Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI
|
| 2 |
+
from pydantic import BaseModel
|
| 3 |
+
import joblib
|
| 4 |
+
import nltk
|
| 5 |
+
from nltk.corpus import stopwords
|
| 6 |
+
from nltk.stem import PorterStemmer
|
| 7 |
+
import re
|
| 8 |
+
|
| 9 |
+
nltk.download('stopwords')
|
| 10 |
+
|
| 11 |
+
app = FastAPI()
|
| 12 |
+
|
| 13 |
+
# Load the model pipeline
|
| 14 |
+
pipeline = joblib.load('spam_classifier_pipeline.joblib')
|
| 15 |
+
|
| 16 |
+
class EmailRequest(BaseModel):
|
| 17 |
+
subject: str
|
| 18 |
+
body: str
|
| 19 |
+
|
| 20 |
+
def preprocess_text(text):
|
| 21 |
+
text = text.lower()
|
| 22 |
+
text = re.sub(r'[^a-zA-Z\s]', '', text)
|
| 23 |
+
words = text.split()
|
| 24 |
+
stop_words = set(stopwords.words('english'))
|
| 25 |
+
words = [word for word in words if word not in stop_words]
|
| 26 |
+
stemmer = PorterStemmer()
|
| 27 |
+
words = [stemmer.stem(word) for word in words]
|
| 28 |
+
return ' '.join(words)
|
| 29 |
+
|
| 30 |
+
@app.post("/predict")
|
| 31 |
+
async def predict(email: EmailRequest):
|
| 32 |
+
processed_text = preprocess_text(email.subject + ' ' + email.body)
|
| 33 |
+
prediction = pipeline.predict([processed_text])[0]
|
| 34 |
+
return {'prediction': ['ham', 'not_spam', 'spam'][prediction]}
|
| 35 |
+
|
| 36 |
+
@app.get("/")
|
| 37 |
+
async def root():
|
| 38 |
+
return {"message": "Spam Classification API"}
|