def test_empty_blocks(self, simil_df):
X = simil_df.copy()
X['blocks'].iloc[1] = ['']
assert (SimilaritySelector().fit(
X['blocks'], X['Ingrédients']).predict(X['blocks'])[1] == '')
model = SimilaritySelector().fit(X['blocks'], X['Ingrédients'])
model.predict([X['blocks'].iloc[0]])
assert (model.predict([['']]) == np.array([''])).all()
def test_hashing_type(self, simil_df):
model = SimilaritySelector(count_vect_type='HashingVectorizer', )
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
target_data = ['100% sucre', 'E110, farine', 'haricots']
target_ds = pd.Series(
target_data,
simil_df.index,
)
assert pd.Series(out_ds).equals(target_ds)
def test_predict_cosine(self, simil_df):
model = SimilaritySelector(similarity='cosine', )
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
target_data = ['100% sucre', 'E110, farine', 'haricots']
target_ds = pd.Series(
target_data,
simil_df.index,
)
assert pd.Series(out_ds).equals(target_ds)
def test_predict(self, simil_df):
transformer = SimilaritySelector().fit(simil_df['blocks'],
simil_df['Ingrédients'])
test_blocks = [[
'fabriqué en Italie', 'mélange de nougat',
'sucre, eau et betteraves'
]]
assert (all(
transformer.predict(test_blocks) == pd.Series(
['sucre, eau et betteraves'])))
def test_embedding(self, simil_df):
with pytest.raises(ValueError):
(SimilaritySelector(embedding_method='incorrect').fit(
simil_df['blocks'], simil_df['Ingrédients']))
model = SimilaritySelector(embedding_method='Word2Vec',
count_vect_kwargs={'stop_words': {'de'}})
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
target_data = ['100% sucre', 'E110, farine', 'haricots']
target_ds = pd.Series(
target_data,
simil_df.index,
)
assert pd.Series(out_ds).equals(target_ds)
embed_parms = {'n_components': 5}
model = SimilaritySelector(embedding_method='tSVD',
embedding_parms=embed_parms)
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
assert pd.Series(out_ds).equals(target_ds)
def test_cosine_with_score(self, simil_df):
# absolute scoring
model = SimilaritySelector(similarity='cosine',
scoring='absolute_score')
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
target_data = ['100% sucre', 'E110, farine', 'haricots']
target_ds = pd.Series(
target_data,
simil_df.index,
)
assert pd.Series(out_ds).equals(target_ds)
# relative scoring
model = SimilaritySelector(similarity='cosine',
scoring='relative_score')
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
target_data = ['100% sucre', 'E110, farine', 'haricots']
target_ds = pd.Series(
target_data,
simil_df.index,
)
assert pd.Series(out_ds).equals(target_ds)
def test_l_norm_values(self, simil_df):
l2_norm = partial(sparse_norm, axis=1, ord=2)
model = SimilaritySelector(
similarity='projection',
source_norm='l3',
projected_norm=l2_norm,
)
model.fit(simil_df['blocks'], simil_df['Ingrédients'])
out_ds = model.predict(simil_df['blocks'])
target_data = ['100% sucre', 'E110, farine', 'haricots']
target_ds = pd.Series(
target_data,
simil_df.index,
)
assert pd.Series(out_ds).equals(target_ds)
def test_predict_no_transform(self, simil_df):
transformer = SimilaritySelector().fit(simil_df['blocks'],
simil_df['Ingrédients'])
assert (all(
transformer.predict([['haricot', 'exploité en Inde']]) ==
pd.Series(['haricot'])))