Update app.py

app.py

@@ -1,170 +1,189 @@
-# app.py
-
 import os
 import gradio as gr
 import pandas as pd
 import numpy as np
 import joblib
 import spacy
-
+from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
 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
-from transformers import pipeline
 
-### 1. Translator ###
+# --- Translator App ---
 chat = ChatOpenAI()
-
 class TextTranslator(BaseModel):
-    output: str = Field(description="Translated output")
+    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:
-    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_prompt = HumanMessagePromptTemplate.from_template(template)
-    prompt = ChatPromptTemplate.from_messages([human_prompt]).format_prompt(
-        input_text=input_text, language=language, format_instructions=format_instructions)
-    response = chat(messages=prompt.to_messages())
-    return output_parser.parse(response.content).output
-
-### 2. Sentiment ###
+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)
+    return output.output
+
+translator_tab = gr.Interface(fn=text_translator, 
+    inputs=[gr.Textbox(label="Text to translate"), gr.Textbox(label="Target Language")],
+    outputs=[gr.Textbox(label="Translated Text")],
+    title="Text Translator")
+
+# --- Sentiment Analysis App ---
 sentiment_model = pipeline("sentiment-analysis", model="cardiffnlp/twitter-xlm-roberta-base-sentiment")
 def sentiment_analysis(message, history):
     result = sentiment_model(message)
-    return f"Sentimiento : {result[0]['label']} (Probabilidad: {result[0]['score']:.2f})"
+    return f"Sentiment: {result[0]['label']} (Probability: {result[0]['score']:.2f})"
+
+sentiment_tab = gr.ChatInterface(fn=sentiment_analysis, title="Sentiment Analysis")
+
+# --- Financial Analyst ---
+spacy_model = spacy.load('en_core_web_sm')
+spacy_model.add_pipe('sentencizer')
+auth_token = os.environ.get("HF_Token")
+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')
 
-### 3. Financial Analyst ###
-nlp = spacy.load('en_core_web_sm')
-nlp.add_pipe('sentencizer')
 def split_in_sentences(text):
-    return [str(sent).strip() for sent in nlp(text).sents]
+    doc = spacy_model(text)
+    return [str(sent).strip() for sent in doc.sents]
 
 def make_spans(text, results):
-    labels = [r['label'] for r in results]
-    return list(zip(split_in_sentences(text), labels))
+    return list(zip(split_in_sentences(text), [r["label"] for r in results]))
 
-auth_token = os.environ.get("HF_Token")
+def speech_to_text(speech):
+    return asr(speech)["text"]
 
-asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
-def speech_to_text(audio):
-    return asr(audio)["text"]
-
-summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")
 def summarize_text(text):
     return summarizer(text)[0]['summary_text']
 
-fin_model = pipeline("sentiment-analysis", model='yiyanghkust/finbert-tone')
 def text_to_sentiment(text):
     return fin_model(text)[0]["label"]
 
-def fin_ner(text):
-    return gr.Interface.load("dslim/bert-base-NER", src='models', use_auth_token=auth_token)(text)
-
 def fin_ext(text):
-    return make_spans(text, fin_model(split_in_sentences(text)))
+    results = fin_model(split_in_sentences(text))
+    return make_spans(text, results)
 
 def fls(text):
-    model = pipeline("text-classification", model="demo-org/finbert_fls", tokenizer="demo-org/finbert_fls", use_auth_token=auth_token)
-    return make_spans(text, model(split_in_sentences(text)))
+    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_personal_info(text):
-    model = gr.Interface.load("iiiorg/piiranha-v1-detect-personal-information")
-    return model(text)
-
-### 5. Customer Churn ###
+def fin_ner(text):
+    api = gr.Interface.load("dslim/bert-base-NER", src='models', use_auth_token=auth_token)
+    return api(text)
+
+financial_tab = gr.Blocks()
+with financial_tab:
+    gr.Markdown("## Financial Analyst AI")
+    audio_file = gr.Audio(source="microphone", type="filepath")
+    text = gr.Textbox(label="Recognized Text")
+    summary = gr.Textbox(label="Summary")
+    tone = gr.Label(label="Financial Tone")
+    spans = gr.HighlightedText()
+    fls_spans = gr.HighlightedText()
+    ner_spans = gr.HighlightedText()
+    with gr.Row():
+        gr.Button("Recognize Speech").click(speech_to_text, inputs=audio_file, outputs=text)
+        gr.Button("Summarize Text").click(summarize_text, inputs=text, outputs=summary)
+        gr.Button("Classify Tone").click(text_to_sentiment, inputs=summary, outputs=tone)
+    with gr.Row():
+        gr.Button("Financial Sentiment").click(fin_ext, inputs=text, outputs=spans)
+        gr.Button("Forward Looking").click(fls, inputs=text, outputs=fls_spans)
+        gr.Button("NER Companies").click(fin_ner, inputs=text, outputs=ner_spans)
+
+# --- Personal Information Detection ---
+pii_tab = gr.load("models/iiiorg/piiranha-v1-detect-personal-information")
+
+# --- Customer 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')
-pipeline_model = joblib.load(pipeline_path)
-model = joblib.load(model_path)
+pipeline = joblib.load(os.path.join(script_dir, 'toolkit', 'pipeline.joblib'))
+model = joblib.load(os.path.join(script_dir, 'toolkit', 'Random Forest Classifier.joblib'))
 
 def calculate_total_charges(tenure, monthly_charges):
     return tenure * monthly_charges
 
-def predict(SeniorCitizen, Partner, Dependents, tenure,
+def predict_churn(SeniorCitizen, Partner, Dependents, tenure,
             InternetService, OnlineSecurity, OnlineBackup, DeviceProtection, TechSupport,
             StreamingTV, StreamingMovies, Contract, PaperlessBilling, PaymentMethod,
             MonthlyCharges):
-
     TotalCharges = calculate_total_charges(tenure, MonthlyCharges)
     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]
+        '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]
     })
-
-    X_processed = pipeline_model.transform(input_df)
-    cat_encoder = pipeline_model.named_steps['preprocessor'].named_transformers_['cat'].named_steps['onehot']
-    feature_names = [*input_df.select_dtypes(exclude='object').columns, *cat_encoder.get_feature_names_out()]
+    X_processed = pipeline.transform(input_df)
+    cat_encoder = pipeline.named_steps['preprocessor'].named_transformers_['cat'].named_steps['onehot']
+    cat_cols = [col for col in input_df.columns if input_df[col].dtype == 'object']
+    feature_names = [col for col in input_df.columns if input_df[col].dtype != 'object'] + list(cat_encoder.get_feature_names_out(cat_cols))
     final_df = pd.DataFrame(X_processed, columns=feature_names)
-    pred_probs = model.predict_proba(final_df)[0]
+    final_df = pd.concat([final_df.iloc[:, 3:], final_df.iloc[:, :3]], axis=1)
+    prediction_probs = model.predict_proba(final_df)[0]
     return {
-        "Prediction: CHURN 🔴": pred_probs[1],
-        "Prediction: STAY ✅": pred_probs[0]
+        "Prediction: CHURN 🔴": prediction_probs[1],
+        "Prediction: STAY ✅": prediction_probs[0]
     }
 
-### COMBINED UI ###
-with gr.Blocks() as demo:
-    with gr.Tab("Translator"):
-        gr.Markdown("## Translator")
-        input_text = gr.Textbox(label="Text to Translate")
-        language = gr.Textbox(label="Target Language")
-        output = gr.Textbox(label="Translated Text")
-        gr.Button("Translate").click(text_translator, inputs=[input_text, language], outputs=output)
-
-    with gr.Tab("Sentiment"):
-        gr.Markdown("## Sentiment Analysis")
-        gr.ChatInterface(sentiment_analysis, type="messages")
-
-    with gr.Tab("Financial Analyst"):
-        gr.Markdown("## Financial Analyst")
-        audio = gr.Audio(source="microphone", type="filepath")
-        text_input = gr.Textbox()
-        summary = gr.Textbox()
-        tone_label = gr.Label()
-        gr.Button("Speech to Text").click(speech_to_text, inputs=audio, outputs=text_input)
-        gr.Button("Summarize").click(summarize_text, inputs=text_input, outputs=summary)
-        gr.Button("Classify Tone").click(text_to_sentiment, inputs=summary, outputs=tone_label)
-        gr.HighlightedText(label="Tone").render()
-        gr.HighlightedText(label="Forward-Looking").render()
-        gr.Button("Analyze All").click(fn=fin_ext, inputs=text_input, outputs=None).click(fls, inputs=text_input, outputs=None)
-        gr.Button("Entities").click(fin_ner, inputs=text_input, outputs=None)
-
-    with gr.Tab("Personal Info Detector"):
-        gr.Markdown("## Detect Personal Info")
-        pi_input = gr.Textbox()
-        pi_output = gr.HighlightedText()
-        gr.Button("Detect").click(detect_personal_info, inputs=pi_input, outputs=pi_output)
-
-    with gr.Tab("Customer Churn"):
-        gr.Markdown("## Customer Churn Prediction")
-        inputs = [
-            gr.Radio(["Yes", "No"], label="SeniorCitizen"),
-            gr.Radio(["Yes", "No"], label="Partner"),
-            gr.Radio(["No", "Yes"], label="Dependents"),
-            gr.Slider(1, 73, step=1, label="Tenure"),
-            gr.Radio(["DSL", "Fiber optic", "No Internet"], label="InternetService"),
-            gr.Radio(["No", "Yes"], label="OnlineSecurity"),
-            gr.Radio(["No", "Yes"], label="OnlineBackup"),
-            gr.Radio(["No", "Yes"], label="DeviceProtection"),
-            gr.Radio(["No", "Yes"], label="TechSupport"),
-            gr.Radio(["No", "Yes"], label="StreamingTV"),
-            gr.Radio(["No", "Yes"], label="StreamingMovies"),
-            gr.Radio(["Month-to-month", "One year", "Two year"], label="Contract"),
-            gr.Radio(["Yes", "No"], label="PaperlessBilling"),
-            gr.Radio(["Electronic check", "Mailed check", "Bank transfer (automatic)", "Credit card (automatic)"], label="PaymentMethod"),
-            gr.Slider(18.40, 118.65, label="MonthlyCharges")
-        ]
-        churn_output = gr.Label()
-        gr.Button("Predict").click(predict, inputs=inputs, outputs=churn_output)
-
-if __name__ == "__main__":
+churn_tab = gr.Interface(
+    fn=predict_churn,
+    inputs=[
+        gr.Radio(['Yes', 'No'], label="Senior Citizen"),
+        gr.Radio(['Yes', 'No'], label="Partner"),
+        gr.Radio(['No', 'Yes'], label="Dependents"),
+        gr.Slider(1, 73, step=1, label="Tenure (months)"),
+        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"),
+        gr.Radio(['Yes', 'No'], label="Paperless Billing"),
+        gr.Radio(['Electronic check', 'Mailed check', 'Bank transfer (automatic)', 'Credit card (automatic)'], label="Payment Method"),
+        gr.Slider(18.4, 118.65, label="Monthly Charges")
+    ],
+    outputs=gr.Label(label="Prediction"),
+    title="Customer Churn Prediction"
+)
+
+# --- Launching All Tabs ---
+demo = gr.TabbedInterface(
+    interface_list=[
+        translator_tab,
+        sentiment_tab,
+        financial_tab,
+        pii_tab,
+        churn_tab
+    ],
+    tab_names=[
+        "Translator",
+        "Sentiment Analysis",
+        "Financial Analyst",
+        "Personal Info Detection",
+        "Customer Churn"
+    ]
+)
+
+if __name__ == '__main__':
     demo.launch()