0. 핵심개념 및 사이킷런 알고리즘 API 링크
ensemble
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. 모델적용
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import StackingClassifier
estimators = [('rf', RandomForestClassifier(n_estimators=10, random_state=42)),
('svr', SVC(random_state=42))]
model = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.986328125
from sklearn.metrics import confusion_matrix
confusion_train=confusion_matrix(y_train, pred_train)
print("훈련데이터 오차행렬:\n", confusion_train)
훈련데이터 오차행렬:
[[330 3]
[ 4 175]]
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 0.99 0.99 333
1 0.98 0.98 0.98 179
accuracy 0.99 512
macro avg 0.99 0.98 0.98 512
weighted avg 0.99 0.99 0.99 512
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.9649122807017544
confusion_test=confusion_matrix(y_test, pred_test)
print("테스트데이터 오차행렬:\n", confusion_test)
테스트데이터 오차행렬:
[[106 5]
[ 1 59]]
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 0.99 0.95 0.97 111
1 0.92 0.98 0.95 60
accuracy 0.96 171
macro avg 0.96 0.97 0.96 171
weighted avg 0.97 0.96 0.97 171
Part2. 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. 모델적용
from sklearn.linear_model import LinearRegression
from sklearn.neighbors import KNeighborsRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import StackingRegressor
estimators = [('lr', LinearRegression()),
('knn', KNeighborsRegressor())]
model = StackingRegressor(estimators=estimators,
final_estimator=RandomForestRegressor(n_estimators=10, random_state=42))
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.543404932348004
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.4781188528801523
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: 64493.60476580374
테스트 데이터 RMSE: 69063.45138802647
