[Kaggle] London Bike Sharing Dataset 데이터 전처리 해보기

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 = pd.read_csv('/kaggle/input/london-bike-sharing-dataset/london_merged.csv')
df.head()

 

print('< 데이터 구조 >\n', df.shape)
print('< 데이터 타입 >\n', df.dtypes)
print('< 데이터 컬럼 >\n', df.columns)

 

print('< 결측치 >')
df.isna().sum()

 

print('< 결측치 시각화 >')
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()

 

a, b = plt.subplots(1, 1, figsize=(10, 5))
sns.boxplot(df['year'], df['cnt'])

 

a, b = plt.subplots(1,1, figsize=(10, 5))
sns.boxplot(df['month'], df['cnt'])

 

a, b = plt.subplots(1,1, figsize=(10, 5))
sns.boxplot(df['dayofweek'], df['cnt'])

 

a, b = plt.subplots(1,1, figsize=(10, 5))
sns.boxplot(df['hour'], df['cnt'])

 

 

def plot_bar(data, feature):
    fig = plt.figure(figsize = (12, 3))
    sns.barplot(x = feature, y = 'cnt', data = data, palette = 'Set3')

 

 

plot_bar(df, 'hour')

 

plot_bar(df, 'dayofweek')

 

def is_outliers(s):
    lower_limit = s.mean() - (s.std() * 3)
    upper_limit = s.mean() + (s.std() * 3)
    return ~s.between(lower_limit, upper_limit)

 

 

df_out = df[~df.groupby('hour')['cnt'].apply(is_outliers)]

print('이상치 제거 전 :', df.shape)
print('이상치 제거 후 :', df_out.shape)

 

df_out.dtypes

 

df_out['weather_code'] = df_out['weather_code'].astype('category')
df_out['season'] = df_out['season'].astype('category')
df_out['year'] = df_out['year'].astype('category')
df_out['month'] = df_out['month'].astype('category')
df_out['hour'] = df_out['hour'].astype('category')

 

df_out.dtypes

 

df_out['season']

 

df_out = pd.get_dummies(df_out, columns=['weather_code', 'season', 'year', 'month', 'hour'])
df_out.head()

 

df_out.shape

 

df_y = df_out['cnt']
df_x = df_out.drop(['timestamp', 'cnt'], axis = 1)
df_x.head()

 

df_y.head()

 

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(df_x, df_y, random_state = 1004, test_size = 0.3, shuffle = False)

 

print('x_train의 구조 :', x_train.shape)
print('y_train의 구조 :', y_train.shape)

print('x_test의 구조 :', x_test.shape)
print('y_test의 구조 :', y_test.shape)