Update app.py

app.py

@@ -1,4 +1,4 @@
-from fastapi import FastAPI, UploadFile, File
+from fastapi import FastAPI
 import pandas as pd
 import uvicorn
 import joblib
@@ -8,22 +8,30 @@ from sklearn.preprocessing import LabelEncoder
 from pydantic import BaseModel
 import gradio as gr
 import os
+import requests
 
 app = FastAPI()
 
-# Ensure file upload directory exists
-UPLOAD_DIR = "uploaded_files"
-os.makedirs(UPLOAD_DIR, exist_ok=True)
+# Hugging Face Dataset URL
+DATASET_URL = "https://huggingface.co/datasets/SailajaS/CDART/resolve/main/train.csv"
+
+# File path for saving dataset
+DATASET_PATH = "dataset.csv"
+
+# Function to download dataset
+def download_dataset():
+    if not os.path.exists(DATASET_PATH):
+        response = requests.get(DATASET_URL)
+        if response.status_code == 200:
+            with open(DATASET_PATH, "wb") as file:
+                file.write(response.content)
+            print("✅ Dataset downloaded successfully!")
+        else:
+            raise Exception(f"❌ Failed to download dataset: {response.status_code}")
 
 # 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.")
-    
+    df = pd.read_csv(file_path)  # Load CSV directly
     return df
 
 # Placeholder for dataset and model
@@ -31,35 +39,26 @@ 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)
+# Download dataset at startup
+download_dataset()
 
-    # Encode categorical variables
-    df["Case Problem"] = encoder.fit_transform(df["Case Problem"])
-    df["Feedback"] = encoder.fit_transform(df["Feedback"])
+# Load dataset
+df = load_data(DATASET_PATH)
 
-    # 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)
+# Encode categorical variables
+df["Case Problem"] = encoder.fit_transform(df["Case Problem"])
+df["Feedback"] = encoder.fit_transform(df["Feedback"])
 
-    # Save model
-    joblib.dump(model, "feedback_model.pkl")
+# 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)
 
-    return {"message": f"File '{file.filename}' uploaded and model trained successfully."}
+# Save model
+joblib.dump(model, "feedback_model.pkl")
+print("✅ Model trained successfully!")
 
 # API Input Model
 class PredictionInput(BaseModel):
@@ -69,7 +68,7 @@ class PredictionInput(BaseModel):
 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."}
+        return {"error": "Model is not trained yet."}
 
     case_problem_encoded = encoder.transform([data.case_problem])
     prediction = model.predict([[case_problem_encoded[0]]])
@@ -79,7 +78,7 @@ def predict_feedback(data: PredictionInput):
 # Gradio UI
 def gradio_interface(case_problem):
     if model is None:
-        return "Model not trained yet. Please upload a dataset first."
+        return "Model not trained yet."
 
     case_problem_encoded = encoder.transform([case_problem])
     prediction = model.predict([[case_problem_encoded[0]]])