Spaces:
Sleeping
Sleeping
Download api.py from SunbalAzizLCWU/enterprise-spam-api: direct link, hf CLI and curl.
- Browser
- Download file 1.39 kB
-
https://huggingface.co/spaces/SunbalAzizLCWU/enterprise-spam-api/resolve/main/api.py
- Command line
-
hf download hf://spaces/SunbalAzizLCWU/enterprise-spam-api/api.py
-
curl -L -o api.py https://huggingface.co/spaces/SunbalAzizLCWU/enterprise-spam-api/resolve/main/api.py
1.39 kB
| from fastapi import FastAPI | |
| from pydantic import BaseModel | |
| import joblib | |
| import pandas as pd | |
| import re | |
| from collections import Counter | |
| from fastapi.middleware.cors import CORSMiddleware | |
| # Initialize App | |
| app = FastAPI(title="Enterprise Spam Classifier API") | |
| # Allow Streamlit UI to talk to this API | |
| app.add_middleware( | |
| CORSMiddleware, | |
| allow_origins=["*"], | |
| allow_methods=["*"], | |
| allow_headers=["*"], | |
| ) | |
| # Load the trained model and our 3,000 vocabulary words into memory | |
| model = joblib.load('spam_model.pkl') | |
| features = joblib.load('feature_names.pkl') | |
| # Define the expected JSON payload | |
| class EmailPayload(BaseModel): | |
| content: str | |
| def predict_spam(payload: EmailPayload): | |
| # 1. Clean and tokenize the raw incoming text | |
| text = payload.content.lower() | |
| words = re.findall(r'\b\w+\b', text) | |
| word_counts = Counter(words) | |
| # 2. Map the user's words to the exact 3,000 columns the model expects | |
| input_data = {feature: [word_counts.get(feature, 0)] for feature in features} | |
| df_input = pd.DataFrame(input_data) | |
| # 3. Run Inference | |
| prediction = model.predict(df_input)[0] | |
| probabilities = model.predict_proba(df_input)[0] | |
| confidence = probabilities.max() | |
| return { | |
| "prediction": "Spam" if prediction == 1 else "Not Spam", | |
| "confidence": float(confidence), | |
| "status": 200 | |
| } |