인프런 커뮤니티 질문&답변

def fillna(df):
    df['Age'].fillna(df['Age'].mean(),inplace=True)
    df['Cabin'].fillna('N',inplace=True)
    df['Embarked'].fillna('N',inplace=True)
    df['Fare'].fillna(0, inplace=True)
    return df

def drop_features(df):
    df.drop(['PassengerId','Name','Ticket'],axis=1,inplace=True)
    return df

def format_features(df):
    df['Cabin'] = df['Cabin'].str[:1]
    features = ['Cabin','Sex','Embarked']
    for feature in features:
        le = LabelEncoder()
        le = le.fit(df[feature])
        df[feature] = le.transform(df[feature])
    return df

def transform_features(df):
    df = fillna(df)
    df = drop_features(df)
    df = format_features(df)
    return df

titanic_df = pd.read_csv('C:/dev/machine learning/titanic/train.csv')

y_titanic_df = titanic_df['Survived']
X_titanic_df = titanic_df.drop('Survived',axis=1)
X_titanic_df = transform_features(X_titanic_df)