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/7-pandas数据集成merge.ipynb

1273 lines
32 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

{
"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
}
Reference in New Issue View Git Blame Copy Permalink