def test_bias_user_predict():
algo = Bias(items=False)
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 2, 3])
assert len(p) == 3
assert p.values == approx(algo.mean_ + 1.0)
p = algo.predict_for_user(12, [1, 3])
assert len(p) == 2
assert p.values == approx(algo.mean_ - 0.5)
def test_bias_item_predict():
algo = Bias(users=False)
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 2, 3])
assert len(p) == 3
assert p.values == approx((algo.item_offsets_ + algo.mean_).values)
def test_bias_predict_unknown_user():
algo = Bias()
algo.fit(simple_df)
p = algo.predict_for_user(15, [1, 3])
assert len(p) == 2
assert p.values == approx((algo.item_offsets_.loc[[1, 3]] + algo.mean_).values)
def test_bias_global_predict():
algo = Bias(items=False, users=False)
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 2, 3])
assert len(p) == 3
assert (p == algo.mean_).all()
assert p.values == approx(algo.mean_)
def test_bias_predict_unknown_item():
algo = Bias()
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 3, 4])
assert len(p) == 3
intended = algo.item_offsets_.loc[[1, 3]] + algo.mean_ + 0.25
assert p.loc[[1, 3]].values == approx(intended.values)
assert p.loc[4] == approx(algo.mean_ + 0.25)
def test_bias_new_user_predict():
algo = Bias()
algo.fit(simple_df)
ratings = pd.DataFrame({'item': [1, 2, 3], 'rating': [1.5, 2.5, 3.5]})
ratings = ratings.set_index('item').rating
p = algo.predict_for_user(None, [1, 3], ratings=ratings)
offs = ratings - algo.mean_ - algo.item_offsets_
umean = offs.mean()
_log.info('user mean is %f', umean)
assert len(p) == 2
assert p.values == approx((algo.mean_ + algo.item_offsets_ + umean).loc[[1, 3]].values)
def test_bias_train_ml_ratings():
algo = Bias()
ratings = ml_test.ratings
algo.fit(ratings)
assert algo.mean_ == approx(ratings.rating.mean())
imeans_data = ratings.groupby('item').rating.mean()
imeans_algo = algo.item_offsets_ + algo.mean_
ares, data = imeans_algo.align(imeans_data)
assert ares.values == approx(data.values)
urates = ratings.set_index('user').loc[2].set_index('item').rating
umean = (urates - imeans_data[urates.index]).mean()
p = algo.predict_for_user(2, [10, 11, -1])
assert len(p) == 3
assert p.iloc[0] == approx(imeans_data.loc[10] + umean)
assert p.iloc[1] == approx(imeans_data.loc[11] + umean)
assert p.iloc[2] == approx(ratings.rating.mean() + umean)