数据转换

import pandas as pd
df_1 = pd.DataFrame({'k1': ['one', 'two','one']*2,
                     'k2': ['1','2', '3']*2})
series_1 = df_1.duplicated()
df_2 = df_1.drop_duplicates()  # 删除重复行,默认判断所有行，默认保留第一次出现的数据
df_3 = df_1[series_1]
df_4 = df_1.drop_duplicates(['k1'])  # 保留最后一次出现的数据
df_5 = df_1.drop_duplicates(['k1'], keep='last')  # 删除重复行，只判读K1列

print('df_1\n', df_1)
print('\nseries_1\n', series_1)
print('\ndf_2\n', df_2)
print('\ndf_3\n', df_3)
print('\ndf_4\n', df_4)
print('\ndf_5\n', df_5)

import pandas as pd
from numpy import nan as NA

df_1 = pd.DataFrame([[1, 2, 3, 4], [5, 6, 998, 999], [999, 999, 999, 999]])
df_2 = df_1.replace(999, NA)                    # 一对一替换
df_3 = df_1.replace([998, 999], NA)             # 多对一替换
df_4 = df_1.replace([998, 999], [NA, 0])        # 多对多替换
df_5 = df_1.replace({998: NA, 999: 0})          # 多对多替换

print('df_1\n', df_1)
print('\ndf_2\n', df_2)
print('\ndf_3\n', df_3)
print('\ndf_4\n', df_4)
print('\ndf_5\n', df_5)

import numpy as np
df_1 =pd.DataFrame(np.arange(12).reshape(3, 4), index=['Ohio', 'Colorado', 'New York'],
                   columns=['one', 'two', 'three', 'four'])
transform = lambda x: x[:4].upper()
df_1.index = df_1.index.map(transform)
df_2 = df_1.rename(index=str.title, columns=str.upper)
df_3 = df_1.rename(index={'OHIO':'INDIANA'}, columns={'three':'peekaboo'})
print('df_1\n', df_1)
print('\ndf_2\n', df_2)
print('\ndf_3\n', df_3)