Update app.py

app.py

@@ -11,21 +11,44 @@ nlp = spacy.load("en_core_web_sm")
 cues = pd.read_excel('link_cues.xlsx')
 list_causalmarkers = cues['causal_markers']
 
+# def contains_words_or_phrases(words_list, sentence):
+#     """
+#     Check if any word or phrase from words_list is present in the sentence.
+
+#     :param words_list: List of words or phrases to check
+#     :param sentence: The input sentence where to look for words or phrases
+#     :return: Entities if any word or phrase is found, otherwise None
+#     """
+#     # Normalize the sentence to lower case to make the search case insensitive
+#     normalized_sentence = sentence.lower()
+
+#     # Check each word or phrase in the list
+#     for word_or_phrase in words_list:
+#         # Check if the word or phrase is in the normalized sentence
+#         if word_or_phrase.lower() in normalized_sentence:
+#             return True  # Return True immediately if any word or phrase is found
+
+#     return False  # Return False if none of the words or phrases are found
+
 def contains_words_or_phrases(words_list, sentence):
     """
     Check if any word or phrase from words_list is present in the sentence.
-
     :param words_list: List of words or phrases to check
     :param sentence: The input sentence where to look for words or phrases
-    :return: Entities if any word or phrase is found, otherwise None
+    :return: True if any word or phrase is found, otherwise False
     """
-    # Normalize the sentence to lower case to make the search case insensitive
-    normalized_sentence = sentence.lower()
+    # Process the sentence with spaCy to obtain the lemmatized form of each token
+    processed_sentence = nlp(sentence.lower())
+    lemmatized_sentence = " ".join(token.lemma_ for token in processed_sentence)
 
-    # Check each word or phrase in the list
+    # Process each word or phrase for lemmatization
     for word_or_phrase in words_list:
-        # Check if the word or phrase is in the normalized sentence
-        if word_or_phrase.lower() in normalized_sentence:
+        # Process and create a lemma string for the word or phrase
+        processed_word_or_phrase = nlp(word_or_phrase.lower())
+        lemmatized_word_or_phrase = " ".join(token.lemma_ for token in processed_word_or_phrase)
+
+        # Check if the lemmatized word or phrase is in the lemmatized sentence
+        if lemmatized_word_or_phrase in lemmatized_sentence:
             return True  # Return True immediately if any word or phrase is found
 
     return False  # Return False if none of the words or phrases are found