라쏘(Lasso) 회귀모델

0. 핵심개념 및 사이킷런 알고리즘 API 링크

sklearn.linear_model.Lasso

1. 분석 데이터 준비

import warnings
warnings.filterwarnings("ignore")
import pandas as pd
data2=pd.read_csv('house_price.csv', encoding='utf-8')
X=data2[data2.columns[1:5]]
y=data2[["house_value"]]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X, y, random_state=42)

from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler()
scaler.fit(X_train)
X_scaled_train=scaler.transform(X_train)
X_scaled_test=scaler.transform(X_test)

2. 기본 모델 적용

from sklearn.linear_model import Lasso
model=Lasso()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)

0.5455724679313863

pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)

0.5626850497564577

# RMSE (Root Mean Squared Error)
import numpy as np
from sklearn.metrics import mean_squared_error 
MSE_train = mean_squared_error(y_train, pred_train)
MSE_test = mean_squared_error(y_test, pred_test)
print("훈련   데이터 RMSE:", np.sqrt(MSE_train))
print("테스트 데이터 RMSE:", np.sqrt(MSE_test))

훈련   데이터 RMSE: 64340.34152172676
테스트 데이터 RMSE: 63220.748913873045

3. Grid Search

param_grid={'alpha': [0.0, 1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 0.1, 0.5, 1.0, 2.0, 3.0]}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(Lasso(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)

GridSearchCV(cv=5, estimator=Lasso(),
             param_grid={'alpha': [0.0, 1e-06, 1e-05, 0.0001, 0.001, 0.01, 0.1,
                                   0.5, 1.0, 2.0, 3.0]})
                                   
print("Best Parameter: {}".format(grid_search.best_params_))
print("Best Score: {:.4f}".format(grid_search.best_score_))
print("TestSet Score: {:.4f}".format(grid_search.score(X_scaled_test, y_test)))

Best Parameter: {'alpha': 0.5}
Best Score: 0.5452
TestSet Score: 0.5627

4. Random Search

from scipy.stats import randint
param_distribs = {'alpha': randint(low=0.00001, high=10)}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(Lasso(), 
                                 param_distributions=param_distribs, n_iter=100, cv=5)
random_search.fit(X_scaled_train, y_train)

RandomizedSearchCV(cv=5, estimator=Lasso(), n_iter=100,
                   param_distributions={'alpha': <scipy.stats._distn_infrastructure.rv_frozen object at 0x000001DECE3673A0>})

print("Best Parameter: {}".format(random_search.best_params_))
print("Best Score: {:.4f}".format(random_search.best_score_))
print("TestSet Score: {:.4f}".format(random_search.score(X_scaled_test, y_test)))

Best Parameter: {'alpha': 1}
Best Score: 0.5452
TestSet Score: 0.5627