Spaces:
Sleeping
Sleeping
File size: 2,308 Bytes
dda9786 4d1bb38 dda9786 4d1bb38 dda9786 9bb2037 dda9786 9bb2037 dda9786 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
import gradio as gr
import joblib
import xgboost as xgb
import numpy as np
def classify_email(email_text):
tfidf = joblib.load('tfidf_vectorizer.joblib')
model = joblib.load('spam_model.joblib')
email_tfidf = tfidf.transform([email_text])
email_dmatrix = xgb.DMatrix(email_tfidf)
prediction = model.predict(email_dmatrix)[0]
confidence = max(prediction, 1 - prediction)
label = "Spam" if prediction > 0.5 else "Not Spam"
return {label: float(confidence)}
def analyze_email(email_text):
tfidf = joblib.load('tfidf_vectorizer.joblib')
model = joblib.load('spam_model.joblib')
email_tfidf = tfidf.transform([email_text])
email_dmatrix = xgb.DMatrix(email_tfidf)
prediction = model.predict(email_dmatrix)[0]
confidence = max(prediction, 1 - prediction)
label = "Spam" if prediction > 0.5 else "Not Spam"
# Create Gradio interface
with gr.Blocks(css="footer {visibility: hidden}") as iface:
gr.Markdown(
"""
# 🚀 Spam Email Classifier
Using Machine Learning to detect spam emails with high accuracy!
"""
)
with gr.Row():
with gr.Column(scale=2):
email_input = gr.Textbox(lines=5, label="Enter email text")
with gr.Row():
classify_btn = gr.Button("Classify")
with gr.Column(scale=1):
label_output = gr.Label(label="Classification")
examples = [
["Get fat quick! Buy our cheese burger now!"],
["Hi Ajibola, let's go out on a date tonight"],
["Congratulations! You've won a free iPhone. Click here to claim."],
["Please find attached the report for Q2 sales figures."]
]
gr.Examples(examples, inputs=email_input)
classify_btn.click(classify_email, inputs=email_input, outputs=label_output)
gr.Markdown(
"""
### How it works
This classifier uses an XGBoost model trained on a large dataset of over 190,000 emails.
The model achieved a 98% accuracy on the training data and 94% accuracy on the test data.
It analyzes the content and structure of the email to determine if it's spam or not.
### Tip for use
- Enter the full text of the email for best results
"""
)
# Launch the interface
iface.launch()
|