def test_CountVectorizerWrapper_on_Serie():
df = get_sample_df(size=100, seed=123)
X = df["text_col"]
vect = CountVectorizerWrapper()
Xres = vect.fit_transform(X)
assert len(Xres.shape) == 2
assert Xres.shape[0] == X.shape[0]
assert Xres.shape[1] == len(vect.get_feature_names())
Xres = vect.transform(X)
assert len(Xres.shape) == 2
assert Xres.shape[0] == X.shape[0]
assert Xres.shape[1] == len(vect.get_feature_names())
def test_CountVectorizerWrapper():
df = get_sample_df(size=100, seed=123)
vect = CountVectorizerWrapper(columns_to_use=["text_col"])
vect.fit(df)
cols = vect.get_feature_names()
for c in cols:
assert c.startswith("text_col__BAG")
vect = CountVectorizerWrapper(columns_to_use=[2])
vect.fit(df)
cols = vect.get_feature_names()
for c in cols:
assert c.startswith("text_col__BAG")
X = df.values
vect = CountVectorizerWrapper(columns_to_use=[2])
vect.fit(X)
cols = vect.get_feature_names()
for c in cols:
assert c.startswith("2__BAG")