n",
" <th>salary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A</td>\n",
" <td>男</td>\n",
" <td>1</td>\n",
" <td>22.0</td>\n",
" <td>12000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>B</td>\n",
" <td>女</td>\n",
" <td>2</td>\n",
" <td>25.0</td>\n",
" <td>15000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>C</td>\n",
" <td>女</td>\n",
" <td>3</td>\n",
" <td>27.0</td>\n",
" <td>20000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>D</td>\n",
" <td>女</td>\n",
" <td>4</td>\n",
" <td>21.0</td>\n",
" <td>30000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>E</td>\n",
" <td>男</td>\n",
" <td>5</td>\n",
" <td>18.0</td>\n",
" <td>10000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>F</td>\n",
" <td>男</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7</td>\n",
" <td>29.0</td>\n",
" <td>8000.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" name sex id age salary\n",
"0 A 男 1 22.0 12000.0\n",
"1 B 女 2 25.0 15000.0\n",
"2 C 女 3 27.0 20000.0\n",
"3 D 女 4 21.0 30000.0\n",
"4 E 男 5 18.0 10000.0\n",
"5 F 男 6 NaN NaN\n",
"6 NaN NaN 7 29.0 8000.0"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1.merge(df2,how = 'outer')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>40</td>\n",
" <td>15</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>59</td>\n",
" <td>52</td>\n",
" <td>83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>14</td>\n",
" <td>138</td>\n",
" <td>137</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>89</td>\n",
" <td>78</td>\n",
" <td>53</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>81</td>\n",
" <td>101</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>75</td>\n",
" <td>79</td>\n",
" <td>86</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 40 15 90\n",
"B 59 52 83\n",
"C 14 138 137\n",
"D 89 78 53\n",
"E 81 101 3\n",
"F 75 79 86"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('ABCDEF'),columns=['Python','Math','En'])\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"Python 59.7\n",
"Math 77.2\n",
"En 75.3\n",
"dtype: float64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s = df.mean().round(1)\n",
"s"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>score_mean</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Python</th>\n",
" <td>59.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Math</th>\n",
" <td>77.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>En</th>\n",
" <td>75.3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" score_mean\n",
"Python 59.7\n",
"Math 77.2\n",
"En 75.3"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2 = DataFrame(s)\n",
"df2.columns = ['score_mean']\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>score_mean</th>\n",
" <td>59.7</td>\n",
" <td>77.2</td>\n",
" <td>75.3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"score_mean 59.7 77.2 75.3"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df3 = df2.T\n",
"df3"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>40.0</td>\n",
" <td>15.0</td>\n",
" <td>90.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>59.0</td>\n",
" <td>52.0</td>\n",
" <td>83.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>14.0</td>\n",
" <td>138.0</td>\n",
" <td>137.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>89.0</td>\n",
" <td>78.0</td>\n",
" <td>53.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>81.0</td>\n",
" <td>101.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>75.0</td>\n",
" <td>79.0</td>\n",
" <td>86.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>score_mean</th>\n",
" <td>59.7</td>\n",
" <td>77.2</td>\n",
" <td>75.3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En\n",
"A 40.0 15.0 90.0\n",
"B 59.0 52.0 83.0\n",
"C 14.0 138.0 137.0\n",
"D 89.0 78.0 53.0\n",
"E 81.0 101.0 3.0\n",
"F 75.0 79.0 86.0\n",
"score_mean 59.7 77.2 75.3"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df4 = df.append(df3)\n",
"df4"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>score_mean</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>48.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>64.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>96.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>73.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>61.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>score_mean</th>\n",
" <td>70.7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" score_mean\n",
"A 48.3\n",
"B 64.7\n",
"C 96.3\n",
"D 73.3\n",
"E 61.7\n",
"F 80.0\n",
"score_mean 70.7"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df5 = DataFrame(df4.mean(axis = 1).round(1))\n",
"df5.columns = ['score_mean']\n",
"df5"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Python</th>\n",
" <th>Math</th>\n",
" <th>En</th>\n",
" <th>score_mean</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>40.0</td>\n",
" <td>15.0</td>\n",
" <td>90.0</td>\n",
" <td>48.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>59.0</td>\n",
" <td>52.0</td>\n",
" <td>83.0</td>\n",
" <td>64.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>14.0</td>\n",
" <td>138.0</td>\n",
" <td>137.0</td>\n",
" <td>96.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>89.0</td>\n",
" <td>78.0</td>\n",
" <td>53.0</td>\n",
" <td>73.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>81.0</td>\n",
" <td>101.0</td>\n",
" <td>3.0</td>\n",
" <td>61.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>75.0</td>\n",
" <td>79.0</td>\n",
" <td>86.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>score_mean</th>\n",
" <td>59.7</td>\n",
" <td>77.2</td>\n",
" <td>75.3</td>\n",
" <td>70.7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Python Math En score_mean\n",
"A 40.0 15.0 90.0 48.3\n",
"B 59.0 52.0 83.0 64.7\n",
"C 14.0 138.0 137.0 96.3\n",
"D 89.0 78.0 53.0 73.3\n",
"E 81.0 101.0 3.0 61.7\n",
"F 75.0 79.0 86.0 80.0\n",
"score_mean 59.7 77.2 75.3 70.7"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df4.merge(df5,left_index=True,right_index=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/8-pandas分组聚合操作.ipynb 0 → 100644
View file @ 43c147da
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# 分组聚合透视\n",
"# 很多时候属性是相似的\n",
"\n",
"import numpy as np\n",
"\n",
"import pandas as pd\n",
"\n",
"from pandas import Series,DataFrame"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Hand</th>\n",
" <th>Smoke</th>\n",
" <th>sex</th>\n",
" <th>weight</th>\n",
" <th>IQ</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>right</td>\n",
" <td>yes</td>\n",
" <td>male</td>\n",
" <td>80</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>left</td>\n",
" <td>yes</td>\n",
" <td>female</td>\n",
" <td>50</td>\n",
" <td>120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>left</td>\n",
" <td>no</td>\n",
" <td>female</td>\n",
" <td>48</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>male</td>\n",
" <td>75</td>\n",
" <td>130</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>right</td>\n",
" <td>yes</td>\n",
" <td>male</td>\n",
" <td>68</td>\n",
" <td>140</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>male</td>\n",
" <td>100</td>\n",
" <td>80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>female</td>\n",
" <td>40</td>\n",
" <td>94</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>female</td>\n",
" <td>90</td>\n",
" <td>110</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>left</td>\n",
" <td>no</td>\n",
" <td>male</td>\n",
" <td>88</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>right</td>\n",
" <td>yes</td>\n",
" <td>female</td>\n",
" <td>76</td>\n",
" <td>160</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Hand Smoke sex weight IQ\n",
"0 right yes male 80 100\n",
"1 left yes female 50 120\n",
"2 left no female 48 90\n",
"3 right no male 75 130\n",
"4 right yes male 68 140\n",
"5 right no male 100 80\n",
"6 right no female 40 94\n",
"7 right no female 90 110\n",
"8 left no male 88 100\n",
"9 right yes female 76 160"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 走右手习惯，是否抽烟，性别，对体重，智商，有一定影响\n",
"\n",
"df = DataFrame({'Hand':['right','left','left','right','right','right','right','right','left','right'],\n",
" 'Smoke':['yes','yes','no','no','yes','no','no','no','no','yes'],\n",
" 'sex':['male','female','female','male','male','male','female','female','male','female'],\n",
" 'weight':[80,50,48,75,68,100,40,90,88,76],\n",
" 'IQ':[100,120,90,130,140,80,94,110,100,160]})\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 分组聚合查看规律，某一条件下规律"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>weight</th>\n",
" <th>IQ</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Hand</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>left</th>\n",
" <td>62.0</td>\n",
" <td>103.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>right</th>\n",
" <td>75.6</td>\n",
" <td>116.3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" weight IQ\n",
"Hand \n",
"left 62.0 103.3\n",
"right 75.6 116.3"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = df.groupby(by = ['Hand'])[['weight','IQ']].mean().round(1)\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>weight</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Hand</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>left</th>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>right</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" weight\n",
"Hand \n",
"left 62.0\n",
"right 75.6"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.groupby(by = ['Hand'])[['weight']].apply(np.mean).round(1)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"df2 = df.groupby(by = ['Hand'])[['weight']].transform(np.mean).round(1)\n"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>weight_mean</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>75.6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" weight_mean\n",
"0 75.6\n",
"1 62.0\n",
"2 62.0\n",
"3 75.6\n",
"4 75.6\n",
"5 75.6\n",
"6 75.6\n",
"7 75.6\n",
"8 62.0\n",
"9 75.6"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2 = df2.add_suffix('_mean')\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Hand</th>\n",
" <th>Smoke</th>\n",
" <th>sex</th>\n",
" <th>weight</th>\n",
" <th>IQ</th>\n",
" <th>weight_mean</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>right</td>\n",
" <td>yes</td>\n",
" <td>male</td>\n",
" <td>80</td>\n",
" <td>100</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>left</td>\n",
" <td>yes</td>\n",
" <td>female</td>\n",
" <td>50</td>\n",
" <td>120</td>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>left</td>\n",
" <td>no</td>\n",
" <td>female</td>\n",
" <td>48</td>\n",
" <td>90</td>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>male</td>\n",
" <td>75</td>\n",
" <td>130</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>right</td>\n",
" <td>yes</td>\n",
" <td>male</td>\n",
" <td>68</td>\n",
" <td>140</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>male</td>\n",
" <td>100</td>\n",
" <td>80</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>female</td>\n",
" <td>40</td>\n",
" <td>94</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>right</td>\n",
" <td>no</td>\n",
" <td>female</td>\n",
" <td>90</td>\n",
" <td>110</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>left</td>\n",
" <td>no</td>\n",
" <td>male</td>\n",
" <td>88</td>\n",
" <td>100</td>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>right</td>\n",
" <td>yes</td>\n",
" <td>female</td>\n",
" <td>76</td>\n",
" <td>160</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Hand Smoke sex weight IQ weight_mean\n",
"0 right yes male 80 100 75.6\n",
"1 left yes female 50 120 62.0\n",
"2 left no female 48 90 62.0\n",
"3 right no male 75 130 75.6\n",
"4 right yes male 68 140 75.6\n",
"5 right no male 100 80 75.6\n",
"6 right no female 40 94 75.6\n",
"7 right no female 90 110 75.6\n",
"8 left no male 88 100 62.0\n",
"9 right yes female 76 160 75.6"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df3 = df.merge(df2,left_index=True,right_index=True)\n",
"df3"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Hand\n",
"left ([3, 3], [62.0, 103.3])\n",
"right ([7, 7], [75.6, 116.3])\n",
"dtype: object"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def count(x):\n",
" \n",
" return (x.count(),x.mean().round(1))\n",
"\n",
"df.groupby(by = ['Hand'])[['weight','IQ']].apply(count)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>IQ</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Hand</th>\n",
" <th>sex</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">left</th>\n",
" <th>female</th>\n",
" <td>120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>male</th>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">right</th>\n",
" <th>female</th>\n",
" <td>160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>male</th>\n",
" <td>140</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" IQ\n",
"Hand sex \n",
"left female 120\n",
" male 100\n",
"right female 160\n",
" male 140"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.groupby(by = ['Hand','sex'])[['IQ']].max()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<pandas.core.groupby.generic.DataFrameGroupBy object at 0x0000019E24051EF0>"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = df.groupby(by = ['Hand'])['IQ','weight']\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe thead tr:last-of-type th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">IQ</th>\n",
" <th colspan=\"2\" halign=\"left\">weight</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>max</th>\n",
" <th>mean</th>\n",
" <th>max</th>\n",
" <th>mean</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Hand</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>left</th>\n",
" <td>120</td>\n",
" <td>103.3</td>\n",
" <td>88</td>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>right</th>\n",
" <td>160</td>\n",
" <td>116.3</td>\n",
" <td>100</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" IQ weight \n",
" max mean max mean\n",
"Hand \n",
"left 120 103.3 88 62.0\n",
"right 160 116.3 100 75.6"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.agg(['max','mean']).round(1)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>IQ</th>\n",
" <th>weight</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Hand</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>left</th>\n",
" <td>120</td>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>right</th>\n",
" <td>160</td>\n",
" <td>75.6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" IQ weight\n",
"Hand \n",
"left 120 62.0\n",
"right 160 75.6"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.agg({'IQ':'max','weight':'mean'}).round(1)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Day76-90/code/9-pandas数据集成实战.ipynb 0 → 100644
View file @ 43c147da
This source diff could not be displayed because it is too large. You can view the blob instead.
Day76-90/code/state-abbrevs.csv 0 → 100644
View file @ 43c147da
"state","abbreviation"
"Alabama","AL"
"Alaska","AK"
"Arizona","AZ"
"Arkansas","AR"
"California","CA"
"Colorado","CO"
"Connecticut","CT"
"Delaware","DE"
"District of Columbia","DC"
"Florida","FL"
"Georgia","GA"
"Hawaii","HI"
"Idaho","ID"
"Illinois","IL"
"Indiana","IN"
"Iowa","IA"
"Kansas","KS"
"Kentucky","KY"
"Louisiana","LA"
"Maine","ME"
"Montana","MT"
"Nebraska","NE"
"Nevada","NV"
"New Hampshire","NH"
"New Jersey","NJ"
"New Mexico","NM"
"New York","NY"
"North Carolina","NC"
"North Dakota","ND"
"Ohio","OH"
"Oklahoma","OK"
"Oregon","OR"
"Maryland","MD"
"Massachusetts","MA"
"Michigan","MI"
"Minnesota","MN"
"Mississippi","MS"
"Missouri","MO"
"Pennsylvania","PA"
"Rhode Island","RI"
"South Carolina","SC"
"South Dakota","SD"
"Tennessee","TN"
"Texas","TX"
"Utah","UT"
"Vermont","VT"
"Virginia","VA"
"Washington","WA"
"West Virginia","WV"
"Wisconsin","WI"
"Wyoming","WY"
\ No newline at end of file
Day76-90/code/state-areas.csv 0 → 100644
View file @ 43c147da
state,area (sq. mi)
Alabama,52423
Alaska,656425
Arizona,114006
Arkansas,53182
California,163707
Colorado,104100
Connecticut,5544
Delaware,1954
Florida,65758
Georgia,59441
Hawaii,10932
Idaho,83574
Illinois,57918
Indiana,36420
Iowa,56276
Kansas,82282
Kentucky,40411
Louisiana,51843
Maine,35387
Maryland,12407
Massachusetts,10555
Michigan,96810
Minnesota,86943
Mississippi,48434
Missouri,69709
Montana,147046
Nebraska,77358
Nevada,110567
New Hampshire,9351
New Jersey,8722
New Mexico,121593
New York,54475
North Carolina,53821
North Dakota,70704
Ohio,44828
Oklahoma,69903
Oregon,98386
Pennsylvania,46058
Rhode Island,1545
South Carolina,32007
South Dakota,77121
Tennessee,42146
Texas,268601
Utah,84904
Vermont,9615
Virginia,42769
Washington,71303
West Virginia,24231
Wisconsin,65503
Wyoming,97818
District of Columbia,68
Puerto Rico,3515
Day76-90/code/state-population.csv 0 → 100644
View file @ 43c147da
state/region,ages,year,population
AL,under18,2012,1117489
AL,total,2012,4817528
AL,under18,2010,1130966
AL,total,2010,4785570
AL,under18,2011,1125763
AL,total,2011,4801627
AL,total,2009,4757938
AL,under18,2009,1134192
AL,under18,2013,1111481
AL,total,2013,4833722
AL,total,2007,4672840
AL,under18,2007,1132296
AL,total,2008,4718206
AL,under18,2008,1134927
AL,total,2005,4569805
AL,under18,2005,1117229
AL,total,2006,4628981
AL,under18,2006,1126798
AL,total,2004,4530729
AL,under18,2004,1113662
AL,total,2003,4503491
AL,under18,2003,1113083
AL,total,2001,4467634
AL,under18,2001,1120409
AL,total,2002,4480089
AL,under18,2002,1116590
AL,under18,1999,1121287
AL,total,1999,4430141
AL,total,2000,4452173
AL,under18,2000,1122273
AL,total,1998,4404701
AL,under18,1998,1118252
AL,under18,1997,1122893
AL,total,1997,4367935
AL,total,1996,4331103
AL,total,1995,4296800
AL,under18,1995,1110553
AL,under18,1996,1112092
AL,total,1994,4260229
AL,total,1993,4214202
AL,under18,1993,1085606
AL,under18,1994,1097180
AL,under18,1992,1072873
AL,total,1992,4154014
AL,total,1991,4099156
AL,under18,1991,1060794
AL,under18,1990,1050041
AL,total,1990,4050055
AK,total,1990,553290
AK,under18,1990,177502
AK,total,1992,588736
AK,under18,1991,182180
AK,under18,1992,184878
AK,total,1994,603308
AK,under18,1994,187439
AK,total,1991,570193
AK,total,1993,599434
AK,under18,1993,187190
AK,total,1995,604412
AK,under18,1995,184990
AK,total,1996,608569
AK,under18,1996,185360
AK,under18,1997,188280
AK,under18,1998,192636
AK,total,1998,619933
AK,total,1997,612968
AK,under18,1999,191422
AK,total,1999,624779
AK,total,2000,627963
AK,under18,2000,190615
AK,total,2001,633714
AK,under18,2001,188771
AK,total,2002,642337
AK,under18,2002,188482
AK,total,2003,648414
AK,under18,2003,186843
AK,total,2004,659286
AK,under18,2004,186335
AK,total,2005,666946
AK,under18,2005,185304
AK,total,2006,675302
AK,under18,2006,185580
AK,total,2007,680300
AK,under18,2007,184344
AK,total,2008,687455
AK,under18,2008,183124
AK,under18,2013,188132
AK,total,2013,735132
AK,total,2009,698895
AK,under18,2009,186351
AK,under18,2010,187902
AK,total,2010,713868
AK,under18,2011,188329
AK,total,2011,723375
AK,under18,2012,188162
AK,total,2012,730307
AZ,under18,2012,1617149
AZ,total,2012,6551149
AZ,under18,2011,1616353
AZ,total,2011,6468796
AZ,under18,2010,1628563
AZ,total,2010,6408790
AZ,under18,2013,1616814
AZ,total,2013,6626624
AZ,total,2009,6343154
AZ,under18,2009,1627343
AZ,total,2007,6167681
AZ,under18,2007,1607895
AZ,total,2008,6280362
AZ,under18,2008,1628651
AZ,total,2005,5839077
AZ,under18,2005,1529168
AZ,total,2006,6029141
AZ,under18,2006,1574867
AZ,total,2004,5652404
AZ,under18,2004,1484454
AZ,total,2003,5510364
AZ,under18,2003,1453671
AZ,total,2001,5273477
AZ,under18,2001,1399015
AZ,total,2002,5396255
AZ,under18,2002,1427938
AZ,under18,1999,1332396
AZ,total,1999,5023823
AZ,total,2000,5160586
AZ,under18,2000,1373414
AZ,total,1998,4883342
AZ,under18,1998,1285794
AZ,total,1997,4736990
AZ,under18,1997,1237159
AZ,under18,1996,1215285
AZ,total,1996,4586940
AZ,total,1995,4432499
AZ,under18,1995,1173391
AZ,total,1993,4065440
AZ,under18,1993,1094233
AZ,under18,1994,1119857
AZ,total,1994,4245089
AZ,under18,1992,1055572
AZ,under18,1991,1028285
AZ,total,1991,3788576
AZ,total,1992,3915740
AZ,under18,1990,1006040
AZ,total,1990,3684097
AR,under18,1990,620933
AR,total,1990,2356586
AR,total,1991,2383144
AR,under18,1991,626212
AR,under18,1992,638269
AR,total,1992,2415984
AR,under18,1994,653842
AR,total,1994,2494019
AR,total,1993,2456303
AR,under18,1993,643474
AR,under18,1995,667671
AR,total,1995,2535399
AR,under18,1996,677912
AR,total,1996,2572109
AR,under18,1998,683637
AR,total,1997,2601091
AR,under18,1997,680203
AR,total,1998,2626289
AR,total,2000,2678588
AR,under18,2000,680378
AR,under18,1999,681940
AR,total,1999,2651860
AR,total,2002,2705927
AR,under18,2002,678798
AR,total,2001,2691571
AR,under18,2001,679606
AR,total,2004,2749686
AR,under18,2004,683166
AR,total,2003,2724816
AR,under18,2003,679579
AR,total,2006,2821761
AR,under18,2006,697842
AR,total,2005,2781097
AR,under18,2005,689787
AR,total,2008,2874554
AR,under18,2008,705725
AR,total,2007,2848650
AR,under18,2007,702737
AR,total,2009,2896843
AR,under18,2009,707886
AR,under18,2013,709866
AR,total,2013,2959373
AR,under18,2011,710576
AR,total,2011,2938506
AR,under18,2010,711947
AR,total,2010,2922280
AR,under18,2012,710471
AR,total,2012,2949828
CA,under18,2012,9209007
CA,total,2012,37999878
CA,under18,2011,9252336
CA,total,2011,37668681
CA,under18,2010,9284094
CA,total,2010,37333601
CA,under18,2013,9174877
CA,total,2013,38332521
CA,total,2009,36961229
CA,under18,2009,9294501
CA,total,2007,36250311
CA,under18,2007,9335620
CA,total,2008,36604337
CA,under18,2008,9321621
CA,total,2005,35827943
CA,under18,2005,9405565
CA,total,2006,36021202
CA,under18,2006,9370884
CA,total,2003,35253159
CA,under18,2003,9404594
CA,total,2004,35574576
CA,under18,2004,9418497
CA,total,2001,34479458
CA,under18,2001,9325466
CA,total,2002,34871843
CA,under18,2002,9365142
CA,under18,1999,9207878
CA,total,1999,33499204
CA,total,2000,33987977
CA,under18,2000,9267089
CA,under18,1998,9163238
CA,total,1998,32987675
CA,under18,1997,9135359
CA,total,1997,32486010
CA,under18,1996,9079519
CA,total,1996,32018834
CA,total,1995,31696582
CA,under18,1995,8920578
CA,total,1993,31274928
CA,under18,1993,8624810
CA,under18,1994,8790058
CA,total,1994,31484435
CA,total,1991,30470736
CA,under18,1991,8245605
CA,under18,1992,8439647
CA,total,1992,30974659
CA,under18,1990,7980501
CA,total,1990,29959515
CO,total,1990,3307618
CO,under18,1990,881640
CO,total,1992,3495939
CO,under18,1992,925577
CO,under18,1991,896537
CO,total,1991,3387119
CO,total,1994,3724168
CO,under18,1994,966412
CO,under18,1993,947806
CO,total,1993,3613734
CO,under18,1995,984310
CO,total,1995,3826653
CO,total,1996,3919972
CO,under18,1996,1003946
CO,under18,1997,1030557
CO,total,1997,4018293
CO,total,1998,4116639
CO,under18,1998,1060066
CO,total,2000,4326921
CO,under18,2000,1106676
CO,total,1999,4226018
CO,under18,1999,1083938
CO,total,2002,4490406
CO,under18,2002,1138273
CO,total,2001,4425687
CO,under18,2001,1126647
CO,total,2004,4575013
CO,under18,2004,1146369
CO,total,2003,4528732
CO,under18,2003,1144597
CO,total,2006,4720423
CO,under18,2006,1171832
CO,total,2005,4631888
CO,under18,2005,1156399
CO,total,2008,4889730
CO,under18,2008,1203289
CO,total,2007,4803868
CO,under18,2007,1189434
CO,total,2009,4972195
CO,under18,2009,1217213
CO,under18,2013,1237932
CO,total,2013,5268367
CO,under18,2010,1226619
CO,total,2010,5048196
CO,under18,2011,1230178
CO,total,2011,5118400
CO,under18,2012,1232864
CO,total,2012,5189458
CT,under18,2012,794959
CT,total,2012,3591765
CT,under18,2011,805109
CT,total,2011,3588948
CT,under18,2010,814187
CT,total,2010,3579210
CT,under18,2013,785566
CT,total,2013,3596080
CT,total,2009,3561807
CT,under18,2009,820839
CT,total,2007,3527270
CT,under18,2007,833484
CT,total,2008,3545579
CT,under18,2008,826626
CT,total,2005,3506956
CT,under18,2005,844034
CT,total,2006,3517460
CT,under18,2006,839372
CT,total,2003,3484336
CT,under18,2003,851115
CT,total,2004,3496094
CT,under18,2004,848979
CT,total,2001,3432835
CT,under18,2001,845850
CT,total,2002,3458749
CT,under18,2002,848877
CT,total,1999,3386401
CT,under18,1999,834654
CT,total,2000,3411777
CT,under18,2000,842242
CT,under18,1998,824600
CT,total,1998,3365352
CT,total,1997,3349348
CT,under18,1997,814373
CT,under18,1996,811855
CT,total,1996,3336685
CT,total,1995,3324144
CT,under18,1995,808623
CT,total,1993,3309175
CT,under18,1993,790749
CT,under18,1994,801231
CT,total,1994,3316121
CT,under18,1991,766304
CT,total,1991,3302895
CT,under18,1992,777264
CT,total,1992,3300712
CT,total,1990,3291967
CT,under18,1990,752666
DE,under18,1990,165628
DE,total,1990,669567
DE,under18,1992,174166
DE,total,1992,694927
DE,total,1991,683080
DE,under18,1991,169910
DE,total,1994,717545
DE,under18,1994,180833
DE,total,1993,706378
DE,under18,1993,176916
DE,under18,1995,181736
DE,total,1995,729735
DE,total,1996,740978
DE,under18,1996,184021
DE,under18,1997,186607
DE,total,1997,751487
DE,total,1998,763335
DE,under18,1998,189302
DE,total,2000,786373
DE,under18,2000,194914
DE,total,1999,774990
DE,under18,1999,192510
DE,total,2002,806169
DE,under18,2002,196946
DE,total,2001,795699
DE,under18,2001,196038
DE,total,2004,830803
DE,under18,2004,199631
DE,total,2003,818003
DE,under18,2003,198045
DE,total,2006,859268
DE,under18,2006,203729
DE,total,2005,845150
DE,under18,2005,201988
DE,total,2008,883874
DE,under18,2008,206116
DE,total,2007,871749
DE,under18,2007,205155
DE,under18,2013,203558
DE,total,2013,925749
DE,total,2009,891730
DE,under18,2009,206213
DE,under18,2010,205478
DE,total,2010,899711
DE,under18,2011,204801
DE,total,2011,907985
DE,under18,2012,204586
DE,total,2012,917053
DC,under18,2012,107642
DC,total,2012,633427
DC,under18,2011,103906
DC,total,2011,619624
DC,under18,2010,101309
DC,total,2010,605125
DC,under18,2013,111474
DC,total,2013,646449
DC,total,2009,592228
DC,under18,2009,102098
DC,total,2007,574404
DC,under18,2007,104126
DC,total,2008,580236
DC,under18,2008,102257
DC,total,2005,567136
DC,under18,2005,107187
DC,total,2006,570681
DC,under18,2006,105651
DC,total,2003,568502
DC,under18,2003,111403
DC,total,2004,567754
DC,under18,2004,109756
DC,total,2001,574504
DC,under18,2001,114625
DC,total,2002,573158
DC,under18,2002,113822
DC,total,1999,570220
DC,under18,1999,115003
DC,total,2000,572046
DC,under18,2000,114503
DC,under18,1998,113839
DC,total,1998,565232
DC,under18,1997,119531
DC,total,1997,567739
DC,under18,1996,121210
DC,total,1996,572379
DC,total,1995,580519
DC,under18,1995,123620
DC,total,1993,595302
DC,under18,1993,120471
DC,under18,1994,122170
DC,total,1994,589240
DC,total,1991,600870
DC,under18,1991,116825
DC,under18,1992,118636
DC,total,1992,597567
DC,under18,1990,112632
DC,total,1990,605321
FL,total,1990,13033307
FL,under18,1990,2988807
FL,under18,1991,3045638
FL,total,1991,13369798
FL,total,1994,14239444
FL,under18,1994,3299887
FL,under18,1993,3214066
FL,total,1993,13927185
FL,total,1992,13650553
FL,under18,1992,3120439
FL,under18,1995,3366468
FL,total,1995,14537875
FL,total,1996,14853360
FL,under18,1996,3431695
FL,under18,1998,3557561
FL,under18,1997,3502269
FL,total,1997,15186304
FL,total,1998,15486559
FL,total,1999,15759421
FL,under18,1999,3611711
FL,total,2000,16047515
FL,under18,2000,3654880
FL,total,2001,16356966
FL,under18,2001,3714439
FL,total,2002,16689370
FL,under18,2002,3774624
FL,total,2003,17004085
FL,under18,2003,3820876
FL,total,2004,17415318
FL,under18,2004,3890734
FL,total,2005,17842038
FL,under18,2005,3968178
FL,total,2006,18166990
FL,under18,2006,4022912
FL,total,2007,18367842
FL,under18,2007,4031098
FL,total,2008,18527305
FL,under18,2008,4018372
FL,total,2009,18652644
FL,under18,2009,3997283
FL,under18,2013,4026674
FL,total,2013,19552860
FL,under18,2010,3999532
FL,total,2010,18846054
FL,under18,2011,4002550
FL,total,2011,19083482
FL,under18,2012,4012421
FL,total,2012,19320749
GA,total,2012,9915646
GA,under18,2012,2487831
GA,under18,2011,2488898
GA,total,2011,9810181
GA,under18,2010,2490884
GA,total,2010,9713248
GA,total,2013,9992167
GA,total,2009,9620846
GA,under18,2009,2485781
GA,under18,2013,2489709
GA,total,2007,9349988
GA,under18,2007,2456249
GA,total,2008,9504843
GA,under18,2008,2479097
GA,total,2005,8925922
GA,under18,2005,2353604
GA,total,2006,9155813
GA,under18,2006,2406014
GA,total,2003,8622793
GA,under18,2003,2278710
GA,total,2004,8769252
GA,under18,2004,2308855
GA,total,2001,8377038
GA,under18,2001,2215390
GA,total,2002,8508256
GA,under18,2002,2249784
GA,total,1999,8045965
GA,under18,1999,2130698
GA,total,2000,8227303
GA,under18,2000,2176576
GA,total,1997,7685099
GA,under18,1997,2034163
GA,under18,1998,2078998
GA,total,1998,7863536
GA,under18,1996,1993171
GA,total,1996,7501069
GA,total,1995,7328413
GA,under18,1995,1949818
GA,under18,1992,1817781
GA,total,1992,6817203
GA,total,1993,6978240
GA,under18,1993,1865021
GA,under18,1994,1906539
GA,total,1994,7157165
GA,total,1991,6653005
GA,under18,1991,1773675
GA,under18,1990,1747363
GA,total,1990,6512602
HI,under18,1990,279983
HI,total,1990,1113491
HI,total,1991,1136754
HI,under18,1991,287871
HI,under18,1994,307517
HI,total,1994,1187536
HI,total,1993,1172838
HI,under18,1993,301473
HI,under18,1992,295124
HI,total,1992,1158613
HI,total,1995,1196854
HI,under18,1995,310325
HI,under18,1996,311213
HI,total,1996,1203755
HI,under18,1998,304576
HI,total,1998,1215233
HI,total,1997,1211640
HI,under18,1997,309465
HI,total,2000,1213519
HI,under18,2000,295352
HI,total,1999,1210300
HI,under18,1999,299680
HI,total,2002,1239613
HI,under18,2002,293600
HI,total,2001,1225948
HI,under18,2001,294133
HI,total,2004,1273569
HI,under18,2004,298103
HI,total,2003,1251154
HI,under18,2003,294519
HI,total,2006,1309731
HI,under18,2006,299313
HI,total,2005,1292729
HI,under18,2005,298497
HI,total,2008,1332213
HI,under18,2008,301094
HI,total,2007,1315675
HI,under18,2007,300207
HI,under18,2013,307266
HI,total,2009,1346717
HI,under18,2009,302796
HI,total,2013,1404054
HI,total,2010,1363731
HI,under18,2010,303812
HI,total,2011,1376897
HI,under18,2011,305396
HI,under18,2012,305981
HI,total,2012,1390090
ID,total,2012,1595590
ID,under18,2012,427177
ID,under18,2011,428535
ID,total,2011,1583930
ID,under18,2010,428961
ID,total,2010,1570718
ID,total,2013,1612136
ID,total,2009,1554439
ID,under18,2009,426076
ID,under18,2013,427781
ID,total,2007,1505105
ID,under18,2007,415024
ID,total,2008,1534320
ID,under18,2008,422347
ID,total,2005,1428241
ID,under18,2005,394651
ID,total,2006,1468669
ID,under18,2006,404753
ID,total,2003,1363380
ID,under18,2003,379241
ID,total,2004,1391802
ID,under18,2004,384692
ID,total,2001,1319962
ID,under18,2001,373145
ID,total,2002,1340372
ID,under18,2002,375986
ID,total,1999,1275674
ID,under18,1999,366689
ID,total,2000,1299430
ID,under18,2000,370430
ID,total,1997,1228520
ID,under18,1997,357779
ID,under18,1998,362189
ID,total,1998,1252330
ID,under18,1996,353824
ID,total,1996,1203083
ID,total,1995,1177322
ID,under18,1995,349248
ID,under18,1992,324972
ID,total,1992,1071685
ID,total,1993,1108768
ID,under18,1993,333838
ID,under18,1994,344242
ID,total,1994,1145140
ID,total,1991,1041316
ID,under18,1991,316732
ID,under18,1990,313373
ID,total,1990,1012384
IL,under18,1990,2940837
IL,total,1990,11453316
IL,total,1991,11568964
IL,under18,1991,2988715
IL,under18,1994,3110938
IL,total,1994,11912585
IL,total,1993,11809579
IL,under18,1993,3066541
IL,under18,1992,3033427
IL,total,1992,11694184
IL,total,1995,12008437
IL,under18,1995,3152984
IL,under18,1996,3192916
IL,total,1996,12101997
IL,under18,1998,3225252
IL,total,1998,12271847
IL,total,1997,12185715
IL,under18,1997,3222114
IL,total,2000,12434161
IL,under18,2000,3244944
IL,total,1999,12359020
IL,under18,1999,3240034
IL,total,2002,12525556
IL,under18,2002,3238362
IL,total,2001,12488445
IL,under18,2001,3243617
IL,total,2004,12589773
IL,under18,2004,3211599
IL,total,2003,12556006
IL,under18,2003,3225547
IL,total,2006,12643955
IL,under18,2006,3181246
IL,total,2005,12609903
IL,under18,2005,3197318
IL,total,2008,12747038
IL,under18,2008,3153401
IL,total,2007,12695866
IL,under18,2007,3170134
IL,under18,2013,3023307
IL,total,2009,12796778
IL,under18,2009,3138406
IL,total,2013,12882135
IL,total,2010,12839695
IL,under18,2010,3122092
IL,total,2011,12855970
IL,under18,2011,3089833
IL,under18,2012,3057042
IL,total,2012,12868192
IN,total,2012,6537782
IN,under18,2012,1589655
IN,under18,2011,1598091
IN,total,2011,6516336
IN,under18,2010,1605883
IN,total,2010,6489965
IN,total,2013,6570902
IN,total,2009,6459325
IN,under18,2009,1609704
IN,under18,2013,1586027
IN,total,2007,6379599
IN,under18,2007,1609494
IN,total,2008,6424806
IN,under18,2008,1611494
IN,total,2005,6278616
IN,under18,2005,1593898
IN,total,2006,6332669
IN,under18,2006,1603107
IN,total,2003,6196638
IN,under18,2003,1582560
IN,total,2004,6233007
IN,under18,2004,1586281
IN,total,2001,6127760
IN,under18,2001,1579527
IN,total,2002,6155967
IN,under18,2002,1580814
IN,total,1999,6044970
IN,under18,1999,1566079
IN,total,2000,6091866
IN,under18,2000,1574989
IN,total,1997,5955267
IN,under18,1997,1539270
IN,under18,1998,1551960
IN,total,1998,5998881
IN,under18,1996,1517961
IN,total,1996,5906013
IN,total,1995,5851459
IN,under18,1995,1507916
IN,under18,1992,1461650
IN,total,1992,5674547
IN,total,1993,5739019
IN,under18,1993,1473007
IN,under18,1994,1491802
IN,total,1994,5793526
IN,total,1991,5616388
IN,under18,1991,1450759
IN,under18,1990,1437209
IN,total,1990,5557798
IA,under18,1990,719366
IA,total,1990,2781018
IA,total,1991,2797613
IA,under18,1991,724446
IA,under18,1994,728397
IA,total,1994,2850746
IA,total,1993,2836972
IA,under18,1993,727751
IA,under18,1992,724798
IA,total,1992,2818401
IA,total,1995,2867373
IA,under18,1995,726961
IA,under18,1996,729177
IA,total,1996,2880001
IA,under18,1998,729943
IA,total,1998,2902872
IA,total,1997,2891119
IA,under18,1997,729806
IA,total,2000,2929067
IA,under18,2000,733337
IA,total,1999,2917634
IA,under18,1999,732671
IA,total,2002,2934234
IA,under18,2002,723685
IA,total,2001,2931997
IA,under18,2001,728601
IA,total,2004,2953635
IA,under18,2004,718708
IA,total,2003,2941999
IA,under18,2003,720102
IA,total,2006,2982644
IA,under18,2006,721703
IA,total,2005,2964454
IA,under18,2005,718488
IA,total,2008,3016734
IA,under18,2008,725658
IA,total,2007,2999212
IA,under18,2007,723632
IA,under18,2013,724032
IA,total,2009,3032870
IA,under18,2009,726969
IA,total,2013,3090416
IA,total,2010,3050314
IA,under18,2010,727717
IA,total,2011,3064102
IA,under18,2011,725522
IA,under18,2012,723917
IA,total,2012,3075039
KS,total,2012,2885398
KS,under18,2012,726668
KS,under18,2011,726787
KS,total,2011,2869548
KS,under18,2010,727729
KS,total,2010,2858910
KS,total,2013,2893957
KS,total,2009,2832704
KS,under18,2009,721841
KS,under18,2013,724092
KS,total,2007,2783785
KS,under18,2007,711005
KS,total,2008,2808076
KS,under18,2008,714689
KS,total,2005,2745299
KS,under18,2005,704689
KS,total,2006,2762931
KS,under18,2006,705277
KS,total,2003,2723004
KS,under18,2003,707847
KS,total,2004,2734373
KS,under18,2004,705456
KS,total,2001,2702162
KS,under18,2001,710923
KS,total,2002,2713535
KS,under18,2002,709416
KS,total,1999,2678338
KS,under18,1999,713022
KS,total,2000,2693681
KS,under18,2000,713887
KS,total,1997,2635292
KS,under18,1997,704001
KS,under18,1998,710402
KS,total,1998,2660598
KS,under18,1996,696298
KS,total,1996,2614554
KS,total,1995,2601008
KS,under18,1995,694124
KS,under18,1992,680871
KS,total,1992,2532395
KS,total,1993,2556547
KS,under18,1993,687262
KS,under18,1994,693673
KS,total,1994,2580513
KS,total,1991,2498722
KS,under18,1991,672033
KS,under18,1990,662641
KS,total,1990,2481349
KY,under18,1990,945951
KY,total,1990,3694048
KY,total,1991,3722328
KY,under18,1991,951512
KY,under18,1994,981439
KY,total,1994,3849088
KY,total,1993,3812206
KY,under18,1993,971134
KY,under18,1992,963861
KY,total,1992,3765469
KY,total,1995,3887427
KY,under18,1995,984486
KY,under18,1996,987062
KY,total,1996,3919536
KY,under18,1998,997296
KY,total,1998,3985391
KY,total,1997,3952747
KY,under18,1997,1002609
KY,total,2000,4049021
KY,under18,2000,994984
KY,total,1999,4018053
KY,under18,1999,996382
KY,total,2002,4089875
KY,under18,2002,995251
KY,total,2001,4068132
KY,under18,2001,994105
KY,total,2004,4146101
KY,under18,2004,998459
KY,total,2003,4117170
KY,under18,2003,998485
KY,total,2006,4219239
KY,under18,2006,1011295
KY,total,2005,4182742
KY,under18,2005,1004020
KY,total,2008,4289878
KY,under18,2008,1022001
KY,total,2007,4256672
KY,under18,2007,1016288
KY,under18,2013,1014004
KY,total,2009,4317074
KY,under18,2009,1021710
KY,total,2013,4395295
KY,total,2010,4347698
KY,under18,2010,1023679
KY,total,2011,4366869
KY,under18,2011,1021926
KY,under18,2012,1017350
KY,total,2012,4379730
LA,total,2012,4602134
LA,under18,2012,1114620
LA,under18,2011,1116579
LA,total,2011,4575197
LA,under18,2010,1118576
LA,total,2010,4545392
LA,total,2013,4625470
LA,total,2009,4491648
LA,under18,2009,1114228
LA,under18,2013,1112957
LA,total,2007,4375581
LA,under18,2007,1096642
LA,total,2008,4435586
LA,under18,2008,1108728
LA,total,2005,4576628
LA,under18,2005,1177954
LA,total,2006,4302665
LA,under18,2006,1078779
LA,total,2003,4521042
LA,under18,2003,1188070
LA,total,2004,4552238
LA,under18,2004,1182731
LA,total,2001,4477875
LA,under18,2001,1204187
LA,total,2002,4497267
LA,under18,2002,1194819
LA,total,2000,4471885
LA,under18,2000,1217670
LA,total,1999,4460811
LA,under18,1999,1227167
LA,total,1997,4421072
LA,under18,1997,1239665
LA,under18,1998,1232984
LA,total,1998,4440344
LA,under18,1996,1244627
LA,total,1996,4398877
LA,total,1995,4378779
LA,under18,1995,1250112
LA,under18,1992,1237034
LA,total,1992,4293003
LA,total,1993,4316428
LA,under18,1993,1239161
LA,under18,1994,1247631
LA,total,1994,4347481
LA,total,1991,4253279
LA,under18,1991,1222330
LA,under18,1990,1205984
LA,total,1990,4221532
ME,under18,1990,308066
ME,total,1990,1231719
ME,total,1991,1237081
ME,under18,1991,309871
ME,under18,1994,311570
ME,total,1994,1242662
ME,total,1993,1242302
ME,under18,1993,310966
ME,under18,1992,310679
ME,total,1992,1238508
ME,total,1995,1243481
ME,under18,1995,309173
ME,under18,1996,307740
ME,total,1996,1249060
ME,under18,1998,304496
ME,total,1998,1259127
ME,total,1997,1254774
ME,under18,1997,305097
ME,total,1999,1266808
ME,under18,1999,302321
ME,total,2000,1277072
ME,under18,2000,301407
ME,total,2002,1295960
ME,under18,2002,298595
ME,total,2001,1285692
ME,under18,2001,300088
ME,total,2004,1313688
ME,under18,2004,294791
ME,total,2003,1306513
ME,under18,2003,296786
ME,total,2006,1323619
ME,under18,2006,288945
ME,total,2005,1318787
ME,under18,2005,292039
ME,total,2008,1330509
ME,under18,2008,282204
ME,total,2007,1327040
ME,under18,2007,286185
ME,under18,2013,261276
ME,total,2009,1329590
ME,under18,2009,277946
ME,total,2013,1328302
ME,total,2010,1327366
ME,under18,2010,273061
ME,total,2011,1327844
ME,under18,2011,268737
ME,under18,2012,264846
ME,total,2012,1328501
MD,total,2012,5884868
MD,under18,2012,1346235
MD,under18,2011,1348766
MD,total,2011,5840241
MD,under18,2010,1351983
MD,total,2010,5787193
MD,total,2013,5928814
MD,total,2009,5730388
MD,under18,2009,1353631
MD,under18,2013,1344522
MD,total,2007,5653408
MD,under18,2007,1369563
MD,total,2008,5684965
MD,under18,2008,1359214
MD,total,2005,5592379
MD,under18,2005,1382966
MD,total,2006,5627367
MD,under18,2006,1377756
MD,total,2003,5496269
MD,under18,2003,1379641
MD,total,2004,5546935
MD,under18,2004,1383450
MD,total,2001,5374691
MD,under18,2001,1366552
MD,total,2002,5440389
MD,under18,2002,1375354
MD,total,2000,5311034
MD,under18,2000,1356961
MD,total,1999,5254509
MD,under18,1999,1348659
MD,total,1997,5157328
MD,under18,1997,1321306
MD,under18,1998,1338727
MD,total,1998,5204464
MD,under18,1996,1303816
MD,total,1996,5111986
MD,total,1995,5070033
MD,under18,1995,1300695
MD,under18,1992,1235498
MD,total,1992,4923369
MD,total,1993,4971889
MD,under18,1993,1261738
MD,under18,1994,1280772
MD,total,1994,5023060
MD,total,1991,4867641
MD,under18,1991,1208898
MD,under18,1990,1180426
MD,total,1990,4799770
MA,under18,1990,1353806
MA,total,1990,6022639
MA,total,1991,6018470
MA,under18,1991,1375110
MA,under18,1994,1437069
MA,total,1994,6095241
MA,total,1993,6060569
MA,under18,1993,1415724
MA,under18,1992,1390188
MA,total,1992,6028709
MA,total,1995,6141445
MA,under18,1995,1453489
MA,under18,1996,1468614
MA,total,1996,6179756
MA,under18,1998,1491652
MA,total,1998,6271838
MA,total,1997,6226058
MA,under18,1997,1478203
MA,total,1999,6317345
MA,under18,1999,1495818
MA,total,2000,6361104
MA,under18,2000,1501334
MA,total,2001,6397634
MA,under18,2001,1505028
MA,total,2002,6417206
MA,under18,2002,1502652
MA,total,2004,6412281
MA,under18,2004,1479541
MA,total,2003,6422565
MA,under18,2003,1493372
MA,total,2006,6410084
MA,under18,2006,1450202
MA,total,2005,6403290
MA,under18,2005,1464140
MA,total,2008,6468967
MA,under18,2008,1429727
MA,total,2007,6431559
MA,under18,2007,1439757
MA,under18,2013,1393946
MA,total,2009,6517613
MA,under18,2009,1422935
MA,total,2013,6692824
MA,total,2010,6563263
MA,under18,2010,1415962
MA,total,2011,6606285
MA,under18,2011,1407240
MA,under18,2012,1399417
MA,total,2012,6645303
MI,total,2012,9882519
MI,under18,2012,2269365
MI,under18,2011,2299116
MI,total,2011,9874589
MI,under18,2010,2333121
MI,total,2010,9876149
MI,total,2013,9895622
MI,total,2009,9901591
MI,under18,2009,2372603
MI,under18,2013,2245201
MI,total,2007,10001284
MI,under18,2007,2470063
MI,total,2008,9946889
MI,under18,2008,2418879
MI,total,2005,10051137
MI,under18,2005,2531839
MI,total,2006,10036081
MI,under18,2006,2503548
MI,total,2003,10041152
MI,under18,2003,2569080
MI,total,2004,10055315
MI,under18,2004,2553314
MI,total,2002,10015710
MI,under18,2002,2584310
MI,total,2001,9991120
MI,under18,2001,2593310
MI,total,2000,9952450
MI,under18,2000,2596114
MI,total,1999,9897116
MI,under18,1999,2591944
MI,total,1997,9809051
MI,under18,1997,2582270
MI,under18,1998,2586343
MI,total,1998,9847942
MI,under18,1996,2569745
MI,total,1996,9758645
MI,total,1995,9676211
MI,under18,1995,2556799
MI,under18,1992,2501765
MI,total,1992,9479065
MI,total,1993,9540114
MI,under18,1993,2522249
MI,under18,1994,2535196
MI,total,1994,9597737
MI,total,1991,9400446
MI,under18,1991,2484957
MI,under18,1990,2459633
MI,total,1990,9311319
MN,under18,1990,1176680
MN,total,1990,4389857
MN,total,1991,4440859
MN,under18,1991,1191207
MN,under18,1994,1238949
MN,total,1994,4610355
MN,total,1993,4555956
MN,under18,1993,1226723
MN,under18,1992,1213068
MN,total,1992,4495572
MN,total,1995,4660180
MN,under18,1995,1245932
MN,under18,1996,1252722
MN,total,1996,4712827
MN,under18,1998,1275940
MN,total,1998,4813412
MN,total,1997,4763390
MN,under18,1997,1264250
MN,total,1999,4873481
MN,under18,1999,1283102
MN,total,2000,4933692
MN,under18,2000,1289715
MN,total,2001,4982796
MN,under18,2001,1291261
MN,total,2002,5018935
MN,under18,2002,1288795
MN,total,2004,5087713
MN,under18,2004,1281946
MN,total,2003,5053572
MN,under18,2003,1283687
MN,total,2006,5163555
MN,under18,2006,1282381
MN,total,2005,5119598
MN,under18,2005,1280557
MN,total,2008,5247018
MN,under18,2008,1284179
MN,total,2007,5207203
MN,under18,2007,1285074
MN,under18,2013,1279111
MN,total,2009,5281203
MN,under18,2009,1284103
MN,total,2013,5420380
MN,total,2010,5310337
MN,under18,2010,1282693
MN,total,2011,5347108
MN,under18,2011,1280424
MN,under18,2012,1278050
MN,total,2012,5379646
MS,total,2012,2986450
MS,under18,2012,742941
MS,under18,2011,747742
MS,total,2011,2977886
MS,under18,2010,754111
MS,total,2010,2970047
MS,total,2013,2991207
MS,total,2009,2958774
MS,under18,2009,758539
MS,under18,2013,737432
MS,total,2007,2928350
MS,under18,2007,761171
MS,total,2008,2947806
MS,under18,2008,760572
MS,total,2005,2905943
MS,under18,2005,760870
MS,total,2006,2904978
MS,under18,2006,756990
MS,total,2003,2868312
MS,under18,2003,759447
MS,total,2004,2889010
MS,under18,2004,760410
MS,total,2002,2858681
MS,under18,2002,763148
MS,total,2001,2852994
MS,under18,2001,768418
MS,total,2000,2848353
MS,under18,2000,774353
MS,total,1999,2828408
MS,under18,1999,775662
MS,total,1997,2777004
MS,under18,1997,774832
MS,under18,1998,773721
MS,total,1998,2804834
MS,under18,1996,769680
MS,total,1996,2748085
MS,total,1995,2722659
MS,under18,1995,767892
MS,under18,1992,750224
MS,total,1992,2623734
MS,total,1993,2655100
MS,under18,1993,755820
MS,under18,1994,763795
MS,total,1994,2688992
MS,total,1991,2598733
MS,under18,1991,738911
MS,under18,1990,733660
MS,total,1990,2578897
MO,under18,1990,1316423
MO,total,1990,5128880
MO,total,1991,5170800
MO,under18,1991,1332306
MO,under18,1994,1378700
MO,total,1994,5324497
MO,total,1993,5271175
MO,under18,1993,1365903
MO,under18,1992,1349729
MO,total,1992,5217101
MO,under18,1996,1408732
MO,total,1996,5431553
MO,total,1995,5378247
MO,under18,1995,1393554
MO,under18,1998,1428999
MO,total,1998,5521765
MO,total,1997,5481193
MO,under18,1997,1419837
MO,total,1999,5561948
MO,under18,1999,1428047
MO,total,2000,5607285
MO,under18,2000,1428383
MO,total,2001,5641142
MO,under18,2001,1426575
MO,total,2002,5674825
MO,under18,2002,1424513
MO,total,2004,5747741
MO,under18,2004,1420956
MO,total,2003,5709403
MO,under18,2003,1421927
MO,total,2006,5842704
MO,under18,2006,1428324
MO,total,2005,5790300
MO,under18,2005,1422978
MO,total,2008,5923916
MO,under18,2008,1428945
MO,total,2007,5887612
MO,under18,2007,1431346
MO,under18,2013,1397685
MO,total,2009,5961088
MO,under18,2009,1426603
MO,total,2013,6044171
MO,total,2010,5996063
MO,under18,2010,1424042
MO,total,2011,6010065
MO,under18,2011,1414444
MO,under18,2012,1405015
MO,total,2012,6024522
MT,total,2012,1005494
MT,under18,2012,222905
MT,under18,2011,222977
MT,total,2011,997600
MT,under18,2010,223292
MT,total,2010,990527
MT,total,2013,1015165
MT,total,2009,983982
MT,under18,2009,223675
MT,under18,2013,223981
MT,total,2007,964706
MT,under18,2007,223135
MT,total,2008,976415
MT,under18,2008,223814
MT,total,2005,940102
MT,under18,2005,221685
MT,total,2006,952692
MT,under18,2006,221930
MT,total,2003,919630
MT,under18,2003,223012
MT,total,2004,930009
MT,under18,2004,221999
MT,total,2002,911667
MT,under18,2002,224772
MT,total,2001,906961
MT,under18,2001,227118
MT,total,1999,897508
MT,under18,1999,231133
MT,total,2000,903773
MT,under18,2000,230067
MT,total,1997,889865
MT,under18,1997,232813
MT,under18,1998,231746
MT,total,1998,892431
MT,total,1995,876553
MT,under18,1995,236583
MT,under18,1996,235294
MT,total,1996,886254
MT,under18,1992,230868
MT,total,1992,825770
MT,total,1993,844761
MT,under18,1993,234987
MT,under18,1994,237289
MT,total,1994,861306
MT,total,1991,809680
MT,under18,1991,225259
MT,under18,1990,223677
MT,total,1990,800204
NE,under18,1990,430068
NE,total,1990,1581660
NE,total,1991,1595919
NE,under18,1991,434525
NE,under18,1994,442589
NE,total,1994,1639041
NE,total,1993,1625590
NE,under18,1993,439313
NE,under18,1992,436378
NE,total,1992,1611687
NE,under18,1996,446841
NE,total,1996,1673740
NE,total,1995,1656993
NE,under18,1995,444418
NE,under18,1998,451192
NE,total,1998,1695817
NE,total,1997,1686418
NE,under18,1997,450076
NE,total,1999,1704764
NE,under18,1999,451047
NE,total,2000,1713820
NE,under18,2000,450380
NE,total,2001,1719836
NE,under18,2001,448307
NE,total,2002,1728292
NE,under18,2002,447714
NE,total,2004,1749370
NE,under18,2004,448360
NE,total,2003,1738643
NE,under18,2003,447444
NE,total,2006,1772693
NE,under18,2006,450098
NE,total,2005,1761497
NE,under18,2005,448918
NE,total,2008,1796378
NE,under18,2008,453787
NE,total,2007,1783440
NE,under18,2007,451946
NE,under18,2013,464348
NE,total,2009,1812683
NE,under18,2009,456543
NE,total,2013,1868516
NE,total,2010,1829838
NE,under18,2010,459621
NE,total,2011,1841749
NE,under18,2011,460872
NE,under18,2012,462673
NE,total,2012,1855350
NV,total,2012,2754354
NV,under18,2012,659655
NV,under18,2011,659236
NV,total,2011,2717951
NV,under18,2010,663180
NV,total,2010,2703230
NV,total,2013,2790136
NV,total,2009,2684665
NV,under18,2009,666041
NV,under18,2013,661605
NV,total,2007,2601072
NV,under18,2007,654053
NV,total,2008,2653630
NV,under18,2008,662621
NV,total,2005,2432143
NV,under18,2005,611595
NV,total,2006,2522658
NV,under18,2006,634403
NV,total,2003,2248850
NV,under18,2003,568963
NV,total,2004,2346222
NV,under18,2004,591314
NV,total,2002,2173791
NV,under18,2002,552816
NV,total,2001,2098399
NV,under18,2001,534708
NV,total,1999,1934718
NV,under18,1999,493701
NV,total,2000,2018741
NV,under18,2000,516018
NV,total,1997,1764104
NV,under18,1997,443626
NV,under18,1998,469424
NV,total,1998,1853192
NV,total,1995,1581578
NV,under18,1995,396223
NV,under18,1996,419133
NV,total,1996,1666320
NV,under18,1992,337396
NV,total,1992,1351367
NV,total,1993,1411215
NV,under18,1993,354990
NV,under18,1994,376745
NV,total,1994,1499298
NV,total,1991,1296172
NV,under18,1991,325033
NV,under18,1990,316406
NV,total,1990,1220695
NH,under18,1990,277454
NH,total,1990,1112384
NH,total,1991,1109929
NH,under18,1991,281127
NH,under18,1994,295563
NH,total,1994,1142561
NH,total,1993,1129458
NH,under18,1993,290409
NH,under18,1992,286314
NH,total,1992,1117785
NH,under18,1996,300161
NH,total,1996,1174719
NH,total,1995,1157561
NH,under18,1995,298246
NH,under18,1998,307292
NH,total,1998,1205941
NH,total,1997,1189425
NH,under18,1997,302834
NH,total,2000,1239882
NH,under18,2000,310352
NH,total,1999,1222015
NH,under18,1999,308423
NH,total,2001,1255517
NH,under18,2001,311877
NH,total,2002,1269089
NH,under18,2002,312743
NH,total,2004,1290121
NH,under18,2004,309243
NH,total,2003,1279840
NH,under18,2003,311412
NH,total,2005,1298492
NH,under18,2005,307403
NH,total,2006,1308389
NH,under18,2006,305169
NH,total,2008,1315906
NH,under18,2008,296029
NH,total,2007,1312540
NH,under18,2007,300918
NH,under18,2013,271122
NH,total,2009,1316102
NH,under18,2009,290850
NH,total,2013,1323459
NH,total,2010,1316614
NH,under18,2010,285702
NH,total,2011,1318075
NH,under18,2011,280486
NH,under18,2012,275818
NH,total,2012,1321617
NJ,total,2012,8867749
NJ,under18,2012,2035106
NJ,under18,2011,2049453
NJ,total,2011,8836639
NJ,under18,2010,2062013
NJ,total,2010,8802707
NJ,total,2013,8899339
NJ,total,2009,8755602
NJ,under18,2009,2068684
NJ,under18,2013,2022117
NJ,total,2007,8677885
NJ,under18,2007,2091023
NJ,total,2008,8711090
NJ,under18,2008,2076366
NJ,total,2006,8661679
NJ,under18,2006,2106403
NJ,total,2005,8651974
NJ,under18,2005,2121878
NJ,total,2003,8601402
NJ,under18,2003,2126014
NJ,total,2004,8634561
NJ,under18,2004,2129051
NJ,total,2002,8552643
NJ,under18,2002,2116591
NJ,total,2001,8492671
NJ,under18,2001,2102838
NJ,total,1999,8359592
NJ,under18,1999,2066678
NJ,total,2000,8430621
NJ,under18,2000,2088885
NJ,total,1997,8218808
NJ,under18,1997,2028349
NJ,under18,1998,2042080
NJ,total,1998,8287418
NJ,total,1995,8083242
NJ,under18,1995,1997187
NJ,under18,1996,2016502
NJ,total,1996,8149596
NJ,under18,1992,1890108
NJ,total,1992,7880508
NJ,total,1993,7948915
NJ,under18,1993,1928623
NJ,under18,1994,1968232
NJ,total,1994,8014306
NJ,total,1991,7814676
NJ,under18,1991,1849605
NJ,under18,1990,1818187
NJ,total,1990,7762963
NM,total,1990,1521574
NM,under18,1990,453538
NM,under18,1991,461811
NM,total,1991,1555305
NM,under18,1994,497542
NM,under18,1993,487742
NM,total,1993,1636453
NM,total,1992,1595442
NM,under18,1992,473176
NM,total,1994,1682398
NM,under18,1996,508100
NM,total,1995,1720394
NM,under18,1995,504558
NM,total,1996,1752326
NM,under18,1998,512801
NM,total,1998,1793484
NM,total,1997,1774839
NM,under18,1997,514500
NM,under18,1999,511135
NM,total,1999,1808082
NM,total,2000,1821204
NM,under18,2000,508132
NM,total,2001,1831690
NM,under18,2001,503404
NM,total,2002,1855309
NM,under18,2002,502779
NM,total,2004,1903808
NM,under18,2004,501184
NM,total,2003,1877574
NM,under18,2003,500777
NM,total,2005,1932274
NM,under18,2005,502612
NM,total,2006,1962137
NM,under18,2006,505125
NM,total,2008,2010662
NM,under18,2008,511214
NM,total,2007,1990070
NM,under18,2007,508725
NM,under18,2013,507540
NM,total,2013,2085287
NM,total,2009,2036802
NM,under18,2009,515470
NM,total,2010,2064982
NM,under18,2010,518763
NM,under18,2011,516513
NM,total,2011,2077919
NM,under18,2012,512314
NM,total,2012,2083540
NY,total,2012,19576125
NY,under18,2012,4264694
NY,total,2011,19502728
NY,under18,2011,4294555
NY,under18,2010,4318033
NY,total,2010,19398228
NY,total,2009,19307066
NY,under18,2009,4342926
NY,total,2013,19651127
NY,under18,2013,4239976
NY,total,2007,19132335
NY,under18,2007,4410949
NY,total,2008,19212436
NY,under18,2008,4372170
NY,total,2006,19104631
NY,under18,2006,4457777
NY,total,2005,19132610
NY,under18,2005,4514456
NY,total,2003,19175939
NY,under18,2003,4619506
NY,total,2004,19171567
NY,under18,2004,4574065
NY,total,2002,19137800
NY,under18,2002,4652232
NY,total,2001,19082838
NY,under18,2001,4672425
NY,under18,1999,4672587
NY,total,1999,18882725
NY,total,2000,19001780
NY,under18,2000,4687374
NY,under18,1997,4670787
NY,total,1997,18656546
NY,total,1998,18755906
NY,under18,1998,4652140
NY,total,1996,18588460
NY,under18,1995,4648419
NY,total,1995,18524104
NY,under18,1996,4667647
NY,total,1994,18459470
NY,under18,1992,4465539
NY,total,1992,18246653
NY,total,1993,18374954
NY,under18,1993,4538171
NY,under18,1994,4605284
NY,total,1991,18122510
NY,under18,1991,4372727
NY,under18,1990,4281643
NY,total,1990,18020784
NC,under18,1990,1625804
NC,total,1990,6664016
NC,total,1991,6784280
NC,under18,1991,1640394
NC,total,1993,7042818
NC,under18,1993,1710267
NC,under18,1992,1674144
NC,total,1992,6897214
NC,under18,1994,1750754
NC,total,1994,7187398
NC,total,1995,7344674
NC,under18,1995,1785150
NC,under18,1996,1821506
NC,total,1996,7500670
NC,under18,1998,1894753
NC,total,1998,7809122
NC,total,1997,7656825
NC,under18,1997,1861621
NC,total,2000,8081614
NC,under18,2000,1967626
NC,total,1999,7949362
NC,under18,1999,1932141
NC,total,2001,8210122
NC,under18,2001,2003782
NC,total,2002,8326201
NC,under18,2002,2034451
NC,total,2004,8553152
NC,under18,2004,2085165
NC,total,2003,8422501
NC,under18,2003,2060838
NC,total,2005,8705407
NC,under18,2005,2122485
NC,total,2006,8917270
NC,under18,2006,2166393
NC,total,2008,9309449
NC,under18,2008,2252101
NC,total,2007,9118037
NC,under18,2007,2219168
NC,under18,2013,2285605
NC,total,2013,9848060
NC,total,2009,9449566
NC,under18,2009,2272955
NC,total,2010,9559533
NC,under18,2010,2282288
NC,under18,2011,2284238
NC,total,2011,9651377
NC,under18,2012,2284122
NC,total,2012,9748364
ND,total,2012,701345
ND,under18,2012,156765
ND,total,2011,684867
ND,under18,2011,152357
ND,under18,2010,150179
ND,total,2010,674344
ND,total,2009,664968
ND,under18,2009,148674
ND,total,2013,723393
ND,under18,2013,162688
ND,total,2007,652822
ND,under18,2007,147263
ND,total,2008,657569
ND,under18,2008,147462
ND,total,2006,649422
ND,under18,2006,147331
ND,total,2005,646089
ND,under18,2005,148119
ND,total,2003,638817
ND,under18,2003,150406
ND,total,2004,644705
ND,under18,2004,149128
ND,total,2002,638168
ND,under18,2002,153097
ND,total,2001,639062
ND,under18,2001,156113
ND,total,1999,644259
ND,under18,1999,163056
ND,total,2000,642023
ND,under18,2000,160477
ND,total,1997,649716
ND,under18,1997,167475
ND,under18,1998,165448
ND,total,1998,647532
ND,under18,1996,169257
ND,total,1996,650382
ND,total,1995,647832
ND,under18,1995,171146
ND,under18,1994,172160
ND,total,1994,644806
ND,under18,1992,172052
ND,total,1992,638223
ND,total,1993,641216
ND,under18,1993,172168
ND,total,1991,635753
ND,under18,1991,171730
ND,under18,1990,170920
ND,total,1990,637685
OH,under18,1990,2778491
OH,total,1990,10864162
OH,total,1991,10945762
OH,under18,1991,2806959
OH,total,1993,11101140
OH,under18,1993,2855785
OH,under18,1992,2839356
OH,total,1992,11029431
OH,under18,1994,2875397
OH,total,1994,11152455
OH,total,1995,11202751
OH,under18,1995,2879930
OH,under18,1996,2883443
OH,total,1996,11242827
OH,under18,1998,2896255
OH,total,1998,11311536
OH,total,1997,11277357
OH,under18,1997,2897375
OH,total,2000,11363543
OH,under18,2000,2886585
OH,total,1999,11335454
OH,under18,1999,2893270
OH,total,2001,11387404
OH,under18,2001,2878123
OH,total,2002,11407889
OH,under18,2002,2865674
OH,total,2004,11452251
OH,under18,2004,2836068
OH,total,2003,11434788
OH,under18,2003,2849573
OH,total,2005,11463320
OH,under18,2005,2819794
OH,total,2006,11481213
OH,under18,2006,2804828
OH,total,2008,11515391
OH,under18,2008,2768968
OH,total,2007,11500468
OH,under18,2007,2790347
OH,under18,2013,2649830
OH,total,2013,11570808
OH,total,2009,11528896
OH,under18,2009,2748051
OH,total,2010,11545435
OH,under18,2010,2722589
OH,under18,2011,2693469
OH,total,2011,11549772
OH,under18,2012,2668125
OH,total,2012,11553031
OK,total,2012,3815780
OK,under18,2012,939911
OK,total,2011,3785534
OK,under18,2011,935714
OK,under18,2010,931483
OK,total,2010,3759263
OK,total,2009,3717572
OK,under18,2009,922711
OK,total,2013,3850568
OK,under18,2013,947027
OK,total,2007,3634349
OK,under18,2007,904328
OK,total,2008,3668976
OK,under18,2008,910617
OK,total,2006,3594090
OK,under18,2006,894761
OK,total,2005,3548597
OK,under18,2005,885316
OK,total,2003,3504892
OK,under18,2003,883959
OK,total,2004,3525233
OK,under18,2004,881606
OK,total,2002,3489080
OK,under18,2002,884961
OK,total,2001,3467100
OK,under18,2001,885218
OK,total,1999,3437148
OK,under18,1999,895678
OK,total,2000,3454365
OK,under18,2000,891847
OK,total,1997,3372918
OK,under18,1997,893835
OK,under18,1998,898501
OK,total,1998,3405194
OK,under18,1996,887093
OK,total,1996,3340129
OK,total,1995,3308208
OK,under18,1995,883667
OK,under18,1994,877803
OK,total,1994,3280940
OK,under18,1992,862548
OK,total,1992,3220517
OK,total,1993,3252285
OK,under18,1993,870137
OK,total,1991,3175440
OK,under18,1991,849639
OK,under18,1990,841715
OK,total,1990,3148825
OR,under18,1990,742436
OR,total,1990,2860375
OR,total,1991,2928507
OR,under18,1991,752442
OR,total,1993,3060367
OR,under18,1993,778973
OR,under18,1992,770191
OR,total,1992,2991755
OR,under18,1994,793435
OR,total,1994,3121264
OR,total,1995,3184369
OR,under18,1995,806512
OR,under18,1996,816102
OR,total,1996,3247111
OR,under18,1998,837928
OR,total,1998,3352449
OR,total,1997,3304310
OR,under18,1997,830002
OR,total,2000,3429708
OR,under18,2000,847511
OR,total,1999,3393941
OR,under18,1999,843484
OR,total,2001,3467937
OR,under18,2001,848663
OR,total,2002,3513424
OR,under18,2002,850733
OR,total,2004,3569463
OR,under18,2004,846786
OR,total,2003,3547376
OR,under18,2003,850251
OR,total,2005,3613202
OR,under18,2005,849323
OR,total,2006,3670883
OR,under18,2006,857003
OR,total,2008,3768748
OR,under18,2008,865664
OR,total,2007,3722417
OR,under18,2007,862161
OR,under18,2013,857606
OR,total,2013,3930065
OR,total,2009,3808600
OR,under18,2009,866194
OR,total,2010,3837208
OR,under18,2010,865129
OR,under18,2011,862518
OR,total,2011,3867937
OR,under18,2012,859910
OR,total,2012,3899801
PA,total,2012,12764475
PA,under18,2012,2737905
PA,total,2011,12741310
PA,under18,2011,2761343
PA,under18,2010,2785316
PA,total,2010,12710472
PA,total,2009,12666858
PA,under18,2009,2804929
PA,total,2013,12773801
PA,under18,2013,2715645
PA,total,2007,12563937
PA,under18,2007,2839574
PA,total,2008,12612285
PA,under18,2008,2821004
PA,total,2006,12510809
PA,under18,2006,2850778
PA,total,2005,12449990
PA,under18,2005,2859793
PA,total,2003,12374658
PA,under18,2003,2883270
PA,total,2004,12410722
PA,under18,2004,2873125
PA,total,2002,12331031
PA,under18,2002,2894935
PA,total,2001,12298970
PA,under18,2001,2905836
PA,total,1999,12263805
PA,under18,1999,2930193
PA,total,2000,12284173
PA,under18,2000,2918850
PA,total,1997,12227814
PA,under18,1997,2942240
PA,under18,1998,2940285
PA,total,1998,12245672
PA,under18,1996,2937411
PA,total,1996,12220464
PA,total,1995,12198403
PA,under18,1995,2941531
PA,under18,1994,2932851
PA,total,1994,12166050
PA,under18,1992,2873013
PA,total,1992,12049450
PA,total,1993,12119724
PA,under18,1993,2907351
PA,total,1991,11982164
PA,under18,1991,2830059
PA,under18,1990,2799168
PA,total,1990,11903299
RI,under18,1990,225923
RI,total,1990,1005995
RI,total,1991,1010649
RI,under18,1991,229448
RI,total,1993,1015113
RI,under18,1993,237218
RI,under18,1992,232630
RI,total,1992,1012581
RI,under18,1994,239100
RI,total,1994,1015960
RI,total,1995,1017002
RI,under18,1995,240553
RI,under18,1996,240569
RI,total,1996,1020893
RI,under18,1998,241760
RI,total,1998,1031155
RI,total,1997,1025353
RI,under18,1997,242079
RI,total,2000,1050268
RI,under18,2000,248065
RI,total,1999,1040402
RI,under18,1999,247014
RI,total,2001,1057142
RI,under18,2001,248296
RI,total,2002,1065995
RI,under18,2002,248690
RI,total,2004,1074579
RI,under18,2004,246228
RI,total,2003,1071342
RI,under18,2003,248075
RI,total,2005,1067916
RI,under18,2005,241932
RI,total,2006,1063096
RI,under18,2006,237348
RI,total,2008,1055003
RI,under18,2008,229798
RI,total,2007,1057315
RI,under18,2007,233655
RI,under18,2013,213987
RI,total,2013,1051511
RI,total,2009,1053646
RI,under18,2009,225902
RI,total,2010,1052669
RI,under18,2010,223088
RI,under18,2011,219783
RI,total,2011,1050350
RI,under18,2012,216591
RI,total,2012,1050304
SC,total,2012,4723417
SC,under18,2012,1077455
SC,total,2011,4673509
SC,under18,2011,1076524
SC,under18,2010,1079978
SC,total,2010,4636361
SC,total,2009,4589872
SC,under18,2009,1079729
SC,total,2013,4774839
SC,under18,2013,1079798
SC,total,2007,4444110
SC,under18,2007,1064190
SC,total,2008,4528996
SC,under18,2008,1074116
SC,total,2006,4357847
SC,under18,2006,1050042
SC,total,2005,4270150
SC,under18,2005,1036941
SC,total,2003,4150297
SC,under18,2003,1023785
SC,total,2004,4210921
SC,under18,2004,1029111
SC,total,2002,4107795
SC,under18,2002,1020531
SC,total,2001,4064995
SC,under18,2001,1016134
SC,total,1999,3974682
SC,under18,1999,1007050
SC,total,2000,4024223
SC,under18,2000,1010641
SC,total,1997,3859696
SC,under18,1997,1001681
SC,under18,1998,1006371
SC,total,1998,3919235
SC,under18,1996,987576
SC,total,1996,3796200
SC,total,1995,3748582
SC,under18,1995,975884
SC,under18,1994,969766
SC,total,1994,3705397
SC,under18,1992,947868
SC,total,1992,3620464
SC,total,1993,3663314
SC,under18,1993,956951
SC,total,1991,3570404
SC,under18,1991,936122
SC,under18,1990,921041
SC,total,1990,3501155
SD,under18,1990,199453
SD,total,1990,697101
SD,total,1991,703669
SD,under18,1991,201749
SD,total,1993,722160
SD,under18,1993,207975
SD,under18,1992,206632
SD,total,1992,712801
SD,under18,1994,208443
SD,total,1994,730790
SD,total,1995,737926
SD,under18,1995,207890
SD,under18,1996,205780
SD,total,1996,742214
SD,under18,1998,204786
SD,total,1998,746059
SD,total,1997,744223
SD,under18,1997,205978
SD,total,2000,755844
SD,under18,2000,202681
SD,total,1999,750413
SD,under18,1999,203737
SD,total,2001,757972
SD,under18,2001,200795
SD,total,2002,760020
SD,under18,2002,198694
SD,total,2004,770396
SD,under18,2004,196804
SD,total,2003,763729
SD,under18,2003,197326
SD,total,2005,775493
SD,under18,2005,196476
SD,total,2006,783033
SD,under18,2006,197332
SD,total,2008,799124
SD,under18,2008,199848
SD,total,2007,791623
SD,under18,2007,198847
SD,under18,2013,207959
SD,total,2013,844877
SD,total,2009,807067
SD,under18,2009,201204
SD,total,2010,816211
SD,under18,2010,203145
SD,under18,2011,203948
SD,total,2011,823772
SD,under18,2012,205298
SD,total,2012,834047
TN,total,2012,6454914
TN,under18,2012,1492689
TN,total,2011,6398361
TN,under18,2011,1491837
TN,under18,2010,1495090
TN,total,2010,6356683
TN,total,2009,6306019
TN,under18,2009,1494687
TN,total,2013,6495978
TN,under18,2013,1491577
TN,total,2007,6175727
TN,under18,2007,1482747
TN,total,2008,6247411
TN,under18,2008,1494354
TN,total,2006,6088766
TN,under18,2006,1470166
TN,total,2005,5991057
TN,under18,2005,1449326
TN,total,2003,5847812
TN,under18,2003,1424861
TN,total,2004,5910809
TN,under18,2004,1433343
TN,total,2002,5795918
TN,under18,2002,1414857
TN,total,2001,5750789
TN,under18,2001,1407578
TN,total,1999,5638706
TN,under18,1999,1385997
TN,total,2000,5703719
TN,under18,2000,1399685
TN,total,1997,5499233
TN,under18,1997,1359030
TN,under18,1998,1369987
TN,total,1998,5570045
TN,under18,1996,1345723
TN,total,1996,5416643
TN,total,1995,5326936
TN,under18,1995,1331616
TN,under18,1994,1310988
TN,total,1994,5231438
TN,under18,1992,1259458
TN,total,1992,5049742
TN,total,1993,5137584
TN,under18,1993,1285044
TN,total,1991,4966587
TN,under18,1991,1233260
TN,under18,1990,1220200
TN,total,1990,4894492
TX,under18,1990,4906220
TX,total,1990,17056755
TX,total,1991,17398005
TX,under18,1991,5000793
TX,total,1993,18161612
TX,under18,1993,5217899
TX,under18,1992,5109805
TX,total,1992,17759738
TX,under18,1994,5331524
TX,total,1994,18564062
TX,total,1995,18958751
TX,under18,1995,5421784
TX,under18,1996,5551447
TX,total,1996,19340342
TX,under18,1998,5759054
TX,total,1998,20157531
TX,total,1997,19740317
TX,under18,1997,5655482
TX,total,2000,20944499
TX,under18,2000,5906301
TX,total,1999,20558220
TX,under18,1999,5840211
TX,total,2001,21319622
TX,under18,2001,5980187
TX,total,2002,21690325
TX,under18,2002,6060372
TX,total,2004,22394023
TX,under18,2004,6208259
TX,total,2003,22030931
TX,under18,2003,6132980
TX,total,2005,22778123
TX,under18,2005,6290970
TX,total,2006,23359580
TX,under18,2006,6446798
TX,total,2008,24309039
TX,under18,2008,6675917
TX,total,2007,23831983
TX,under18,2007,6565872
TX,under18,2013,7041986
TX,total,2013,26448193
TX,total,2009,24801761
TX,under18,2009,6792907
TX,total,2010,25245178
TX,under18,2010,6879014
TX,under18,2011,6931758
TX,total,2011,25640909
TX,under18,2012,6985807
TX,total,2012,26060796
UT,total,2012,2854871
UT,under18,2012,888578
UT,total,2011,2814784
UT,under18,2011,881350
UT,under18,2010,873019
UT,total,2010,2774424
UT,total,2009,2723421
UT,under18,2009,857853
UT,total,2013,2900872
UT,under18,2013,896589
UT,total,2007,2597746
UT,under18,2007,815496
UT,total,2008,2663029
UT,under18,2008,837258
UT,total,2006,2525507
UT,under18,2006,789957
UT,total,2005,2457719
UT,under18,2005,767888
UT,total,2003,2360137
UT,under18,2003,740483
UT,total,2004,2401580
UT,under18,2004,751771
UT,total,2002,2324815
UT,under18,2002,733517
UT,total,2001,2283715
UT,under18,2001,726819
UT,total,1999,2203482
UT,under18,1999,715398
UT,total,2000,2244502
UT,under18,2000,721686
UT,total,1997,2119784
UT,under18,1997,699528
UT,under18,1998,709386
UT,total,1998,2165961
UT,under18,1996,687078
UT,total,1996,2067976
UT,total,1995,2014179
UT,under18,1995,679636
UT,under18,1994,673935
UT,total,1994,1960446
UT,under18,1992,648725
UT,total,1992,1836799
UT,total,1993,1898404
UT,under18,1993,662968
UT,total,1991,1779780
UT,under18,1991,637216
UT,under18,1990,627122
UT,total,1990,1731223
VT,under18,1990,143296
VT,total,1990,564798
VT,total,1991,568606
VT,under18,1991,145219
VT,total,1993,577748
VT,under18,1993,148705
VT,under18,1992,146983
VT,total,1992,572751
VT,under18,1994,150794
VT,total,1994,583836
VT,total,1995,589003
VT,under18,1995,151439
VT,under18,1996,151490
VT,total,1996,593701
VT,under18,1998,148467
VT,total,1998,600416
VT,total,1997,597239
VT,under18,1997,150040
VT,total,2000,609618
VT,under18,2000,147549
VT,total,1999,604683
VT,under18,1999,147859
VT,total,2001,612223
VT,under18,2001,146040
VT,total,2002,615442
VT,under18,2002,144441
VT,total,2004,619920
VT,under18,2004,141068
VT,total,2003,617858
VT,under18,2003,142718
VT,total,2005,621215
VT,under18,2005,138933
VT,total,2006,622892
VT,under18,2006,136731
VT,total,2008,624151
VT,under18,2008,132600
VT,total,2007,623481
VT,under18,2007,134695
VT,under18,2013,122701
VT,total,2013,626630
VT,total,2009,624817
VT,under18,2009,130450
VT,total,2010,625793
VT,under18,2010,128601
VT,under18,2011,126500
VT,total,2011,626320
VT,under18,2012,124555
VT,total,2012,625953
VA,total,2012,8186628
VA,under18,2012,1861323
VA,total,2011,8105850
VA,under18,2011,1857585
VA,under18,2010,1855025
VA,total,2010,8024417
VA,total,2009,7925937
VA,under18,2009,1845132
VA,total,2013,8260405
VA,under18,2013,1864535
VA,total,2007,7751000
VA,under18,2007,1834386
VA,total,2008,7833496
VA,under18,2008,1838361
VA,total,2005,7577105
VA,under18,2005,1816270
VA,total,2006,7673725
VA,under18,2006,1826368
VA,total,2003,7366977
VA,under18,2003,1782254
VA,total,2004,7475575
VA,under18,2004,1801958
VA,total,2002,7286873
VA,under18,2002,1771247
VA,total,2001,7198362
VA,under18,2001,1754549
VA,total,1999,7000174
VA,under18,1999,1723125
VA,total,2000,7105817
VA,under18,2000,1741420
VA,total,1997,6829183
VA,under18,1997,1683766
VA,under18,1998,1706261
VA,total,1998,6900918
VA,under18,1996,1664147
VA,total,1996,6750884
VA,total,1995,6670693
VA,under18,1995,1649005
VA,under18,1994,1628711
VA,total,1994,6593139
VA,under18,1992,1581544
VA,total,1992,6414307
VA,total,1993,6509630
VA,under18,1993,1604758
VA,total,1991,6301217
VA,under18,1991,1548258
VA,under18,1990,1520670
VA,total,1990,6216884
WA,under18,1990,1301545
WA,total,1990,4903043
WA,total,1991,5025624
WA,under18,1991,1326527
WA,total,1993,5278842
WA,under18,1993,1387716
WA,under18,1992,1365480
WA,total,1992,5160757
WA,under18,1994,1409922
WA,total,1994,5375161
WA,total,1995,5481027
WA,under18,1995,1429397
WA,under18,1996,1449613
WA,total,1996,5569753
WA,under18,1998,1494784
WA,total,1998,5769562
WA,total,1997,5674747
WA,under18,1997,1473646
WA,total,2000,5910512
WA,under18,2000,1516361
WA,total,1999,5842564
WA,under18,1999,1507824
WA,total,2001,5985722
WA,under18,2001,1517527
WA,total,2002,6052349
WA,under18,2002,1517655
WA,total,2004,6178645
WA,under18,2004,1520751
WA,total,2003,6104115
WA,under18,2003,1514877
WA,total,2005,6257305
WA,under18,2005,1523890
WA,total,2006,6370753
WA,under18,2006,1536926
WA,total,2008,6562231
WA,under18,2008,1560302
WA,total,2007,6461587
WA,under18,2007,1549582
WA,under18,2013,1595795
WA,total,2013,6971406
WA,total,2009,6667426
WA,under18,2009,1574403
WA,total,2010,6742256
WA,under18,2010,1581436
WA,under18,2011,1584709
WA,total,2011,6821481
WA,under18,2012,1588451
WA,total,2012,6895318
WV,total,2012,1856680
WV,under18,2012,384030
WV,total,2011,1855184
WV,under18,2011,385283
WV,under18,2010,387224
WV,total,2010,1854146
WV,total,2009,1847775
WV,under18,2009,389036
WV,total,2013,1854304
WV,under18,2013,381678
WV,total,2007,1834052
WV,under18,2007,390661
WV,total,2008,1840310
WV,under18,2008,390210
WV,total,2006,1827912
WV,under18,2006,390637
WV,total,2005,1820492
WV,under18,2005,390431
WV,total,2003,1812295
WV,under18,2003,392460
WV,total,2004,1816438
WV,under18,2004,391856
WV,total,2002,1805414
WV,under18,2002,393569
WV,total,2001,1801481
WV,under18,2001,395307
WV,total,1999,1811799
WV,under18,1999,406784
WV,total,2000,1807021
WV,under18,2000,401062
WV,total,1997,1819113
WV,under18,1997,418037
WV,under18,1998,412793
WV,total,1998,1815609
WV,under18,1996,422831
WV,total,1996,1822808
WV,total,1995,1823700
WV,under18,1995,428790
WV,under18,1994,429128
WV,total,1994,1820421
WV,under18,1992,433116
WV,total,1992,1806451
WV,total,1993,1817539
WV,under18,1993,432364
WV,total,1991,1798735
WV,under18,1991,433918
WV,under18,1990,436797
WV,total,1990,1792548
WI,under18,1990,1302869
WI,total,1990,4904562
WI,total,1991,4964343
WI,under18,1991,1314855
WI,total,1993,5084889
WI,under18,1993,1337334
WI,under18,1992,1330555
WI,total,1992,5025398
WI,under18,1994,1348110
WI,total,1994,5133678
WI,total,1995,5184836
WI,under18,1995,1351343
WI,under18,1996,1352877
WI,total,1996,5229986
WI,under18,1998,1362907
WI,total,1998,5297673
WI,total,1997,5266213
WI,under18,1997,1359712
WI,total,1999,5332666
WI,under18,1999,1367019
WI,total,2000,5373999
WI,under18,2000,1370440
WI,total,2001,5406835
WI,under18,2001,1367593
WI,total,2002,5445162
WI,under18,2002,1365315
WI,total,2004,5514026
WI,under18,2004,1354643
WI,total,2003,5479203
WI,under18,2003,1358505
WI,total,2005,5546166
WI,under18,2005,1349866
WI,total,2006,5577655
WI,under18,2006,1348785
WI,total,2008,5640996
WI,under18,2008,1345573
WI,total,2007,5610775
WI,under18,2007,1348901
WI,under18,2013,1307776
WI,total,2013,5742713
WI,total,2009,5669264
WI,under18,2009,1342411
WI,total,2010,5689060
WI,under18,2010,1336094
WI,under18,2011,1325870
WI,total,2011,5708785
WI,under18,2012,1316113
WI,total,2012,5724554
WY,total,2012,576626
WY,under18,2012,136526
WY,total,2011,567329
WY,under18,2011,135407
WY,under18,2010,135351
WY,total,2010,564222
WY,total,2009,559851
WY,under18,2009,134960
WY,total,2013,582658
WY,under18,2013,137679
WY,total,2007,534876
WY,under18,2007,128760
WY,total,2008,546043
WY,under18,2008,131511
WY,total,2006,522667
WY,under18,2006,125525
WY,total,2005,514157
WY,under18,2005,124022
WY,total,2003,503453
WY,under18,2003,124182
WY,total,2004,509106
WY,under18,2004,123974
WY,total,2002,500017
WY,under18,2002,125495
WY,total,2001,494657
WY,under18,2001,126212
WY,total,2000,494300
WY,under18,2000,128774
WY,total,1999,491780
WY,under18,1999,130793
WY,total,1997,489452
WY,under18,1997,134328
WY,under18,1998,132602
WY,total,1998,490787
WY,under18,1996,135698
WY,total,1996,488167
WY,total,1995,485160
WY,under18,1995,136785
WY,under18,1994,137733
WY,total,1994,480283
WY,under18,1992,137308
WY,total,1992,466251
WY,total,1993,473081
WY,under18,1993,137458
WY,total,1991,459260
WY,under18,1991,136720
WY,under18,1990,136078
WY,total,1990,453690
PR,under18,1990,NaN
PR,total,1990,NaN
PR,total,1991,NaN
PR,under18,1991,NaN
PR,total,1993,NaN
PR,under18,1993,NaN
PR,under18,1992,NaN
PR,total,1992,NaN
PR,under18,1994,NaN
PR,total,1994,NaN
PR,total,1995,NaN
PR,under18,1995,NaN
PR,under18,1996,NaN
PR,total,1996,NaN
PR,under18,1998,NaN
PR,total,1998,NaN
PR,total,1997,NaN
PR,under18,1997,NaN
PR,total,1999,NaN
PR,under18,1999,NaN
PR,total,2000,3810605
PR,under18,2000,1089063
PR,total,2001,3818774
PR,under18,2001,1077566
PR,total,2002,3823701
PR,under18,2002,1065051
PR,total,2004,3826878
PR,under18,2004,1035919
PR,total,2003,3826095
PR,under18,2003,1050615
PR,total,2005,3821362
PR,under18,2005,1019447
PR,total,2006,3805214
PR,under18,2006,998543
PR,total,2007,3782995
PR,under18,2007,973613
PR,total,2008,3760866
PR,under18,2008,945705
PR,under18,2013,814068
PR,total,2013,3615086
PR,total,2009,3740410
PR,under18,2009,920794
PR,total,2010,3721208
PR,under18,2010,896945
PR,under18,2011,869327
PR,total,2011,3686580
PR,under18,2012,841740
PR,total,2012,3651545
USA,under18,1990,64218512
USA,total,1990,249622814
USA,total,1991,252980942
USA,under18,1991,65313018
USA,under18,1992,66509177
USA,total,1992,256514231
USA,total,1993,259918595
USA,under18,1993,67594938
USA,under18,1994,68640936
USA,total,1994,263125826
USA,under18,1995,69473140
USA,under18,1996,70233512
USA,total,1995,266278403
USA,total,1996,269394291
USA,total,1997,272646932
USA,under18,1997,70920738
USA,under18,1998,71431406
USA,total,1998,275854116
USA,under18,1999,71946051
USA,total,2000,282162411
USA,under18,2000,72376189
USA,total,1999,279040181
USA,total,2001,284968955
USA,under18,2001,72671175
USA,total,2002,287625193
USA,under18,2002,72936457
USA,total,2003,290107933
USA,under18,2003,73100758
USA,total,2004,292805298
USA,under18,2004,73297735
USA,total,2005,295516599
USA,under18,2005,73523669
USA,total,2006,298379912
USA,under18,2006,73757714
USA,total,2007,301231207
USA,under18,2007,74019405
USA,total,2008,304093966
USA,under18,2008,74104602
USA,under18,2013,73585872
USA,total,2013,316128839
USA,total,2009,306771529
USA,under18,2009,74134167
USA,under18,2010,74119556
USA,total,2010,309326295
USA,under18,2011,73902222
USA,total,2011,311582564
USA,under18,2012,73708179
USA,total,2012,313873685
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment