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
2-1. AdaBoosting
from sklearn.ensemble import AdaBoostClassifier
model = AdaBoostClassifier(n_estimators=100, random_state=0)
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
1.0
from sklearn.metrics import confusion_matrix
confusion_train=confusion_matrix(y_train, pred_train)
print("훈련데이터 오차행렬:\n", confusion_train)
훈련데이터 오차행렬:
[[333 0]
[ 0 179]]
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 1.00 1.00 1.00 333
1 1.00 1.00 1.00 179
accuracy 1.00 512
macro avg 1.00 1.00 1.00 512
weighted avg 1.00 1.00 1.00 512
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.9532163742690059
confusion_test=confusion_matrix(y_test, pred_test)
print("테스트데이터 오차행렬:\n", confusion_test)
테스트데이터 오차행렬:
[[106 5]
[ 3 57]]
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 0.97 0.95 0.96 111
1 0.92 0.95 0.93 60
accuracy 0.95 171
macro avg 0.95 0.95 0.95 171
weighted avg 0.95 0.95 0.95 171
2-2. Gradient Boosting
from sklearn.ensemble import GradientBoostingClassifier
model = GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0)
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
1.0
from sklearn.metrics import confusion_matrix
confusion_train=confusion_matrix(y_train, pred_train)
print("훈련데이터 오차행렬:\n", confusion_train)
훈련데이터 오차행렬:
[[333 0]
[ 0 179]]
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]]
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
2-1. AdaBoosting
from sklearn.ensemble import AdaBoostRegressor
model = AdaBoostRegressor(random_state=0, n_estimators=100)
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.4353130085971758
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.43568387094087124
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: 71722.42012035428
테스트 데이터 RMSE: 71816.41231019037
2-2. Gradient Boosting
from sklearn.ensemble import GradientBoostingRegressor
model = GradientBoostingRegressor(random_state=0)
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.6178724780500952
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.5974112241813845
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: 59000.433545962376
테스트 데이터 RMSE: 60658.72886338227
