hf4

app.py

@@ -131,8 +131,9 @@ elif len(uploaded_file)>0:
 
 
 
-            ############################ 2. Sentiment Analysis ############################
+            ############################ 2. Running models ############################
             text = text.replace("\n", " " )
+            text = text.replace("$", "dollar " )
             sentences = sent_tokenize(text)
             title = sentences[0]
             long_sentence=[]
@@ -159,7 +160,7 @@ elif len(uploaded_file)>0:
                 tokenizer = tokenizer_emotion
                 model = model_emotion
                 classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
-                output_emotion = classifier(useful_sentence)
+                temp_emotion = classifier(useful_sentence)
                 
 
                 df = pd.DataFrame.from_dict(output)
@@ -185,7 +186,7 @@ elif len(uploaded_file)>0:
             pos_df = pos_df.sort_values('score', ascending=False)
             pos_df_mean = pos_df.score.mean()
             pos_df['score'] = pos_df['score'].round(4)
-            pos_df.rename(columns = {'Sentence':'Positive Sentences'}, inplace = True)
+            pos_df.rename(columns = {'Sentence':'Positive Sentences'}, inplace = True)    
 
             neg_df = df[df['label']=='negative']
             neg_df = neg_df[['score', 'Sentence']]
@@ -207,6 +208,10 @@ elif len(uploaded_file)>0:
 
             ############################ 3.2. Emotion Analysis ############################
         
+            output_emotion = []
+            for temp in temp_emotion:
+                output_emotion.append(temp[0])
+
             df_emotion = pd.DataFrame.from_dict(output_emotion)
             df_emotion['Sentence']= pd.Series(useful_sentence)
 
@@ -216,6 +221,8 @@ elif len(uploaded_file)>0:
             df_joy['score'] = df_joy['score'].round(4)
             df_joy.rename(columns = {'Sentence':'Joy Sentences'}, inplace = True)
             num_of_joy_sentences = df_joy.shape[0]
+            if num_of_joy_sentences == 0:
+                df_joy.loc[0] = [0.0, '-------No joy sentences found in report-------']
 
             df_sadness = df_emotion[df_emotion['label']=='sadness']
             df_sadness = df_sadness[['score', 'Sentence']]
@@ -223,6 +230,8 @@ elif len(uploaded_file)>0:
             df_sadness['score'] = df_sadness['score'].round(4)
             df_sadness.rename(columns = {'Sentence':'Sad Sentences'}, inplace = True)
             num_of_sad_sentences = df_sadness.shape[0]
+            if num_of_sad_sentences == 0:
+                df_sadness.loc[0] = [0.0, '-------No sad sentences found in report-------']
 
             df_anger = df_emotion[df_emotion['label']=='anger']
             df_anger = df_anger[['score', 'Sentence']]
@@ -230,6 +239,8 @@ elif len(uploaded_file)>0:
             df_anger['score'] = df_anger['score'].round(4)
             df_anger.rename(columns = {'Sentence':'Angry Sentences'}, inplace = True)
             num_of_anger_sentences = df_anger.shape[0]
+            if num_of_anger_sentences == 0:
+                df_anger.loc[0] = [0.0, '-------No angry sentences found in report-------']
 
             df_surprise = df_emotion[df_emotion['label']=='surprise']
             df_surprise = df_surprise[['score', 'Sentence']]
@@ -237,14 +248,16 @@ elif len(uploaded_file)>0:
             df_surprise['score'] = df_surprise['score'].round(4)
             df_surprise.rename(columns = {'Sentence':'Surprised Sentences'}, inplace = True)
             num_of_surprise_sentences = df_surprise.shape[0]
+            if num_of_surprise_sentences == 0:
+                df_surprise.loc[0] = [0.0, '-------No surprised sentences found in report-------']
             
             ############################ 4. Plotting ############################
 
             fig = make_subplots(
-                rows=30, cols=6,
+                rows=41, cols=6,
                 specs=[ [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
-                        [None, None, None, None, None, None],
+                        [None, None, {"type": "indicator", "rowspan": 3, "colspan": 2}, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [{"type": "pie", "rowspan": 6, "colspan": 2}, None, {"type": "indicator", "rowspan": 6, "colspan": 2}, None, {"type": "indicator", "rowspan": 6, "colspan": 2}, None],
@@ -253,22 +266,33 @@ elif len(uploaded_file)>0:
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
-                        [{"type": "image", "rowspan": 15, "colspan": 3}, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None],
+                        [None, None, None, None, None, None],
+                        [{"type": "image", "rowspan": 5, "colspan": 3}, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None],
+                        [None, None, None, None, None, None],
+                        [None, None, None, None, None, None],
+                        [None, None, None, None, None, None],
+                        [None, None, None, None, None, None],
+                        [{"type": "table", "rowspan": 5, "colspan": 3}, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None],
+                        [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
-                        [None, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None],
+                        [None, None, {"type": "indicator", "rowspan": 3, "colspan": 2}, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
+                        [{"type": "bar", "rowspan": 6, "colspan": 6}, None, None, None, None, None],
                         [None, None, None, None, None, None],
-                        [None, None, None, {"type": "table", "rowspan": 5, "colspan": 3}, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
+                        [{"type": "table", "rowspan": 2, "colspan": 3}, None, None, {"type": "table", "rowspan": 2, "colspan": 3}, None, None],
+                        [None, None, None, None, None, None],
+                        [None, None, None, None, None, None],
+                        [{"type": "table", "rowspan": 2, "colspan": 3}, None, None, {"type": "table", "rowspan": 2, "colspan": 3}, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
                         [None, None, None, None, None, None],
@@ -276,6 +300,11 @@ elif len(uploaded_file)>0:
             )
 
             ############################ 4.1. Sentiment Analysis ############################
+            fig.add_trace(go.Indicator(
+                mode = "number",
+                value = None,
+                title = {"text": "Sentiment Analysis"}), row=3, col=3)
+
             colors = px.colors.diverging.Portland#RdBu
             fig.add_trace(go.Pie(labels=labels, values=values, hole = 0.5,
                         title = 'Count by label', 
@@ -283,10 +312,12 @@ elif len(uploaded_file)>0:
                         line=dict(width=2, color='white'))),
                         row=6, col=1)
 
+
             fig.add_trace(go.Indicator(
                 mode = "number",
                 value = len(df.label.values.tolist()),
                 title = {"text": "Count of Sentence"}), row=6, col=3)
+            #fig.update_traces(title_text="Sentiment Analysis", selector=dict(type='indicator'), row=6, col=3)
 
             fig.add_trace(go.Indicator(
                 mode = "gauge+number",
@@ -316,36 +347,93 @@ elif len(uploaded_file)>0:
             else:
                 fig.update_traces(title_text="Cummulative Sentiment Positive", selector=dict(type='indicator'), row=6, col=5)
 
-            fig.add_trace(go.Image(z=image), row=12, col=1)
-            fig.update_xaxes(visible=False, row=12, col=1)
-            fig.update_yaxes(visible=False, row=12, col=1)
+            fig.add_trace(go.Image(z=image), row=13, col=1)
+            fig.update_xaxes(visible=False, row=13, col=1)
+            fig.update_yaxes(visible=False, row=13, col=1)
 
             table_trace1 = go.Table(
                 header=dict(values=list(pos_df.columns), fill_color='lightgray', align='left'),
                 cells=dict(values=[pos_df[name] for name in pos_df.columns], fill_color='white', align='left'),
                 columnwidth=[1, 4]
             )
-            fig.add_trace(table_trace1, row=12, col=4)
+            fig.add_trace(table_trace1, row=13, col=4)
 
             table_trace2 = go.Table(
                 header=dict(values=list(neg_df.columns), fill_color='lightgray', align='left'),
                 cells=dict(values=[neg_df[name] for name in neg_df.columns], fill_color='white', align='left'),
                 columnwidth=[1, 4]
             )
-            fig.add_trace(table_trace2, row=17, col=4)
+            fig.add_trace(table_trace2, row=18, col=4)
 
             table_trace2 = go.Table(
                 header=dict(values=list(neu_df.columns), fill_color='lightgray', align='left'),
                 cells=dict(values=[neu_df[name] for name in neu_df.columns], fill_color='white', align='left'),
                 columnwidth=[1, 4]
             )
-            fig.add_trace(table_trace2, row=22, col=4)
+            fig.add_trace(table_trace2, row=18, col=1)
 
+            fig.add_trace(go.Indicator(
+                mode = "number",
+                value = None,
+                title = {"text": "Emotion Analysis"}), row=24, col=3)
 
             ############## Under Construction ##############
 
             ############################ 4.2. Emotion Analysis ############################
-            go.Bar(x=['Joy', 'Sadness', 'Anger', 'Surprise'], y=[3, 4, 1])
+            #go.Bar(x=['Joy', 'Sadness', 'Anger', 'Surprise'], y=[3, 4, 1])
+
+            # Add bar chart
+            colors_emotions = ['#174ecf', '#cfc517', '#940625', '#17cfcb']
+            emotion_bar_xlabels = ['Joy', 'Sadness', 'Anger', 'Surprise']
+            emotion_bar_ylabels = [num_of_joy_sentences, 
+                                num_of_sad_sentences,
+                                num_of_anger_sentences,
+                                num_of_surprise_sentences]
+            #annotations = [dict(x=x, y=y, text='😀', showarrow=False) for x, y in zip(emotion_bar_xlabels, emotion_bar_ylabels)]
+            annotations = ['😀', '😞', '😡', '😯']
+            fig.add_trace(
+                go.Bar(x=emotion_bar_xlabels, y= emotion_bar_ylabels, 
+                    showlegend=True,
+                    marker_color=colors_emotions,
+                    text=annotations,
+                    textfont=dict(size=40)),
+                        row=28, col=1)
+            fig.update_xaxes(title_text='Emotions', title_font=dict(size=16), row=28, col=1)
+            fig.update_yaxes(title_text='Number of sentences', title_font=dict(size=16), row=28, col=1)
+
+            # df_anger.loc[0] = [0.0, 'None']
+            # df_anger
+            ################## happiness table
+            table_trace2 = go.Table(
+                header=dict(values=list(df_joy.columns), fill_color='lightgray', align='left'),
+                cells=dict(values=[df_joy[name] for name in df_joy.columns], fill_color='white', align='left'),
+                columnwidth=[1, 4]
+            )
+            fig.add_trace(table_trace2, row=35, col=1)
+
+            ################## sadness table
+            table_trace2 = go.Table(
+                header=dict(values=list(df_sadness.columns), fill_color='lightgray', align='left'),
+                cells=dict(values=[df_sadness[name] for name in df_sadness.columns], fill_color='white', align='left'),
+                columnwidth=[1, 4]
+            )
+            fig.add_trace(table_trace2, row=35, col=4)
+
+            ################## surprise table
+            table_trace2 = go.Table(
+                header=dict(values=list(df_surprise.columns), fill_color='lightgray', align='left'),
+                cells=dict(values=[df_surprise[name] for name in df_surprise.columns], fill_color='white', align='left'),
+                columnwidth=[1, 4]
+            )
+            fig.add_trace(table_trace2, row=38, col=1)
+
+            ################## anger table
+            table_trace2 = go.Table(
+                header=dict(values=list(df_anger.columns), fill_color='lightgray', align='left'),
+                cells=dict(values=[df_anger[name] for name in df_anger.columns], fill_color='white', align='left'),
+                columnwidth=[1, 4]
+            )
+            fig.add_trace(table_trace2, row=38, col=4)
 
             import textwrap
             wrapped_title = "\n".join(textwrap.wrap(title, width=50))
@@ -353,7 +441,7 @@ elif len(uploaded_file)>0:
             # Add HTML tags to force line breaks in the title text
             wrapped_title = "<br>".join(wrapped_title.split("\n"))
 
-            fig.update_layout(height=1500, showlegend=False, title={'text': f"<b>{wrapped_title} - Sentiment Analysis Report</b>", 'x': 0.5, 'xanchor': 'center','font': {'size': 32}})
+            fig.update_layout(height=3000, showlegend=False, title={'text': f"<b>{wrapped_title} - Text Analysis Report</b>", 'x': 0.5, 'xanchor': 'center','font': {'size': 32}})
 
             #pyo.plot(fig, filename='report.html')