0. 핵심개념 및 사이킷런 알고리즘 API 링크
sklearn.naive_bayes
sklearn.naive_bayes.GaussianNB
sklearn.linear_model.BayesianRidge
Part1. 분류(Classification)
1. 분석 데이터 준비
import warnings
warnings.filterwarnings("ignore")
import pandas as pd
data1=pd.read_csv('breast-cancer-wisconsin.csv', encoding='utf-8')
X=data1[data1.columns[1:10]]
y=data1[["Class"]]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X, y, stratify=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. 기본모델 적용
from sklearn.naive_bayes import GaussianNB
model=GaussianNB()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.966796875
from sklearn.metrics import confusion_matrix
confusion_train=confusion_matrix(y_train, pred_train)
print("훈련데이터 오차행렬:\n", confusion_train)
훈련데이터 오차행렬:
[[319 14]
[ 3 176]]
from sklearn.metrics import classification_report
cfreport_train=classification_report(y_train, pred_train)
print("분류예측 레포트:\n", cfreport_train)
분류예측 레포트:
precision recall f1-score support
0 0.99 0.96 0.97 333
1 0.93 0.98 0.95 179
accuracy 0.97 512
macro avg 0.96 0.97 0.96 512
weighted avg 0.97 0.97 0.97 512
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.9590643274853801
confusion_test=confusion_matrix(y_test, pred_test)
print("테스트데이터 오차행렬:\n", confusion_test)
테스트데이터 오차행렬:
[[106 5]
[ 2 58]]
from sklearn.metrics import classification_report
cfreport_test=classification_report(y_test, pred_test)
print("분류예측 레포트:\n", cfreport_test)
분류예측 레포트:
precision recall f1-score support
0 0.98 0.95 0.97 111
1 0.92 0.97 0.94 60
accuracy 0.96 171
macro avg 0.95 0.96 0.96 171
weighted avg 0.96 0.96 0.96 171
3. Grid Search
param_grid={'var_smoothing': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9 , 10]}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(GaussianNB(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)
GridSearchCV(cv=5, estimator=GaussianNB(),
param_grid={'var_smoothing': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})
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: {'var_smoothing': 0}
Best Score: 0.9649
TestSet Score: 0.95914. Random Search
from scipy.stats import randint
param_distribs = {'var_smoothing': randint(low=0, high=20)}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(GaussianNB(),
param_distributions=param_distribs, n_iter=100, cv=5)
random_search.fit(X_scaled_train, y_train)
RandomizedSearchCV(cv=5, estimator=GaussianNB(), n_iter=100,
param_distributions={'var_smoothing': <scipy.stats._distn_infrastructure.rv_frozen object at 0x0000015C527D68E0>})
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: {'var_smoothing': 0}
Best Score: 0.9649
TestSet Score: 0.9591Part2. 회귀(Regression)
1. 분석 데이터 준비
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. 기본모델 적용
from sklearn.naive_bayes import GaussianNB
model=GaussianNB()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
from sklearn.linear_model import BayesianRidge
model=BayesianRidge()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.5455724466331763
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.5626859871488646
# 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: 64340.34302948542
테스트 데이터 RMSE: 63220.6811564344753. Grid Search
param_grid={'alpha_1': [1e-06, 1e-05, 1e-04, 1e-03, 1e-02, 1e-01, 1, 2, 3, 4],
'lambda_1': [1e-06, 1e-05, 1e-04, 1e-03, 1e-02, 1e-01, 1, 2, 3, 4]}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(BayesianRidge(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)
GridSearchCV(cv=5, estimator=BayesianRidge(),
param_grid={'alpha_1': [1e-06, 1e-05, 0.0001, 0.001, 0.01, 0.1, 1,
2, 3, 4],
'lambda_1': [1e-06, 1e-05, 0.0001, 0.001, 0.01, 0.1, 1,
2, 3, 4]})
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_1': 4, 'lambda_1': 1e-06}
Best Score: 0.5452
TestSet Score: 0.56274. Random Search
param_distribs = {'alpha_1': randint(low=1e-06, high=10),
'lambda_1': randint(low=1e-06, high=10)}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(BayesianRidge(),
param_distributions=param_distribs, n_iter=50, cv=5)
random_search.fit(X_scaled_train, y_train)
RandomizedSearchCV(cv=5, estimator=BayesianRidge(), n_iter=50,
param_distributions={'alpha_1': <scipy.stats._distn_infrastructure.rv_frozen object at 0x0000015C538F40D0>,
'lambda_1': <scipy.stats._distn_infrastructure.rv_frozen object at 0x0000015C538F4DC0>})
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': 6, 'lambda_1': 0}
Best Score: 0.5452
TestSet Score: 0.5627