update dockerfile

Dockerfile

@@ -2,24 +2,28 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install system dependencies
+# System deps + git-lfs
 RUN apt-get update && apt-get install -y \
+    git \
+    git-lfs \
     build-essential \
+    && git lfs install \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements and install Python dependencies
+# Copy requirements and install Python deps
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy application
+# Copy app code (includes LFS pointers)
 COPY . .
 
-# Expose port
+# 🔴 THIS IS THE IMPORTANT PART
+RUN git lfs pull
+
 EXPOSE 7860
 
-# Run Flask app
 ENV FLASK_APP=app.py
 ENV FLASK_ENV=production
 ENV BACKEND_PORT=7860
 
-CMD ["python", "app.py"]
+CMD ["python", "app.py"]

app.py

@@ -11,53 +11,76 @@ import pandas as pd
 from flask import Flask, jsonify, request
 from flask_cors import CORS
 from sklearn.preprocessing import LabelEncoder
+from datasets import load_dataset as hf_load_dataset
 
-warnings.filterwarnings('ignore')
+warnings.filterwarnings("ignore")
 
 app = Flask(__name__)
 CORS(app, resources={r"/api/*": {"origins": "*"}})
 
-
 # ============================================================================
-# FIX: Use raw strings or forward slashes for Windows paths
-# ================================================
-# Base directory = where app.py lives
+# Paths
+# ============================================================================
 BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-
-# model/ is INSIDE the same folder as app.py
-MODEL_DIR = os.path.join(BASE_DIR, 'model')
-DATASET_PATH = os.path.join(MODEL_DIR, 'dataset_cleaned.csv')
+MODEL_DIR = os.path.join(BASE_DIR, "model")
+DATASET_PATH = os.path.join(MODEL_DIR, "dataset_cleaned.csv")
 
 print(f"\n📂 BASE_DIR: {BASE_DIR}")
-print(f"📊 DATASET_PATH: {DATASET_PATH}")
 print(f"📂 MODEL_DIR: {MODEL_DIR}")
-print(f"✓ Dataset exists: {os.path.exists(DATASET_PATH)}")
-print(f"✓ Model dir exists: {os.path.exists(MODEL_DIR)}\n")
+print(f"📊 DATASET_PATH: {DATASET_PATH}")
+print(f"✓ Model dir exists: {os.path.exists(MODEL_DIR)}")
+print(f"✓ Dataset exists (local): {os.path.exists(DATASET_PATH)}\n")
 
+# ============================================================================
+# Globals
+# ============================================================================
 df = None
 model1 = None
 model2 = None
 le = None
 
-def load_dataset():
-    """Load the crime dataset"""
+# ============================================================================
+# Dataset loader (HF first, local fallback)
+# ============================================================================
+def load_crime_dataset():
     global df
+
+    # ---- Attempt 1: Hugging Face dataset (LFS-safe) ----
+    try:
+        print("🚀 Attempting to load dataset via Hugging Face Datasets...")
+        ds = hf_load_dataset(
+            "Unmeshraj/opensight",
+            data_files="model/dataset_cleaned.csv",
+            split="train"
+        )
+
+        df = ds.to_pandas()
+        print(f"✅ HF dataset loaded: {len(df)} rows")
+        print(f"📊 Columns: {list(df.columns)}")
+        return True
+
+    except Exception as hf_error:
+        print("⚠️ HF dataset load failed, falling back to local CSV")
+        print(hf_error)
+
+    # ---- Attempt 2: Local CSV fallback ----
     try:
         if not os.path.exists(DATASET_PATH):
-            print(f"❌ Dataset not found at: {DATASET_PATH}")
+            print(f"❌ Local dataset not found at: {DATASET_PATH}")
             df = pd.DataFrame()
             return False
-        
+
         df = pd.read_csv(DATASET_PATH)
-        print(f"✅ Dataset loaded: {len(df)} records")
-        print(f"   Columns: {list(df.columns)}")
+        print(f"✅ Local dataset loaded: {len(df)} rows")
+        print(f"📊 Columns: {list(df.columns)}")
         return True
-    except Exception as e:
-        print(f"❌ Error loading dataset: {e}")
+
+    except Exception as local_error:
+        print("❌ Local dataset load failed")
         traceback.print_exc()
         df = pd.DataFrame()
         return False
-
+    
 def load_models():
     """Load trained models with fallback options"""
     global model1, model2, le