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. 기본모델 적용
from sklearn.ensemble import RandomForestClassifier
model=RandomForestClassifier()
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)
0.9649122807017544
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
3. Grid Search
param_grid={'n_estimators': range(100, 1000, 100),
'max_features': ['auto', 'sqrt', 'log2']}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(RandomForestClassifier(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)
GridSearchCV(cv=5, estimator=RandomForestClassifier(),
param_grid={'max_features': ['auto', 'sqrt', 'log2'],
'n_estimators': range(100, 1000, 100)})
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: {'max_features': 'auto', 'n_estimators': 100}
Best Score: 0.9765
TestSet Score: 0.9649
4. Random Search
from scipy.stats import randint
param_distribs = {'n_estimators': randint(low=100, high=1000),
'max_features': ['auto', 'sqrt', 'log2']}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(RandomForestClassifier(),
param_distributions=param_distribs, n_iter=20, cv=5)
random_search.fit(X_scaled_train, y_train)
RandomizedSearchCV(cv=5, estimator=RandomForestClassifier(), n_iter=20,
param_distributions={'max_features': ['auto', 'sqrt',
'log2'],
'n_estimators': <scipy.stats._distn_infrastructure.rv_frozen object at 0x000002030B3E7790>})
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: {'max_features': 'sqrt', 'n_estimators': 441}
Best Score: 0.9746
TestSet Score: 0.9649
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. 기본모델 적용
from sklearn.ensemble import RandomForestRegressor
model=RandomForestRegressor()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.9382384580348281
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.5832046084465448
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: 23719.75009257334
테스트 데이터 RMSE: 61719.717290624714
3. Grid Search
param_grid={'n_estimators': range(100, 500, 100),
'max_features': ['auto', 'sqrt', 'log2']}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(RandomForestRegressor(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)
GridSearchCV(cv=5, estimator=RandomForestRegressor(),
param_grid={'max_features': ['auto', 'sqrt', 'log2'],
'n_estimators': range(100, 500, 100)})
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: {'max_features': 'log2', 'n_estimators': 300}
Best Score: 0.5687
TestSet Score: 0.5934
4. Random Search
param_distribs = {'n_estimators': randint(low=100, high=500),
'max_features': ['auto', 'sqrt', 'log2']}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(RandomForestRegressor(),
param_distributions=param_distribs, n_iter=20, cv=5)
random_search.fit(X_scaled_train, y_train)
RandomizedSearchCV(cv=5, estimator=RandomForestRegressor(), n_iter=20,
param_distributions={'max_features': ['auto', 'sqrt',
'log2'],
'n_estimators': <scipy.stats._distn_infrastructure.rv_frozen object at 0x000002030B3FB8E0>})
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: {'max_features': 'sqrt', 'n_estimators': 338}
Best Score: 0.5693
TestSet Score: 0.5928
