fcols = [col for col in orig_dataset.columns if col in settings.FEATURES]
catconversion = FeatureUnion([feature_sets.CATEGORICAL_CONVERSION],
n_jobs=1)
dataset = pd.DataFrame(data=catconversion.fit_transform(orig_dataset),
columns=fcols,
index=orig_dataset.index)
target = FeatureColumnsExtractor(
settings.TARGET).fit_transform(orig_dataset).apply(nonlinearity)
# import time
# before = time.time()
pipeline = overall_pipeline()
cv = KFold(len(target), n_folds=4, random_state=2, shuffle=False)
submission = SqrtHazardSubmission(pipeline, 'XGB_Direct_Reduced', cv=cv)
submission.fit(dataset,
target,
perform_cv=True,
scoring=scorer_normalized_gini,
n_jobs=1,
verbose=3)
original_test_set = pd.read_csv(settings.TEST_FILE)
test_set = pd.DataFrame(data=catconversion.transform(original_test_set),
columns=fcols,
index=original_test_set.index)
predictions = submission.predict(test_set)
submission.create_submission(predictions, original_test_set,
fcols = [col for col in orig_dataset.columns if col in settings.FEATURES]
catconversion = FeatureUnion([feature_sets.CATEGORICAL_CONVERSION],
n_jobs=1)
dataset = pd.DataFrame(data=catconversion.fit_transform(orig_dataset),
columns=fcols,
index=orig_dataset.index)
target = FeatureColumnsExtractor(
settings.TARGET).fit_transform(orig_dataset).apply(nonlinearity)
# import time
# before = time.time()
pipeline = overall_pipeline()
cv = KFold(len(target), n_folds=4, random_state=2, shuffle=False)
submission = SqrtHazardSubmission(pipeline, 'XGB_SVM_Ensemble', cv=cv)
submission.fit(dataset,
target,
perform_cv=True,
scoring=scorer_normalized_gini,
n_jobs=2,
verbose=3)
original_test_set = pd.read_csv(settings.TEST_FILE)
test_set = pd.DataFrame(data=catconversion.transform(original_test_set),
columns=fcols,
index=original_test_set.index)
predictions = submission.predict(test_set)
submission.create_submission(predictions, original_test_set,