adds all emotions

src/probability_emote.py

@@ -7,7 +7,7 @@ from .lib import set_input
 def get_w(f, ec=0.86, rv=0.50):
     result = (rv + f-1)/(ec + f-1)
     result = np.clip(result, 0, 1)
-    print(f'w = {result}')
+    # print(f'w = {result}')
     return result
 
 
@@ -15,7 +15,7 @@ def get_w(f, ec=0.86, rv=0.50):
 def get_f(w, ec=0.86, rv=0.50):
     result = 1+(ec*w-rv)/(1-w)
     result = np.clip(result, 0, 1)
-    print(f'f = {result}')
+    # print(f'f = {result}')
     return result
 
 
@@ -23,7 +23,7 @@ def get_f(w, ec=0.86, rv=0.50):
 def get_pe(w, ec=0.86, f=0.50):
     result = ec*w+(1-w)*(1-f)
     result = np.clip(result, 0, 1)
-    print(f'f = {result}')
+    # print(f'f = {result}')
     return result
 
 

src/read_logs.py

@@ -44,10 +44,10 @@ class LogAnalyser:
         # self.container_param.markdown(
         #     f'st.session_state.button1_counter: {st.session_state.button1_counter}')
 
-        if exists(self.df_path):
-            self.df = pd.read_csv(self.df_path)
-        else:
+        if not exists(self.df_path) or self.container_button.button('Detect Emotion'):
             self.df = self.get_log()
+        # else:
+        self.df = pd.read_csv(self.df_path)
 
         # if 'path' not in st.session_state:
         #     st.session_state.path=self.path
@@ -80,6 +80,7 @@ class LogAnalyser:
                                      step=.01,)
         table_mode = self.container_param.radio(
             "Table Style:", ["Dataframe", "Table"])
+        self.emotion_type = self.container_param.select_slider('Emotion', ['Max-only', '2', '3', '4', '5', '6', 'All 7'])
         self.show_pe_data = self.container_param.checkbox(
             'Show Probability Emote', value=True, key='show_pe_data_log')
         self.score_threshold = set_input(self.container_param,
@@ -145,16 +146,18 @@ class LogAnalyser:
                 dfs.drop(c, axis=1, inplace=True)
 
             st.markdown(f'#### Story {story_id}')
-            dfs = dfs.style
-            dfs = dfs.hide_index()
-            if self.show_pe_data:
-                dfs = dfs.apply(self.dfstyle_color_text_col, axis=1)
-            # dfs = dfs.applymap(self.dfstyle_color_text)
-            dfs = dfs.apply(self.rower, axis=None)
-            dfs = dfs.set_table_styles([{
-                'selector': 'tr:hover',
-                'props': 'color: #000000'  # background-color: #eeee66;font-size: 1.01em;
-            }])   # .hide_index()
+            
+            
+            # dfs = dfs.style
+            # dfs = dfs.hide_index()
+            # if self.show_pe_data:
+            #     dfs = dfs.apply(self.dfstyle_color_text_col, axis=1)
+            # # dfs = dfs.applymap(self.dfstyle_color_text)
+            # dfs = dfs.apply(self.rower, axis=None)
+            # dfs = dfs.set_table_styles([{
+            #     'selector': 'tr:hover',
+            #     'props': 'color: #000000'  # background-color: #eeee66;font-size: 1.01em;
+            # }])   # .hide_index()
 
             if table_mode == 'Dataframe':
                 st.dataframe(dfs)
@@ -177,14 +180,14 @@ class LogAnalyser:
                 ['color: #333333']+['color: #fcfcfc']*3
         if s.Score < self.score_threshold and s.Turn == 'user':
             result[3:-1] = ['color: #992222'] + ['color: #fcfcfc']*3
-            printj.red(result)
+            # printj.red(result)
         if s.reaction_show == 1:
             result[-1] = 'color: #222222'
         elif s.reaction_show == 0:
             result[-1] = 'color: #222222'
         else:
-            print(s.reaction_show)
-            print(type(s.reaction_show))
+            # print(s.reaction_show)
+            # print(type(s.reaction_show))
             result[4:] = ['color: #fcfcfc']*4
         # if s.probability_emote!=s.probability_emote:
         #     result[5] = 'color: #eeeeee'
@@ -230,9 +233,21 @@ class LogAnalyser:
                 continue
             log_dict['Sentence'] = line[3:]
             log_dict['Story'] = story_num
-            emotion = self.gen.get_emotion(log_dict['Sentence'])
-            log_dict['Emotion'] = emotion['label']
-            log_dict['Score'] = emotion['score']
+            emotion_type = 'sorted'  # 'max'
+            if self.emotion_type == 'max':
+                emotion_type = 'max'
+            else:
+                emotion_type = 'sorted'  # 
+            emotion = self.gen.get_emotion(log_dict['Sentence'], filter_by=emotion_type)
+            if emotion_type =='max':
+                log_dict['Emotion'] = emotion['label']
+                log_dict['Score'] = emotion['score']
+            elif emotion_type =='sorted':
+                log_dict['Emotion'] = emotion[0]['label']
+                log_dict['Score'] = emotion[0]['score']
+                for sorted_i in range(1, len(emotion)):
+                    log_dict[f'Emotion_{sorted_i+1}'] = emotion[sorted_i]['label']
+                    log_dict[f'Score_{sorted_i+1}'] = emotion[sorted_i]['score']
             df = pd.concat(
                 [df, pd.DataFrame(log_dict, index=[f'idx_{i}'])])
             df = df.reset_index(drop=True)
@@ -255,4 +270,4 @@ if __name__ == '__main__':
 
     # Create DataFrame
     df = pd.DataFrame(data)
-    print(df, type(df))
+    # print(df, type(df))

src/story_gen.py

@@ -52,11 +52,15 @@ class StoryGenerator:
     def clear_stats(self):
         self.stats_df = pd.DataFrame(data=[], columns=[])
 
-    def get_emotion(self, text):
+    def get_emotion(self, text, filter_by='max'):
         emotions = self.classifier(text)
-        emotion = max(emotions[0], key=lambda x: x['score'])
-        return emotion
+        if filter_by=='max':
+            emotion = max(emotions[0], key=lambda x: x['score'])
+            return emotion
+        elif filter_by=='sorted':
+            return sorted(emotions[0], key=lambda x: x['score'], reverse=True)
 
+             
     @staticmethod
     def get_num_token(text):
         # return len(nltk.word_tokenize(text))
@@ -117,14 +121,14 @@ class StoryGenerator:
             # Text generation for User
             last_length = len(story_till_now)
             printj.cyan(story_till_now)
-            printj.red.bold_on_white(
-                f'loop: {i}; generate user text; length: {last_length}')
+            # printj.red.bold_on_white(
+            #     f'loop: {i}; generate user text; length: {last_length}')
             genreate_user_sentence = self.generator(story_till_now, max_length=self.get_num_token(
                 story_till_now)+length, num_return_sequences=1)
             story_till_now = genreate_user_sentence[0]['generated_text']
             new_sentence_user = story_till_now[last_length:]
 
-            printj.red.bold_on_white(f'loop: {i}; check emotion')
+            # printj.red.bold_on_white(f'loop: {i}; check emotion')
             # Emotion self.classifier for User
             emotion_user = self.get_emotion(new_sentence_user)
             if emotion_user['label'] == 'neutral':
@@ -156,8 +160,8 @@ class StoryGenerator:
             # Text generation for Robot
             last_length = len(story_till_now)
             printj.cyan(story_till_now)
-            printj.red.bold_on_white(
-                f'loop: {i}; generate robot text; length: {last_length}')
+            # printj.red.bold_on_white(
+            #     f'loop: {i}; generate robot text; length: {last_length}')
             genreate_robot_sentence = self.generator(story_till_now, max_length=self.get_num_token(
                 story_till_now)+length, num_return_sequences=1)
             story_till_now = genreate_robot_sentence[0]['generated_text']
@@ -211,7 +215,7 @@ class StoryGenerator:
             self.stories.append(_story_till_now)
             self.data.append(story_data)
         self.stats_df = self.stats_df.reset_index(drop=True)
-        print(self.stats_df)
+        # print(self.stats_df)
 
     def save_stats(self, path='pandas_simple.xlsx'):
         writer = pd.ExcelWriter(path, engine='xlsxwriter')

src/test.py

@@ -49,3 +49,14 @@ iplot([{'x': x, 'y': 1-np.exp(-x)}])
 
 # df.style.apply(highlight_greaterthan_1, axis=1)
 # %%
+from transformers import pipeline
+classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
+emotion = classifier("the sentence")
+# %%
+emotion[0]
+# %%
+emotion[0][0]
+# %%
+sorted(emotion[0], key=lambda x: x['score'], reverse=True)
+
+# %%