Create app.py

app.py

@@ -0,0 +1,92 @@
+import json
+import os
+import gradio as gr
+import pandas as pd
+from openai import OpenAI
+from transformers import pipeline
+from dotenv import load_dotenv
+
+load_dotenv()
+api_key = os.getenv("OPENAI_API_KEY")
+client = OpenAI(api_key=api_key)
+
+pipe = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment-latest")
+
+def process_csv(file):
+    df = pd.read_csv(file)
+    if "Feedback" not in df.columns or "Employee" not in df.columns:
+        return None, "❌ Error: CSV must contain 'Employee' and 'Feedback' columns."
+    df["Sentiment"] = df["Feedback"].apply(lambda x: pipe(x)[0]["label"])
+    return {"df": df}, "✅ CSV processed!"
+
+def predict_attrition_risk(employee_name: str, sentiment: str):
+    risk_mapping = {"positive": "Low Risk", "neutral": "Medium Risk", "negative": "High Risk"}
+    return f"{employee_name}: {risk_mapping.get(sentiment.lower(), 'Unknown Sentiment')}"
+
+def analyze_attrition_with_llm(df_dict, hr_query):
+    if df_dict is None or "df" not in df_dict:
+        return "❌ Error: No processed data. Upload a CSV first."
+    
+    df = df_dict["df"]
+    employees_data = [
+        {"employee_name": row["Employee"], "sentiment": row["Sentiment"], "feedback": row["Feedback"]}
+        for _, row in df.iterrows()
+    ]
+    
+    prompt = f"HR asked: '{hr_query}'. Here is the employee sentiment data:\n{json.dumps(employees_data, indent=2)}\n"
+    prompt += "If an employee is not found, return 'No records found for this employee.' If the question is irrelevant, refuse to answer politely."
+    
+    response = client.chat.completions.create(
+        model="gpt-4-turbo",
+        messages=[{"role": "user", "content": prompt}],
+        functions=[
+            {
+                "name": "predict_attrition_risk",
+                "description": "Predicts attrition risk based on sentiment.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "employee_name": {"type": "string"},
+                        "sentiment": {"type": "string"}
+                    },
+                    "required": ["employee_name", "sentiment"]
+                }
+            }
+        ],
+        function_call="auto"
+    )
+    
+    message = response.choices[0].message
+    
+    if hasattr(message, "function_call") and message.function_call:
+        try:
+            function_calls = json.loads(message.function_call.arguments)
+            results = []
+            for call in function_calls if isinstance(function_calls, list) else [function_calls]:
+                employee_name = call.get("employee_name")
+                sentiment = call.get("sentiment")
+                
+                if not any(emp["employee_name"] == employee_name for emp in employees_data):
+                    return "No records found for this employee."
+                
+                results.append(predict_attrition_risk(employee_name, sentiment))
+            return "\n".join(results)
+        except Exception:
+            return "No records found for this employee."
+    
+    return "I'm sorry, but I can only answer HR-related questions about employee sentiment and attrition risk." 
+
+with gr.Blocks() as demo:
+    gr.Markdown("<h1>AI-Driven Employee Attrition Risk Analysis</h1>")
+    file_input = gr.File(label="Upload Employee Feedback CSV", file_types=[".csv"])
+    process_button = gr.Button("Process CSV")
+    process_message = gr.Markdown()
+    hr_input = gr.Textbox(label="HR Query")
+    analyze_button = gr.Button("Ask HR Query")
+    output_text = gr.Markdown()
+    df_state = gr.State()
+
+    process_button.click(process_csv, inputs=file_input, outputs=[df_state, process_message])
+    analyze_button.click(analyze_attrition_with_llm, inputs=[df_state, hr_input], outputs=output_text)
+
+demo.launch(share=True)