import update_severity_index as severity_index
import load_data
import merge_data
import numpy as np
import pandas as pd
if __name__ == "__main__":
data_dir = oj(parentdir, 'data')
# load in county data
df_county = load_data.load_county_level(data_dir=oj(parentdir, 'data'))
# add predictions
NUM_DAYS_LIST = [1, 2, 3, 4, 5]
df_county = add_preds(df_county,
NUM_DAYS_LIST=NUM_DAYS_LIST,
cached_dir=data_dir)
deaths_fig = viz_map.plot_cumulative_deaths_map_with_slider(
df_county,
auto_open=False,
target_days=np.array([0] + NUM_DAYS_LIST),
filename=oj(parentdir, 'results', 'deaths.html'))
print('successfully updated map of deaths')
deaths_fig.write_image(oj(parentdir, 'results', 'deaths.png'),
width=900,
height=600,
scale=2)
print('successfully updated png of map of deaths')
# load in hospital data and merge
add_predictions_7day(pd.read_pickle(cached_fname), df_tab)
else:
k += 1
if k > 1:
break
return df_tab, date2
if __name__ == '__main__':
print('loading data...')
NUM_DAYS_LIST = [1, 2, 3, 4, 5, 6, 7]
df_county = load_data.load_county_level(
data_dir=oj(parentdir, 'data')).fillna(0)
df_county = add_preds(
df_county,
NUM_DAYS_LIST=NUM_DAYS_LIST,
cached_dir=oj(parentdir,
'data')) # adds keys like "Predicted Deaths 1-day"
## orgnize predicts as array
add_pre(df_county, 'Predicted Cases ', 'pred_cases', 'pred_new_cases')
add_pre(df_county, 'Predicted Deaths ', 'pred_deaths', 'pred_new_deaths')
## add new cases/death to dataframe
add_new(df_county)
## Add new cases/deaths predictions and their intervals
df_county = add_new_pre(df_county, 'Predicted Cases ', 'tot_cases',
'pred_new_cases')
df_county = add_new_pre(df_county, 'Predicted Deaths ', 'tot_deaths',
'pred_new_deaths')
ks.append(f'Surge {i}-day')
ks.append(f'Predicted New Deaths Hospital {i}-day')
ks.append(f'Predicted Deaths Hospital {i}-day')
df[f'Severity Index {i}-day'] = [remap[x] for x in df[f'Severity {i}-day']]
ks.append(f'Severity Index {i}-day')
ks += ['Surge County 3-day', 'tot_deaths', 'SVIPercentile'] # county keys
return df[ks]
if __name__ == '__main__':
# load and merge data
print('loading data...')
NUM_DAYS_LIST = [1, 2, 3, 4, 5, 6, 7]
df_county = load_data.load_county_level(data_dir=oj(parentdir, 'data'))
df_county = add_preds(df_county, NUM_DAYS_LIST=NUM_DAYS_LIST + [14, 21, 28],
cached_dir=oj(parentdir, 'data'), add_predict_interval=True, interval_target_days=NUM_DAYS_LIST) # adds keys like "Predicted Deaths 1-day"
df_hospital = load_data.load_hospital_level(data_dir=oj(os.path.dirname(parentdir),
'covid-19-private-data'))
df = merge_data.merge_county_and_hosp(df_county, df_hospital)
df = add_severity_index(df, NUM_DAYS_LIST)
df = df.sort_values('Total Deaths Hospital', ascending=False)
# write to gsheets
dfc = prep_county_df(df_county, NUM_DAYS_LIST) # data for chicago mapping team
print('dfc.shape', dfc.shape)
write_to_gsheet(dfc, sheet_name='County-level Predictions',
service_file=oj(parentdir, 'creds.json'))
ks_output = ['Severity 1-day', 'Severity 2-day', 'Severity 3-day', 'Severity 4-day',
'Severity 5-day', 'Severity 6-day', 'Severity 7-day',
'Total Deaths Hospital', 'Hospital Name', 'CMS Certification Number',
'countyFIPS', 'CountyName', 'StateName',
ks.append(f'Severity Index {i}-day')
ks += ['Surge County 3-day', 'tot_deaths', 'SVIPercentile'] # county keys
return df[ks]
if __name__ == '__main__':
# load and merge data
print('severity index loading data...')
NUM_DAYS_LIST = [1, 2, 3, 4, 5, 6, 7]
df_county = load_data.load_county_level(data_dir=oj(parentdir, 'data'))
print('loaded county level!')
df_county = add_preds(
df_county,
NUM_DAYS_LIST=NUM_DAYS_LIST +
[14, 21, 28], # should save the cached pkl
cached_dir=oj(parentdir, 'data'),
add_predict_interval=True,
interval_target_days=NUM_DAYS_LIST,
force_predict=True
) #, force_predict=True) # adds keys like "Predicted Deaths 1-day"
print('loading hosp data...')
df_hospital = load_data.load_hospital_level(
data_dir=oj(os.path.dirname(parentdir), 'covid-19-private-data'))
df = merge_data.merge_county_and_hosp(df_county, df_hospital)
print('adding severity index...')
df = add_severity_index(df, NUM_DAYS_LIST)
df = df.sort_values('Total Deaths Hospital', ascending=False)
# write to gsheets
print('\tprep for gsheets')
dfc = prep_county_df(df_county,
import numpy as np
import pandas as pd
from os.path import join as oj
import pygsheets
import pandas as pd
import sys
sys.path.append('../modeling')
sys.path.append('..')
import load_data
from fit_and_predict import add_preds
from functions import merge_data
if __name__ == '__main__':
NUM_DAYS_LIST = [1]
df_county = load_data.load_county_level(data_dir='../data')
df_hospital = load_data.load_hospital_level(
data_dir='../data_hospital_level')
df_county = add_preds(
df_county,
NUM_DAYS_LIST=NUM_DAYS_LIST) # adds keys like "Predicted Deaths 1-day"
print('succesfully ran pipeline!')
import load_data
import numpy as np
import pandas as pd
if __name__ == "__main__":
data_dir = oj(parentdir, 'data')
# load in county data
df = load_data.load_county_level(data_dir=oj(parentdir, 'data'))
# add lat and lon to the dataframe
county_lat_lon = pd.read_csv(oj(data_dir, 'county_pop_centers.csv'),
dtype={
'STATEFP': str,
'COUNTYFP': str
})
county_lat_lon['fips'] = (county_lat_lon['STATEFP'] +
county_lat_lon['COUNTYFP']).astype(np.int64)
# add predictions
df = add_preds(df, NUM_DAYS_LIST=[1, 2, 3, 4, 5], cached_dir=data_dir)
# join lat / lon to df
df = df.join(county_lat_lon.set_index('fips'), on='countyFIPS',
how='left').rename(columns={
'LATITUDE': 'lat',
'LONGITUDE': 'lon'
})
# create plot
plot_counties_slider(df,
auto_open=False,
n_past_days=1,
target_days=np.array([1, 2, 3, 4, 5]),
filename=oj(parentdir, 'results', 'deaths.html'))
if __name__ == '__main__':
print('loading data...')
NUM_DAYS_LIST = [1, 2, 3, 4, 5, 6, 7]
df_county = load_data.load_county_level(
data_dir=oj(parentdir, 'data')).fillna(0)
df_county_dis = load_data.load_county_level(
data_dir=oj(parentdir, 'data'),
discard=True).fillna(0) # discard one day in time series
num_days_in_past = 3
output_key = f'Predicted Deaths {num_days_in_past}-day Lagged'
df_county = add_preds(
df_county,
NUM_DAYS_LIST=NUM_DAYS_LIST,
cached_dir=oj(parentdir, 'data'),
discard=False) # adds keys like "Predicted Deaths 1-day"
df_county_old = add_preds(
df_county_dis,
NUM_DAYS_LIST=NUM_DAYS_LIST,
cached_dir=oj(parentdir, 'data'),
d=datetime.date.today() -
timedelta(days=1)) # adds keys like "Predicted Deaths 1-day"
'''
# don't use add_preds here, since we need preds from 3 days ago
df_county = fit_and_predict_ensemble(df_county,
outcome='deaths',
mode='eval_mode',
target_day=np.array([num_days_in_past]),
output_key=output_key)
