From 1730572aa669ee4ec1ecceef3ec00cc7daa1c51b Mon Sep 17 00:00:00 2001
From: Jorge Escobar <83969469+esfoobar-usds@users.noreply.github.com>
Date: Wed, 9 Mar 2022 08:55:17 -0500
Subject: [PATCH] Reducing Docker start up and adding ArcGIS URL (#1386)

* Reducing Docker start up and adding ArcGIS URL

* Updating ArcGIS URLs
---
 data/data-pipeline/README.md                  |  5 +++
 .../data_pipeline/application.py              | 42 ++++++++++---------
 2 files changed, 27 insertions(+), 20 deletions(-)

diff --git a/data/data-pipeline/README.md b/data/data-pipeline/README.md
index 243ef6b6..a4e60e5d 100644
--- a/data/data-pipeline/README.md
+++ b/data/data-pipeline/README.md
@@ -81,6 +81,11 @@ The CSV with the combined data from all of these sources [can be accessed here](
 
 Once we have all the data from the previous stages, we convert it to tiles to make it usable on a map. We render the map on the client side which can be seen using `docker-compose up`.
 
+#### 5. Shapefiles
+
+If you want to use the shapefiles in mapping applications, you can access them here [shp](https://justice40-data.s3.amazonaws.com/data-pipeline/data/score/shapefile/usa.shp) and [shx](https://justice40-data.s3.amazonaws.com/data-pipeline/data/score/shapefile/usa.shx).
+
+
 ### Score generation and comparison workflow
 
 The descriptions below provide a more detailed outline of what happens at each step of ETL and score calculation workflow.
diff --git a/data/data-pipeline/data_pipeline/application.py b/data/data-pipeline/data_pipeline/application.py
index 10f038f2..cd4e5e96 100644
--- a/data/data-pipeline/data_pipeline/application.py
+++ b/data/data-pipeline/data_pipeline/application.py
@@ -239,31 +239,33 @@ def data_full_run(check: bool, data_source: str):
     """
     data_path = settings.APP_ROOT / "data"
 
-    if check and not check_first_run():
-        # check if the data full run has been run before
-        logger.info("*** The data full run was already executed")
-        sys.exit()
+    if check:
+        if not check_first_run():
+            # check if the data full run has been run before
+            logger.info("*** The data full run was already executed")
+            sys.exit()
 
-    # census directories
-    logger.info("*** Initializing all data folders")
-    census_reset(data_path)
-    data_folder_cleanup()
-    score_folder_cleanup()
-    temp_folder_cleanup()
+    else:
+        # census directories
+        logger.info("*** Initializing all data folders")
+        census_reset(data_path)
+        data_folder_cleanup()
+        score_folder_cleanup()
+        temp_folder_cleanup()
 
-    if data_source == "local":
-        logger.info("*** Downloading census data")
-        etl_runner("census")
+        if data_source == "local":
+            logger.info("*** Downloading census data")
+            etl_runner("census")
 
-    logger.info("*** Running all ETLs")
-    etl_runner()
+        logger.info("*** Running all ETLs")
+        etl_runner()
 
-    logger.info("*** Generating Score")
-    score_generate()
+        logger.info("*** Generating Score")
+        score_generate()
 
-    logger.info("*** Running Post Score scripts")
-    downloadable_cleanup()
-    score_post(data_source)
+        logger.info("*** Running Post Score scripts")
+        downloadable_cleanup()
+        score_post(data_source)
 
     logger.info("*** Combining Score with Census Geojson")
     score_geo(data_source)