Geocode Documentation

Consensus/EsriConnector.py

@@ -178,16 +178,7 @@ async def service_metadata(self, session: aiohttp.ClientSession) -> Dict[str, An
         Returns:
             Dict[str, Any]: The metadata as a JSON object.
         """
-
-        """if not self.layers and not self.tables:
-            service_url = f"{self.url}/0?f=json"
-        elif self.layers and not self.tables:
-            service_url = f"{self.url}/{self.layers[0]['id']}?f=json"
-        elif self.tables and not self.layers:
-            service_url = f"{self.url}/{self.tables[0]['id']}?f=json"
-        else:
-            service_url = f"{self.url}/0?f=json"
-        print(service_url)"""
+
         if self.layers:
             metadata_urls = [f"{self.url}/{layer['id']}?f=json" for layer in self.layers]
         elif self.tables:

Consensus/GeocodeMerger.py

@@ -9,44 +9,48 @@
 The end result is not by any means perfect and you are advised to try different paths and to check that the output makes sense.
 
 Usage:
+------
 
-    This class works as follows.
+This class works as follows.
 
-    Internally, on initialising the class with `await SmartLinker().initialise`, a json lookup file of the available tables in Open Geography Portal is read if the json file exists or created if it is not available.
-    Then, using the information contained in the json file, a graph of connections between table columns is created using the `run_graph()` method. At this point the user provides the names of the starting and ending columns,
-    an optional list of `geographic_areas` and an optional list of columns for the `geographic_area_columns` that the geographic_areas uses to create a subset of data.
+Internally, on initialising the class with `await SmartLinker().initialise`, a json lookup file of the available tables in Open Geography Portal is read if the json file exists or created if it is not available.
+Then, using the information contained in the json file, a graph of connections between table columns is created using the `run_graph()` method. At this point the user provides the names of the starting and ending columns,
+an optional list of `geographic_areas` and an optional list of columns for the `geographic_area_columns` that the geographic_areas uses to create a subset of data.
 
-    Following the creation of the graph, all possible starting points are searched for (i.e., which tables contain the user-provided starting_table). After this, we look for the shortest paths to the ending column.
-    To do this, we look for all possible paths from all starting_columns to ending_columns and count how many steps there are between each table.
-    The `run_graph()` method prints out a numbered list of possible paths.
+Following the creation of the graph, all possible starting points are searched for (i.e., which tables contain the user-provided starting_table). After this, we look for the shortest paths to the ending column.
+To do this, we look for all possible paths from all starting_columns to ending_columns and count how many steps there are between each table.
+The `run_graph()` method prints out a numbered list of possible paths.
 
-    The user can get their chosen data using the `geodata()` method by providing an integer matching their chosen path to the `selected_path` argument.
+The user can get their chosen data using the `geodata()` method by providing an integer matching their chosen path to the `selected_path` argument.
 
-    The intended workflow is:
-    =========================
+Intended workflow
+^^^^^^^^^^^^^^^^^
 
-    First explore the possible geographies.
-    .. code-block:: python
+First explore the possible geographies.
 
-            from Consensus import SmartLinker, GeoHelper
+.. code-block:: python
 
-            gh = GeoHelper()
-            print(gh.geography_keys())
+        from Consensus import SmartLinker, GeoHelper
 
-            print(gh.available_geographies())
+        gh = GeoHelper()
+        print(gh.geography_keys())
 
-            print(gh.geographies_filter('WD'))  # outputs all columns referring to wards.
+        print(gh.available_geographies())
+
+        print(gh.geographies_filter('WD'))  # outputs all columns referring to wards.
+
+Once you've decided you want to look at 2022 wards, you can do the following:
+
+.. code-block:: python
 
-    Once you've decided you want to look at 2022 wards, you can do the following:
-    .. code-block:: python
+    gss = SmartLinker()
+    gss.allow_geometry('geometry_only')  # use this method to restrict the graph search space to tables with geometry
 
-        gss = SmartLinker()
-        gss.allow_geometry('geometry_only')  # use this method to restrict the graph search space to tables with geometry
+    await gss.initialise()
+    gss.run_graph(starting_column='WD22CD', ending_column='LAD22CD', geographic_areas=['Lewisham', 'Southwark'], geographic_area_columns=['LAD22NM'])  # the starting and ending columns should end in CD
+    codes = await gss.geodata(selected_path=9, chunk_size=50)  # the selected path is the ninth in the list of potential paths output by `run_graph()` method. Increase chunk_size if your download is slow and try decreasing it if you are being throttled (or encounter weird errors).
+    print(codes['table_date'][0])  # the output is a dictionary of {'path': [[table1_of_path_1, table2_of_path1], [table1_of_path2, table2_of_path2]], 'table_data':[data_for_path1, data_for_path2]}
 
-        await gss.initialise()
-        gss.run_graph(starting_column='WD22CD', ending_column='LAD22CD', geographic_areas=['Lewisham', 'Southwark'], geographic_area_columns=['LAD22NM'])  # the starting and ending columns should end in CD
-        codes = await gss.geodata(selected_path=9, chunk_size=50)  # the selected path is the ninth in the list of potential paths output by `run_graph()` method. Increase chunk_size if your download is slow and try decreasing it if you are being throttled (or encounter weird errors).
-        print(codes['table_date'][0])  # the output is a dictionary of {'path': [[table1_of_path_1, table2_of_path1], [table1_of_path2, table2_of_path2]], 'table_data':[data_for_path1, data_for_path2]}
 """
 import pandas as pd
 import json

tests/test_ConfigManager.py

@@ -10,10 +10,10 @@
 
 class TestConfigManager(unittest.TestCase):
     def setUp(self) -> None:
-        self.conf_dict = {"nomis_api_key":"xxx",
-                        "proxies.http": "proxy",
-                        "proxies.https": "proxy"}
-        
+        self.conf_dict = {"nomis_api_key": "xxx",
+                          "proxies.http": "proxy",
+                          "proxies.https": "proxy"}
+
         self.conf = ConfigManager()
         self.conf.default_config = self.conf_dict
 
@@ -31,5 +31,6 @@ def test_update(self) -> None:
         self.assertEqual(updated_config['nomis_api_key'], "xxx")
         self.assertNotEqual(loaded_config, updated_config)
 
+
 if __name__ == '__main__':
     unittest.main()