pandas 数据转换函数map、apply、applymap

1
2
3
4
5
6
import pandas as pd
import os
os.chdir(r'C:UsersHansDesktopdata_analysis')
df = pd.read_excel('pandas_multiindex.xls')
df.head()

1
2
df["公司"].unique()

1
2
array(['BABA', 'JD', 'JSR', 'HR'], dtype=object)

1
2
3
4
5
6
#（1）map用于Series值的转换。实例：将股票代码英文转换成中文名字
dict_names = {"BABA":"阿里巴巴","JD":"京东","JSR":"金斯瑞","HR":"恒瑞"}
#方法一：Series.map(dict)
df["公司中文名称1"] = df["公司"].map(dict_names)
df.head()

1
2
3
4
5
#方法二：Series.map(function)
df["公司中文2"]=df["公司"].map(lambda x:dict_names[x])
df.head()
#lambda函数不会！！

1
2
3
4
5
#（2）apply 用于Series和DataFrame的转换，Series.apply(function),函数的参数是每个值。
#DataFrame.apply(function)，函数的参数是Series
df["公司中文3"]=df["公司"].apply(lambda x:dict_names[x])
df.head()

1
2
3
df["公司中文4"]=df.apply(lambda x:dict_names[x["公司"]],axis = 1)#注意等式右侧是df.apply，需要指定axis
df.head()

1
2
3
4
#（3）applymap 用于DataFrame的数据转换
sub_df = df[["收盘","开盘","高","低","交易量"]]
sub_df.head()

1
2
3
4
sub_df["交易量"] = sub_df["交易量"].str.replace("M","")
sub_df.head()
#没有解决怎么将字符串变成数字类型

1
2
3
4
5
6
C:ProgramDataAnaconda3libsite-packagesipykernel_launcher.py:1: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
"""Entry point for launching an IPython kernel.

1
2
3
4
sub_df02 = df[["收盘","开盘","高","低"]]
sub_df02.applymap(lambda x: int(x)).head()
#将表中的这些数字取整，应用于所有元素，applymap本身就是对多有的DataFrame进行操作

1
2
3
#直接修改原df的几列
df.loc[:,['收盘','开盘','高','低']] = sub_df02.applymap(lambda x: int(x)).head()

1
2
df.head()

1
2