Pythonで機械学習を学ぶ ラッソ回帰・リッジ回帰

import pandas as pd
import requests
from sklearn.linear_model import Ridge
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# 読み込み
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00477/Real%20estate%20valuation%20data%20set.xlsx'
res = requests.get(url).content

data = pd.read_excel(res, sheet_name=0, encoding="utf-8", header=0)

data.columns = ['No', 'X1 transaction date', 'X2 house age', 'X3 distance to the nearest MRT station',
                'X4 number of convenience stores', 'X5 latitude', 'X6 longitude', 'Y house price of unit area']

# 確認
print('データ形式:{}'.format(data.shape))
print(data.head())

# 使うものに絞る
data = data[['X2 house age', 'X3 distance to the nearest MRT station',
             'X4 number of convenience stores', 'X5 latitude', 'X6 longitude', 'Y house price of unit area']]

# データ形式の確認
print(data.dtypes)

# 相関を確認
print(data.corr())

# 目的変数、説明変数
X = data.drop('Y house price of unit area', axis=1)
y = data['Y house price of unit area']

# 訓練データ、テストデータの準備
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=0)


# モデルの構築と評価
model_linear = LinearRegression()
model_ridge = Ridge(random_state=0)

# 学習
model_linear.fit(X_train, y_train)
model_ridge.fit(X_train, y_train)

# 結果
print('LinearRegression')
print('train:{:.8f}'.format(model_linear.score(X_train, y_train)))
print('test:{:.8f}'.format(model_linear.score(X_test, y_test)))
print('')
print('Ridge')
print('train:{:.8f}'.format(model_ridge.score(X_train, y_train)))
print('test:{:.8f}'.format(model_ridge.score(X_test, y_test)))

LinearRegression
train:0.56951458
test:0.56810185

Ridge
train:0.53779037
test:0.54716499