Adding missing scripts

src/custom_sklearn_text_transformer_mlflow.py

@@ -390,20 +390,20 @@ def prepare_stanza_pipeline(
     #     return ngrams_per_line
 
     @classmethod
-    def ngrams_maker(min_ngram_length, max_ngram_length):
-        def ngrams_per_line(row):
+    def ngram_maker(self, min_ngram_length: int, max_ngram_length: int):
+        def ngrams_per_line(row: str):
             for ln in row.split(" brk "):
                 at_least_two_english_characters_whole_words = r"(?u)\b\w{2,}\b"
                 terms = re.findall(at_least_two_english_characters_whole_words, ln)
-                for ngramLength in range(min_ngram_length, max_ngram_length + 1):
+                for ngram_length in range(min_ngram_length, max_ngram_length + 1):
 
                     # find and return all ngrams
                     # for ngram in zip(*[terms[i:] for i in range(3)]):
                     # <-- solution without a generator (works the same but has higher memory usage)
                     for ngram in (
                         word
-                        for i in range(len(terms) - ngramLength + 1)
-                        for word in (" ".join(terms[i : i + ngramLength]),)
+                        for i in range(len(terms) - ngram_length + 1)
+                        for word in (" ".join(terms[i : i + ngram_length]),)
                     ):
                         yield ngram
 

src/custom_stanza_mlflow.py

@@ -14,19 +14,19 @@ class CustomSKLearnWrapper(mlflow.pyfunc.PythonModel):
     custom PythonModel
     """
 
-    # def __init__(self, model):
-    #     """
-    #     Constructor method. Initializes the model with a Stanza libary language
-    #     type. The default is "en" for English
+    def __init__(self, model):
+        """
+        Constructor method. Initializes the model with a Stanza libary language
+        type. The default is "en" for English
 
-    #     model:          sklearn.Transformer
-    #             The sklearn text Transformer or Pipeline that ends in a
-    #             Transformer
+        model:          sklearn.Transformer
+                The sklearn text Transformer or Pipeline that ends in a
+                Transformer
 
-    #     later can add functionality to include pretrained models needed for Stanza
+        later can add functionality to include pretrained models needed for Stanza
 
-    #     """
-    #     self.model = model
+        """
+        self.model = model
 
     def load_context(self, context):
         """
@@ -74,7 +74,6 @@ def predict(self, context, model_input, params):
         print(model_input.shape)
         print(model_input.sample(3, random_state=200))
 
-        # response = self.sklearn_transformer.transform(model_input)
         response = self.sklearn_transformer.transform(model_input.values)
 
         transformed_recipe = pd.DataFrame(