From 524e1bf8bc4f42aab5322960ee875ca7e8ec186b Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 16:45:01 -0500
Subject: [PATCH 1/7] Update lib.py

Adding COVID Vaccination Data
---
 fetcher/lib.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/fetcher/lib.py b/fetcher/lib.py
index a2a0418..742119a 100644
--- a/fetcher/lib.py
+++ b/fetcher/lib.py
@@ -3,6 +3,8 @@
 import typing
 import hydra
 import pandas as pd
+import os
+import urllib.request
 
 from fetcher.utils import Fields
 from fetcher.source_utils import fetch_source, process_source_responses
@@ -13,6 +15,8 @@
 TS = 'TIMESTAMP'
 STATE = Fields.STATE.name
 
+site_url = "https://raw.githubusercontent.com/govex/COVID-19/master/data_tables/vaccine_data/raw_data" \
+           "/vaccine_data_us_state_timeline.csv "
 
 class Fetcher:
     def __init__(self, cfg):
@@ -169,6 +173,14 @@ def save_df_to_db(db_config, df):
     engine = create_engine(engine_conf)
     df.to_sql(db_config.table, engine, if_exists='append', chunksize=200, method='multi')
 
+def get_covid_vaccination_data(outputdir):
+    """Download COVID Vaccination data in CSV format
+    """
+    if os.path.exists(outputdir + '/' + 'covid_vaccination_US.csv'):
+        os.remove(outputdir + '/' + 'covid_vaccination_US.csv')
+
+    urllib.request.urlretrieve(site_url, os.path.join(outputdir, 'covid_vaccination_US.csv'))
+
 
 @hydra.main(config_path='..', config_name="config")
 def main(cfg):
@@ -184,5 +196,8 @@ def main(cfg):
     df = build_dataframe(results, cfg.state, cfg.dataset, cfg.output_date_format, cfg.output)
     print(df)
 
+    # get vaccination data	
+    get_covid_vaccination_data(cfg.outputs)
+	
     if 'db' in cfg.dataset and cfg.dataset.db.store:
         save_df_to_db(cfg.dataset.db, df)

From 7b660971a9b96dd355c27572340e0755bbe0a55f Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 16:46:20 -0500
Subject: [PATCH 2/7] Update run.sh

Adding COVID Vaccination data
---
 bin/run.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/bin/run.sh b/bin/run.sh
index 6a8b3b3..29e9087 100755
--- a/bin/run.sh
+++ b/bin/run.sh
@@ -18,3 +18,4 @@ fi
 # run fetch
 conda run -n c19-data python get_my_data.py dataset=states
 conda run -n c19-data python tools/push_to_spreadsheet.py push.spreadsheet_id=1brHKBhqiXkkLyiDTDfaBK-tms-R4KVkI-NPFfFZwqYk push.sheet_id=0 push.file=outputs/states.csv creds.type=service creds.key_filepath=../creds/credentials.json
+conda run -n c19-data python tools/push_to_spreadsheet.py push.spreadsheet_id=1brHKBhqiXkkLyiDTDfaBK-tms-R4KVkI-NPFfFZwqYk push.sheet_id=289169575 push.file=outputs/covid_vaccination_US.csv creds.type=service creds.key_filepath=../creds/credentials.json

From 39ce00ce44445ad3693a56bd876d387bd0e00566 Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 16:47:20 -0500
Subject: [PATCH 3/7] Update config.yaml

Adding COVID Vaccination data
---
 config.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/config.yaml b/config.yaml
index bfabd40..29006b7 100644
--- a/config.yaml
+++ b/config.yaml
@@ -28,6 +28,7 @@ dataset:
 output: ${dataset.name}
 data_root: ${hydra:runtime.cwd}/dataset/${dataset.name}
 output_date_format: "%Y%m%d"
+outputs: ${hydra:runtime.cwd}/outputs
 
 # fetch a single state (or a list)
 state: ['AK', 'AL', 'AR', 'AS', 'AZ', 'CA', 'CO', 'CT', 'DC', 'DE', 'FL', 'GA', 'GU',

From b2c23930df3557035f702784e49fcaf6b6862a8b Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 17:03:42 -0500
Subject: [PATCH 4/7] Update config.yaml

Added extra line as per build verification
---
 config.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/config.yaml b/config.yaml
index 29006b7..264aaec 100644
--- a/config.yaml
+++ b/config.yaml
@@ -30,6 +30,7 @@ data_root: ${hydra:runtime.cwd}/dataset/${dataset.name}
 output_date_format: "%Y%m%d"
 outputs: ${hydra:runtime.cwd}/outputs
 
+
 # fetch a single state (or a list)
 state: ['AK', 'AL', 'AR', 'AS', 'AZ', 'CA', 'CO', 'CT', 'DC', 'DE', 'FL', 'GA', 'GU',
         'HI', 'IA', 'ID', 'IL', 'IN', 'KS', 'KY', 'LA', 'MA', 'MD', 'ME', 'MI',

From 49b9eb80a496b6592e3c80a91507bc2cccc038cc Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 17:12:32 -0500
Subject: [PATCH 5/7] Update lib.py

---
 fetcher/lib.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fetcher/lib.py b/fetcher/lib.py
index 742119a..4066bb3 100644
--- a/fetcher/lib.py
+++ b/fetcher/lib.py
@@ -10,7 +10,6 @@
 from fetcher.source_utils import fetch_source, process_source_responses
 from fetcher.sources import build_sources
 
-
 # Indices
 TS = 'TIMESTAMP'
 STATE = Fields.STATE.name
@@ -18,6 +17,7 @@
 site_url = "https://raw.githubusercontent.com/govex/COVID-19/master/data_tables/vaccine_data/raw_data" \
            "/vaccine_data_us_state_timeline.csv "
 
+
 class Fetcher:
     def __init__(self, cfg):
         '''Initialize source information'''
@@ -173,6 +173,7 @@ def save_df_to_db(db_config, df):
     engine = create_engine(engine_conf)
     df.to_sql(db_config.table, engine, if_exists='append', chunksize=200, method='multi')
 
+
 def get_covid_vaccination_data(outputdir):
     """Download COVID Vaccination data in CSV format
     """
@@ -198,6 +199,6 @@ def main(cfg):
 
     # get vaccination data	
     get_covid_vaccination_data(cfg.outputs)
-	
+
     if 'db' in cfg.dataset and cfg.dataset.db.store:
         save_df_to_db(cfg.dataset.db, df)

From 97ffa4d0ba83f86885c7f28dc5c37e622d1d58c0 Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 17:18:33 -0500
Subject: [PATCH 6/7] Update lib.py

---
 fetcher/lib.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fetcher/lib.py b/fetcher/lib.py
index 4066bb3..783b7b0 100644
--- a/fetcher/lib.py
+++ b/fetcher/lib.py
@@ -196,8 +196,7 @@ def main(cfg):
     # This stores the CSV with the requsted fields in order
     df = build_dataframe(results, cfg.state, cfg.dataset, cfg.output_date_format, cfg.output)
     print(df)
-
-    # get vaccination data	
+	
     get_covid_vaccination_data(cfg.outputs)
 
     if 'db' in cfg.dataset and cfg.dataset.db.store:

From bd081f1b99f77a421205e5190f42d5f2ac3b6627 Mon Sep 17 00:00:00 2001
From: mgithub46 <76885622+mgithub46@users.noreply.github.com>
Date: Sat, 2 Jan 2021 17:27:51 -0500
Subject: [PATCH 7/7] Update lib.py

---
 fetcher/lib.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fetcher/lib.py b/fetcher/lib.py
index 783b7b0..6d3be9c 100644
--- a/fetcher/lib.py
+++ b/fetcher/lib.py
@@ -196,7 +196,6 @@ def main(cfg):
     # This stores the CSV with the requsted fields in order
     df = build_dataframe(results, cfg.state, cfg.dataset, cfg.output_date_format, cfg.output)
     print(df)
-	
     get_covid_vaccination_data(cfg.outputs)
 
     if 'db' in cfg.dataset and cfg.dataset.db.store: