[Kaggle] London bike sharing dataset 데이터 살펴보기

https://www.kaggle.com/datasets/hmavrodiev/london-bike-sharing-dataset

London bike sharing dataset

 

import numpy as np
import pandas as pd

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

 

import matplotlib.pyplot as plt
import seaborn as sns
import missingno as msno

 

df = pd.read_csv('/kaggle/input/london-bike-sharing-dataset/london_merged.csv', parse_dates = ['timestamp'])
df.head()

 

print('데이터 구조 :', df.shape)
print('데이터 타입 :', df.dtypes)
print('데이터 컬럼 :', df.columns)

 

df.isna().sum()

 

msno.matrix(df)
plt.show()

 

df['year'] = df['timestamp'].dt.year
df['month'] = df['timestamp'].dt.month
df['dayofweek'] = df['timestamp'].dt.dayofweek
df['hour'] = df['timestamp'].dt.hour
df.head()

 

df['year'].value_counts()
# df['month'].value_counts()
# df['dayofweek'].value_counts()
# df['weather_code'].value_counts()