Update app.py

app.py

@@ -1,213 +1,89 @@
-from transformers import pipeline
 import gradio as gr
-
-classifier = pipeline("sentiment-analysis", model="cardiffnlp/twitter-xlm-roberta-base-sentiment")
-
-def sentiment_analysis(message, history):
-    """
-    Función para analizar el sentimiento de un mensaje.
-    Retorna la etiqueta de sentimiento con su probabilidad.
-    """
-    result = classifier(message)
-    return f"Sentimiento : {result[0]['label']} (Probabilidad: {result[0]['score']:.2f})"
-
-with gr.Blocks() as demo:
-    gr.Markdown("""
-    # Análisis de Sentimientos
-    Esta aplicación utiliza un modelo de Machine Learning para analizar el sentimiento de los mensajes ingresados. 
-    Puede detectar si un texto es positivo, negativo o neutral con su respectiva probabilidad.
-    """)
-    
-    chat = gr.ChatInterface(sentiment_analysis, type="messages")
-    
-    gr.Markdown("""
-    ---
-    ### Conéctate conmigo:
-    [Instagram 📸](https://www.instagram.com/srjosueaaron/)
-    
-    [TikTok 🎵](https://www.tiktok.com/@srjosueaaron)
-    
-    [YouTube 🎬](https://www.youtube.com/@srjosueaaron)
-    ---
-    Demostración de Análisis de Sentimientos usando el modelo de [CardiffNLP](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment).
-    
-    Desarrollado con ❤️ por [@srjosueaaron](https://www.instagram.com/srjosueaaron/).
-    """)
-
-
+from transformers import pipeline
 import os
-os.system("pip install gradio==3.0.18")
-from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
-import gradio as gr
+import pandas as pd
+import numpy as np
+import joblib
 import spacy
-nlp = spacy.load('en_core_web_sm')
-nlp.add_pipe('sentencizer')
-
-def split_in_sentences(text):
-    doc = nlp(text)
-    return [str(sent).strip() for sent in doc.sents]
-
-def make_spans(text,results):
-    results_list = []
-    for i in range(len(results)):
-        results_list.append(results[i]['label'])
-    facts_spans = []
-    facts_spans = list(zip(split_in_sentences(text),results_list))
-    return facts_spans
-    
-auth_token = os.environ.get("HF_Token")
-
-##Speech Recognition
-asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
-def transcribe(audio):
-    text = asr(audio)["text"]
-    return text
-def speech_to_text(speech):
-    text = asr(speech)["text"]
-    return text
-
-##Summarization 
-summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")
-def summarize_text(text):
-    resp = summarizer(text)
-    stext = resp[0]['summary_text']
-    return stext
-
-##Fiscal Tone Analysis
-fin_model= pipeline("sentiment-analysis", model='yiyanghkust/finbert-tone', tokenizer='yiyanghkust/finbert-tone')
-def text_to_sentiment(text):
-    sentiment = fin_model(text)[0]["label"]
-    return sentiment 
-
-##Company Extraction    
-def fin_ner(text):
-    api = gr.Interface.load("dslim/bert-base-NER", src='models', use_auth_token=auth_token)
-    replaced_spans = api(text)
-    return replaced_spans    
-
-##Fiscal Sentiment by Sentence
-def fin_ext(text):
-    results = fin_model(split_in_sentences(text))
-    return make_spans(text,results)
-    
-##Forward Looking Statement
-def fls(text):
-#    fls_model = pipeline("text-classification", model="yiyanghkust/finbert-fls", tokenizer="yiyanghkust/finbert-fls")
-    fls_model = pipeline("text-classification", model="demo-org/finbert_fls", tokenizer="demo-org/finbert_fls", use_auth_token=auth_token)
-    results = fls_model(split_in_sentences(text))
-    return make_spans(text,results) 
-
-demo = gr.Blocks()
-
-with demo:
-    gr.Markdown("## Financial Analyst AI")
-    gr.Markdown("This project applies AI trained by our financial analysts to analyze earning calls and other financial documents.")
-    with gr.Row():
-        with gr.Column():
-            audio_file = gr.inputs.Audio(source="microphone", type="filepath")
-            with gr.Row():
-                b1 = gr.Button("Recognize Speech") 
-            with gr.Row():
-                text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
-                b1.click(speech_to_text, inputs=audio_file, outputs=text)
-            with gr.Row():
-                b2 = gr.Button("Summarize Text")
-                stext = gr.Textbox()
-                b2.click(summarize_text, inputs=text, outputs=stext)     
-            with gr.Row():
-                b3 = gr.Button("Classify Financial Tone")
-                label = gr.Label()
-                b3.click(text_to_sentiment, inputs=stext, outputs=label)  
-        with gr.Column():
-            b5 = gr.Button("Financial Tone and Forward Looking Statement Analysis")
-            with gr.Row():
-                fin_spans = gr.HighlightedText()
-                b5.click(fin_ext, inputs=text, outputs=fin_spans)
-            with gr.Row():
-                fls_spans = gr.HighlightedText()
-                b5.click(fls, inputs=text, outputs=fls_spans)
-            with gr.Row():
-                b4 = gr.Button("Identify Companies & Locations")
-                replaced_spans = gr.HighlightedText()
-                b4.click(fin_ner, inputs=text, outputs=replaced_spans)
-
-import os
-import gradio as gr
-
 from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain.prompts import HumanMessagePromptTemplate, ChatPromptTemplate
 from langchain.output_parsers import PydanticOutputParser
 from langchain_openai import ChatOpenAI
 
+# Set up models for each app
 chat = ChatOpenAI()
+classifier = pipeline("sentiment-analysis", model="cardiffnlp/twitter-xlm-roberta-base-sentiment")
+asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
+summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")
+fin_model = pipeline("sentiment-analysis", model='yiyanghkust/finbert-tone', tokenizer='yiyanghkust/finbert-tone')
+fls_model = pipeline("text-classification", model="demo-org/finbert_fls", tokenizer="demo-org/finbert_fls")
 
-# Define the Pydantic Model
+# --- Translator App ---
 class TextTranslator(BaseModel):
     output: str = Field(description="Python string containing the output text translated in the desired language")
-    
+
 output_parser = PydanticOutputParser(pydantic_object=TextTranslator)
 format_instructions = output_parser.get_format_instructions()
 
 def text_translator(input_text : str, language : str) -> str:
-    human_template = """Enter the text that you want to translate: 
-                {input_text}, and enter the language that you want it to translate to {language}. {format_instructions}"""
+    human_template = """Enter the text that you want to translate:
+    {input_text}, and enter the language that you want it to translate to {language}. {format_instructions}"""
     human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
-    
     chat_prompt = ChatPromptTemplate.from_messages([human_message_prompt])
-    
     prompt = chat_prompt.format_prompt(input_text = input_text, language = language, format_instructions = format_instructions)
-    
     messages = prompt.to_messages()
-    
     response = chat(messages = messages)
-    
     output = output_parser.parse(response.content)
-    
     output_text = output.output
-    
     return output_text
 
-# Interface
-with gr.Blocks() as demo:
-    gr.HTML("<h1 align = 'center'> Text Translator </h1>")
-    gr.HTML("<h4 align = 'center'> Translate to any language </h4>")
-    
-    inputs = [gr.Textbox(label = "Enter the text that you want to translate"), gr.Textbox(label = "Enter the language that you want it to translate to", placeholder = "Example : Hindi,French,Bengali,etc")]
-    generate_btn = gr.Button(value = 'Generate')
-    outputs  = [gr.Textbox(label = "Translated text")]
-    generate_btn.click(fn = text_translator, inputs= inputs, outputs = outputs)
+# --- Sentiment Analysis App ---
+def sentiment_analysis(message, history):
+    result = classifier(message)
+    return f"Sentimiento : {result[0]['label']} (Probabilidad: {result[0]['score']:.2f})"
 
-import gradio as gr
+# --- Financial Analyst App ---
+nlp = spacy.load('en_core_web_sm')
+nlp.add_pipe('sentencizer')
 
-gr.load("models/iiiorg/piiranha-v1-detect-personal-information").launch()
+def split_in_sentences(text):
+    doc = nlp(text)
+    return [str(sent).strip() for sent in doc.sents]
 
-import gradio as gr
-import pandas as pd
-import numpy as np
-import joblib, os
+def make_spans(text, results):
+    results_list = [results[i]['label'] for i in range(len(results))]
+    return list(zip(split_in_sentences(text), results_list))
+
+def summarize_text(text):
+    resp = summarizer(text)
+    return resp[0]['summary_text']
 
+def text_to_sentiment(text):
+    sentiment = fin_model(text)[0]["label"]
+    return sentiment
+
+def fin_ext(text):
+    results = fin_model(split_in_sentences(text))
+    return make_spans(text, results)
+
+def fls(text):
+    results = fls_model(split_in_sentences(text))
+    return make_spans(text, results)
+
+# --- Customer Churn App ---
 script_dir = os.path.dirname(os.path.abspath(__file__))
 pipeline_path = os.path.join(script_dir, 'toolkit', 'pipeline.joblib')
 model_path = os.path.join(script_dir, 'toolkit', 'Random Forest Classifier.joblib')
 
-# Load transformation pipeline and model
 pipeline = joblib.load(pipeline_path)
 model = joblib.load(model_path)
 
-# Create a function to calculate TotalCharges
 def calculate_total_charges(tenure, monthly_charges):
     return tenure * monthly_charges
 
-# Create a function that applies the ML pipeline and makes predictions
-def predict(SeniorCitizen, Partner, Dependents, tenure,
-            InternetService, OnlineSecurity, OnlineBackup, DeviceProtection, TechSupport,
-            StreamingTV, StreamingMovies, Contract, PaperlessBilling, PaymentMethod,
-            MonthlyCharges):
-    
-    # Calculate TotalCharges
+def predict(SeniorCitizen, Partner, Dependents, tenure, InternetService, OnlineSecurity, OnlineBackup, DeviceProtection,
+            TechSupport, StreamingTV, StreamingMovies, Contract, PaperlessBilling, PaymentMethod, MonthlyCharges):
     TotalCharges = calculate_total_charges(tenure, MonthlyCharges)
-
-    # Create a dataframe with the input data
     input_df = pd.DataFrame({
         'SeniorCitizen': [SeniorCitizen],
         'Partner': [Partner],
@@ -227,103 +103,80 @@ def predict(SeniorCitizen, Partner, Dependents, tenure,
         'TotalCharges': [TotalCharges]
     })
 
-    # Selecting categorical and numerical columns separately
+    X_processed = pipeline.transform(input_df)
     cat_cols = [col for col in input_df.columns if input_df[col].dtype == 'object']
     num_cols = [col for col in input_df.columns if input_df[col].dtype != 'object']
-    
-    X_processed = pipeline.transform(input_df)
 
-    # Extracting feature names for categorical columns after one-hot encoding
     cat_encoder = pipeline.named_steps['preprocessor'].named_transformers_['cat'].named_steps['onehot']
     cat_feature_names = cat_encoder.get_feature_names_out(cat_cols)
 
-    # Concatenating numerical and categorical feature names
     feature_names = num_cols + list(cat_feature_names)
-
-    # Convert X_processed to DataFrame
     final_df = pd.DataFrame(X_processed, columns=feature_names)
+    final_df = pd.concat([final_df.iloc[:, 3:], final_df.iloc[:, :3]], axis=1)
 
-    # Extract the first three columns and remaining columns, then merge
-    first_three_columns = final_df.iloc[:, :3]
-    remaining_columns = final_df.iloc[:, 3:]
-    final_df = pd.concat([remaining_columns, first_three_columns], axis=1)
-
-    # Make predictions using the model
     prediction_probs = model.predict_proba(final_df)[0]
     prediction_label = {
         "Prediction: CHURN 🔴": prediction_probs[1],
         "Prediction: STAY ✅": prediction_probs[0]
     }
-
     return prediction_label
 
-input_interface = []
-
-with gr.Blocks(theme=gr.themes.Soft()) as app:
-
-    Title = gr.Label('Customer Churn Prediction App')
-
-    with gr.Row():
-        Title
-
-    with gr.Row():
-        gr.Markdown("This app predicts likelihood of a customer to leave or stay with the company")
-
-    with gr.Row():
-        with gr.Column():
-            input_interface_column_1 = [
-                gr.components.Radio(['Yes', 'No'], label="Are you a Seniorcitizen?"),
-                gr.components.Radio(['Yes', 'No'], label='Do you have Partner?'),
-                gr.components.Radio(['No', 'Yes'], label='Do you have any Dependents?'),
-                gr.components.Slider(label='Enter lenghth of Tenure in Months', minimum=1, maximum=73, step=1),
-                gr.components.Radio(['DSL', 'Fiber optic', 'No Internet'], label='What is your Internet Service?'),
-                gr.components.Radio(['No', 'Yes'], label='Do you have Online Security?'),
-                gr.components.Radio(['No', 'Yes'], label='Do you have Online Backup?'),
-                gr.components.Radio(['No', 'Yes'], label='Do you have Device Protection?')
-            ]
-
-        with gr.Column():
-            input_interface_column_2 = [
-                gr.components.Radio(['No', 'Yes'], label='Do you have Tech Support?'),
-                gr.components.Radio(['No', 'Yes'], label='Do you have Streaming TV?'),
-                gr.components.Radio(['No', 'Yes'], label='Do you have Streaming Movies?'),
-                gr.components.Radio(['Month-to-month', 'One year', 'Two year'], label='What is your Contract Type?'),
-                gr.components.Radio(['Yes', 'No'], label='Do you prefer Paperless Billing?'),
-                gr.components.Radio(['Electronic check', 'Mailed check', 'Bank transfer (automatic)', 'Credit card (automatic)'], label='Which PaymentMethod do you prefer?'),
-                gr.components.Slider(label="Enter monthly charges", minimum=18.40, maximum=118.65)
-            ]
-
-    with gr.Row():
-        input_interface.extend(input_interface_column_1)
-        input_interface.extend(input_interface_column_2)
-
-    with gr.Row():
-        predict_btn = gr.Button('Predict')
-        output_interface = gr.Label(label="churn")
-    
-    with gr.Accordion("Open for information on inputs", open=False):
-        gr.Markdown("""This app receives the following as inputs and processes them to return the prediction on whether a customer, will churn or not.
-                    
-                    - SeniorCitizen: Whether a customer is a senior citizen or not
-                    - Partner: Whether the customer has a partner or not (Yes, No)
-                    - Dependents: Whether the customer has dependents or not (Yes, No)
-                    - Tenure: Number of months the customer has stayed with the company
-                    - InternetService: Customer's internet service provider (DSL, Fiber Optic, No)
-                    - OnlineSecurity: Whether the customer has online security or not (Yes, No, No Internet)
-                    - OnlineBackup: Whether the customer has online backup or not (Yes, No, No Internet)
-                    - DeviceProtection: Whether the customer has device protection or not (Yes, No, No internet service)
-                    - TechSupport: Whether the customer has tech support or not (Yes, No, No internet)
-                    - StreamingTV: Whether the customer has streaming TV or not (Yes, No, No internet service)
-                    - StreamingMovies: Whether the customer has streaming movies or not (Yes, No, No Internet service)
-                    - Contract: The contract term of the customer (Month-to-Month, One year, Two year)
-                    - PaperlessBilling: Whether the customer has paperless billing or not (Yes, No)
-                    - Payment Method: The customer's payment method (Electronic check, mailed check, Bank transfer(automatic), Credit card(automatic))
-                    - MonthlyCharges: The amount charged to the customer monthly
-                    """)
-        
-    predict_btn.click(fn=predict, inputs=input_interface, outputs=output_interface)
-
-if __name__ == "__main__":
-    demo.launch()
+# --- Personal Information Detection App ---
+import gradio as gr
+gr.load("models/iiiorg/piiranha-v1-detect-personal-information").launch()
 
-    app.launch(share=True)
+# --- Gradio Interface ---
+with gr.Blocks() as demo:
+    gr.Markdown("# All-in-One AI Apps")
+    with gr.Tab("Text Translator"):
+        gr.HTML("<h1 align='center'>Text Translator</h1>")
+        text_input = gr.Textbox(label="Enter Text")
+        language_input = gr.Textbox(label="Enter Language")
+        translate_btn = gr.Button("Translate")
+        translated_text = gr.Textbox(label="Translated Text")
+        translate_btn.click(fn=text_translator, inputs=[text_input, language_input], outputs=translated_text)
+
+    with gr.Tab("Sentiment Analysis"):
+        gr.Markdown("# Sentiment Analysis")
+        sentiment_input = gr.Textbox(label="Enter Message")
+        sentiment_output = gr.Textbox(label="Sentiment")
+        sentiment_btn = gr.Button("Analyze Sentiment")
+        sentiment_btn.click(fn=sentiment_analysis, inputs=sentiment_input, outputs=sentiment_output)
+
+    with gr.Tab("Financial Analyst"):
+        gr.Markdown("# Financial Analyst AI")
+        financial_input = gr.Textbox(label="Enter Text for Financial Analysis")
+        summarize_btn = gr.Button("Summarize")
+        sentiment_btn = gr.Button("Classify Financial Tone")
+        financial_output = gr.Textbox(label="Analysis Results")
+        summarize_btn.click(fn=summarize_text, inputs=financial_input, outputs=financial_output)
+        sentiment_btn.click(fn=text_to_sentiment, inputs=financial_input, outputs=financial_output)
+
+    with gr.Tab("Customer Churn Prediction"):
+        gr.Markdown("# Customer Churn Prediction")
+        churn_inputs = [
+            gr.Radio(['Yes', 'No'], label="Are you a Seniorcitizen?"),
+            gr.Radio(['Yes', 'No'], label="Do you have a Partner?"),
+            gr.Radio(['No', 'Yes'], label="Do you have Dependents?"),
+            gr.Slider(label="Tenure (Months)", minimum=1, maximum=73),
+            gr.Radio(['DSL', 'Fiber optic', 'No Internet'], label="Internet Service"),
+            gr.Radio(['No', 'Yes'], label="Online Security"),
+            gr.Radio(['No', 'Yes'], label="Online Backup"),
+            gr.Radio(['No', 'Yes'], label="Device Protection"),
+            gr.Radio(['No', 'Yes'], label="Tech Support"),
+            gr.Radio(['No', 'Yes'], label="Streaming TV"),
+            gr.Radio(['No', 'Yes'], label="Streaming Movies"),
+            gr.Radio(['Month-to-month', 'One year', 'Two year'], label="Contract Type"),
+            gr.Radio(['Yes', 'No'], label="Paperless Billing"),
+            gr.Radio(['Electronic check', 'Mailed check', 'Bank transfer (automatic)', 'Credit card (automatic)'], label="Payment Method"),
+            gr.Slider(label="Monthly Charges", minimum=18.4, maximum=118.65)
+        ]
+        churn_output = gr.Label(label="Churn Prediction")
+        churn_btn = gr.Button("Predict Churn")
+        churn_btn.click(fn=predict, inputs=churn_inputs, outputs=churn_output)
+
+    with gr.Tab("Personal Information Detection"):
+        gr.HTML("<h1 align='center'>Personal Information Detection</h1>")
+        gr.Interface.load("models/iiiorg/piiranha-v1-detect-personal-information").launch()
+
+demo.launch(share=True)