jackfrued
/
Python-100-Days
mirror of https://github.com/jackfrued/Python-100-Days.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
Python-100-Days/Day76-90/code/4-pandas多层索引.ipynb

569 lines
14 KiB
Plaintext
Raw Normal View History

'pandas使用'
2019-05-16 11:59:06 +08:00
{
"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
}