pandas系列4_合并和连接

import pandas as pd
import numpy as np

s1 = pd.Series([0,1], index=['a','b'])

s2 = pd.Series([2,3,4], index=['c','d','e'])

s3 = pd.Series([5, 6], index=['f', 'g'])

# 默认是得到S型数据
pd.concat([s1, s2])

a    0
b    1
c    2
d    3
e    4
dtype: int64

# 转成DF型数据：axis=1
pd.concat([s1, s2], axis=1, sort=True)

pd.concat([s1,s2,s3], axis=1,sort=True)

s4 = pd.concat([s1, s3])
s4

a    0
b    1
f    5
g    6
dtype: int64

# join='inner'：交集；join='outer'：并集
pd.concat([s1,s4], axis=1, sort=True, join='inner')

pd.concat([s1,s4],axis=1,join_axes=[['a','c','b','e']])

# keys参数生成层次化索引
result = pd.concat([s1,s1,s3],keys=['one','two','three'])
result

one    a    0
       b    1
two    a    0
       b    1
three  f    5
       g    6
dtype: int64

result.unstack()

# 沿着axis=1合并，keys成为DF的列头
pd.concat([s1,s2,s3], axis=1, sort=True, keys=['one','two','three'])

df1 = pd.DataFrame({'key': ['b', 'b', 'a', 'c', 'a', 'a','c'], 
                    'data1': range(7)})
df1

df2 = pd.DataFrame({'key': ['a', 'b', 'd'],
                    'data2': range(3)})
df2

# 将两个df数据中相同的值进行合并
pd.merge(df1, df2)

df3 = pd.DataFrame({'lkey': ['b', 'b', 'a', 'c', 'a', 'a','c'], 
                    'data1': range(7)})
df3

df4 = pd.DataFrame({'rkey': ['a', 'b', 'd'],
                    'data2': range(3)})
df4

pd.merge(df3,df4,left_on='lkey',right_on='rkey')  # 相同的列属性指定新生成的df数据中的新列名

pd.merge(df1, df2, how="outer")  # 外键求并集，默认是inner求交集

left = pd.DataFrame({'key1': ['foo', 'foo', 'bar'],
                    'key2': ['one', 'two', 'one'],
                     'lval': [1, 2, 3]})

right = pd.DataFrame({'key1': ['foo', 'foo', 'bar', 'bar'],
                      'key2': ['one', 'one', 'one', 'two'],
                      'rval': [4, 5, 6, 7]})

pd.merge(left, right, on=["key1", "key2"], how="outer")  # 使用相同的列名key1和key2

pd.merge(left, right, on='key1')   # 通过key1进行连接，key2重复了，默认是在key2的后面添加_x、_y

pd.merge(left, right, on='key1',suffixes=('_left', '_right'))  # 指定后缀连接符