def test_staged_predict():
train_pool = Pool(TRAIN_FILE, column_description=CD_FILE)
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=10, random_seed=0)
model.fit(train_pool)
preds = []
for pred in model.staged_predict(test_pool):
preds.append(pred)
np.save(PREDS_PATH, np.array(preds))
return local_canonical_file(PREDS_PATH)
def test_staged_predict():
train_pool = Pool(TRAIN_FILE, column_description=CD_FILE)
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=10, random_seed=0)
model.fit(train_pool)
preds = []
for pred in model.staged_predict(test_pool):
preds.append(pred)
np.save(PREDS_PATH, np.array(preds))
return local_canonical_file(PREDS_PATH)
# Fit model
model.fit(train_pool)
# Only prediction_type='RawFormulaVal' is allowed with custom `loss_function`
preds_raw = model.predict(X_test, prediction_type='RawFormulaVal')
# ### 3.7 Staged Predict
# CatBoost model has `staged_predict` method. It allows you to iteratively get predictions for a given range of trees.
# In[29]:
model = CatBoostClassifier(iterations=10,
random_seed=42,
logging_level='Silent').fit(train_pool)
ntree_start, ntree_end, eval_period = 3, 9, 2
predictions_iterator = model.staged_predict(validate_pool, 'Probability',
ntree_start, ntree_end,
eval_period)
for preds, tree_count in zip(predictions_iterator,
range(ntree_start, ntree_end, eval_period)):
print('First class probabilities using the first {} trees: {}'.format(
tree_count, preds[:5, 1]))
# ### 3.8 Feature Importances
# Sometimes it is very important to understand which feature made the greatest contribution to the final result. To do this, the CatBoost model has a `get_feature_importance` method.
# In[30]:
model = CatBoostClassifier(iterations=50,
random_seed=42,
logging_level='Silent').fit(train_pool)
feature_importances = model.get_feature_importance(train_pool)
