Do not print skipped compound words

BigNerd · Oct 1, 2020 · 0267eaa · 0267eaa
1 parent 311b00f
commit 0267eaa
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/justmltools/nlp/word_embedder.py b/justmltools/nlp/word_embedder.py
@@ -155,7 +155,8 @@ def __create_word_index_dict_and_embedding_matrix(
                     embedding_matrix[next_word_index] = np.asarray(tokens[1:], dtype='float32')
                     next_word_index += 1
                 else:
-                    print(f"skipping line with compound word {word} because it splits into {word_sequence}")
+                    #print(f"skipping line with compound word {word} because it splits into {word_sequence}")
+                    pass
         embedding_file.close()
         print(f"loaded {next_word_index - 1} word embeddings")
         non_lower_case_percentage: float = 100 * number_of_non_lower_case_words / max(next_word_index, 1)