Update TextAnalysisSpacy.py

TextAnalysisSpacy.py

@@ -17,6 +17,7 @@ import nltk
 from nltk.probability import FreqDist
 from nltk.text import Text
 from lexical_diversity import lex_div as ld
+from transformers import pipeline
 
 class TextAnalysisSpacy():
             
@@ -306,6 +307,39 @@ class TextAnalysisSpacy():
       self.showGraph(col_complexity,'heatmap')
       return self.df
 
+    def emotions(self):
+      classifier6 = pipeline("text-classification",model='model1_path', return_all_scores=True) 
+      classifier27 = pipeline("text-classification",model='model2_path', return_all_scores=True) 
+      
+      i=0
+      for text in tqdm(self.df['text']):
+        text = str(text[:512])
+        prediction = classifier6(text)
+        prediction2 = classifier27(text)
+        for pred in prediction[0]:
+          self.df.loc[i,'emo6_'+pred['label']] = pred['score']
+        for pred in prediction2[0]:
+          self.df.loc[i,'emo28_'+pred['label']] = pred['score']
+        i+=1
+
+      # Emotions for each category
+      i = 0
+      col_emotions = ['emo6_sadness','emo6_joy','emo6_love','emo6_anger','emo6_fear','emo6_surprise',
+            'emo28_admiration','emo28_amusement','emo28_anger','emo28_annoyance','emo28_approval',
+            'emo28_caring','emo28_confusion','emo28_curiosity','emo28_desire','emo28_disappointment',
+            'emo28_disapproval','emo28_disgust','emo28_embarrassment','emo28_excitement','emo28_fear',
+            'emo28_gratitude','emo28_grief','emo28_joy','emo28_love','emo28_nervousness',
+            'emo28_optimism','emo28_pride','emo28_realization','emo28_relief','emo28_remorse',
+            'emo28_sadness','emo28_surprise','emo28_neutral']
+      
+      print('Emotions for each text')
+      display(self.df.head())
+      print('Emotions for each category')
+      display(self.df.groupby('category').agg(['mean', 'median','std']))
+      self.showGraph(col_emotions,'strip')
+      self.showGraph(col_emotions,'box')
+      self.showGraph(col_emotions,'heatmap')
+
     def featureSelection(self):
       df = self.df.fillna(0)
       X = df.iloc[:,2:]
@@ -337,7 +371,6 @@ class TextAnalysisSpacy():
       df = self.df.fillna(0)
       X = df.iloc[:,2:]
       y = df.iloc[:,0]
-      
       # Univariate feature selection
       from sklearn.feature_selection import SelectKBest
       from sklearn.feature_selection import f_classif, mutual_info_classif