'min_samples_split': 10, 'max_features': 'sqrt', 'max_depth': 6}
model = RandomForestClassifier(**parameters)
model.fit(train, targets)
output = model.predict(test).astype(int)
df_output = pd.DataFrame()
aux = pd.read_csv('test.csv')
df_output['PassengerId'] = aux['PassengerId']
df_output['Survived'] = output
df_output[['PassengerId', 'Survived']].to_csv('gridsearch_rf.csv', index=False)
trained_models = []
for model in models:
model.fit(train, targets)
trained_models.append(model)
predictions = []
for model in trained_models:
predictions.append(model.predict_proba(test)[:, 1])
predictions_df = pd.DataFrame(predictions).T
predictions_df['out'] = predictions_df.mean(axis=1)
predictions_df['PassengerId'] = aux['PassengerId']
predictions_df['out'] = predictions_df['out'].map(lambda s: 1 if s >= 0.5 else 0)
predictions_df = predictions_df[['PassengerId', 'out']]
predictions_df.columns = ['PassengerId', 'Survived']
predictions_df.to_csv('blending_base_models.csv', index=False)
modeler = [
DecisionTreeClassifier(),
RandomForestClassifier(),
GradientBoostingClassifier()
]
S_X_train, S_X_test = stacking(modeler,
X_train,
y_train,
X_test,
regression=False,
metric=metrics.log_loss,
needs_proba=True,
stratified=True,
shuffle=True,
random_state=42,
verbose=2)
# %%
model = LogisticRegression(penalty='l1', C=1, random_state=42)
model = model.fit(S_X_train, y_train)
y_pred = pd.Series(model.predict(S_X_test))
y_pred_proba = model.predict_proba(S_X_test)[:, 1]
print("R Square:", metrics.accuracy_score(y_test, model.predict(S_X_test)))
print("kappa:", metrics.cohen_kappa_score(y_test, model.predict(S_X_test)))
# %%
# In[ ]:
# Using Ensemble model technique by considering all the models trained to predict Survival (Trial 4)
models = [
logreg_model, logreg_cv_model, rf_model, gboost_model, dt_model, ab_model
]
trained_models = []
for model in models:
model.fit(train_reduced, final_train_set_y)
trained_models.append(model)
predictions = []
for model in trained_models:
predictions.append(model.predict_proba(test_reduced)[:, 1])
# Take the mean of probability identified by each model
kaggle_df = pd.DataFrame(predictions).T
kaggle_df['out'] = kaggle_df.mean(axis=1)
kaggle_df['PassengerId'] = titanic_test_org['PassengerId']
kaggle_df['out'] = kaggle_df['out'].map(lambda s: 1 if s >= 0.5 else 0)
# dataframe with predictions
kaggle_df = kaggle_df[['PassengerId', 'out']]
kaggle_df.columns = ['PassengerId', 'Survived']
# save to csv
kaggle_df.to_csv('RFTunedsubmission.csv', index=False)
# In[ ]:
print("Accuracy: %.2f%%" % (accuracy * 100.0))
print(classification_report(y_test, predictions))
end = time.clock()
print('预测163个结果，所需时间为' + str(end - start))
# In[ ]:
print(model)
# In[ ]:
xgb.to_graphviz(model, num_trees=10)
# In[ ]:
y_score = model.predict_proba(DataFrame(X_test, dtype='float'))
y_score = [a[1] for a in y_score]
fpr, tpr, threshold = roc_curve(y_test, y_score) ###计算真正率和假正率
roc_auc = auc(fpr, tpr) ###计算auc的值
plt.figure()
lw = 2
plt.figure(figsize=(10, 10))
plt.plot(fpr,
tpr,
color='darkorange',
lw=lw,
label='ROC curve (area = %0.2f)' % roc_auc) ###假正率为横坐标，真正率为纵坐标做曲线
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
X_test_rf_selected = X_test[X_test.columns.intersection(rf_selected_features)]
y_rf_predictions = random_forest.predict(X_test_rf_selected)
conf_matrix = metrics.confusion_matrix(y_test, y_rf_predictions)
sns.heatmap(pd.DataFrame(conf_matrix), annot=True, fmt='g', cmap='coolwarm_r')
plt.title('Random Forests')
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
#plt.savefig('RF_CM.png', quality=95)
plt.show()
print(f"Accuracy: {metrics.accuracy_score(y_test, y_rf_predictions)}")
print(classification_report(y_test, y_rf_predictions))
y_pred_prob_rf = random_forest.predict_proba(X_test_rf_selected)[::, 1]
fpr, tpr, _ = metrics.roc_curve(y_test, y_pred_prob_rf)
auc = metrics.roc_auc_score(y_test, y_pred_prob_rf)
plt.plot(fpr, tpr)
plt.title(f'Random Forests - Area Under Curve : {str(auc)[:4]}')
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
#plt.savefig('RF_AUC.png', quality = 95)
plt.show()
print(f'Area Under Curve : {auc}')
# Boosted Trees
print('\n Gradient Boosted Trees model')
data_dmatrix = xgb.DMatrix(data=X_train, label=y_train)
