pandas.basic

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

---

CARD_SUBWAY_MONTH_201905.txt

1.16MB

 

data =pd.read_csv('CARD_SUBWAY_MONTH_201905.txt')

 

data.head(20)

 

data.tail()

 

data.info()

data.describe()

data.index

data.columns

data['사용일자']
data.사용일자
# 같은 표현

data2=data[['승차총승객수','하차총승객수']]
data2

data2.values
# pandas ->numpy

data[data.승차총승객수<10]

data[data.사용일자==20190501]

len(data[data.사용일자==20190501])
#593

data[data.사용일자==20190501].shape
#(593, 7)​

[[day, data[data.사용일자==day].shape[0]] for day in range(20190501,20190532)]

{day: data[data.사용일자==day].shape[0] for day in range(20190501,20190532)}

 

data.isnull()
#data.notnull()

data.isnull().sum()