Update app.py

app.py

@@ -9,24 +9,100 @@ from langchain_openai import ChatOpenAI
 from langchain_core.output_parsers import StrOutputParser
 
 # 1. Translator
-translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr")
+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 translate_text(text):
-    return translator(text)[0]['translation_text']
+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_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
 
 # 2. Sentiment Analysis
-sentiment = pipeline("sentiment-analysis")
+classifier = pipeline("sentiment-analysis", model="cardiffnlp/twitter-xlm-roberta-base-sentiment")
 
-def analyze_sentiment(text):
-    return sentiment(text)[0]
+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})"
 
 # 3. Financial Analyst (LangChain with OpenAI, requires API key)
-def financial_analysis(text, api_key):
-    chat = ChatOpenAI(api_key=api_key)
-    template = "Analyze the financial context of this text:\n\n{text}"
-    prompt = PromptTemplate.from_template(template)
-    chain = LLMChain(llm=chat, prompt=prompt, output_parser=StrOutputParser())
-    return chain.run({"text": text})
+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) 
+
 
 # 4. Personal Info Detection
 def detect_pii(text):
@@ -43,33 +119,144 @@ def detect_pii(text):
     return found or "No personal information found."
 
 # 5. Telco Customer Churn Prediction
-model = joblib.load("model.joblib")
-def churn_prediction(gender, SeniorCitizen, Partner, tenure, MonthlyCharges):
-    input_df = pd.DataFrame([[gender, SeniorCitizen, Partner, tenure, MonthlyCharges]],
-                            columns=["gender", "SeniorCitizen", "Partner", "tenure", "MonthlyCharges"])
-    prediction = model.predict(input_df)[0]
-    return "Churn" if prediction == 1 else "Not Churn"
+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
+    TotalCharges = calculate_total_charges(tenure, MonthlyCharges)
+
+    # Create a dataframe with the input data
+    input_df = pd.DataFrame({
+        'SeniorCitizen': [SeniorCitizen],
+        'Partner': [Partner],
+        'Dependents': [Dependents],
+        'tenure': [tenure],
+        'InternetService': [InternetService],
+        'OnlineSecurity': [OnlineSecurity],
+        'OnlineBackup': [OnlineBackup],
+        'DeviceProtection': [DeviceProtection],
+        'TechSupport': [TechSupport],
+        'StreamingTV': [StreamingTV],
+        'StreamingMovies': [StreamingMovies],
+        'Contract': [Contract],
+        'PaperlessBilling': [PaperlessBilling],
+        'PaymentMethod': [PaymentMethod],
+        'MonthlyCharges': [MonthlyCharges],
+        'TotalCharges': [TotalCharges]
+    })
+
+    # Selecting categorical and numerical columns separately
+    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)
+
+    # 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 = []
 
 # Gradio UI setup
 with gr.Blocks() as demo:
     with gr.Tab("Translator"):
-        input_text = gr.Textbox(label="Input Text")
-        output_text = gr.Textbox(label="Translated Text")
-        translate_button = gr.Button("Translate")
-        translate_button.click(fn=translate_text, inputs=input_text, outputs=output_text)
+        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)
 
     with gr.Tab("Sentiment Analysis"):
-        sentiment_input = gr.Textbox(label="Text")
-        sentiment_output = gr.Textbox(label="Sentiment")
-        sentiment_button = gr.Button("Analyze")
-        sentiment_button.click(fn=analyze_sentiment, inputs=sentiment_input, outputs=sentiment_output)
+        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/).
+    """)
 
     with gr.Tab("Financial Analyst"):
-        finance_input = gr.Textbox(label="Financial Text")
-        api_key_input = gr.Textbox(label="OpenAI API Key", type="password")
-        finance_output = gr.Textbox(label="Analysis")
-        finance_button = gr.Button("Analyze")
-        finance_button.click(fn=financial_analysis, inputs=[finance_input, api_key_input], outputs=finance_output)
+        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)
 
     with gr.Tab("PII Detector"):
         pii_input = gr.Textbox(label="Text")
@@ -78,15 +265,66 @@ with gr.Blocks() as demo:
         pii_button.click(fn=detect_pii, inputs=pii_input, outputs=pii_output)
 
     with gr.Tab("Telco Churn Predictor"):
-        gender = gr.Dropdown(choices=["Male", "Female"], label="Gender")
-        senior = gr.Dropdown(choices=[0, 1], label="Senior Citizen")
-        partner = gr.Dropdown(choices=["Yes", "No"], label="Partner")
-        tenure = gr.Number(label="Tenure (months)")
-        charges = gr.Number(label="Monthly Charges")
-        churn_output = gr.Textbox(label="Prediction")
-        churn_button = gr.Button("Predict")
-        churn_button.click(fn=churn_prediction,
-                           inputs=[gender, senior, partner, tenure, charges],
-                           outputs=churn_output)
+        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)
 
 demo.launch()