一些pandas的备忘

对比两个DataFrame

import pandas as pd
import numpy as np

np.random.seed(0)

df1 = pd.DataFrame(np.random.randint(1, 4, (10, 2)))

df2 = pd.DataFrame(np.random.randint(1, 2, (10, 2)))

res = df1.values == df2.values
check = False if False in res else True

更改index和colums

data = pd.DataFrame(np.arange(12).reshape((3, 4)),
                    index=['Ohio', 'Colorado', 'New York'],
                    columns=['one', 'two', 'three', 'four'])

data = data.rename(index={'Ohio': 'INDIANA'},
            columns={'three': 'peekaboo'})

判断重复

data.duplicated()