add docs

Author: cjber

.dvc/config

@@ -13,4 +13,5 @@ routing:
 	- python -m ahah.routing
 
 docs:
-	pdoc --html --force --output-dir docs ahah
+	pdoc --html --force --output-dir docs ahah \
+		&& mv -f docs/ahah/* docs

.dvcignore

@@ -33,7 +33,7 @@ Liverpool, United Kingdom_
 
 This project identifies the time-weighted distance required to travel by road between every postcode in Great Britain and a selection of health related points of interest. A ranked combination of these drive-times is used to create the AHAH index.
 
-Access is defined through the average time-weighted road network distance for each postcode within each LSOA to the nearest point of interest of a particular type. For this, the road highways network and road speed estimates provided through [Ordnance Survey](https://www.ordnancesurvey.co.uk/business-government/products/open-map-roads) was used, alongside the [ONS Postcode Directory for May 2020](https://data.gov.uk/dataset/06803af0-6054-410a-822a-f7ab30bcd8b1/ons-postcode-directory-may-2020), which gives centroids for every postcode in the country.
+Access is defined through the average time-weighted road network distance for each postcode within each LSOA to the nearest point of interest of a particular type. For this, the road highways network and road speed estimates provided through [Ordnance Survey](https://www.ordnancesurvey.co.uk/business-government/products/open-map-roads) was used, alongside the [OWNS Postcode Directory for May 2020](https://data.gov.uk/dataset/06803af0-6054-410a-822a-f7ab30bcd8b1/ons-postcode-directory-may-2020), which gives centroids for every postcode in the country.
 
 This is a computationally intense calculation, with the total road network used having 3,816,897 edges, and 3,215,522 nodes. Access to each nearest health related POI was calculated using the _Single Source Shortest Path_ algorithm, for all 1,659,451 postcodes in Great Britain.
 
@@ -112,12 +112,13 @@ ahah
 
 - [OS
   Open Roads](https://www.ordnancesurvey.co.uk/business-government/products/open-map-roads)
+- [Ferry Routes](https://www.ordnancesurvey.co.uk/business-government/products/strategi)
 - [Air quality](https://uk-air.defra.gov.uk/data/pcm-data)
-- [Greenspace](https://osdatahub.os.uk/downloads/open/OpenGreenspace)
-- [LSOA
-  Polygons](https://borders.ukdataservice.ac.uk/easy_download_data.html?data=England_lsoa_2011)
+- Greenspace (NDVI Classification)
 - [NHS
   England](https://digital.nhs.uk/services/organisation-data-service/data-downloads)
 - [NHS Scotland](https://www.opendata.nhs.scot/dataset/)
-- [Postcodes](<https://geoportal.statistics.gov.uk/search?collection=Dataset&sort=name&tags=all(PRD_ONSPD%2CFEB_2021)>)
-- NDVI (Private)
+
+- [Postcodes](https://geoportal.statistics.gov.uk/datasets/ons-postcode-directory-february-2022/about)
+- [LSOA
+  Polygons](https://borders.ukdataservice.ac.uk/easy_download_data.html?data=England_lsoa_2011)

Dockerfile

@@ -38,19 +38,15 @@ <h1 class="title">Module <code>ahah.aggregate_lsoa</code></h1>
 
 def read_dists(dist_files: Generator, pcs: cudf.DataFrame, ndvi) -&gt; pd.DataFrame:
     dfs = (
-        cudf.concat(
-            [
-                cudf.read_csv(file)
-                .drop_duplicates(&#34;postcode&#34;)
-                .set_index(&#34;postcode&#34;)
-                .rename(columns={&#34;distance&#34;: re.split(r&#34;_|\.&#34;, file.name)[1]})
-                for file in dist_files
-            ],
-            axis=1,
-        )
-        .reset_index()
-        .pipe(fix_postcodes)
+        [
+            cudf.read_csv(file)
+            .drop_duplicates(&#34;postcode&#34;)
+            .set_index(&#34;postcode&#34;)
+            .rename(columns={&#34;distance&#34;: re.split(r&#34;_|\.&#34;, file.name)[1]})
+            for file in dist_files
+        ],
     )
+    dfs = cudf.concat(dfs, axis=1).reset_index().pipe(fix_postcodes)
 
     return (
         dfs.set_index(&#34;postcode&#34;)
@@ -99,19 +95,15 @@ <h2 class="section-title" id="header-functions">Functions</h2>
 </summary>
 <pre><code class="python">def read_dists(dist_files: Generator, pcs: cudf.DataFrame, ndvi) -&gt; pd.DataFrame:
     dfs = (
-        cudf.concat(
-            [
-                cudf.read_csv(file)
-                .drop_duplicates(&#34;postcode&#34;)
-                .set_index(&#34;postcode&#34;)
-                .rename(columns={&#34;distance&#34;: re.split(r&#34;_|\.&#34;, file.name)[1]})
-                for file in dist_files
-            ],
-            axis=1,
-        )
-        .reset_index()
-        .pipe(fix_postcodes)
+        [
+            cudf.read_csv(file)
+            .drop_duplicates(&#34;postcode&#34;)
+            .set_index(&#34;postcode&#34;)
+            .rename(columns={&#34;distance&#34;: re.split(r&#34;_|\.&#34;, file.name)[1]})
+            for file in dist_files
+        ],
     )
+    dfs = cudf.concat(dfs, axis=1).reset_index().pipe(fix_postcodes)
 
     return (
         dfs.set_index(&#34;postcode&#34;)