def test_CountVectorizerWrapper_output_type():
vect = CountVectorizerWrapper()
res = vect.fit_transform(pd.DataFrame({"a": ["AA", "AAA", "bb"]}))
assert res.dtype == "int32"
vect = CountVectorizerWrapper()
res = vect.fit_transform(
pd.DataFrame({
"a": ["AA", "AAA", "bb"],
"b": ["xxx", "zzz", "xxx"]
}))
assert res.dtype == "int32"
vect = CountVectorizerWrapper(dtype="int64")
res = vect.fit_transform(pd.DataFrame({"a": ["AA", "AAA", "bb"]}))
assert res.dtype == "int64"
vect = CountVectorizerWrapper(dtype="int64")
res = vect.fit_transform(
pd.DataFrame({
"a": ["AA", "AAA", "bb"],
"b": ["xxx", "zzz", "xxx"]
}))
assert res.dtype == "int64"
def test_CountVectorizerWrapper_few_sample():
Xtrain = load_dataset("titanic")[0]
vect = CountVectorizerWrapper(min_df=1)
X = Xtrain.loc[0:10, ["name", "ticket"]]
Xres = vect.fit_transform(X)
assert Xres.shape[0] == 11
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())