add global and word by word sentiment

Author: rfaria

__pycache__/menu.cpython-310.pyc

@@ -49,14 +49,26 @@ def main():
             print(f"The new text is: \"{new_text}\"\n\n")
 
         elif choice == "3":
-            print("Selected: 3 - Extract text sentiment")
+            print("Selected: 3 - Extract global text sentiment")
             print("Insert text: ")
             text = input()
-            test(text)
+            result = global_sentiment(text)
 
+            print(f"\nThe global text sentiment is: \"{result}\"\n\n")
 
+        elif choice == "4":
+            print("Selected: 4 - Extract sentiment of each word")
+            print("Insert text: ")
+            text = input()
+            result = sentiment_word_list(text)
+
+            neg = result["negative"]
+            neu = result["neutral"]
+            pos = result["positive"]
 
-            # print(f"The new text is: \"{new_text}\"\n\n")
+            print(f"\nThe negative words are: \"{neg}\"\n")
+            print(f"The neutral words are: \"{neu}\"\n")
+            print(f"The positive words are: \"{pos}\"\n")
 
         elif choice == "quit":
             break

__pycache__/sentiment.cpython-310.pyc

@@ -3,7 +3,8 @@ def choose_func():
     print("0 - Count appearances of a character in a manually inputed text")
     print("1 - Total number of characters in a manually inputed text")
     print("2 - Swap words in a text")
-    print("3 - Extract text sentiment")
+    print("3 - Extract global text sentiment")
+    print("4 - Extract sentiment of each word")
     print("quit - Finish the app")
 
     choice = input()

main.py

@@ -3,25 +3,37 @@
 nltk.download('punkt')
 nltk.download('vader_lexicon')
 
-def test(test_subset):
+def global_sentiment(sentence, optimism_rate=0.75):
 
-    tokens = nltk.word_tokenize(test_subset)
+    sid = SentimentIntensityAnalyzer()
+    polarity = sid.polarity_scores(sentence)             
+    
+    if polarity["compound"] >= (1-optimism_rate):
+        return "Positive"
+    elif polarity["compound"] <= -(1-optimism_rate):
+        return "Negative"
+    else:
+        return "Neutral"
+
+
+def sentiment_word_list(sentence, optimism_rate=0.75):
+    
+    tokens = nltk.word_tokenize(sentence)
 
     sid = SentimentIntensityAnalyzer()
+
     pos_word_list=[]
     neu_word_list=[]
     neg_word_list=[]
 
     for word in tokens:
-        if (sid.polarity_scores(word)['compound']) >= 0.25:
+        if (sid.polarity_scores(word)['compound']) >= (1-optimism_rate):
             pos_word_list.append(word)
-        elif (sid.polarity_scores(word)['compound']) <= -0.25:
+        elif (sid.polarity_scores(word)['compound']) <= -(1-optimism_rate):
             neg_word_list.append(word)
         else:
-            neu_word_list.append(word)                
+            neu_word_list.append(word)
 
-    print('Positive :',pos_word_list)        
-    print('Neutral :',neu_word_list)    
-    print('Negative :',neg_word_list)  
-    
-    print(sid.polarity_scores(test_subset))
+    result = {"negative": neg_word_list, "neutral": neu_word_list, "positive": pos_word_list}           
+
+    return result