dataframe设置两个条件取值的实例

 >>> import pandas as pd >>> import numpy as np >>> from pandas import Series, DataFrame >>> df = DataFrame({'name':['a','a','b','b'],'classes':[1,2,3,4],'price':[11,22,33,44]}) >>> df classes name price 0  1 a  11 1  2 a  22 2  3 b  33 3  4 b  44 >>> 

 >>> s = df.loc[0,'price'] >>> s 11

 >>> sex = df.loc[(df.classes==1)&(df.name=='a'),'price'] >>> sex 0 11 Name: price, dtype: int64 >>> sex = df.loc[(df.classes==1)&(df.name=='a'),'price'].values[0] >>> sex 11

 >>> name,price = df.loc[df.classes==1,('name','price')].values[0] >>> name 'a' >>> price 11 >>>

 >>> df.loc[: , 'price']=0 >>> df classes name price 0  1 a  0 1  2 a  0 2  3 b  0 3  4 b  0 >>>

 【1】 >>> df['name'] = df['name'].apply(lambda x: x.upper()) >>> df classes name price 0  1 A  11 1  2 A  22 2  3 B  33 3  4 B  44 【2】 >>> df.loc[:, 'name'] = df['name'].apply(lambda x: x.upper()) >>> df classes name price 0  1 A  11 1  2 A  22 2  3 B  33 3  4 B  44 >>>

 【1】 >>> df[['classes','price']] = df[['classes', 'price']].applymap(lambda x: str(x)) >>> print(type(df.loc[0, "classes"]))  >>> print(df.loc[0, "classes"]) 1 【2】 >>> df.loc[:, ['classes','price']] = df[['classes', 'price']].applymap(lambda x: int(x)) >>> print(type(df.loc[0, "classes"]))  >>> print(df.loc[0, "classes"]) 1 >>> 

 >>> df classes name price 0  1 a  11 1  1 a  22 2  3 b  33 3  4 b  44 >>> df.drop_duplicates(subset=['classes', 'name'], inplace=True) >>> df classes name price 0  1 a  11 2  3 b  33 3  4 b  44

 >>> fund_memeber = '赵四、 王五' >>> fund_manager_list = re.split('[；， 、]', fund_memeber) >>> fund_manager_list ['赵四', '', '王五'] #DataFrame构造器 >>> df = DataFrame({'x':[1],'y':[2]}) >>> df x y 0 1 2 >>>

 >>> df = DataFrame({'name':['a','b','c','d'],'classes':[1,2,3,4],'price':[11,22,33,44]}) >>> df classes name price 0  1 a  11 1  2 b  22 2  3 c  33 3  4 d  44 【方法一】 >>> df = df.loc[df['name']!='a'] >>> df classes name price 1  2 b  22 2  3 c  33 3  4 d  44 >>> 【方法二】 df.drop(df[df.name=='a'].index,axis=0) #筛选df的每列值包含某个字段‘/a' >>> import pandas as pd >>> df = pd.DataFrame({'a':['A', 'B'], 'b': ['AA', 'BB']}) >>> df a b 0 A AA 1 B BB >>> df[df['a'].str.contains(r'A')] a b 0 A AA >>> df = pd.DataFrame({'a':['/api/', 'B'], 'b': ['AA', 'BB']}) >>> df a b 0 /api/ AA 1  B BB >>> df[df['a'].str.contains(r'/api/')] a b 0 /api/ AA >>>

 df request_url visit_times 9 fofeasy_产品基本信息   7 8   投顾挖掘   6 5   投顾挖掘   5 6   投顾挖掘   5 7 fofeasy_产品基本信息   5 3 fofeasy_产品基本信息   4 4 fofeasy_产品基本信息   4 2   投顾挖掘   2 0  行业数据――其他   1 1  行业数据――其他   1 x = df.set_index('request_url') x visit_times request_url fofeasy_产品基本信息   7 投顾挖掘      6 投顾挖掘      5 投顾挖掘      5 fofeasy_产品基本信息   5 fofeasy_产品基本信息   4 fofeasy_产品基本信息   4 投顾挖掘      2 行业数据――其他     1 行业数据――其他     1 x.reset_index('request_url') request_url visit_times 0 fofeasy_产品基本信息   7 1   投顾挖掘   6 2   投顾挖掘   5 3   投顾挖掘   5 4 fofeasy_产品基本信息   5 5 fofeasy_产品基本信息   4 6 fofeasy_产品基本信息   4 7   投顾挖掘   2 8  行业数据――其他   1 9  行业数据――其他   1

 >>>df.groupby(by=['request_url'])['visit_times'].sum() >>> request_url fofeasy_产品基本信息 20 投顾挖掘    18 行业数据――其他   2 Name: visit_times, dtype: int64

 In [15]: dict = pd.DataFrame({'x':1, 'y':2}, index=[0]) In [16]: dict Out[16]: x y 0 1 2 

 In [69]: df1.iloc[1:5, 2:4] Out[69]: 4   6 2 0.301624 -2.179861 4 1.462696 -1.743161 6 1.314232 0.690579 8 0.014871 3.357427