Numpy学习笔记--07.Pandas设置值、导入导出

代码与注释如下

import pandas as pd
import numpy as np

dates = pd.date_range('20191218', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)), index=dates, columns=['A', 'B', 'C', 'D'])


print(df)
df.iloc[2, 2] = 1111 # 改变第二列第二行的值为1111
df.loc['20191218', 'B'] = 2222 # 横向标签是20191218，纵向标签是B的值设为2222

df[df.A>4] = 0 # 
#             A     B  C  D
# 2019-12-18  0  2222  2  3
# 2019-12-19  4     5  6  7
# 2019-12-20  0     0  0  0
# 2019-12-21  0     0  0  0
# 2019-12-22  0     0  0  0
# 2019-12-23  0     0  0  0

df.A[df.A>4] = 0 # 
#             A     B     C   D
# 2019-12-18  0  2222     2   3
# 2019-12-19  4     5     6   7
# 2019-12-20  0     9  1111  11
# 2019-12-21  0    13    14  15
# 2019-12-22  0    17    18  19
# 2019-12-23  0    21    22  23

# 加入空列F
df['F'] = np.nan
#             A     B  C  D   F
# 2019-12-18  0  2222  2  3 NaN
# 2019-12-19  4     5  6  7 NaN
# 2019-12-20  0     0  0  0 NaN
# 2019-12-21  0     0  0  0 NaN
# 2019-12-22  0     0  0  0 NaN
# 2019-12-23  0     0  0  0 NaN

# 加入列E
df['E'] = pd.Series([1,2,3,4,5,6], index=pd.date_range('20191218', periods=6))
print(df)
#             A     B  C  D   F  E
# 2019-12-18  0  2222  2  3 NaN  1
# 2019-12-19  4     5  6  7 NaN  2
# 2019-12-20  0     0  0  0 NaN  3
# 2019-12-21  0     0  0  0 NaN  4
# 2019-12-22  0     0  0  0 NaN  5
# 2019-12-23  0     0  0  0 NaN  6

导入导出部分

# pandas能读取、保存csv excel hdf sql json masgpack html gbq stata sas cilpboard pickle等格式
# 读取使用.read_格式名，例如.read_csv()

data = pd.read_csv('student.csv')
print(data)

data.to_pickle('student.pickle')
# 导入使用.to_格式名，例如.to_pickle()