pandas.merge(left, right, how='inner', on=None, left_on=None, right_on=None, left_index=False, right_index=False, sort=False, suffixes=('_x', '_y'), copy=True, indicator=False, validate=None)

import pandas as pd

from pandas import DataFrame

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

df2 = DataFrame({'key':['a','b','d','b'],'data2':range(4)})

# pd.merge(df1,df2,on='key')#设定列进行连接

# pd.merge(df1,df2,left_on='data1',right_on='data2')

# pd.merge(df1,df2,how='outer')#外连接，求取的是键的并集

# pd.merge(df1,df2,on='key',how='left')#左连接

# pd.merge(df1,df2,on='key',how='right')#右连接

# pd.merge(df1,df2,on='key',how='inner')#内连接，求取的是键的交集

# pd.merge(df1,df2,left_index=True,right_index=True)#索引被用作连接键

pandas.concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False, keys=None, levels=None, names=None, verify_integrity=False, sort=None, copy=True)

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

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

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

s4 = pd.concat([s1*5,s3])#concat默认axis=0,所以得出的是新的Series，取并集；axis=1,所以得出的是新的DataFrame

# pd.concat([s1,s4],axis=1,sort=False,join='outer')#axis=1 表示针对列，join='outer'表示取并集

# pd.concat([s1,s4],axis=1,sort=False,join='inner')#axis=1 表示针对列，join='inner'表示取交集

# pd.concat([s1,s4],axis=1,sort=False,join_axes=[['a','c','b','e']])#指定索引

# result = pd.concat([s1,s2,s3],keys=['one','two','three'])

result = pd.concat([s1,s2,s3],axis=1,sort=False,keys=['one','two','three'])

import pandas as pd

from pandas import DataFrame,Series

s1 = Series(['a','a','a'],index=['i1','i2','i3'])

s2 = Series(['a','a','a'],index=['i1','i2','i3'])

df = pd.concat([s1,s2],axis=1,sort=False)

df

df.duplicated()#返回一个布尔类型的Series

df.drop_duplicates()#移除全部列重复行的数据，默认保留第一个出现的值

df.drop_duplicates(take = True)#移除全部列重复行的数据，默认保留最后一个值

import pandas as pd

from pandas import DataFrame,Series

s1 = Series(['a','a','a'],index=['i1','i2','i3'])

s2 = Series(['a','b','a'],index=['i1','i2','i3'])

df = pd.concat([s1,s2],axis=1,sort=False,keys=['key1','key2'])

df.drop_duplicates('key2')

df.drop_duplicates('key2')#移除指定列重复行的数据

import pandas as pd

from pandas import DataFrame,Series

data = DataFrame({'name':['张三','李四','王五','刘四'],'sex':['male','female','male','male'],'age':[30,32,28,35]})

student_to_class = {#比如，男性的班级是class1，女性的班级是class2

    'male':'class1',

    'female':'class2'

}

data['class'] = data['sex'].map(person_to_class)

data

import pandas as pd

import numpy as np

from numpy import array

file = 'D:\全部A股-行情报价.xls'

df = pd.read_excel(file)

region = [-100,-50,-30,-20,-10,0,10,20,30,50,100]

regions = np.array(region)

ratio = df['市净率'].dropna()

arrs = np.array(ratio)

ratios = pd.cut(ratio,regions)

pd.value_counts(ratios)

ratios = pd.cut(ratio,regions,labels=['非常非常不好','非常不好','不好','很一般','一般一般','一般好','好','很好','非常好','非常非常好'])