File size: 12,034 Bytes
27880c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
import os
import pandas as pd
import numpy as np
import easyocr
import streamlit as st
from annotated_text import annotated_text
from streamlit_option_menu import option_menu
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
from PIL import ImageDraw
from PIL import ImageFont
import time

# Imports de Object Detection
import tensorflow as tf
import tensorflow_hub as hub
# Load compressed models from tensorflow_hub
os.environ['TFHUB_MODEL_LOAD_FORMAT'] = 'COMPRESSED'
import matplotlib.pyplot as plt
import matplotlib as mpl
# For drawing onto the image.
import numpy as np
from tensorflow.python.ops.numpy_ops import np_config
np_config.enable_numpy_behavior()

import torch
import librosa
from models import infere_speech_emotion, infere_text_emotion, infere_voice2text

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(
            """
            """
        )

        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)

        max_keywords = st.slider('# of Keywords Max Limit', min_value=1, max_value=10, value=5, step=1)

        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.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')

            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(
            """
            """
        )

        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(
        """
        """
        )

        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
            
                # 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}")