2021-04-27 머신러닝 완벽가이드 titanic 예측

from sklearn import preprocessing

def encode_features(dataDF):
    features = ['Cabin', 'Sex', 'Embarked']
    for feature in features:
        le = preprocessing.LabelEncoder()
        le = le.fit(dataDF[feature])
        dataDF[feature] = le.transform(dataDF[feature])
        
    return dataDF

titanic_df = encode_features(titanic_df)
titanic_df.head()
PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	1	22.0	1	0	A/5 21171	7.2500	7	3
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	0	38.0	1	0	PC 17599	71.2833	2	0
2	3	1	3	Heikkinen, Miss. Laina	0	26.0	0	0	STON/O2. 3101282	7.9250	7	3
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	0	35.0	1	0	113803	53.1000	2	3
4	5	0	3	Allen, Mr. William Henry	1	35.0	0	0	373450	8.0500	7	3
from sklearn.preprocessing import LabelEncoder

# Null 처리 함수
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

# 머신러닝 알고리즘에 불필요한 속성 제거
def drop_features(df):
    df.drop(['PassengerId','Name','Ticket'],axis=1,inplace=True)
    return df

# 레이블 인코딩 수행. 
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

# 앞에서 설정한 Data Preprocessing 함수 호출
def transform_features(df):
    df = fillna(df)
    df = drop_features(df)
    df = format_features(df)
    return df
# 원본 데이터를 재로딩 하고, feature데이터 셋과 Label 데이터 셋 추출. 
titanic_df = pd.read_csv('./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)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X_titanic_df, y_titanic_df, \
                                                  test_size=0.2, random_state=11)
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# 결정트리, Random Forest, 로지스틱 회귀를 위한 사이킷런 Classifier 클래스 생성
dt_clf = DecisionTreeClassifier(random_state=11)
rf_clf = RandomForestClassifier(random_state=11)
lr_clf = LogisticRegression()

# DecisionTreeClassifier 학습/예측/평가
dt_clf.fit(X_train , y_train)
dt_pred = dt_clf.predict(X_test)
print('DecisionTreeClassifier 정확도: {0:.4f}'.format(accuracy_score(y_test, dt_pred)))

# RandomForestClassifier 학습/예측/평가
rf_clf.fit(X_train , y_train)
rf_pred = rf_clf.predict(X_test)
print('RandomForestClassifier 정확도:{0:.4f}'.format(accuracy_score(y_test, rf_pred)))

# LogisticRegression 학습/예측/평가
lr_clf.fit(X_train , y_train)
lr_pred = lr_clf.predict(X_test)
print('LogisticRegression 정확도: {0:.4f}'.format(accuracy_score(y_test, lr_pred)))
DecisionTreeClassifier 정확도: 0.7877
RandomForestClassifier 정확도:0.8547
LogisticRegression 정확도: 0.8492
C:\Users\SM2130\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(