정리를 위한 블로그

df = pd.DataFrame([[1,'a'],[2,'b']],columns=['value','name'])
df.set_index('name')['value'].to_dict()
# {'a': 1, 'b': 2}

import pandas as pd
pd.options.display.max_columns = 300

import pandas as pd
df = pd.read_csv("data.csv")
pd.to_datetime(df['date+col']).dt.date
pd.to_datetime(df['date+col']).dt.month
pd.to_datetime(df['date+col']).dt.hour

df[['col1','col2']].value_counts().rename_axis(['col1','col2']).to_frame('counts')

df = pd.read_csv("")

df.loc[df['column'] == 'target', 'column'] = 'change_target'

def percentile(n):
    def percentile_(x):
        return np.percentile(x, n)
    percentile_.__name__ = 'percentile_%s' % n
    return percentile_
    
column.agg([np.sum, np.mean, np.std, np.median,
                     np.var, np.min, np.max, percentile(50), percentile(95)])

temp_list = [1,2,3]
df[df['대상column'].isin(temp_list)]

dataframe isin 함수 이용해서 

df = pd.read_csv('FILENAME',
        header=0,
        usecols=["Time", "Name"])

usecols parameter 사용

df2 = df[~df.Name.str.contains('단어')]

bins = list(range(0, 100, 10))
bins_label = [str(x)+"~"+str(x+10) for x in bins]
df["labels"] = pd.cut(df['value'], bins, right=False, labels=bins_label[:-1])