Create model.py

model.py

@@ -0,0 +1,76 @@
+import pandas as pd
+from datasets import Dataset
+from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
+import torch
+import gradio as gr
+from huggingface_hub import HfApi, Repository
+import os
+
+# Step 1: Set your Hugging Face access token
+hf_token = ""  # Replace with your actual token
+
+# Initialize the Hugging Face API client
+api = HfApi()
+
+# Step 2: Create a sample dataset
+data = {
+    "Name": ["John Doe", "Jane Smith", "Mike Johnson"],
+    "Email": ["johndoe@example.com", "janesmith@example.com", "mikej@example.com"],
+    "Case Problem": ["Login Issues", "Payment Failure", "UI Bug"],
+    "Feedback": ["Negative", "Positive", "Neutral"],
+    "Details": [
+        "Unable to login after password reset.",
+        "Payment went through after retrying.",
+        "The interface is a bit confusing at times."
+    ]
+}
+
+# Create a DataFrame from the sample data
+df = pd.DataFrame(data)
+
+# Convert the DataFrame into a Hugging Face Dataset
+dataset = Dataset.from_pandas(df)
+
+# Step 3: Upload the dataset to Hugging Face
+repo_id = "SailajaS/case-feedback-dataset"  # Replace with your actual Hugging Face repo name
+try:
+    # Create a repository on Hugging Face to store the dataset
+    api.create_repo(repo_id=repo_id, repo_type="dataset", token=hf_token)
+    print(f"Successfully created repository: {repo_id}")
+except Exception as e:
+    print(f"Error creating repository: {e}")
+
+# Initialize the repository and push the dataset to Hugging Face
+repo = Repository(local_dir="./dataset_repo", clone_from=repo_id)
+dataset.to_csv("./dataset_repo/dataset.csv")
+repo.push_to_hub()
+
+# Step 4: Load pre-trained DistilBERT model and tokenizer
+model_name = "distilbert-base-uncased"
+model = DistilBertForSequenceClassification.from_pretrained(model_name)
+tokenizer = DistilBertTokenizer.from_pretrained(model_name)
+
+# Step 5: Define a function to predict feedback based on case details
+def predict_case_feedback(details):
+    inputs = tokenizer(details, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class = logits.argmax(dim=-1).item()
+    
+    feedback_labels = ["Negative", "Positive", "Neutral"]
+    feedback = feedback_labels[predicted_class]
+    
+    return f"Predicted Feedback: {feedback}"
+
+# Step 6: Create Gradio interface for the prediction function
+interface = gr.Interface(
+    fn=predict_case_feedback,
+    inputs="text",              # Input: Text
+    outputs="text",             # Output: Text
+    title="Case Feedback Prediction",
+    description="Enter the case details to predict feedback (Positive, Negative, Neutral)"
+)
+
+# Step 7: Launch the Gradio app
+interface.launch()