Upload 4 files

app.py

@@ -1,64 +1,33 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+# Your Gradio app code here
+import gradio as gr
+import joblib
+import numpy as np
+from scipy.sparse import hstack
+
+# Load your model and vectorizer
+model = joblib.load("spam_classifier_model.joblib")
+vectorizer = joblib.load("vectorizer.joblib")
+
+def predict_spam(clean_body, num_urls, has_attachment):
+    X_text = vectorizer.transform([clean_body])
+    X_combined = hstack([
+        X_text,
+        np.array([num_urls]).reshape(-1, 1),
+        np.array([has_attachment]).reshape(-1, 1)
+    ])
+    prediction = model.predict(X_combined)[0]
+    return "Spam" if prediction == 1 else "Not Spam"
+
+interface = gr.Interface(
+    fn=predict_spam,
+    inputs=[
+        gr.Textbox(lines=5, label="Email Body"),
+        gr.Slider(0, 50, step=1, label="Number of URLs"),
+        gr.Radio([0, 1], label="Has Attachment (0 = No, 1 = Yes)")
     ],
+    outputs=gr.Text(label="Prediction"),
+    title="Spam Email Classifier",
+    description="Classify emails as Spam or Not Spam."
 )
-
-
-if __name__ == "__main__":
-    demo.launch()
+interface.launch()

requirements.txt.txt

@@ -0,0 +1 @@
+joblib

spam_classifier_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72856a4d31bae421850b6fc8a0ad699f18ff8fbc1e95099db009050c08f68a9e
+size 24895

vectorizer.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c6b583f977afd0ac49ef4b7878e78a897e5e7cdbbc96e7ca5aa1d443044ee2
+size 110204