Create app.py

app.py

@@ -0,0 +1,68 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import joblib
+import re
+
+# Load the model once when the app starts
+model = joblib.load("model.joblib")
+
+app = FastAPI(title="Email Classification API")
+
+@app.get("/")
+def root():
+    return {"message": "Email Classification API is running."}
+
+
+# Input data schema
+class EmailInput(BaseModel):
+    subject: str = ""
+    email: str
+
+# PII masking function (same as your training)
+def mask_and_store_all_pii(text):
+    text = str(text)
+    pii_map = {}
+
+    patterns = {
+        "email": r"\b[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+\b",
+        "phone_number": r"\b\d{10}\b",
+        "dob": r"\b\d{2}[/-]\d{2}[/-]\d{4}\b",
+        "aadhar_num": r"\b\d{4}[- ]?\d{4}[- ]?\d{4}\b",
+        "credit_debit_no": r"\b(?:\d[ -]*?){13,16}\b",
+        "cvv_no": r"\b\d{3}\b",
+        "expiry_no": r"\b(0[1-9]|1[0-2])\/\d{2,4}\b",
+        "full_name": r"\b([A-Z][a-z]+(?:\s[A-Z][a-z]+)+)\b"
+    }
+
+    for label, pattern in patterns.items():
+        matches = re.findall(pattern, text)
+        for i, match in enumerate(matches):
+            placeholder = f"[{label}_{i}]"
+            pii_map[placeholder] = match
+            text = text.replace(match, placeholder)
+
+    return text, pii_map
+
+# Restore PII function
+def restore_pii(masked_text, pii_map):
+    for placeholder, original in pii_map.items():
+        masked_text = masked_text.replace(placeholder, original)
+    return masked_text
+
+@app.post("/classify")
+def classify_email(data: EmailInput):
+    # Combine subject + email text
+    raw_text = f"{data.subject} {data.email}"
+
+    # Mask PII
+    masked_text, pii_map = mask_and_store_all_pii(raw_text)
+
+    # Predict class
+    prediction = model.predict([masked_text])[0]
+
+    # Return prediction and masked email
+    return {
+        "predicted_category": prediction,
+        "masked_text": masked_text,
+        "pii_map": pii_map
+    }