'xgb__colsample_bytree': np.logspace(-0.3, 0, 100) # (~0.5 - 1.0)
}
voting = ScikitModel(voting,
voting_params,
random_search=True,
n_iter=25,
verbose=True)
# Train on whole train-set, predict with 0.5 threshold
voting.train(x_train, y_train)
voting_preds_no_indeterminates = voting.predict(x_test)
# Train on 50%, calibrate on 50%, predict with calibrated thresholds
voting.train_calibrate(x_train, y_train)
voting_preds_with_indeterminates = voting.predict_calibrated(x_test)
print()
### 2 STAGE: LDA --> VOTING ENSEMBLE ###
# Stage 1: LDA
stage1 = LinearDiscriminantAnalysis()
# Stage 2: LR-SVC-XGB Voting Classifier
clf1 = SVC(probability=True)
clf2 = LogisticRegression()
clf3 = xgb.XGBClassifier(n_jobs=N_JOBS)
voting = VotingClassifier(estimators=[('svm', clf1), ('lr', clf2),
('xgb', clf3)],
voting='soft',
n_jobs=N_JOBS)
