[작업형2] 암기할 것들

데이터 전처리 

• 라벨 인코딩 

from sklearn.preprocessing import LabelEncoder

for col in cols :
	le = LabelEncoder()
    train[col] = le.fit_transform(train[col])
    test[col] = le.transform(test[col])

 

검증 데이터 분리 

from sklearn.model_selection import train_test_split

X_tr, X_val,y_tr,y_val = train_test_split(train, target, test_size=0.2, random_state=0)

 

 

모델 및 평가

• 분류_랜덤포래스트

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(random_state=0)
rf.fit(X_tr,y_tr)
pred = rf.predict(X_val)

 

• 회귀_랜덤포레스트

from sklearn.ensemble import RandomForestRegressor

rf = RandomForestRegressor(random_state=0)
rf.fit(X_tr,y_tr)
pred = rf.predict(X_val)

 

• 분류 평가지표

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score

# 정확도
print(accuracy_score(y_val, pred))

# 정밀도
print(precision_score(y_val, pred))

# 재현율 (민감도)
print(recall_score(y_val, pred))

# F1
print(f1_score(y_val , pred))

# roc-auc
pred_proba = rf.predict_proba(X_val)
print(roc_auc_score(y_val, pred[:, 1]))

 

• 회귀 평가지표

from sklearn.metrics import root_mean_squared_error, mean_squared_error, mean_absolute_error, r2_score

result = root_mean_squared_error(y_val, y_pred)
print('RMSE:', result)

# 추가 평가지표 학습
result = mean_squared_error(y_val, y_pred)
print('MSE:', result)

result = mean_absolute_error(y_val, y_pred)
print('MAE:', result)

result = r2_score(y_val, y_pred)
print('R2:', result)

---

 

from sklearn.preprocessing import LabelEncoder

from sklearn.ensemble import RandomForestRegressor

from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score

from sklearn.metrics import root_mean_squared_error, mean_squared_error, mean_absolute_error, r2_score