pandas模块基本应用一

#pandas基本应用
import pandas as pd
#两种数据结构，Series和DataFrame

#Series
df1=pd.Series([1,2,3,4,5],index=("a","b","c","d","e"))
print(df1)
# a    1
# b    2
# c    3
# d    4
# e    5
# dtype: int64

#DataFrame
df2=pd.DataFrame([[1,2,3,4],[11,22,33,44],[111,222,333,444],[1111,2222,3333,4444]],
                 columns=["甲","乙","丙","丁"])
print(df2)
#       甲     乙     丙     丁
# 0     1     2     3     4
# 1    11    22    33    44
# 2   111   222   333   444
# 3  1111  2222  3333  4444

#获取指定单行
print(df2.loc[3])
# 甲    1111
# 乙    2222
# 丙    3333
# 丁    4444
# Name: 3, dtype: int64

#获取指定连续行
print(df2.loc[1:3])
#       甲     乙     丙     丁
# 1    11    22    33    44
# 2   111   222   333   444
# 3  1111  2222  3333  4444
#获取指定不连续多行
print(df2.loc[[1,3]])
#       甲     乙     丙     丁
# 1    11    22    33    44
# 3  1111  2222  3333  4444

#获取指定行指定列
print(df2.loc[1,"丙"])
#33

#获取指定连续多行多列
print(df2.loc[0:2,"乙":"丁"])
#      乙    丙    丁
# 0    2    3    4
# 1   22   33   44
# 2  222  333  444

#获取指定不连续列
print(df2.loc[:,["甲","丙"]])
#       甲     丙
# 0     1     3
# 1    11    33
# 2   111   333
# 3  1111  3333

#获取指定连续列
print(df2.loc[:,"甲":"丙"])
#       甲     乙     丙
# 0     1     2     3
# 1    11    22    33
# 2   111   222   333
# 3  1111  2222  3333

#添加行数据append
df3=pd.DataFrame([[11,22,33,44]],columns=["甲","乙","丙","丁"])
print(df3)
df4=df2.append(df3,ignore_index=True)
print(df4)
#       甲     乙     丙     丁
# 0     1     2     3     4
# 1    11    22    33    44
# 2   111   222   333   444
# 3  1111  2222  3333  4444
# 0    11    22    33    44

#添加列数据
df4["申"]=["A","B","C","D","E"]
print(df4)

#去重drop_duplicates
del df4["申"]
df5=df4.drop_duplicates()
print(df5)
#       甲     乙     丙     丁
# 0     1     2     3     4
# 1    11    22    33    44
# 2   111   222   333   444
# 3  1111  2222  3333  4444

#保存成csv文件，没有行号
df5.to_csv("df5.csv",index=False)
df5.to_excel("df5.xlsx",sheet_name="df5",index=False)