제로베이스 데이터취업스쿨 DAY64-77 통신사이탈고객예측 Case1

Case1

• 기초 전처리
• 결측치 포함 행 제거
• Customer ID, HandsetPrice 컬럼 Drop
• 라벨인코딩

from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold, cross_val_score
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

data1_rows = pd.read_csv('./data1.csv')

# Create an empty DataFrame
results_df = pd.DataFrame(columns=['Model', 'Accuracy', 'Precision', 'Recall', 'F1 Score'])

# Function to add results to the DataFrame
def df_add(model_name, y_test, pred):
    accuracy = accuracy_score(y_test, pred)
    precision = precision_score(y_test, pred)
    recall = recall_score(y_test, pred)
    f1 = f1_score(y_test, pred)

    results_df.loc[len(results_df)] = [model_name, accuracy, precision, recall, f1]


X = data1_rows.drop(columns=['Churn'])
y = data1_rows['Churn']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=70)

models = []
models.append(('RandomForestClassifier', RandomForestClassifier()))
models.append(('DecisionTreeClassifier', DecisionTreeClassifier()))
models.append(('AdaBoostClassifier', AdaBoostClassifier()))
models.append(('GradientBoostingClassifier', GradientBoostingClassifier()))
models.append(('LogisticRegression', LogisticRegression()))

for name, model in models:
    kfold = KFold(n_splits=5, random_state=70, shuffle=True)
    cv_results = cross_val_score(model, X_train, y_train, cv=kfold, scoring='accuracy')
    
    model.fit(X_train, y_train)
    pred = model.predict(X_test)

    df_add(name, y_test, pred)