Create replace_explitives.py

replace_explitives.py

@@ -0,0 +1,33 @@
+import nltk
+from nltk.tokenize import word_tokenize, sent_tokenize
+import re
+
+
+nltk.download('punkt')  # For tokenization
+nltk.download('averaged_perceptron_tagger')  # For POS tagging (optional)
+
+
+def replace_explitives(textfile, selection):
+
+    replacetext = "person"
+
+    # text = word_tokenize(textfile)
+    # print(text)
+    # sentences = sent_tokenize(textfile)
+
+    if selection == "B":
+        target_word = r"\bbitch\b"
+    elif selection == "N":
+        target_word = r"\bnigg\b"
+    elif selection == "all":
+        target_word = r"\bshit\b"
+    else:
+        target_word = None
+        
+    print("selection:", selection, "target_word:", target_word)
+
+    if target_word:
+        print("target word was found, ", target_word)
+        print(text)
+        textfile = re.sub(target_word, replacetext, textfile, flags=re.IGNORECASE)
+    return textfile