[데이터 분석] DataFrame 함수 요약 정리

print(df.min(axis=1))
print(df.max(axis=1))
print(df.sum())
print(df.var())
print(df.std())
print(df.prod())

 

df.fillna('-')

df.isna()

 

df = DataFrame(data, index=['20200615', '20200616', '20200617', '20200618'])

df.index.name = 'a'
df.columns.name = 'b'

df.reset_index()

res = df.set_index('종가')

df = pd.concat([df1, df2], axis=1)

pd.merge(df1, df2, on="구분")

 

import pandas as pd
df = pd.read_excel('test.xlsx')

df = pd.read_excel(r"data/행정동코드_매핑정보_20200325.xlsx", engine='openpyxl')

df = pd.read_csv(r"data/서울시 지하철호선별 역별 승하차 인원 정보.csv", encoding='cp949')

 

df['호선명'].info()

df['호선명'] = df['호선명'].astype('category')

 

df['사용일자'] = pd.to_datetime(df['사용일자'])

df['년'] = df['등록일자'] // 10000
df['월'] = df['등록일자'] % 10000 // 100
df['일'] = df['등록일자'] % 100

df['년1'] = df['등록일자'].astype('string').str[:4]
df['월1'] = df['등록일자'].astype('string').str[4:6]
df['일1'] = df['등록일자'].astype('string').str[6:8]

 

df['승차총승객수'].idxmax()

 

index = ['x','y']
data = [ [1,2],[3,4] ]
column = ['a','b']
df = DataFrame(data, index, column)

 

import matplotlib
import matplotlib.pyplot as plt
plt.rcParams["font.family"] = "NanumGothic"

 

t.plot(figsize=(10,2))

t.plot.line(figsize=(10,2))

 

df['승차총승객수'].value_counts()

df['승차총승객수'].plot.hist()

 

df.corr( numeric_only = True)

df.isna().sum()