Update app.py

app.py

@@ -1,20 +1,112 @@
-runtime error
-Exit code: 1. Reason: 📥 Downloading dataset from Hugging Face...
-✅ Dataset downloaded successfully!
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 39, in <module>
-    df = pd.read_csv(DATASET_PATH)
-  File "/usr/local/lib/python3.10/site-packages/pandas/io/parsers/readers.py", line 1026, in read_csv
-    return _read(filepath_or_buffer, kwds)
-  File "/usr/local/lib/python3.10/site-packages/pandas/io/parsers/readers.py", line 626, in _read
-    return parser.read(nrows)
-  File "/usr/local/lib/python3.10/site-packages/pandas/io/parsers/readers.py", line 1923, in read
-    ) = self._engine.read(  # type: ignore[attr-defined]
-  File "/usr/local/lib/python3.10/site-packages/pandas/io/parsers/c_parser_wrapper.py", line 234, in read
-    chunks = self._reader.read_low_memory(nrows)
-  File "parsers.pyx", line 838, in pandas._libs.parsers.TextReader.read_low_memory
-  File "parsers.pyx", line 905, in pandas._libs.parsers.TextReader._read_rows
-  File "parsers.pyx", line 874, in pandas._libs.parsers.TextReader._tokenize_rows
-  File "parsers.pyx", line 891, in pandas._libs.parsers.TextReader._check_tokenize_status
-  File "parsers.pyx", line 2061, in pandas._libs.parsers.raise_parser_error
-pandas.errors.ParserError: Error tokenizing data. C error: Expected 1 fields in line 5, saw 3
+from fastapi import FastAPI
+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
+import requests
+
+app = FastAPI()
+
+# ✅ Correct 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():
+    print("📥 Downloading dataset from Hugging Face...")
+
+    try:
+        response = requests.get(DATASET_URL, timeout=10)
+
+        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}")
+    
+    except requests.exceptions.RequestException as e:
+        print(f"❌ Error downloading dataset: {e}")
+        raise Exception("Dataset download failed.")
+
+# ✅ Download dataset at startup
+download_dataset()
+
+# ✅ Load dataset with error handling
+try:
+    df = pd.read_csv(DATASET_PATH, encoding="utf-8", delimiter=",", error_bad_lines=False)
+except:
+    try:
+        df = pd.read_csv(DATASET_PATH, encoding="utf-8", delimiter=";", error_bad_lines=False)
+    except:
+        raise Exception("❌ Unable to read CSV. Check delimiter and format.")
+
+# ✅ Check if necessary columns exist
+required_columns = ["Case Problem", "Feedback"]
+for col in required_columns:
+    if col not in df.columns:
+        raise Exception(f"❌ Column '{col}' is missing from the dataset!")
+
+# ✅ Encode categorical variables
+encoder = LabelEncoder()
+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")
+print("✅ 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."}
+
+    try:
+        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}
+    except Exception as e:
+        return {"error": str(e)}
+
+# ✅ Gradio UI
+def gradio_interface(case_problem):
+    if model is None:
+        return "Model not trained yet."
+
+    try:
+        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}"
+    except:
+        return "Invalid case problem. Please enter a valid category."
+
+# ✅ Start both API & Gradio
+def start_app():
+    """ Start API and Gradio Interface """
+    gr_interface = gr.Interface(fn=gradio_interface, inputs="text", outputs="text")
+    gr_interface.launch()
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+
+if __name__ == "__main__":
+    start_app()