fix: make paths relative and update readme and test

jaanli · Apr 10, 2024 · c7b337e · c7b337e
1 parent 2d6ed41
commit c7b337e
Show file tree

Hide file tree

Showing 113 changed files with 363 additions and 302 deletions.
diff --git a/README.md b/README.md
@@ -53,14 +53,14 @@ A typical Framework project looks like this:
 
 ## Command reference
 
-| Command           | Description                                              |
-| ----------------- | -------------------------------------------------------- |
-| `yarn install`            | Install or reinstall dependencies                        |
-| `yarn dev`        | Start local preview server                               |
-| `yarn build`      | Build your static site, generating `./dist`              |
-| `yarn deploy`     | Deploy your project to Observable                        |
-| `yarn clean`      | Clear the local data loader cache                        |
-| `yarn observable` | Run commands like `observable help`                      |
+| Command           | Description                                 |
+| ----------------- | ------------------------------------------- |
+| `yarn install`    | Install or reinstall dependencies           |
+| `yarn dev`        | Start local preview server                  |
+| `yarn build`      | Build your static site, generating `./dist` |
+| `yarn deploy`     | Deploy your project to Observable           |
+| `yarn clean`      | Clear the local data loader cache           |
+| `yarn observable` | Run commands like `observable help`         |
 
 ## GPT-4 reference
 
@@ -123,22 +123,56 @@ brew install duckdb
 ## Usage for 2022 ACS Public Use Microdata Sample (PUMS) Data
 
 To retrieve the list of URLs from the Census Bureau's server and download and extract the archives for all of the 50 states' PUMS files, run the following:
+
 ```
 cd data_processing
-dbt run --exclude "public_use_microdata_sample.generated+" --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2022/1-Year/", "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2022.csv", "output_path": "~/data/american_community_survey"}'
+dbt run --select "public_use_microdata_sample.list_urls" \
+        --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2021/1-Year/",            "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2021.csv", "output_path": "~/data/american_community_survey"}'
+```
+
+Then save the URLs: 
+
+```
+dbt run --select "public_use_microdata_sample.urls" \                                                
+        --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2021/1-Year/",  "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2021.csv", "output_path": "~/data/american_community_survey"}' \
+        --threads 8
+```
+
+Then execute the dbt model for downloading and extract the archives of the microdata (takes ~2min on a Macbook):
+
+```
+dbt run --select "public_use_microdata_sample.download_and_extract_archives" \                         
+        --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2022/1-Year/",  "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2022.csv", "output_path": "~/data/american_community_survey"}' \
+        --threads 8
+```
+
+Then generate the CSV paths:
+
+```
+dbt run --select "public_use_microdata_sample.csv_paths" \                            
+        --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2021/1-Year/",  "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2022.json", "output_path": "~/data/american_community_survey"}' \
+        --threads 8
+```
+
+Then parse the data dictionary:
+
+```
+dbt run --select "public_use_microdata_sample.parse_data_dictionary" \
+        --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2021/1-Year/",  "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2021.csv", "output_path": "~/data/american_community_survey"}' \
+        --threads 8
 ```
 
 Then generate the SQL commands needed to map every state's individual people or housing unit variables to the easier to use (and read) names:
 
 ```
-python scripts/generate_sql_data_dictionary_mapping_for_extracted_csv_files.py \
-  ~/data/american_community_survey/public_use_microdata_sample_csv_paths.parquet \
-  ~/data/american_community_survey/PUMS_Data_Dictionary_2022.json
+python scripts/generate_sql_with_enum_types_and_mapped_values_renamed.py ~/data/american_community_survey/csv_paths.parquet ~/data/american_community_survey/PUMS_Data_Dictionary_2022.json
 ```
 
 Then execute these generated SQL queries using 1 thread (you can adjust this number to be higher depending on the available processor cores on your system):
 ```
-dbt run --select "public_use_microdata_sample.generated+" --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2022/1-Year/", "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2022.csv", "output_path": "~/data/american_community_survey"}' --threads 1
+dbt run --select "public_use_microdata_sample.generated+" \
+        --vars '{"public_use_microdata_sample_url": "https://www2.census.gov/programs-surveys/acs/data/pums/2022/1-Year/", "public_use_microdata_sample_data_dictionary_url": "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2022.csv", "output_path": "~/data/american_community_survey"}' \
+        --threads 8
 ```
 
 Inspect the output folder to see what has been created in the `output_path` specified in the previous command:

diff --git a/data_processing/models/public_use_microdata_sample/config.yml b/data_processing/models/public_use_microdata_sample/config.yml
@@ -1,27 +1,31 @@
 version: 2
 
 models:
-  - name: list_urls
-    config:
-      public_use_microdata_sample_url: "{{ var('public_use_microdata_sample_url') }}"
-      output_path: "{{ var('output_path') }}"
-  - name: download_and_extract_archives
-    config:
-      public_use_microdata_sample_url: "{{ var('public_use_microdata_sample_url') }}"
-      output_path: "{{ var('output_path') }}"
-  - name: parse_data_dictionary
-    config:
-      public_use_microdata_sample_data_dictionary_url: "{{ var('public_use_microdata_sample_data_dictionary_url') }}"
-      output_path: "{{ var('output_path') }}"
-  - name: list_shapefile_urls
-    config:
-      microdata_area_shapefile_url: "{{ var('microdata_area_shapefile_url') }}"
-      output_path: "{{ var('output_path') }}"
-  - name: download_and_extract_shapefiles
-    config:
-      microdata_area_shapefile_url: "{{ var('microdata_area_shapefile_url') }}"
-      output_path: "{{ var('output_path') }}"
-  - name: combine_shapefiles
-    config:
-      microdata_area_shapefile_url: "{{ var('microdata_area_shapefile_url') }}"
-      output_path: "{{ var('output_path') }}"
+- name: list_urls
+  config:
+    public_use_microdata_sample_url: "{{ var('public_use_microdata_sample_url') }}"
+    output_path: "{{ var('output_path') }}"
+- name: download_and_extract_archives
+  config:
+    public_use_microdata_sample_url: "{{ var('public_use_microdata_sample_url') }}"
+    output_path: "{{ var('output_path') }}"
+- name: csv_paths
+  config:
+    public_use_microdata_sample_url: "{{ var('public_use_microdata_sample_url') }}"
+    output_path: "{{ var('output_path') }}"
+- name: parse_data_dictionary
+  config:
+    public_use_microdata_sample_data_dictionary_url: "{{ var('public_use_microdata_sample_data_dictionary_url') }}"
+    output_path: "{{ var('output_path') }}"
+- name: list_shapefile_urls
+  config:
+    microdata_area_shapefile_url: "{{ var('microdata_area_shapefile_url') }}"
+    output_path: "{{ var('output_path') }}"
+- name: download_and_extract_shapefiles
+  config:
+    microdata_area_shapefile_url: "{{ var('microdata_area_shapefile_url') }}"
+    output_path: "{{ var('output_path') }}"
+- name: combine_shapefiles
+  config:
+    microdata_area_shapefile_url: "{{ var('microdata_area_shapefile_url') }}"
+    output_path: "{{ var('output_path') }}"
diff --git a/data_processing/models/public_use_microdata_sample/download_and_extract_archives.py b/data_processing/models/public_use_microdata_sample/download_and_extract_archives.py
@@ -25,7 +25,7 @@ def model(dbt, session):
     base_url = dbt.config.get('public_use_microdata_sample_url')  # Assuming this is correctly set
 
     # Fetch URLs from your table or view
-    query = "SELECT * FROM list_urls"
+    query = "SELECT * FROM list_urls "
     result = session.execute(query).fetchall()
     columns = [desc[0] for desc in session.description]
     url_df = pd.DataFrame(result, columns=columns)
@@ -50,25 +50,4 @@ def model(dbt, session):
     paths_df = pd.DataFrame(extracted_files, columns=['csv_path'])
 
     # Return the DataFrame with paths to the extracted CSV files
-    return paths_df
-
-# Mock dbt and session for demonstration; replace with actual dbt and session in your environment
-class MockDBT:
-    def config(self, key):
-        return {
-            'public_use_microdata_sample_url': 'https://example.com/path/to/your/csv/files',
-            'output_path': '~/path/to/your/output/directory'
-        }.get(key, '')
-
-class MockSession:
-    def execute(self, query):
-        # Mock response; replace with actual fetching logic
-        return [{"URL": "https://example.com/path/to/your/csv_file.zip"} for _ in range(10)]
-
-dbt = MockDBT()
-session = MockSession()
-
-if __name__ == "__main__":
-    # Directly calling model function for demonstration; integrate properly within your dbt project
-    df = model(dbt, session)
-    print(df)
+    return paths_df
diff --git a/...nerated/2022/enum_types_mapped_renamed/housing_units_alabama_enum_mapped_renamed_2022.sql b/...nerated/2022/enum_types_mapped_renamed/housing_units_alabama_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hal/psam_h01.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hal/psam_h01.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...enerated/2022/enum_types_mapped_renamed/housing_units_alaska_enum_mapped_renamed_2022.sql b/...enerated/2022/enum_types_mapped_renamed/housing_units_alaska_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hak/psam_h02.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hak/psam_h02.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...nerated/2022/enum_types_mapped_renamed/housing_units_arizona_enum_mapped_renamed_2022.sql b/...nerated/2022/enum_types_mapped_renamed/housing_units_arizona_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_haz/psam_h04.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_haz/psam_h04.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...erated/2022/enum_types_mapped_renamed/housing_units_arkansas_enum_mapped_renamed_2022.sql b/...erated/2022/enum_types_mapped_renamed/housing_units_arkansas_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_har/psam_h05.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_har/psam_h05.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...ated/2022/enum_types_mapped_renamed/housing_units_california_enum_mapped_renamed_2022.sql b/...ated/2022/enum_types_mapped_renamed/housing_units_california_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hca/psam_h06.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hca/psam_h06.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...erated/2022/enum_types_mapped_renamed/housing_units_colorado_enum_mapped_renamed_2022.sql b/...erated/2022/enum_types_mapped_renamed/housing_units_colorado_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hco/psam_h08.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hco/psam_h08.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...ted/2022/enum_types_mapped_renamed/housing_units_connecticut_enum_mapped_renamed_2022.sql b/...ted/2022/enum_types_mapped_renamed/housing_units_connecticut_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hct/psam_h09.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hct/psam_h09.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...erated/2022/enum_types_mapped_renamed/housing_units_delaware_enum_mapped_renamed_2022.sql b/...erated/2022/enum_types_mapped_renamed/housing_units_delaware_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hde/psam_h10.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hde/psam_h10.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...enum_types_mapped_renamed/housing_units_district_of_columbia_enum_mapped_renamed_2022.sql b/...enum_types_mapped_renamed/housing_units_district_of_columbia_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hdc/psam_h11.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hdc/psam_h11.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...nerated/2022/enum_types_mapped_renamed/housing_units_florida_enum_mapped_renamed_2022.sql b/...nerated/2022/enum_types_mapped_renamed/housing_units_florida_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hfl/psam_h12.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hfl/psam_h12.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...nerated/2022/enum_types_mapped_renamed/housing_units_georgia_enum_mapped_renamed_2022.sql b/...nerated/2022/enum_types_mapped_renamed/housing_units_georgia_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hga/psam_h13.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hga/psam_h13.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...enerated/2022/enum_types_mapped_renamed/housing_units_hawaii_enum_mapped_renamed_2022.sql b/...enerated/2022/enum_types_mapped_renamed/housing_units_hawaii_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hhi/psam_h15.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hhi/psam_h15.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...generated/2022/enum_types_mapped_renamed/housing_units_idaho_enum_mapped_renamed_2022.sql b/...generated/2022/enum_types_mapped_renamed/housing_units_idaho_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hid/psam_h16.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hid/psam_h16.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...erated/2022/enum_types_mapped_renamed/housing_units_illinois_enum_mapped_renamed_2022.sql b/...erated/2022/enum_types_mapped_renamed/housing_units_illinois_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hil/psam_h17.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hil/psam_h17.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...nerated/2022/enum_types_mapped_renamed/housing_units_indiana_enum_mapped_renamed_2022.sql b/...nerated/2022/enum_types_mapped_renamed/housing_units_indiana_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hin/psam_h18.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hin/psam_h18.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/.../generated/2022/enum_types_mapped_renamed/housing_units_iowa_enum_mapped_renamed_2022.sql b/.../generated/2022/enum_types_mapped_renamed/housing_units_iowa_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hia/psam_h19.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hia/psam_h19.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...enerated/2022/enum_types_mapped_renamed/housing_units_kansas_enum_mapped_renamed_2022.sql b/...enerated/2022/enum_types_mapped_renamed/housing_units_kansas_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hks/psam_h20.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hks/psam_h20.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...erated/2022/enum_types_mapped_renamed/housing_units_kentucky_enum_mapped_renamed_2022.sql b/...erated/2022/enum_types_mapped_renamed/housing_units_kentucky_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hky/psam_h21.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hky/psam_h21.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)
diff --git a/...rated/2022/enum_types_mapped_renamed/housing_units_louisiana_enum_mapped_renamed_2022.sql b/...rated/2022/enum_types_mapped_renamed/housing_units_louisiana_enum_mapped_renamed_2022.sql
@@ -905,7 +905,7 @@ CASE FYRBLTP
     WGTP78::VARCHAR AS "Housing Weight replicate 78",
     WGTP79::VARCHAR AS "Housing Weight replicate 79",
     WGTP80::VARCHAR AS "Housing Weight replicate 80",
-FROM read_csv('/Users/me/data/american_community_survey/2022/1-Year/csv_hla/psam_h22.csv', 
+FROM read_csv('~/data/american_community_survey/2022/1-Year/csv_hla/psam_h22.csv', 
               parallel=False,
               all_varchar=True,
-              auto_detect=True)
+              auto_detect=True)