pandas的基本用法——合并数据

#!/usr/bin/env python
# _*_ coding: utf-8 _*_

import pandas as pd
import numpy as np


# Test 1
# 创建DataFrame
df1 = pd.DataFrame(np.ones((3, 4)) * 0, columns = ['a', 'b', 'c', 'd'])
df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns = ['a', 'b', 'c', 'd'])
df3 = pd.DataFrame(np.ones((3, 4)) * 2, columns = ['a', 'b', 'c', 'd'])
print df1
print df2
print df3

# Test 1 result
     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
     a    b    c    d
0  1.0  1.0  1.0  1.0
1  1.0  1.0  1.0  1.0
2  1.0  1.0  1.0  1.0
     a    b    c    d
0  2.0  2.0  2.0  2.0
1  2.0  2.0  2.0  2.0
2  2.0  2.0  2.0  2.0

# Test 2
# 竖向合并三个DataFrame
res = pd.concat([df1, df2, df3], axis = 0)
print res

# 横向合并三个DataFrame
res = pd.concat([df1, df2, df3], axis = 1)
print res

# 合并的同时index重新排序
res = pd.concat([df1, df2, df3], axis = 0, ignore_index = True)
print res

# Test 2 result
     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
0  1.0  1.0  1.0  1.0
1  1.0  1.0  1.0  1.0
2  1.0  1.0  1.0  1.0
0  2.0  2.0  2.0  2.0
1  2.0  2.0  2.0  2.0
2  2.0  2.0  2.0  2.0

     a    b    c    d    a    b    c    d    a    b    c    d
0  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0  2.0  2.0  2.0  2.0
1  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0  2.0  2.0  2.0  2.0
2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0  2.0  2.0  2.0  2.0

     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  1.0  1.0  1.0  1.0
4  1.0  1.0  1.0  1.0
5  1.0  1.0  1.0  1.0
6  2.0  2.0  2.0  2.0
7  2.0  2.0  2.0  2.0
8  2.0  2.0  2.0  2.0

# Test 3
# 创建DataFrame, 部分索引重合
df1 = pd.DataFrame(np.ones((3, 4)) * 0, columns = ['a', 'b', 'c', 'd'], index = [1, 2, 3])
df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns = ['b', 'c', 'd', 'e'], index = [2, 3, 4])
print df1
print df2

# 直接合并, 默认的join模式为outer, 与pd.concat([df1, df2])是一样的
res = pd.concat([df1, df2], join = 'outer')
print res

# 合并模式为inner
res = pd.concat([df1, df2], join = 'inner')
print res

# 合并模式为inner, 同时重新排序
res = pd.concat([df1, df2], join = 'inner', ignore_index = True)
print res

# Test 3 result
     a    b    c    d
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  0.0  0.0  0.0  0.0

     b    c    d    e
2  1.0  1.0  1.0  1.0
3  1.0  1.0  1.0  1.0
4  1.0  1.0  1.0  1.0

     a    b    c    d    e
1  0.0  0.0  0.0  0.0  NaN
2  0.0  0.0  0.0  0.0  NaN
3  0.0  0.0  0.0  0.0  NaN
2  NaN  1.0  1.0  1.0  1.0
3  NaN  1.0  1.0  1.0  1.0
4  NaN  1.0  1.0  1.0  1.0

     b    c    d
1  0.0  0.0  0.0
2  0.0  0.0  0.0
3  0.0  0.0  0.0
2  1.0  1.0  1.0
3  1.0  1.0  1.0
4  1.0  1.0  1.0

     b    c    d
0  0.0  0.0  0.0
1  0.0  0.0  0.0
2  0.0  0.0  0.0
3  1.0  1.0  1.0
4  1.0  1.0  1.0
5  1.0  1.0  1.0

# Test 4
# 横向合并
res = pd.concat([df1, df2], axis = 1)
print res

# 横向合并, 按照df1的index, 忽略df2不一致的index
res = pd.concat([df1, df2], axis = 1, join_axes = [df1.index])
print res

# Test 4 result
     a    b    c    d    b    c    d    e
1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN
2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
4  NaN  NaN  NaN  NaN  1.0  1.0  1.0  1.0

     a    b    c    d    b    c    d    e
1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN
2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0

# Test 5
# 创建DataFrame
df1 = pd.DataFrame(np.ones((3, 4)) * 0, columns = ['a', 'b', 'c', 'd'])
df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns = ['a', 'b', 'c', 'd'])
df3 = pd.DataFrame(np.ones((3, 4)) * 2, columns = ['a', 'b', 'c', 'd'])
# append
print df1.append(df2, ignore_index = True)

# append 多个DataFrame
print df1.append([df2, df3], ignore_index = True)

# Test 5 result
     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  1.0  1.0  1.0  1.0
4  1.0  1.0  1.0  1.0
5  1.0  1.0  1.0  1.0

     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  1.0  1.0  1.0  1.0
4  1.0  1.0  1.0  1.0
5  1.0  1.0  1.0  1.0
6  2.0  2.0  2.0  2.0
7  2.0  2.0  2.0  2.0
8  2.0  2.0  2.0  2.0