fixed unit tests

Author: Alexandre Landeau

tests/python/unit/test_spacy_tokenizer.py

@@ -45,7 +45,7 @@ def test_tokenize_df_multilingual():
     output_df = tokenizer.tokenize_df(df=input_df, text_column="input_text", language_column="language")
     tokenized_documents = output_df[tokenizer.tokenized_column]
     tokenized_documents_length = [len(doc) for doc in tokenized_documents]
-    assert tokenized_documents_length == [12, 8, 13, 9]
+    assert tokenized_documents_length == [12, 8, 19, 9]
 
 
 def test_tokenize_df_long_text():

tests/python/unit/test_wordcloud_visualizer.py

@@ -54,7 +54,7 @@ def test_tokenize_and_count_multilingual():
     assert frequencies == [
         ("en", Counter({"hope": 1, "Nothing": 3, "fear": 1, "free": 1})),
         ("fr", Counter({"sanglots": 1, "longs": 1, "violons": 1, "automne": 1})),
-        ("zh", Counter({"子": 1, "曰": 1, "學而": 1, "不思則": 1, "罔": 1, "思而": 1, "不學則": 1}),),
+        ('zh', Counter({'則': 2, '學': 2, '思': 2, '子': 1, '曰': 1, '罔': 1}))
     ]