machine learning/Predict survival on the Titanic- using scikit-learn

• SVC

svm_clf = SVC(random_state=42)
svm_clf.fit(X_train_prepared, y_train)

SVC(random_state=42)

cross_val_score(svm_clf, X_train_prepared, y_train, cv=3, scoring="accuracy")

array([0.62962963, 0.69023569, 0.68013468])

• kNN

knn_clf = KNeighborsClassifier(n_neighbors = 3)
knn_clf.fit(X_train_prepared, y_train)

KNeighborsClassifier(n_neighbors=3)

cross_val_score(knn_clf, X_train_prepared, y_train, cv=3, scoring="accuracy")

array([0.74410774, 0.78114478, 0.75084175])

• SGD

sgd_clf = SGDClassifier(random_state = 42)
sgd_clf.fit(X_train_prepared, y_train)

SGDClassifier(random_state=42)

cross_val_score(sgd_clf, X_train_prepared, y_train, cv=3, scoring="accuracy")

array([0.72390572, 0.4006734 , 0.41077441])

y_predict_sgd = cross_val_predict(sgd_clf, X_train_prepared, y_train, cv=3)

precision_score(y_train, y_predict_sgd)

0.4340425531914894

recall_score(y_train, y_predict_sgd)

0.8947368421052632

f1_score(y_train, y_predict_sgd)

0.5845272206303724

y_score_sgd = cross_val_predict(sgd_clf, X_train_prepared, y_train, cv=3, method="decision_function")

roc_auc_score(y_train, y_score_sgd)

0.6755025085482377

• RandomForest

forest_clf = RandomForestClassifier(random_state = 42)
forest_clf.fit(X_train_prepared, y_train)

RandomForestClassifier(random_state=42)

cross_val_score(forest_clf, X_train_prepared, y_train, cv=3, scoring="accuracy")

array([0.81481481, 0.7979798 , 0.82154882])

y_predict_forest = cross_val_predict(forest_clf, X_train_prepared, y_train, cv=3)

precision_score(y_train, y_predict_forest)

0.7636363636363637

recall_score(y_train, y_predict_forest)

0.7368421052631579

f1_score(y_train, y_predict_forest)

0.7499999999999999

y_score_forest = cross_val_predict(forest_clf, X_train_prepared, y_train, cv=3, method="predict_proba")

y_score_forest = y_score_forest[:, 1] # 양성 예측률

roc_auc_score(y_train, y_score_forest)

0.8496522118897729

• 파라미터 튜닝

pamran_grid = [
    {'n_estimators': [100,200,300], 'max_features': [2,4,6,8,10,12]}
]

grid_search = GridSearchCV(forest_clf, pamran_grid, cv=5, scoring="accuracy", n_jobs=1)

grid_search.fit(X_train_prepared, y_train)

GridSearchCV(cv=5, estimator=RandomForestClassifier(random_state=42), n_jobs=1,
             param_grid=[{'max_features': [2, 4, 6, 8, 10, 12],
                          'n_estimators': [100, 200, 300]}],
             scoring='accuracy')

grid_search.best_params_

{'max_features': 8, 'n_estimators': 100}

grid_search.best_score_

0.8226727763480006

cvres = grid_search.cv_results_

for mean_score, params in zip(cvres["mean_test_score"], cvres["params"]):
    print(mean_score, params)

0.8125729709371665 {'max_features': 2, 'n_estimators': 100}
0.8125855250768941 {'max_features': 2, 'n_estimators': 200}
0.8137028435126483 {'max_features': 2, 'n_estimators': 300}
0.8103320569957944 {'max_features': 4, 'n_estimators': 100}
0.8136902893729208 {'max_features': 4, 'n_estimators': 200}
0.8148138848785388 {'max_features': 4, 'n_estimators': 300}
0.8170673529596384 {'max_features': 6, 'n_estimators': 100}
0.8193019898311468 {'max_features': 6, 'n_estimators': 200}
0.8170610758897746 {'max_features': 6, 'n_estimators': 300}
0.8226727763480006 {'max_features': 8, 'n_estimators': 100}
0.8204381394764925 {'max_features': 8, 'n_estimators': 200}
0.8170673529596384 {'max_features': 8, 'n_estimators': 300}
0.82045069361622 {'max_features': 10, 'n_estimators': 100}
0.8182035026049841 {'max_features': 10, 'n_estimators': 200}
0.8148327160881301 {'max_features': 10, 'n_estimators': 300}
0.8204444165463561 {'max_features': 12, 'n_estimators': 100}
0.8181909484652564 {'max_features': 12, 'n_estimators': 200}
0.8170736300295023 {'max_features': 12, 'n_estimators': 300}

final_model = grid_search.best_estimator_

• 최종 성능 평가

X_test = preprocess_pipeline.transform(test_data) 
y_pred = final_model.predict(X_test)

fig, (ax1, ax2) = plt.subplots(ncols=2)
fig.set_size_inches(12, 5)

sns.histplot(y_train, ax=ax1, bins=50)
ax1.set(title="y_train")

sns.histplot(y_pred, ax=ax2, bins=50)
ax2.set(title="y_pred")

[Text(0.5, 1.0, 'y_pred')]

• 제출용 CSV 만들기

submission = pd.read_csv("./gender_submission.csv")
submission

submission["Survived"] = y_pred 

print(submission.shape)
submission.head()

ver = 2

submission.to_csv("./ver_{0}_submission.csv".format(ver), index=False)

(418, 2)