Skip to content
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ variableMeasured: dcs:Mean_Concentration_AirPollutant_PM2.5
Node: E:PM25CountyPollution->E2
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PPM25CountyPollution->date
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_med_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
Node: E:PM25CountyPollution->E1
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_mean_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Mean_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E2
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_med_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Median_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E3
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_max_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Max_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E4
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_pop_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:PopulationWeighted_Concentration_AirPollutant_PM2.5
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
Node: E:PM25CountyPollution->E1
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_mean_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Mean_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E2
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_med_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Median_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E3
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_max_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Max_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E4
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_pop_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:PopulationWeighted_Concentration_AirPollutant_PM2.5
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
Node: E:PM25CountyPollution->E1
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_mean_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Mean_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E2
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_med_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Median_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E3
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_max_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Max_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E4
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_pop_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:PopulationWeighted_Concentration_AirPollutant_PM2.5
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
Node: E:PM25CountyPollution->E1
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_mean_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Mean_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E2
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_med_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Median_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E3
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_max_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:Max_Concentration_AirPollutant_PM2.5

Node: E:PM25CountyPollution->E4
observationAbout: C:PM25CountyPollution->dcid
typeOf: dcs:StatVarObservation
observationDate: C:PM25CountyPollution->date
value: C:PM25CountyPollution->pm25_pop_pred
observationPeriod: "P24H"
unit: MicrogramsPerCubicMeter
variableMeasured: dcs:PopulationWeighted_Concentration_AirPollutant_PM2.5
20 changes: 7 additions & 13 deletions scripts/us_cdc/environmental_health_toxicology/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -69,19 +69,13 @@ These data were collected as part of the [CDC National Environment Public Health
[`small_Palmer_expected.csv`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/test_data/small_Palmer_expected.csv)

#### tMCFs
[`OzoneCensusTractPollution.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCensusTractPollution.tmcf)

[`OzoneCountyPollution.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCountyPollution.tmcf)

[`PalmerDroughtSeverityIndex.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PalmerDroughtSeverityIndex.tmcf)

[`PM25CensusTractPollution.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CensusTractPollution.tmcf)

[`PM25CountyPollution.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CountyPollution.tmcf)

[`StandardizedPrecipitationEvapotranspirationIndex.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/StandardizedPrecipitationEvapotranspirationIndex.tmcf)

[`StandardizedPrecipitationIndex.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/StandardizedPrecipitationIndex.tmcf)
* [`OzoneCountyPollution.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCountyPollution.tmcf)
* **Sharded PM2.5 County tMCFs:** [`PM25CountyPollution_part1.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CountyPollution_part1.tmcf), [`part2`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CountyPollution_part2.tmcf), [`part3`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CountyPollution_part3.tmcf), [`part4`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CountyPollution_part4.tmcf)
* **Sharded PM2.5 Census Tract tMCFs:** [`PM25CensusTractPollution_part1.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CensusTractPollution_part1.tmcf), [`part2`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CensusTractPollution_part2.tmcf), [`part3`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CensusTractPollution_part3.tmcf), [`part4`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PM25CensusTractPollution_part4.tmcf)
* **Sharded Ozone Census Tract tMCFs:** [`OzoneCensusTractPollution_part1.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCensusTractPollution_part1.tmcf), [`part2`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCensusTractPollution_part2.tmcf), [`part3`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCensusTractPollution_part3.tmcf), [`part4`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/OzoneCensusTractPollution_part4.tmcf)
* [`PalmerDroughtSeverityIndex.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/PalmerDroughtSeverityIndex.tmcf)
* [`StandardizedPrecipitationEvapotranspirationIndex.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/StandardizedPrecipitationEvapotranspirationIndex.tmcf)
* [`StandardizedPrecipitationIndex.tmcf`](https://github.com/datacommonsorg/data/blob/master/scripts/us_cdc/environmental_health_toxicology/StandardizedPrecipitationIndex.tmcf)

### Import Procedure

Expand Down
21 changes: 7 additions & 14 deletions scripts/us_cdc/environmental_health_toxicology/download_files.py
Original file line number Diff line number Diff line change
Expand Up @@ -36,20 +36,13 @@ def download_files(importname, configs):
@retry(tries=3, delay=2, backoff=2)
def download_with_retry(url, input_file_name):
logging.info(f"Downloading file from URL: {url}")
response = requests.get(url)
response.raise_for_status()
if response.status_code == 200:
if not response.content:
logging.fatal(
f"No data available for URL: {url}. Aborting download.")
return
filename = os.path.join(_INPUT_FILE_PATH, input_file_name)
with file_util.FileIO(filename, 'wb') as f:
f.write(response.content)
else:
logging.error(
f"Failed to download file from URL: {url}. Status code: {response.status_code}"
)
filename = os.path.join(_INPUT_FILE_PATH, input_file_name)
with requests.get(url, stream=True) as response:
response.raise_for_status()
with open(filename, 'wb') as f:
for chunk in response.iter_content(chunk_size=16 * 1024 * 1024):
if chunk:
f.write(chunk)

try:
for config in configs:
Expand Down
56 changes: 36 additions & 20 deletions scripts/us_cdc/environmental_health_toxicology/manifest.json
Original file line number Diff line number Diff line change
Expand Up @@ -12,13 +12,14 @@
"parse_air_quality.py CDC_PM25CensusTract"
],
"source_files": [
"input/*.gz"
"input_files/*"
],
"resource_limits": {
"cpu": 8,
"memory": 64,
"disk": 100
"cpu": 32,
"memory": 512,
"disk": 2000
},
"validation_config_file": "validation_config.json",
"import_inputs": [
{
"template_mcf": "PM25CensusTractPollution_part1.tmcf",
Expand Down Expand Up @@ -51,13 +52,14 @@
"parse_air_quality.py CDC_OzoneCensusTract"
],
"source_files": [
"input/*.gz"
"input_files/*"
],
"resource_limits": {
"cpu": 8,
"memory": 64,
"disk": 100
"cpu": 32,
"memory": 512,
"disk": 2000
},
"validation_config_file": "validation_config.json",
"import_inputs": [
{
"template_mcf": "OzoneCensusTractPollution_part1.tmcf",
Expand Down Expand Up @@ -92,17 +94,30 @@
"source_files": [
"input_files/*"
],
"resource_limits": {
"cpu": 32,
"memory": 512,
"disk": 500
},
"validation_config_file": "validation_config.json",
"import_inputs": [
{
"template_mcf": "PM25CountyPollution.tmcf",
"cleaned_csv": "output/PM25county.csv"
"template_mcf": "PM25CountyPollution_part1.tmcf",
"cleaned_csv": "output/PM25county_0.csv"
},
{
"template_mcf": "PM25CountyPollution_part2.tmcf",
"cleaned_csv": "output/PM25county_1.csv"
},
{
"template_mcf": "PM25CountyPollution_part3.tmcf",
"cleaned_csv": "output/PM25county_2.csv"
},
{
"template_mcf": "PM25CountyPollution_part4.tmcf",
"cleaned_csv": "output/PM25county_3.csv"
}
],
"resource_limits": {
"cpu": 8,
"memory": 128,
"disk": 200
},
"cron_schedule": "0 1 4 * *"
},
{
Expand All @@ -119,17 +134,18 @@
"source_files": [
"input_files/*"
],
"resource_limits": {
"cpu": 32,
"memory": 512,
"disk": 500
},
"validation_config_file": "validation_config.json",
"import_inputs": [
{
"template_mcf": "OzoneCountyPollution.tmcf",
"cleaned_csv": "output/OzoneCounty.csv"
}
],
"resource_limits": {
"cpu": 16,
"memory": 512,
"disk": 500
},
"cron_schedule": "0 1 5 * *"
}
]
Expand Down
Loading
Loading