def test_ignore_nan_values():
estimate = np.array([1, 2, 3, np.nan])
actual = np.array([1, 2, 3, np.nan])
weights = np.array([1, 1, 1, 1])
calculated_nwrmsle = evaluation.nwrmsle(estimate, actual, weights)
assert calculated_nwrmsle == 0.0
def main(model=Model.DECISION_TREE, seed=None):
original_train, original_validate = load_data()
train, validate = encode(original_train, original_validate)
with tracking.track() as track:
track.set_model(model)
model, params = train_model(train, model, seed)
track.log_params(params)
validation_predictions = make_predictions(model, validate)
print("Calculating metrics")
evaluation_metrics = {
'nwrmsle':
evaluation.nwrmsle(validation_predictions,
validate['unit_sales'].values,
validate['perishable'].values),
'r2_score':
metrics.r2_score(y_true=validate['unit_sales'].values,
y_pred=validation_predictions)
}
track.log_metrics(evaluation_metrics)
write_predictions_and_score(evaluation_metrics, model,
original_train.columns)
print("Evaluation done with metrics {}.".format(
json.dumps(evaluation_metrics)))
def test_calculates_nwrmsle_for_perfect_match():
estimate = np.array([1, 2, 3])
actual = np.array([1, 2, 3])
weights = np.array([1, 1, 1])
calculated_nwrmsle = evaluation.nwrmsle(estimate, actual, weights)
assert calculated_nwrmsle == 0.0
def test_eliminate_negative_values():
estimate = np.array([1, 2, 3, -1])
actual = np.array([1, 2, 3, -1])
weights = np.array([1, 1, 1, 1])
calculated_nwrmsle = evaluation.nwrmsle(estimate, actual, weights)
assert calculated_nwrmsle == 0.0
def main():
train, validate = load_data()
print("Not predicting returns...")
train.loc[train['unit_sales'] < 0, 'unit_sales'] = 0
validate.loc[validate['unit_sales'] < 0, 'unit_sales'] = 0
validation_predictions, problem_pairs_part = get_predictions(
validate, train)
preds_sorted = validation_predictions.sort_values(by=['id'])
subset_for_validation = validate[validate.id.isin(
validation_predictions['id'])].sort_values(by=['id'])
print("Calculating estimated error")
validation_score = evaluation.nwrmsle(
preds_sorted['unit_sales'].values,
subset_for_validation['unit_sales'].values,
subset_for_validation['perishable'].values)
write_predictions_and_score(validation_score, 0, train.columns)
print(
"Times series analysis done with a validation score (error rate) of {}."
.format(validation_score))
def test_calculates_nwrmsle_for_perfect_match():
estimate = np.array([1, 2, 3])
actual = np.array([1, 2, 3])
weights = np.array([1, 1, 1])
calculated_nwrmsle = evaluation.nwrmsle(estimate, actual, weights)
assert calculated_nwrmsle == 0.0
def test_calculates_nwrmsle_for_imperfect_match():
estimate = np.array([0, 0, 0])
actual = np.array([1, 1, 1])
weights = np.array([1, 1, 1])
calculated_nwrmsle = evaluation.nwrmsle(estimate, actual, weights)
# Assert by-hand calculation of nwrmsle is reasonably close to python calculation
assert approx(calculated_nwrmsle, 0.69314718)
def test_calculates_nwrmsle_for_imperfect_match():
estimate = np.array([0, 0, 0])
actual = np.array([1, 1, 1])
weights = np.array([1, 1, 1])
calculated_nwrmsle = evaluation.nwrmsle(estimate, actual, weights)
# Assert by-hand calculation of nwrmsle is reasonably close to python calculation
assert approx(calculated_nwrmsle, 0.69314718)
def main(model=Model.RANDOM_FOREST):
original_train, original_validate = load_data()
train, validate = encode(original_train, original_validate)
model = make_model(train, model)
validation_predictions = make_predictions(model, validate)
print("Calculating estimated error")
validation_score = evaluation.nwrmsle(validation_predictions, validate['unit_sales'].values, validate['perishable'].values)
write_predictions_and_score(validation_score, model, original_train.columns)
print("Decision tree analysis done with a validation score (error rate) of {}.".format(validation_score))
def main():
train, validate = load_data()
print("Not predicting returns...")
train.loc[train['unit_sales']<0, 'unit_sales']=0
validate.loc[validate['unit_sales']<0, 'unit_sales']=0
validation_predictions, problem_pairs_part = get_predictions(validate, train)
preds_sorted = validation_predictions.sort_values(by=['id'])
subset_for_validation = validate[validate.id.isin(validation_predictions['id'])].sort_values(by=['id'])
print("Calculating estimated error")
validation_score = evaluation.nwrmsle(preds_sorted['unit_sales'].values, subset_for_validation['unit_sales'].values, subset_for_validation['perishable'].values)
write_predictions_and_score(validation_score, 0, train.columns)
print("Times series analysis done with a validation score (error rate) of {}.".format(validation_score))
