Update app.py

app.py

@@ -5,13 +5,15 @@ import easyocr
 import streamlit as st
 from annotated_text import annotated_text
 from streamlit_option_menu import option_menu
-from sentiment_analysis import SentimentAnalysis
+from sentiment_analysis_v2 import SentimentAnalysis
 from keyword_extraction import KeywordExtractor
 from part_of_speech_tagging import POSTagging
 from emotion_detection import EmotionDetection
 from named_entity_recognition import NamedEntityRecognition
 from Object_Detector import ObjectDetector
 from OCR_Detector import OCRDetector
+from detect_language import LanguageDetector
+
 import PIL
 from PIL import Image
 from PIL import ImageColor
@@ -35,286 +37,301 @@ import torch
 import librosa
 from models import infere_speech_emotion, infere_text_emotion, infere_voice2text
 
-st.set_page_config(layout="wide")
-
-hide_streamlit_style = """
-            <style>
-            #MainMenu {visibility: hidden;}
-            footer {visibility: hidden;}
-            </style>
+from transformers import pipeline
+
+def main():
+
+    st.set_page_config(layout="wide")
+
+    hide_streamlit_style = """
+                <style>
+                #MainMenu {visibility: hidden;}
+                footer {visibility: hidden;}
+                </style>
+                """
+    st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
+    @st.cache_resource
+    def load_sentiment_model():
+        return SentimentAnalysis()
+
+    @st.cache_resource
+    def load_keyword_model():
+        return KeywordExtractor()
+
+    @st.cache_resource
+    def load_pos_model():
+        return POSTagging()
+
+    @st.cache_resource
+    def load_emotion_model():
+        return EmotionDetection()
+
+    @st.cache_resource
+    def load_ner_model():
+        return NamedEntityRecognition()
+
+    @st.cache_resource
+    def load_objectdetector_model():
+        return ObjectDetector()
+
+    @st.cache_resource
+    def load_ocrdetector_model():
+        return OCRDetector()
+
+    @st.cache_resource
+    def load_langdetector_model():
+        return LanguageDetector()
+
+    sentiment_analyzer = load_sentiment_model()
+    keyword_extractor = load_keyword_model()
+    pos_tagger = load_pos_model()
+    emotion_detector = load_emotion_model()
+    ner = load_ner_model()
+    objectdetector1 = load_objectdetector_model()
+    ocrdetector1 = load_ocrdetector_model()
+    langdetector1 = load_langdetector_model()
+
+    def rectangle(image, result):
+        draw = ImageDraw.Draw(image)
+        for res in result:
+            top_left = tuple(res[0][0]) # top left coordinates as tuple
+            bottom_right = tuple(res[0][2]) # bottom right coordinates as tuple
+            draw.rectangle((top_left, bottom_right), outline="blue", width=2)
+        st.image(image)
+
+    example_text = "My name is Daniel: The attention to detail, swift resolution, and accuracy demonstrated by ITACA Insurance Company in Spain  in handling my claim were truly impressive. This undoubtedly reflects their commitment to being a customer-centric insurance provider."
+
+    with st.sidebar:
+        image = Image.open('./itaca_logo.png')
+        st.image(image,width=150) #use_column_width=True)
+        page = option_menu(menu_title='Menu',
+                        menu_icon="robot",
+                        options=["Sentiment Analysis",
+                                    "Keyword Extraction",
+                                    "Part of Speech Tagging",
+                                    "Emotion Detection",
+                                    "Named Entity Recognition",
+                                    "Speech & Text Emotion",
+                                    "Object Detector",
+                                    "OCR Detector"],
+                        icons=["chat-dots",
+                                "key",
+                                "tag",
+                                "emoji-heart-eyes",
+                                "building",
+                                "book",
+                                "camera",
+                                "list-task"],
+                        default_index=0
+                        )
+
+    st.title('ITACA Insurance Core AI Module')
+
+    # Replace '20px' with your desired font size
+    font_size = '20px'
+
+    if page == "Sentiment Analysis":
+        st.header('Sentiment Analysis')
+        # st.markdown("![Alt Text](https://media.giphy.com/media/XIqCQx02E1U9W/giphy.gif)")
+        st.write(
             """
-st.markdown(hide_streamlit_style, unsafe_allow_html=True)
-
-@st.cache_resource
-def load_sentiment_model():
-    return SentimentAnalysis()
-
-@st.cache_resource
-def load_keyword_model():
-    return KeywordExtractor()
-
-@st.cache_resource
-def load_pos_model():
-    return POSTagging()
-
-@st.cache_resource
-def load_emotion_model():
-    return EmotionDetection()
-
-@st.cache_resource
-def load_ner_model():
-    return NamedEntityRecognition()
-
-@st.cache_resource
-def load_objectdetector_model():
-    return ObjectDetector()
-
-@st.cache_resource
-def load_ocrdetector_model():
-    return OCRDetector()
-
-sentiment_analyzer = load_sentiment_model()
-keyword_extractor = load_keyword_model()
-pos_tagger = load_pos_model()
-emotion_detector = load_emotion_model()
-ner = load_ner_model()
-objectdetector1 = load_objectdetector_model()
-ocrdetector1 = load_ocrdetector_model()
-
-def rectangle(image, result):
-    draw = ImageDraw.Draw(image)
-    for res in result:
-        top_left = tuple(res[0][0]) # top left coordinates as tuple
-        bottom_right = tuple(res[0][2]) # bottom right coordinates as tuple
-        draw.rectangle((top_left, bottom_right), outline="blue", width=2)
-    st.image(image)
-
-example_text = "My name is Daniel: The attention to detail, swift resolution, and accuracy demonstrated by ITACA Insurance Company in Spain  in handling my claim were truly impressive. This undoubtedly reflects their commitment to being a customer-centric insurance provider."
-
-with st.sidebar:
-    image = Image.open('./itaca_logo.png')
-    st.image(image,width=150) #use_column_width=True)
-    page = option_menu(menu_title='Menu',
-                       menu_icon="robot",
-                       options=["Sentiment Analysis",
-                                "Keyword Extraction",
-                                "Part of Speech Tagging",
-                                "Emotion Detection",
-                                "Named Entity Recognition",
-                                "Speech & Text Emotion",
-                                "Object Detector",
-                                "OCR Detector"],
-                       icons=["chat-dots",
-                              "key",
-                              "tag",
-                              "emoji-heart-eyes",
-                              "building",
-                              "book",
-                              "camera",
-                              "list-task"],
-                       default_index=0
-                       )
-
-st.title('ITACA Insurance Core AI Module')
-
-# Replace '20px' with your desired font size
-font_size = '20px'
-
-if page == "Sentiment Analysis":
-    st.header('Sentiment Analysis')
-    # st.markdown("![Alt Text](https://media.giphy.com/media/XIqCQx02E1U9W/giphy.gif)")
-    st.write(
-        """
-        """
-    )
+            """
+        )
+
+        text = st.text_area("Paste text here", value=example_text)
+
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                o_lang = langdetector1.predict_language(text)
+
+                preds, html = sentiment_analyzer.run(text, o_lang)
+                st.success('All done!')
+                st.write("")
+                st.subheader("Sentiment Predictions")
+                st.bar_chart(data=preds, width=0, height=0, use_container_width=True)
+                st.write("")
+                st.subheader("Sentiment Justification")
+                raw_html = html._repr_html_()
+                st.components.v1.html(raw_html, height=500)
+
+    elif page == "Keyword Extraction":
+        st.header('Keyword Extraction')
+        # st.markdown("![Alt Text](https://media.giphy.com/media/xT9C25UNTwfZuk85WP/giphy-downsized-large.gif)")
+        st.write(
+            """
+            """
+        )
 
-    text = st.text_area("Paste text here", value=example_text)
+        text = st.text_area("Paste text here", value=example_text)
 
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            preds, html = sentiment_analyzer.run(text)
-            st.success('All done!')
-            st.write("")
-            st.subheader("Sentiment Predictions")
-            st.bar_chart(data=preds, width=0, height=0, use_container_width=True)
-            st.write("")
-            st.subheader("Sentiment Justification")
-            raw_html = html._repr_html_()
-            st.components.v1.html(raw_html, height=500)
-
-elif page == "Keyword Extraction":
-    st.header('Keyword Extraction')
-    # st.markdown("![Alt Text](https://media.giphy.com/media/xT9C25UNTwfZuk85WP/giphy-downsized-large.gif)")
-    st.write(
-        """
-        """
-    )
+        max_keywords = st.slider('# of Keywords Max Limit', min_value=1, max_value=10, value=5, step=1)
 
-    text = st.text_area("Paste text here", value=example_text)
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                annotation, keywords = keyword_extractor.generate(text, max_keywords)
+                st.success('All done!')
 
-    max_keywords = st.slider('# of Keywords Max Limit', min_value=1, max_value=10, value=5, step=1)
+            if annotation:
+                st.subheader("Keyword Annotation")
+                st.write("")
+                annotated_text(*annotation)
+                st.text("")
 
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            annotation, keywords = keyword_extractor.generate(text, max_keywords)
-            st.success('All done!')
-
-        if annotation:
-            st.subheader("Keyword Annotation")
+            st.subheader("Extracted Keywords")
             st.write("")
-            annotated_text(*annotation)
-            st.text("")
-
-        st.subheader("Extracted Keywords")
-        st.write("")
-        df = pd.DataFrame(keywords, columns=['Extracted Keywords'])
-        csv = df.to_csv(index=False).encode('utf-8')
-        st.download_button('Download Keywords to CSV', csv, file_name='news_intelligence_keywords.csv')
+            df = pd.DataFrame(keywords, columns=['Extracted Keywords'])
+            csv = df.to_csv(index=False).encode('utf-8')
+            st.download_button('Download Keywords to CSV', csv, file_name='news_intelligence_keywords.csv')
 
-        data_table = st.table(df)
+            data_table = st.table(df)
 
-elif page == "Part of Speech Tagging":
-    st.header('Part of Speech Tagging')
-    # st.markdown("![Alt Text](https://media.giphy.com/media/WoWm8YzFQJg5i/giphy.gif)")
-    st.write(
+    elif page == "Part of Speech Tagging":
+        st.header('Part of Speech Tagging')
+        # st.markdown("![Alt Text](https://media.giphy.com/media/WoWm8YzFQJg5i/giphy.gif)")
+        st.write(
+            """
+            """
+        )
+
+        text = st.text_area("Paste text here", value=example_text)
+
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                preds = pos_tagger.classify(text)
+                st.success('All done!')
+                st.write("")
+                st.subheader("Part of Speech tags")
+                annotated_text(*preds)
+                st.write("")
+                st.components.v1.iframe('https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html', height=1000)
+
+    elif page == "Emotion Detection":
+        st.header('Emotion Detection')
+        # st.markdown("![Alt Text](https://media.giphy.com/media/fU8X6ozSszyEw/giphy.gif)")
+        st.write(
+            """
+            """
+        )
+
+        text = st.text_area("Paste text here", value=example_text)
+
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                preds, html = emotion_detector.run(text)
+                st.success('All done!')
+                st.write("")
+                st.subheader("Emotion Predictions")
+                st.bar_chart(data=preds, width=0, height=0, use_container_width=True)
+                raw_html = html._repr_html_()
+                st.write("")
+                st.subheader("Emotion Justification")
+                st.components.v1.html(raw_html, height=500)
+
+    elif page == "Named Entity Recognition":
+        st.header('Named Entity Recognition')
+        # st.markdown("![Alt Text](https://media.giphy.com/media/lxO8wdWdu4tig/giphy.gif)")
+        st.write(
+            """
+            """
+        )
+
+        text = st.text_area("Paste text here", value=example_text)
+
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                preds, ner_annotation = ner.classify(text)
+                st.success('All done!')
+                st.write("")
+                st.subheader("NER Predictions")
+                annotated_text(*ner_annotation)
+                st.write("")
+                st.subheader("NER Prediction Metadata")
+                st.write(preds)
+
+    elif page == "Object Detector":
+        st.header('Object Detector')
+        st.write(
         """
         """
-    )
+        )
 
-    text = st.text_area("Paste text here", value=example_text)
+        img_file_buffer = st.file_uploader("Load an image", type=["png", "jpg", "jpeg"])
+        if img_file_buffer is not None:
+            image = np.array(Image.open(img_file_buffer))    
 
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            preds = pos_tagger.classify(text)
-            st.success('All done!')
-            st.write("")
-            st.subheader("Part of Speech tags")
-            annotated_text(*preds)
-            st.write("")
-            st.components.v1.iframe('https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html', height=1000)
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                img, primero = objectdetector1.run_detector(image)
+                st.success('The first image detected is: ' + primero)
+                st.image(img, caption="Imagen", use_column_width=True)
 
-elif page == "Emotion Detection":
-    st.header('Emotion Detection')
-    # st.markdown("![Alt Text](https://media.giphy.com/media/fU8X6ozSszyEw/giphy.gif)")
-    st.write(
+    elif page == "OCR Detector":
+        st.header('OCR Detector')
+        st.write(
         """
         """
-    )
-
-    text = st.text_area("Paste text here", value=example_text)
-
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            preds, html = emotion_detector.run(text)
-            st.success('All done!')
-            st.write("")
-            st.subheader("Emotion Predictions")
-            st.bar_chart(data=preds, width=0, height=0, use_container_width=True)
-            raw_html = html._repr_html_()
-            st.write("")
-            st.subheader("Emotion Justification")
-            st.components.v1.html(raw_html, height=500)
-
-elif page == "Named Entity Recognition":
-    st.header('Named Entity Recognition')
-    # st.markdown("![Alt Text](https://media.giphy.com/media/lxO8wdWdu4tig/giphy.gif)")
-    st.write(
+        )
+
+        file = st.file_uploader("Load an image", type=["png", "jpg", "jpeg"])
+
+        #read the csv file and display the dataframe
+        if file is not None:
+            image = Image.open(file) # read image with PIL library
+
+        if st.button('🔥 Run!'):
+            with st.spinner("Loading..."):
+                result = ocrdetector1.reader.readtext(np.array(image))  # turn image to numpy array
+            
+                # collect the results in dictionary:
+                textdic_easyocr = {}
+                for idx in range(len(result)):
+                    pred_coor = result[idx][0]
+                    pred_text = result[idx][1]
+                    pred_confidence = result[idx][2]
+                    textdic_easyocr[pred_text] = {}
+                    textdic_easyocr[pred_text]['pred_confidence'] = pred_confidence
+        
+                # get boxes on the image 
+                rectangle(image, result)
+                    
+                # create a dataframe which shows the predicted text and prediction confidence
+                df = pd.DataFrame.from_dict(textdic_easyocr).T
+                st.table(df)
+    elif page == "Speech & Text Emotion":
+        st.header('Speech & Text Emotion')
+        st.write(
         """
         """
-    )
-
-    text = st.text_area("Paste text here", value=example_text)
-
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            preds, ner_annotation = ner.classify(text)
-            st.success('All done!')
-            st.write("")
-            st.subheader("NER Predictions")
-            annotated_text(*ner_annotation)
-            st.write("")
-            st.subheader("NER Prediction Metadata")
-            st.write(preds)
-
-elif page == "Object Detector":
-    st.header('Object Detector')
-    st.write(
-    """
-    """
-    )
-
-    img_file_buffer = st.file_uploader("Load an image", type=["png", "jpg", "jpeg"])
-    if img_file_buffer is not None:
-        image = np.array(Image.open(img_file_buffer))    
-
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            img, primero = objectdetector1.run_detector(image)
-            st.success('The first image detected is: ' + primero)
-            st.image(img, caption="Imagen", use_column_width=True)
-
-elif page == "OCR Detector":
-    st.header('OCR Detector')
-    st.write(
-    """
-    """
-    )
-
-    file = st.file_uploader("Load an image", type=["png", "jpg", "jpeg"])
-
-    #read the csv file and display the dataframe
-    if file is not None:
-        image = Image.open(file) # read image with PIL library
-
-    if st.button('🔥 Run!'):
-        with st.spinner("Loading..."):
-            result = ocrdetector1.reader.readtext(np.array(image))  # turn image to numpy array
+        )
+        uploaded_file = st.file_uploader("Choose an audio file", type=["mp3", "wav", "ogg"])
+
+        if uploaded_file is not None:
+            st.audio(uploaded_file, format='audio/' + uploaded_file.type.split('/')[1])
+            st.write("Audio file uploaded and playing.")
+                        
+        else:
+            st.write("Please upload an audio file.")
+
+        if st.button("Analysis"):
+            with st.spinner("Loading..."):
+                st.header('Results of the Audio & Text analysis:')
+                samples, sample_rate = librosa.load(uploaded_file, sr=16000)
+                p_voice2text = infere_voice2text (samples)
+                p_speechemotion = infere_speech_emotion(samples)
+                p_textemotion = infere_text_emotion(p_voice2text)
+                st.subheader("Text from the Audio:")
+                st.write(p_voice2text)
+                st.write("---")
+                st.subheader("Speech emotion:")
+                st.write(p_speechemotion)
+                st.write("---")
+                st.subheader("Text emotion:")
+                st.write(p_textemotion)
+                st.write("---")
         
-            # collect the results in dictionary:
-            textdic_easyocr = {}
-            for idx in range(len(result)):
-                pred_coor = result[idx][0]
-                pred_text = result[idx][1]
-                pred_confidence = result[idx][2]
-                textdic_easyocr[pred_text] = {}
-                textdic_easyocr[pred_text]['pred_confidence'] = pred_confidence
-    
-            # get boxes on the image 
-            rectangle(image, result)
-                
-            # create a dataframe which shows the predicted text and prediction confidence
-            df = pd.DataFrame.from_dict(textdic_easyocr).T
-            st.table(df)
-elif page == "Speech & Text Emotion":
-    st.header('Speech & Text Emotion')
-    st.write(
-    """
-    """
-    )
-    uploaded_file = st.file_uploader("Choose an audio file", type=["mp3", "wav", "ogg"])
-
-    if uploaded_file is not None:
-        st.audio(uploaded_file, format='audio/' + uploaded_file.type.split('/')[1])
-        st.write("Audio file uploaded and playing.")
-                    
-    else:
-        st.write("Please upload an audio file.")
-
-    if st.button("Analysis"):
-        with st.spinner("Loading..."):
-            st.header('Results of the Audio & Text analysis:')
-            samples, sample_rate = librosa.load(uploaded_file, sr=16000)
-            p_voice2text = infere_voice2text (samples)
-            p_speechemotion = infere_speech_emotion(samples)
-            p_textemotion = infere_text_emotion(p_voice2text)
-            st.subheader("Text from the Audio:")
-            st.write(p_voice2text)
-            st.write("---")
-            st.subheader("Speech emotion:")
-            st.write(p_speechemotion)
-            st.write("---")
-            st.subheader("Text emotion:")
-            st.write(p_textemotion)
-            st.write("---")
-    
+try:
+    main()
+except Exception as e:
+    st.sidebar.error(f"An error occurred: {e}")