Update app.py

app.py

@@ -18,7 +18,7 @@ class CRF_POS_Tagger:
         print("Loading Data...")
         self.corpus = nltk.corpus.brown.tagged_sents(tagset='universal')
         print("Data Loaded...")
-        self.corpus = [[(word.lower(), tag) for word, tag in sentence] for sentence in self.corpus]
+        self.corpus = [[(word, tag) for word, tag in sentence] for sentence in self.corpus]
         self.actual_tag = []
         self.predicted_tag = []
         self.prefixes = [
@@ -31,12 +31,6 @@ class CRF_POS_Tagger:
             "ic", "ing", "ion", "tion", "ity", "ty", "ive", "less", "ly", "ment",
             "ness", "ous", "ship", "y", "es", "s"
         ]
-        self.interjections = {
-            'ah', 'alas', 'aha', 'bravo', 'darn', 'drat', 'eh', 'eek', 'eww', 
-            'gosh', 'ha', 'hooray', 'hmm', 'huh', 'oops', 'ouch', 'phew', 
-            'pow', 'yay', 'whoa', 'wow', 'yikes', 'yippee', 'uh', 'um', 
-            'hey', 'hello'
-        }
 
         self.prefix_pattern = f"^({'|'.join(self.prefixes)})"
         self.suffix_pattern = f"({'|'.join(self.suffixes)})$"
@@ -96,34 +90,34 @@ class CRF_POS_Tagger:
             'suffix-2': word[-2:],
             'suffix-3': word[-3:],
 
-            # 'prefix-un': word[:2] == 'un',   #if word starts with un
-            # 'prefix-re': word[:2] == 're',   #if word starts with re
-            # 'prefix-over': word[:4] == 'over',  #if word starts with over
-            # 'prefix-dis': word[:4] == 'dis',   #if word starts with dis
-            # 'prefix-mis': word[:4] == 'mis',   #if word starts with mis
-            # 'prefix-pre': word[:4] == 'pre',   #if word starts with pre
-            # 'prefix-non': word[:4] == 'non',   #if word starts with non
-            # 'prefix-de': word[:3] == 'de',     #if word starts with de
-            # 'prefix-in': word[:3] == 'in',     #if word starts with in
-            # 'prefix-en': word[:3] == 'en',     #if word starts with en
-
-            # 'suffix-ed': word[-2:] == 'ed',   #if word ends with ed
-            # 'suffix-ing': word[-3:] == 'ing',  #if word ends with ing
-            # 'suffix-es': word[-2:] == 'es',    #if word ends with es
-            # 'suffix-ly': word[-2:] == 'ly',    #if word ends with ly
-            # 'suffix-ment': word[-4:] == 'ment',  #if word ends with ment
-            # 'suffix-er': word[-2:] == 'er',     #if word ends with er
-            # 'suffix-ive': word[-3:] == 'ive',
-            # 'suffix-ous': word[-3:] == 'ous',
-            # 'suffix-ness': word[-4:] == 'ness',
-            # 'ends_with_s': word[-1] == 's',
-            # 'ends_with_es': word[-2:] == 'es',
+            'prefix-un': word[:2] == 'un',   #if word starts with un
+            'prefix-re': word[:2] == 're',   #if word starts with re
+            'prefix-over': word[:4] == 'over',  #if word starts with over
+            'prefix-dis': word[:4] == 'dis',   #if word starts with dis
+            'prefix-mis': word[:4] == 'mis',   #if word starts with mis
+            'prefix-pre': word[:4] == 'pre',   #if word starts with pre
+            'prefix-non': word[:4] == 'non',   #if word starts with non
+            'prefix-de': word[:3] == 'de',     #if word starts with de
+            'prefix-in': word[:3] == 'in',     #if word starts with in
+            'prefix-en': word[:3] == 'en',     #if word starts with en
+
+            'suffix-ed': word[-2:] == 'ed',   #if word ends with ed
+            'suffix-ing': word[-3:] == 'ing',  #if word ends with ing
+            'suffix-es': word[-2:] == 'es',    #if word ends with es
+            'suffix-ly': word[-2:] == 'ly',    #if word ends with ly
+            'suffix-ment': word[-4:] == 'ment',  #if word ends with ment
+            'suffix-er': word[-2:] == 'er',     #if word ends with er
+            'suffix-ive': word[-3:] == 'ive',
+            'suffix-ous': word[-3:] == 'ous',
+            'suffix-ness': word[-4:] == 'ness',
+            'ends_with_s': word[-1] == 's',
+            'ends_with_es': word[-2:] == 'es',
 
             'has_hyphen': '-' in word,    #if word has hypen
             'is_numeric': word.isdigit(),  #if word is in numeric
             'capitals_inside': word[1:].lower() != word[1:],
             'is_title_case': word.istitle(),  #if first letter is in uppercase
-            'is_interjection': word.lower() in self.interjections,
+
         }
 
         if i > 0:
@@ -144,7 +138,7 @@ class CRF_POS_Tagger:
             })
 
         if i < len(sentence)-1:
-            next_word = sentence[i+1][0]
+            next_word = sentence[i-1][0]
             next_prefix, next_stem, next_suffix = self.word_splitter(next_word)
             features.update({
                 'next_word': next_word,
@@ -201,18 +195,18 @@ class CRF_POS_Tagger:
 
     def con_matrix(self):
         self.labels = np.unique(self.actual_tag)
-        # print(self.labels, self.actual_tag, self.predicted_tag)
+        print(self.labels, self.actual_tag, self.predicted_tag)
         conf_matrix = confusion_matrix(self.actual_tag, self.predicted_tag, labels=self.labels)
-
+        normalized_matrix = conf_matrix/np.sum(conf_matrix, axis=1, keepdims=True)
         plt.figure(figsize=(10, 7))
-        sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=self.labels, yticklabels=self.labels)
+        sns.heatmap(normalized_matrix, annot=True, fmt='.2f', cmap='Blues', xticklabels=self.labels, yticklabels=self.labels)
         plt.xlabel('Predicted Tags')
         plt.ylabel('Actual Tags')
         plt.title('Confusion Matrix Heatmap')
         plt.savefig("Confusion_matrix.png")
         plt.show()
 
-        return conf_matrix
+        return normalized_matrix
 
     def per_pos_accuracy(self, conf_matrix):
         print("Per Tag Precision, Recall, and F-Score:")
@@ -245,7 +239,7 @@ class CRF_POS_Tagger:
 
     def tagging(self, input):
         sentence = (re.sub(r'(\S)([.,;:!?])', r'\1 \2', input.strip())).split()
-        sentence_list = [[word.lower()] for word in sentence]
+        sentence_list = [[word] for word in sentence]
         features = [self.word_features(sentence_list, i) for i in range(len(sentence_list))]
 
         predicted_tags = self.crf_model.predict([features])
@@ -253,13 +247,13 @@ class CRF_POS_Tagger:
         return output
 
 
-# validate = CRF_POS_Tagger()
-# accuracies, avg_accuracy = validate.cross_validation()
-# print(f"Cross-Validation Accuracies: {accuracies}")
-# print(f"Average Accuracy: {avg_accuracy}")
+validate = CRF_POS_Tagger()
+accuracies, avg_accuracy = validate.cross_validation()
+print(f"Cross-Validation Accuracies: {accuracies}")
+print(f"Average Accuracy: {avg_accuracy}")
 
-# conf_matrix = validate.con_matrix()
-# print(validate.per_pos_accuracy(conf_matrix))
+conf_matrix = validate.con_matrix()
+print(validate.per_pos_accuracy(conf_matrix))
 
 tagger = CRF_POS_Tagger(True)
 interface = gr.Interface(fn = tagger.tagging,