「권철민(2020).파이썬 머신러닝 완벽가이드(개정판).위키북스」 책으로 공부한 뒤 정리한 내용.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
titanic_df = pd.read_csv('./train.csv')
titanic_df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 PassengerId 891 non-null int64
1 Survived 891 non-null int64
2 Pclass 891 non-null int64
3 Name 891 non-null object
4 Sex 891 non-null object
5 Age 714 non-null float64
6 SibSp 891 non-null int64
7 Parch 891 non-null int64
8 Ticket 891 non-null object
9 Fare 891 non-null float64
10 Cabin 204 non-null object
11 Embarked 889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB
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 = preprocessing.LabelEncoder()
le = le.fit(df[feature])
df[feature] = le.transform(df[feature])
return df
def transform_feature(df):
df=fillna(df)
df=drop_features(df)
df=format_features(df)
return df
titanic_df = pd.read_csv('./train.csv')
y_titanic_df = titanic_df['Survived']
X_titanic_df = titanic_df.drop('Survived', axis=1)
X_titanic_df = transform_feature(X_titanic_df)
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
dt_clf = DecisionTreeClassifier(random_state=11)
rf_clf = RandomForestClassifier(random_state=11)
lr_clf = LogisticRegression()
dt_clf.fit(X_train, y_train)
dt_pred = dt_clf.predict(X_test)
print('DT 정확도: ', accuracy_score(y_test, dt_pred))
rf_clf.fit(X_train, y_train)
rf_pred = rf_clf.predict(X_test)
print('RF 정확도: ', accuracy_score(y_test, rf_pred))
lr_clf.fit(X_train, y_train)
lr_pred = lr_clf.predict(X_test)
print('LR 정확도: ', accuracy_score(y_test, lr_pred))
DT 정확도: 0.7877094972067039
RF 정확도: 0.8547486033519553
LR 정확도: 0.8491620111731844
from sklearn.model_selection import KFold
def exec_kfold(clf, folds=5):
kfold = KFold(n_splits=folds)
scores = []
for iter_count, (train_index, test_index) in enumerate(kfold.split(X_titanic_df)):
X_train, X_test = X_titanic_df.values[train_index], X_titanic_df.values[test_index]
y_train, y_test = y_titanic_df.values[train_index], y_titanic_df.values[test_index]
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
scores.append(accuracy)
print('교차검증 {0} 정확도: {1:.4f}'.format(iter_count, accuracy))
mean_score = np.mean(scores)
print('평균 정확도: {0:.4f}'.format(mean_score))
exec_kfold(dt_clf, folds=5)
교차검증 0 정확도: 0.7542
교차검증 1 정확도: 0.7809
교차검증 2 정확도: 0.7865
교차검증 3 정확도: 0.7697
교차검증 4 정확도: 0.8202
평균 정확도: 0.7823
from sklearn.model_selection import cross_val_score
scores = cross_val_score(dt_clf, X_titanic_df, y_titanic_df, cv=5)
for iter_count, accuracy in enumerate(scores):
print('교차 검증 {0} 정확도: {1:.4f}'.format(iter_count, accuracy))
print('평균 정확도: {0:.4f}'.format(np.mean(scores)))
교차 검증 0 정확도: 0.7430
교차 검증 1 정확도: 0.7753
교차 검증 2 정확도: 0.7921
교차 검증 3 정확도: 0.7865
교차 검증 4 정확도: 0.8427
평균 정확도: 0.7879