model/crime_grid_daily_features.csv

import joblib
import pandas as pd
import numpy as np
from flask import Flask, request, jsonify
from flask_cors import CORS
from datetime import datetime

# ---------------- CONFIG ----------------
LAT_MIN = 12.70
LAT_MAX = 13.30
LON_MIN = 77.30
LON_MAX = 78.00
LAT_GRIDS = 50
LON_GRIDS = 50
THRESHOLD = 0.6

FEATURES = [
    "grid_x",
    "grid_y",
    "day_of_week",
    "is_weekend",
    "month",
    "crime_lag_1",
    "crime_lag_7",
    "crime_lag_30"
]

# ---------------- APP ----------------
app = Flask(__name__)
CORS(app)

# ---------------- LOAD MODELS ----------------
model1 = joblib.load("model1.pkl")
model2 = joblib.load("model2.pkl")
le = joblib.load("label_encoder.pkl")

# ---------------- LOAD DATA ----------------
full = pd.read_csv("crime_grid_daily_features.csv")
full["FIR_DATE"] = pd.to_datetime(full["FIR_DATE"])

# ---------------- HELPERS ----------------
def latlon_to_grid(lat, lon):
    return (
        int((lat - LAT_MIN) / ((LAT_MAX - LAT_MIN) / LAT_GRIDS)),
        int((lon - LON_MIN) / ((LON_MAX - LON_MIN) / LON_GRIDS))
    )

def get_lags(grid_x, grid_y):
    hist = full[
        (full["grid_x"] == grid_x) &
        (full["grid_y"] == grid_y)
    ].sort_values("FIR_DATE")

    if hist.empty:
        return 0, 0, 0

    return (
        hist.tail(1)["crime_count"].mean(),
        hist.tail(7)["crime_count"].mean(),
        hist.tail(30)["crime_count"].mean()
    )

# ---------------- ROUTES ----------------

@app.route("/health", methods=["GET"])
def health():
    return jsonify({"status": "ok"})

@app.route("/historical", methods=["GET"])
def historical():
    points = raw_points.dropna().sample(min(5000, len(raw_points)))
    return jsonify(points.to_dict(orient="records"))

@app.route("/predict", methods=["POST"])
def predict():
    data = request.json
    lat = float(data["latitude"])
    lon = float(data["longitude"])
    date = datetime.strptime(data["date"], "%Y-%m-%d")

    grid_x, grid_y = latlon_to_grid(lat, lon)
    crime_lag_1, crime_lag_7, crime_lag_30 = get_lags(grid_x, grid_y)

    row = pd.DataFrame([{
        "grid_x": grid_x,
        "grid_y": grid_y,
        "day_of_week": date.weekday(),
        "is_weekend": int(date.weekday() >= 5),
        "month": date.month,
        "crime_lag_1": crime_lag_1,
        "crime_lag_7": crime_lag_7,
        "crime_lag_30": crime_lag_30
    }])

    prob = model1.predict_proba(row[FEATURES])[0][1]
    response = {
        "crime_probability": float(prob),
        "risk": "UNSAFE" if prob > THRESHOLD else "SAFE"
    }

    if prob > THRESHOLD:
        probs = model2.predict_proba(row[FEATURES])[0]
        top = np.argsort(probs)[-3:][::-1]

        response["top_crimes"] = [
            {
                "type": le.inverse_transform([i])[0],
                "confidence": float(probs[i])
            }
            for i in top
        ]

    return jsonify(response)

@app.route("/hotspots", methods=["GET"])
def hotspots():
    # Load the cleaned dataset
    dataset = pd.read_csv("dataset_cleaned.csv")
    # Group by location and count occurrences
    hotspot_data = dataset.groupby(['Latitude', 'Longitude']).size().reset_index(name='count')
    # Filter hotspots based on a threshold (e.g., at least 5 occurrences)
    hotspots = hotspot_data[hotspot_data['count'] >= 5]
    return jsonify(hotspots.to_dict(orient="records"))

# ---------------- RUN ----------------
if __name__ == "__main__":
    app.run(host="0.0.0.0", port=5000)