def get_usa_state_shapefile(shp, shx, dbf):
shp_writer = shapefile.Writer(shp=shp, shx=shx, dbf=dbf)
public_data_url = get_public_data_base_url()
public_data_path = _file_uri_to_path(public_data_url)
join_and_output_shapefile(get_usa_by_states_df(),
shapefile.Reader(f'{public_data_path}/data/shapefiles-uscensus/tl_2019_us_state'),
'STATEFP', 'State/County FIPS Code', shp_writer)
def get_usa_by_county_df():
url = '{}/data/cases-jhu/csse_covid_19_daily_reports/{}.csv'.format(
get_public_data_base_url(), latest.strftime("%m-%d-%Y"))
raw_df = pd.read_csv(url, dtype={"FIPS": str})
raw_df['FIPS'] = raw_df['FIPS'].astype(str).str.zfill(5)
column_mapping = {"Province_State": "Province/State",
"Country_Region": "Country/Region",
"Last_Update": "Last Update",
"Lat": "Latitude",
"Long_": "Longitude",
"Combined_Key": "Combined Key",
"Admin2": "County",
"FIPS": "State/County FIPS Code"
}
remapped_df = raw_df.rename(columns=column_mapping)
# USA only
us_df = remapped_df[(remapped_df["Country/Region"] == "US")]
final_df = pd.DataFrame(us_df, columns=output_cols)
final_df['Last Update'] = pd.to_datetime(final_df['Last Update'])
final_df['Last Update'] = final_df['Last Update'].dt.strftime(
'%-m/%-d/%Y %H:%M')
final_df['County'] = final_df['County'].replace(county_replace_with_null)
final_df['Combined Key'] = final_df['Combined Key'].str.replace('Unassigned, ','')
final_df = final_df.fillna(NULL_VALUE)
final_df.index.name = 'OBJECTID'
# assert unique key test
assert final_df['Combined Key'].value_counts().max() == 1
return final_df
def get_usa_county_shapefile(shp, shx, dbf):
shp_writer = shapefile.Writer(shp=shp, shx=shx, dbf=dbf)
public_data_url = get_public_data_base_url()
public_data_path = _file_uri_to_path(public_data_url)
join_and_output_shapefile(get_usa_by_county_with_projection_df(),
shapefile.Reader(f'{public_data_path}/data/shapefiles-uscensus/tl_2019_us_county'),
'GEOID', 'State/County FIPS Code', shp_writer)
def _get_usa_by_county_df():
# TODO: read this from a dataset class
url = "{}/data/cases-jhu/csse_covid_19_daily_reports/{}.csv".format(
get_public_data_base_url(), latest.strftime("%m-%d-%Y"))
raw_df = pd.read_csv(url, dtype={"FIPS": str})
raw_df["FIPS"] = raw_df["FIPS"].astype(str).str.zfill(5)
column_mapping = {
"Province_State": "Province/State",
"Country_Region": "Country/Region",
"Last_Update": "Last Update",
"Lat": "Latitude",
"Long_": "Longitude",
"Combined_Key": "Combined Key",
"Admin2": "County",
"FIPS": "State/County FIPS Code",
}
remapped_df = raw_df.rename(columns=column_mapping)
# USA only
us_df = remapped_df[(remapped_df["Country/Region"] == "US")]
jhu_column_names = [
"Province/State",
"Country/Region",
"Last Update",
"Latitude",
"Longitude",
"Confirmed",
"Recovered",
"Deaths",
"Active",
"County",
"State/County FIPS Code",
"Combined Key",
# Incident rate and people tested do not seem to be available yet
# "Incident Rate",
# "People Tested",
]
final_df = pd.DataFrame(us_df, columns=jhu_column_names)
final_df["Last Update"] = pd.to_datetime(final_df["Last Update"])
final_df["Last Update"] = final_df["Last Update"].dt.strftime(
"%-m/%-d/%Y %H:%M")
final_df["County"] = final_df["County"].replace(county_replace_with_null)
final_df["Combined Key"] = final_df["Combined Key"].str.replace(
"Unassigned, ", "")
final_df = final_df.fillna(NULL_VALUE)
final_df = final_df.drop_duplicates(
"State/County FIPS Code"
) # note this is a hack, 49053 is dupped in JHU data :(
final_df.index.name = "OBJECTID"
# assert unique key test
assert final_df["Combined Key"].value_counts().max() == 1
assert final_df["State/County FIPS Code"].value_counts().max() == 1
return final_df
def get_usa_state_shapefile(use_state_df, shp, shx, dbf):
shp_writer = shapefile.Writer(shp=shp, shx=shx, dbf=dbf)
public_data_url = get_public_data_base_url()
public_data_path = _file_uri_to_path(public_data_url)
join_and_output_shapefile(
use_state_df,
shapefile.Reader(
f"{public_data_path}/data/shapefiles-uscensus/tl_2019_us_state"),
"STATEFP",
"State/County FIPS Code",
shp_writer,
)
def get_usa_state_shapefile(
use_state_df) -> Tuple[io.BytesIO, io.BytesIO, io.BytesIO]:
shp = io.BytesIO()
shx = io.BytesIO()
dbf = io.BytesIO()
shp_writer = shapefile.Writer(shp=shp, shx=shx, dbf=dbf)
public_data_url = get_public_data_base_url()
public_data_path = _file_uri_to_path(public_data_url)
join_and_output_shapefile(
use_state_df,
shapefile.Reader(
f"{public_data_path}/data/shapefiles-uscensus/tl_2019_us_state"),
"STATEFP",
CommonFields.FIPS,
shp_writer,
)
return shp, shx, dbf
def get_usa_county_shapefile(
county_df) -> Tuple[io.BytesIO, io.BytesIO, io.BytesIO]:
shp = io.BytesIO()
shx = io.BytesIO()
dbf = io.BytesIO()
shp_writer = shapefile.Writer(shp=shp, shx=shx, dbf=dbf)
public_data_url = get_public_data_base_url()
public_data_path = _file_uri_to_path(public_data_url)
join_and_output_shapefile(
county_df,
shapefile.Reader(
f"{public_data_path}/data/shapefiles-uscensus/tl_2019_us_county"),
"GEOID",
"State/County FIPS Code",
shp_writer,
)
return shp, shx, dbf