def test_python_errors(python_data):
rating_true, rating_pred, _ = python_data(binary_rating=False)
with pytest.raises(ValueError):
rmse(rating_true, rating_true, col_user="******")
with pytest.raises(ValueError):
mae(rating_pred,
rating_pred,
col_rating=PREDICTION_COL,
col_user="******")
with pytest.raises(ValueError):
rsquared(rating_true, rating_pred, col_item="not_item")
with pytest.raises(ValueError):
exp_var(rating_pred,
rating_pred,
col_rating=PREDICTION_COL,
col_item="not_item")
with pytest.raises(ValueError):
precision_at_k(rating_true, rating_pred, col_rating="not_rating")
with pytest.raises(ValueError):
recall_at_k(rating_true, rating_pred, col_prediction="not_prediction")
with pytest.raises(ValueError):
ndcg_at_k(rating_true, rating_true, col_user="******")
with pytest.raises(ValueError):
map_at_k(rating_pred,
rating_pred,
col_rating=PREDICTION_COL,
col_user="******")
def test_python_rmse(rating_true, rating_pred):
assert (rmse(
rating_true=rating_true,
rating_pred=rating_true,
col_prediction=DEFAULT_RATING_COL,
) == 0)
assert rmse(rating_true, rating_pred) == pytest.approx(7.254309, TOL)
def test_python_errors(rating_true, rating_pred):
with pytest.raises(ValueError):
rmse(rating_true, rating_true, col_user="******")
with pytest.raises(ValueError):
mae(rating_pred,
rating_pred,
col_rating=DEFAULT_PREDICTION_COL,
col_user="******")
with pytest.raises(ValueError):
rsquared(rating_true, rating_pred, col_item="not_item")
with pytest.raises(ValueError):
exp_var(rating_pred,
rating_pred,
col_rating=DEFAULT_PREDICTION_COL,
col_item="not_item")
with pytest.raises(ValueError):
precision_at_k(rating_true, rating_pred, col_rating="not_rating")
with pytest.raises(ValueError):
recall_at_k(rating_true, rating_pred, col_prediction="not_prediction")
with pytest.raises(ValueError):
ndcg_at_k(rating_true, rating_true, col_user="******")
with pytest.raises(ValueError):
map_at_k(rating_pred,
rating_pred,
col_rating=DEFAULT_PREDICTION_COL,
col_user="******")
def test_python_errors(rating_true, rating_pred):
with pytest.raises(ValueError):
rmse(rating_true, rating_true, col_user="******")
with pytest.raises(ValueError):
mae(rating_pred, rating_pred, col_rating=DEFAULT_PREDICTION_COL, col_user="******")
with pytest.raises(ValueError):
rsquared(rating_true, rating_pred, col_item="not_item")
with pytest.raises(ValueError):
exp_var(
rating_pred, rating_pred, col_rating=DEFAULT_PREDICTION_COL, col_item="not_item"
)
with pytest.raises(ValueError):
precision_at_k(rating_true, rating_pred, col_rating="not_rating")
with pytest.raises(ValueError):
recall_at_k(rating_true, rating_pred, col_prediction="not_prediction")
with pytest.raises(ValueError):
ndcg_at_k(rating_true, rating_true, col_user="******")
with pytest.raises(ValueError):
map_at_k(
rating_pred, rating_pred, col_rating=DEFAULT_PREDICTION_COL, col_user="******"
)
def test_python_rmse(python_data, target_metrics):
rating_true, rating_pred, _ = python_data
assert (
rmse(rating_true=rating_true, rating_pred=rating_true, col_prediction="rating")
== 0
)
assert rmse(rating_true, rating_pred) == target_metrics["rmse"]
def test_python_rmse(rating_true, rating_pred):
assert (
rmse(
rating_true=rating_true,
rating_pred=rating_true,
col_prediction=DEFAULT_RATING_COL,
)
== 0
)
assert rmse(rating_true, rating_pred) == pytest.approx(7.254309, TOL)
def rating_metrics_python(test, predictions):
return {
"RMSE": rmse(test, predictions, **COL_DICT),
"MAE": mae(test, predictions, **COL_DICT),
"R2": rsquared(test, predictions, **COL_DICT),
"Explained Variance": exp_var(test, predictions, **COL_DICT),
}
def rating_metrics_python(test, predictions):
return {
"RMSE": rmse(test, predictions, **COL_DICT),
"MAE": mae(test, predictions, **COL_DICT),
"R2": rsquared(test, predictions, **COL_DICT),
"Explained Variance": exp_var(test, predictions, **COL_DICT)
}
def test_predict_rating(rating_true):
train_set = cornac.data.Dataset.from_uir(rating_true.itertuples(index=False), seed=42)
mf = cornac.models.MF(k=100, max_iter=10000, seed=42).fit(train_set)
preds = predict_rating(mf, rating_true)
assert set(preds.columns) == {"userID", "itemID", "prediction"}
assert preds["userID"].dtypes == rating_true["userID"].dtypes
assert preds["itemID"].dtypes == rating_true["itemID"].dtypes
assert .02 > mae(rating_true, preds) # ~0.018
assert .03 > rmse(rating_true, preds) # ~0.021
def test_python_rmse(python_data, target_metrics):
rating_true, rating_pred, _ = python_data(binary_rating=False)
assert rmse(rating_true=rating_true,
rating_pred=rating_true,
col_prediction=DEFAULT_RATING_COL) == 0
assert rmse(rating_true, rating_pred) == target_metrics["rmse"]
k=TOP_K)
eval_precision = precision_at_k(test,
top_k,
col_user='******',
col_item='itemID',
col_rating='rating',
k=TOP_K)
eval_recall = recall_at_k(test,
top_k,
col_user='******',
col_item='itemID',
col_rating='rating',
k=TOP_K)
eval_rmse = rmse(test,
top_k,
col_user='******',
col_item='itemID',
col_rating='rating')
eval_mae = mae(test,
top_k,
col_user='******',
col_item='itemID',
col_rating='rating')
eval_rsquared = rsquared(test,
top_k,
col_user='******',
col_item='itemID',
col_rating='rating')
eval_exp_var = exp_var(test,
top_k,
col_user='******',
scores = score(learner,
test_df=test_df.copy(),
user_col=USER,
item_col=ITEM,
prediction_col=PREDICTION)
# calculate some regression metrics
eval_r2 = rsquared(test_df,
scores,
col_user=USER,
col_item=ITEM,
col_rating=RATING,
col_prediction=PREDICTION)
eval_rmse = rmse(test_df,
scores,
col_user=USER,
col_item=ITEM,
col_rating=RATING,
col_prediction=PREDICTION)
eval_mae = mae(test_df,
scores,
col_user=USER,
col_item=ITEM,
col_rating=RATING,
col_prediction=PREDICTION)
eval_exp_var = exp_var(test_df,
scores,
col_user=USER,
col_item=ITEM,
col_rating=RATING,
col_prediction=PREDICTION)