Create utils2.py

utils2.py

@@ -0,0 +1,83 @@
+from collections import Counter
+import pandas as pd
+import numpy as np
+from scipy.spatial import cKDTree
+
+
+df_amenities = pd.read_csv("df_indonesia.csv").rename(
+    columns={"latitude":"lat", "longitude":"lon"}
+)
+df_banks = pd.read_csv("df_bank_indonesia.csv").rename(
+    columns={"latitude":"lat", "longitude":"lon"}
+)
+
+df_amenities["fsq_category_labels"] = df_amenities["fsq_category_labels"].apply(
+    lambda x: eval(x)
+)
+
+bank_coords = df_banks[['lat','lon']].values
+tree_banks = cKDTree(bank_coords)
+
+amenity_coords = df_amenities[['lat','lon']].values
+tree_amenities = cKDTree(amenity_coords)
+
+DATASET_COLUMNS = [
+    'Dining and Drinking', 'Community and Government', 'Retail',
+       'Business and Professional Services', 'Landmarks and Outdoors',
+       'Arts and Entertainment', 'Health and Medicine',
+       'Travel and Transportation', 'Sports and Recreation',
+       'Event'
+]
+
+def compute_features(candidate_point, radius=0.005):
+    lat, lon = candidate_point
+
+    # Banks
+    bank_idxs = tree_banks.query_ball_point([lat, lon], r=radius)
+
+    print("[BANK]", bank_idxs)
+    
+    n_banks = len(bank_idxs)
+    if n_banks > 0:
+        neighbors = df_banks.iloc[bank_idxs]
+        mean_dist_banks = np.mean(np.sqrt((neighbors['lat']-lat)**2 + (neighbors['lon']-lon)**2))
+        min_dist_bank = np.min(np.sqrt((neighbors['lat']-lat)**2 + (neighbors['lon']-lon)**2))
+    else:
+        mean_dist_banks = radius
+        min_dist_bank = radius
+
+    # Amenities
+    amenity_idxs = tree_amenities.query_ball_point([lat, lon], r=radius)
+    amenities = df_amenities.iloc[amenity_idxs]
+
+    total_amenities = len(amenities)
+
+    # Flatten all category IDs
+    # for cats in amenities['fsq_category_labels']:
+    all_category_ids = [cats[0].split(">")[0].strip() for cats in amenities['fsq_category_labels'] if len(cats)>0]
+    category_diversity = len(set(all_category_ids))
+
+    features = {
+        'num_banks_in_radius': n_banks,
+        # 'mean_dist_banks': mean_dist_banks,
+        # 'min_dist_bank': min_dist_bank,
+        'total_amenities': total_amenities,
+        'category_diversity': category_diversity
+    }
+
+    # Count occurrences per category
+    print("[CATEGORIES]", all_category_ids)
+    count_per_category = Counter(all_category_ids)
+    for feat in DATASET_COLUMNS:
+        print("[FEAT]",feat)
+    # for cat, cnt in count_per_category.items():
+        features[f'num_{feat}'] = count_per_category.get(feat, 0)
+
+    
+    # # Count occurrences of first category
+    # first_categories = [cats[0] for cats in amenities['fsq_category_ids'] if len(cats)>0]
+    # count_first_category = Counter(first_categories)
+    # for cat, cnt in count_first_category.items():
+    #     features[f'num_first_{cat}'] = cnt
+
+    return features