Update app.py

app.py

@@ -1,64 +1,48 @@
 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)",
-        ),
-    ],
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score
+import pandas as pd
+
+  # Load and preprocess the dataset
+file_path = "spam.csv"  # Ensure this is the correct path to your dataset
+data = pd.read_csv(file_path, encoding='latin-1')
+data = data.rename(columns={"v1": "label", "v2": "text"}).loc[:, ["label", "text"]]
+data["label"] = data["label"].map({"ham": 0, "spam": 1})
+
+  # TF-IDF Vectorization
+tfidf = TfidfVectorizer(stop_words='english', max_features=3000)
+X = tfidf.fit_transform(data["text"]).toarray()
+y = data["label"]
+
+  # Train-test split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+  # Train a Logistic Regression model
+model = LogisticRegression()
+model.fit(X_train, y_train)
+
+  # Check accuracy
+accuracy = accuracy_score(y_test, model.predict(X_test))
+print(f"Model Accuracy: {accuracy * 100:.2f}%")
+
+  # Prediction function
+def predict_spam(text):
+    transformed_text = tfidf.transform([text]).toarray()
+    prediction = model.predict(transformed_text)[0]
+    return "Spam" if prediction == 1 else "Non-Spam"
+
+  # Gradio Interface
+interface = gr.Interface(
+    fn=predict_spam,
+    inputs=gr.Textbox(lines=5, placeholder="Enter email or message text here..."),
+    outputs=gr.Label(label="Prediction"),
+    title="Spam Email Detection",
+    description="A web application to detect spam emails using machine learning. Enter the email text to check if it's spam or not.",
+    live=False,
 )
 
+  # Launch the app
+interface.launch()
 
-if __name__ == "__main__":
-    demo.launch()