How to handle data frames

import pandas as pd
import numpy as np

df=pd.read_csv('〜〜〜.csv',header=None,names=('name', 'id'))

df=df.replace('A B', 'AB')
df=df.replace('B A', 'BA')

df2 = pd.concat([df, df['name'].str.split(' ', expand=True)], axis=1).drop('name', axis=1)

df=df.loc[:,["Column name","Column name","Column name"]]

df3=pd.concat([df1, df2])

df=df[~df.duplicated()]

df[df["Column name"]=="~~"]

df_list=df.values.tolist()

df_list=np.array(df['Column name'])

Recommended Posts