Fix critical bugs in documentation and library code

## Documentation Fixes
- Fixed Toronto CMA region code from '535' to '35535' in getting_started.md
- Added labels="short" to all get_census calls in working_with_geometry.md
- Removed all sample data fallbacks from tutorials and examples

## Library Bugs Fixed

### 1. labels="short" not working with cached data
- **Bug**: When data was returned from cache, the labels parameter was ignored
- **Fix**: Call _extract_vector_metadata() on cached data in core.py:121
- **Impact**: Vector columns now correctly named 'v_CA21_1' instead of 'v_CA21_1: Population, 2021'

### 2. Missing CRS in GeoDataFrames
- **Bug**: GeoDataFrames had CRS=None, causing incorrect area calculations
- **Fix**: Explicitly set crs="EPSG:4326" when creating GeoDataFrame in core.py:446
- **Impact**: Geographic operations now work correctly with proper coordinate system

## Build Results
- Documentation builds successfully with visualizations now displaying
- All tutorials execute without errors
- Maps and plots now render correctly in HTML output

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: dshkol

docs/api/generated/pycancensus.dataset_attribution.rst

@@ -0,0 +1,6 @@
+pycancensus.dataset\_attribution
+================================
+
+.. currentmodule:: pycancensus
+
+.. autofunction:: dataset_attribution

docs/api/generated/pycancensus.get_intersecting_geometries.rst

@@ -0,0 +1,6 @@
+pycancensus.get\_intersecting\_geometries
+=========================================
+
+.. currentmodule:: pycancensus
+
+.. autofunction:: get_intersecting_geometries

docs/api/generated/pycancensus.label_vectors.rst

@@ -0,0 +1,6 @@
+pycancensus.label\_vectors
+==========================
+
+.. currentmodule:: pycancensus
+
+.. autofunction:: label_vectors

docs/examples/plot_geographic_analysis.py

@@ -41,28 +41,7 @@
 
 except Exception as e:
     print(f"Error retrieving data: {e}")
-    print("Creating sample data for demonstration...")
-    
-    # Create sample data for demonstration when API is not available
-    import numpy as np
-    from shapely.geometry import Point
-    import geopandas as gpd
-    
-    # Sample coordinates around Vancouver area
-    n_points = 50
-    np.random.seed(42)
-    lons = np.random.uniform(-123.3, -122.9, n_points)
-    lats = np.random.uniform(49.15, 49.35, n_points)
-    
-    geo_data = gpd.GeoDataFrame({
-        'GeoUID': [f'59933{i:03d}' for i in range(n_points)],
-        'name': [f'Census Tract {i}' for i in range(n_points)],
-        'v_CA21_1': np.random.randint(1000, 8000, n_points),  # Population
-        'v_CA21_434': np.random.randint(30000, 120000, n_points),  # Median income
-        'geometry': [Point(lon, lat) for lon, lat in zip(lons, lats)]
-    }, crs='EPSG:4326')
-    
-    print("Using sample data for demonstration")
+    raise  # Fail if API call doesn't work - no fallbacks
 
 # %%
 # Creating a Basic Map

docs/tutorials/getting_started.md

@@ -154,7 +154,7 @@ try:
     # Get real data for Toronto CMA using our income hierarchy vectors
     toronto_data = get_census(
         dataset='CA21',
-        regions={'CMA': '535'},  # Toronto CMA
+        regions={'CMA': '35535'},  # Toronto CMA
         vectors=['v_CA21_923', 'v_CA21_939', 'v_CA21_942', 'v_CA21_943'],  # Income categories
         level='CMA',
         use_cache=False

docs/tutorials/working_with_geometry.md

@@ -29,8 +29,10 @@ import pycancensus as pc
 import pandas as pd
 import matplotlib.pyplot as plt
 import geopandas as gpd
+from IPython.display import display
 
-# Set up plotting
+# Set up plotting for notebook display
+%matplotlib inline
 plt.style.use('default')
 plt.rcParams['figure.figsize'] = (12, 8)
 
@@ -70,41 +72,19 @@ try:
         regions={"CMA": "59933"},  # Vancouver CMA
         vectors=["v_CA21_1", "v_CA21_434"],  # Population and median income
         level="CSD",  # Municipality level
-        geo_format="geopandas"
+        geo_format="geopandas",
+        labels="short"
     )
     
     print(f"Retrieved data for {len(vancouver_data)} municipalities")
-    print(f"Columns: {list(vancouver_data.columns)}")
     print(f"CRS: {vancouver_data.crs}")
-    
+
     # Show sample data
     display(vancouver_data[['name', 'v_CA21_1', 'v_CA21_434']].head())
     
 except Exception as e:
     print(f"Error retrieving data: {e}")
-    print("Creating sample data for demonstration...")
-    
-    # Create sample data when API is not available
-    import numpy as np
-    from shapely.geometry import Polygon
-    
-    # Sample Vancouver area municipalities
-    municipalities = [
-        'Vancouver', 'Surrey', 'Burnaby', 'Richmond', 'Coquitlam',
-        'Langley', 'North Vancouver', 'West Vancouver', 'New Westminster'
-    ]
-    
-    np.random.seed(42)
-    vancouver_data = gpd.GeoDataFrame({
-        'GeoUID': [f'59933{i:02d}' for i in range(len(municipalities))],
-        'name': municipalities,
-        'v_CA21_1': np.random.randint(50000, 650000, len(municipalities)),
-        'v_CA21_434': np.random.randint(40000, 100000, len(municipalities)),
-        'geometry': [Polygon([(i, j), (i+1, j), (i+1, j+1), (i, j+1)]) 
-                    for i, j in enumerate(range(len(municipalities)))]
-    }, crs='EPSG:4326')
-    
-    print("Using sample data for demonstration")
+    raise  # Fail if API call doesn't work - no fallbacks
 ```
 
 ## Creating Basic Maps
@@ -129,7 +109,7 @@ ax.set_title('Population by Municipality\nVancouver CMA, 2021', fontsize=16)
 ax.axis('off')  # Remove axes for cleaner look
 
 plt.tight_layout()
-fig  # Display the figure
+display(fig)
 ```
 
 ## Multi-Variable Mapping
@@ -167,7 +147,7 @@ ax2.axis('off')
 
 plt.suptitle('Vancouver CMA: Population vs Income', fontsize=16, y=1.02)
 plt.tight_layout()
-fig  # Display the figure
+display(fig)
 ```
 
 ## Working with Different Geographic Levels
@@ -190,7 +170,8 @@ try:
                 dataset="CA21",
                 regions={"CMA": "59933"},
                 vectors=["v_CA21_1"],
-                level=level
+                level=level,
+                labels="short"
             )
             print(f"{name:15} ({level}): {len(data):4,} regions")
         except Exception as e:
@@ -228,17 +209,11 @@ try:
     boundaries.plot(ax=ax, edgecolor='blue', facecolor='lightblue', alpha=0.7)
     ax.set_title('Vancouver CMA Municipal Boundaries')
     ax.axis('off')
-    fig  # Display the figure
+    display(fig)
     
 except Exception as e:
     print(f"Error getting boundaries: {e}")
-    
-    # Use our sample data
-    fig, ax = plt.subplots(1, 1, figsize=(10, 8))
-    vancouver_data.boundary.plot(ax=ax, color='blue', linewidth=2)
-    ax.set_title('Sample Municipal Boundaries')
-    ax.axis('off')
-    fig  # Display the figure
+    raise  # Fail if API call doesn't work - no fallbacks
 ```
 
 ## Spatial Analysis

pycancensus/core.py

@@ -117,6 +117,8 @@ def get_census(
         if cached_data is not None:
             if not quiet:
                 print(f"Reading data from cache...")
+            # Process labels for cached data
+            cached_data = _extract_vector_metadata(cached_data, vectors, labels)
             return cached_data
 
     # Build API request exactly like the R package
@@ -441,7 +443,7 @@ def _process_geojson_response(data, vectors, labels):
     if "features" not in data:
         raise ValueError("Invalid GeoJSON response: missing 'features' field")
 
-    gdf = gpd.GeoDataFrame.from_features(data["features"])
+    gdf = gpd.GeoDataFrame.from_features(data["features"], crs="EPSG:4326")
 
     # Apply the same numeric conversion logic as CSV processing
     # This was missing and causing all columns to remain as strings