Merge pull request #30 from NSAPH-Data-Processing/convert_gpkg_to_shp

notes script to convert gpkg to shp file

Author: audiracmichelle

notes/global_eda.ipynb

@@ -0,0 +1,30 @@
+import geopandas as gpd
+import os
+import argparse
+import fiona
+
+def convert_gpkg_to_shp(input_dir, output_dir):
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+
+    for filename in os.listdir(input_dir):
+        if filename.endswith(".gpkg"):
+            gpkg_path = os.path.join(input_dir, filename)
+            layers = fiona.listlayers(gpkg_path)
+            
+            for layer_name in layers:
+                layer_gdf = gpd.read_file(gpkg_path, layer=layer_name)
+                layer_output_dir = os.path.join(output_dir, os.path.splitext(filename)[0])
+                if not os.path.exists(layer_output_dir):
+                    os.makedirs(layer_output_dir)
+                layer_output_path = os.path.join(layer_output_dir, f"{layer_name}.shp")
+                layer_gdf.to_file(layer_output_path, driver='ESRI Shapefile')
+                print(f"Saved {layer_name} to {layer_output_path}")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Convert GeoPackage files to Shapefiles")
+    parser.add_argument("--input_dir", help="Directory containing .gpkg files")
+    parser.add_argument("--output_dir", help="Directory to save the converted .shp files")
+    args = parser.parse_args()
+
+    convert_gpkg_to_shp(args.input_dir, args.output_dir)

utils/__init__.py

@@ -0,0 +1,24 @@
+import geopandas as gpd
+import matplotlib.pyplot as plt
+import os
+import argparse
+
+def plot_shapefiles(input_dir):
+    fig, ax = plt.subplots(figsize=(10, 10))
+
+    for root, _, files in os.walk(input_dir):
+        for file in files:
+            if file.endswith(".shp"):
+                shapefile_path = os.path.join(root, file)
+                gdf = gpd.read_file(shapefile_path)
+                gdf.plot(ax=ax, label=file)
+    
+    plt.legend()
+    plt.show()
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Plot multiple shapefiles")
+    parser.add_argument("input_dir", help="Directory containing .shp files")
+    args = parser.parse_args()
+
+    plot_shapefiles(args.input_dir)