Update app.py

app.py

@@ -1,94 +1,32 @@
-from fastapi import FastAPI, UploadFile, File
 import pandas as pd
-import uvicorn
-import joblib
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.preprocessing import LabelEncoder
-from pydantic import BaseModel
-import gradio as gr
-import os
-
-app = FastAPI()
-
-# Ensure file upload directory exists
-UPLOAD_DIR = "uploaded_files"
-os.makedirs(UPLOAD_DIR, exist_ok=True)
-
-# Function to load dataset
-def load_data(file_path):
-    if file_path.endswith(".csv"):
-        df = pd.read_csv(file_path)
-    elif file_path.endswith(".xlsx"):
-        df = pd.read_excel(file_path)
-    else:
-        raise ValueError("Unsupported file format. Please upload a CSV or Excel file.")
-    
-    return df
-
-# Placeholder for dataset and model
-df = None
-model = None
-encoder = LabelEncoder()
-
-@app.post("/upload/")
-async def upload_file(file: UploadFile = File(...)):
-    """ Upload and process the dataset """
-    global df, model, encoder
-
-    file_path = os.path.join(UPLOAD_DIR, file.filename)
-    
-    # Save the uploaded file
-    with open(file_path, "wb") as buffer:
-        buffer.write(await file.read())
-
-    # Load the dataset
-    df = load_data(file_path)
-
-    # Encode categorical variables
-    df["Case Problem"] = encoder.fit_transform(df["Case Problem"])
-    df["Feedback"] = encoder.fit_transform(df["Feedback"])
-
-    # Train Model
-    X = df[["Case Problem"]]
-    y = df["Feedback"]
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-    model = RandomForestClassifier(n_estimators=100, random_state=42)
-    model.fit(X_train, y_train)
-
-    # Save model
-    joblib.dump(model, "feedback_model.pkl")
-
-    return {"message": f"File '{file.filename}' uploaded and model trained successfully."}
-
-# API Input Model
-class PredictionInput(BaseModel):
-    case_problem: str
-
-@app.post("/predict/")
-def predict_feedback(data: PredictionInput):
-    """ Predicts feedback based on Case Problem """
-    if model is None:
-        return {"error": "Model is not trained yet. Please upload a dataset first."}
-
-    case_problem_encoded = encoder.transform([data.case_problem])
-    prediction = model.predict([[case_problem_encoded[0]]])
-    feedback_predicted = encoder.inverse_transform(prediction)[0]
-    return {"Predicted Feedback": feedback_predicted}
-
-# Gradio UI
-def gradio_interface(case_problem):
-    if model is None:
-        return "Model not trained yet. Please upload a dataset first."
-
-    case_problem_encoded = encoder.transform([case_problem])
-    prediction = model.predict([[case_problem_encoded[0]]])
-    feedback_predicted = encoder.inverse_transform(prediction)[0]
-    return f"Predicted Feedback: {feedback_predicted}"
-
-gr_interface = gr.Interface(fn=gradio_interface, inputs="text", outputs="text")
-gr_interface.launch()
-
-# Run API
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+from faker import Faker
+import random
+
+# Initialize Faker
+fake = Faker()
+
+# Sample case problems and feedback
+case_problems = ["Login Issues", "Payment Failure", "UI Bug", "Slow Performance", "Feature Request"]
+feedback_types = ["Negative", "Positive", "Neutral"]
+details = [
+    "Unable to login after password reset.",
+    "Payment went through after retrying.",
+    "The interface is a bit confusing at times.",
+    "The page load time is slow.",
+    "Would love a dark mode feature."
+]
+
+# Generate 50 unique records
+data = {
+    "Name": [fake.name() for _ in range(50)],
+    "Email": [fake.email() for _ in range(50)],
+    "Case Problem": [random.choice(case_problems) for _ in range(50)],
+    "Feedback": [random.choice(feedback_types) for _ in range(50)],
+    "Details": [random.choice(details) for _ in range(50)],
+}
+
+# Create DataFrame and Save as CSV
+df = pd.DataFrame(data)
+df.to_csv("sample_case_records_real_names.csv", index=False)
+
+print("CSV File Generated Successfully!")