인프런 커뮤니티 질문&답변

• 학습 관련 질문을 남겨주세요. 상세히 작성하면 더 좋아요!

• 질문과 관련된 영상 위치를 알려주면 더 빠르게 답변할 수 있어요

• 먼저 유사한 질문이 있었는지 검색해보세요

#1.데이터불러오기 import pandas as pd train = pd.read_csv("energy_train.csv") test = pd.read_csv("energy_test.csv") #2.EDA print(train.shape, test.shape) print(train.info()) print(test.info()) print(train.isnull().sum()) print(test.isnull().sum()) print(train.describe()) print(train.describe(include='O')) print(train.head(2)) print(test.head(2)) target = train.pop('Heat_Load') print(train.shape, test.shape) #3.전처리 #범주형->원핫인코딩 train = pd.get_dummies(train) test = pd.get_dummies(train) #4.검증데이터분리 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=10) print(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape) #5.모델링및평가 from sklearn.ensemble import RandomForestClassifier rf = RandomForestClassifier(random_state=0) rf.fit(X_tr, y_tr) pred = rf.predict(X_val) f1_score(y_val, pred, average='macro') pred = rf.predict(test) submit = pd.DataFrame({ 'pred':pred }) submit.to_csv('result.csv', index=False) df = pd.read_csv("result.csv") print(df.shape)