Merge pull request #31 from Eveerasingam/Eveerasingam-updateAssociatedRepo

Eveerasingam update associated repo

Author: sfc-gh-phachaj

steps/02_access_marketplace_data.sql

@@ -4,5 +4,5 @@ USE ROLE ACCOUNTADMIN;
 SELECT * FROM oag_flight_emissions_data_sample.public.estimated_emissions_schedules_sample LIMIT 100;
 SELECT * FROM oag_flight_status_data_sample.public.flight_status_latest_sample LIMIT 100;
 SELECT * FROM global_weather__climate_data_for_bi.standard_tile.forecast_day LIMIT 100;
-SELECT * FROM global_government.cybersyn.datacommons_timeseries LIMIT 100;
-SELECT * FROM us_addresses__poi.cybersyn.point_of_interest_index LIMIT 100;
+SELECT * FROM SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.DATACOMMONS_TIMESERIES LIMIT 100;
+SELECT * FROM SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.POINT_OF_INTEREST_INDEX LIMIT 100;

steps/03_harmonize_data.py

@@ -150,7 +150,7 @@ def main(df):
         group by postal_code
         """,
     ),
-    # We use the data provided by Cybersyn to limit our pipeline to US cities with atleast
+    # We use the data provided by Snowflake Public Data to limit our pipeline to US cities with atleast
     # 100k residents to enjoy all the benefits a big city provides during our vacation.
     View(
         name="major_us_cities",
@@ -164,10 +164,10 @@ def main(df):
             geo.geo_id, 
             geo.geo_name, 
             max(ts.value) total_population
-        from global_government.cybersyn.datacommons_timeseries ts
-        join global_government.cybersyn.geography_index geo 
+        from SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.DATACOMMONS_TIMESERIES ts
+        join SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.GEOGRAPHY_INDEX geo 
             on ts.geo_id = geo.geo_id
-        join global_government.cybersyn.geography_relationships geo_rel 
+        join SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.GEOGRAPHY_RELATIONSHIPS geo_rel 
             on geo_rel.related_geo_id = geo.geo_id
         where true
             and ts.variable_name = 'Total Population, census.gov'
@@ -179,7 +179,7 @@ def main(df):
         order by total_population desc
         """,
     ),
-    # Using the geography relationships provided by Cybersyn we collect all the
+    # Using the geography relationships provided by Snowflake Public Data we collect all the
     # zip codes belonging to a city.
     View(
         name="zip_codes_in_city",
@@ -195,8 +195,8 @@ def main(df):
             city.geo_name city_geo_name, 
             city.related_geo_id zip_geo_id, 
             city.related_geo_name zip_geo_name
-        from us_addresses__poi.cybersyn.geography_relationships country
-        join us_addresses__poi.cybersyn.geography_relationships city 
+        from SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.GEOGRAPHY_RELATIONSHIPS country
+        join SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.GEOGRAPHY_RELATIONSHIPS city 
             on country.related_geo_id = city.geo_id
         where true
             and country.geo_id = 'country/USA'

steps/05_database_change_management.sh

@@ -20,10 +20,10 @@ View(
         count(case when category_main = 'Aquarium' THEN 1 END) aquarium_cnt,
         count(case when category_main = 'Zoo' THEN 1 END) zoo_cnt,
         count(case when category_main = 'Korean Restaurant' THEN 1 END) korean_restaurant_cnt,
-    from us_addresses__poi.cybersyn.point_of_interest_index poi
-    join us_addresses__poi.cybersyn.point_of_interest_addresses_relationships poi_add 
+    from SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.POINT_OF_INTEREST_INDEX poi
+    join SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.POINT_OF_INTEREST_ADDRESSES_RELATIONSHIPS poi_add 
         on poi_add.poi_id = poi.poi_id
-    join us_addresses__poi.cybersyn.us_addresses address 
+    join SNOWFLAKE_PUBLIC_DATA_FREE.PUBLIC_DATA_FREE.US_ADDRESSES address 
         on address.address_id = poi_add.address_id
     join major_us_cities city on city.geo_id = address.id_city
     where true