293 Remove default value for out_folder

pycode/examples/epidata/PlotCaseData.py

@@ -34,8 +34,9 @@
 
 yesterday = pd.Timestamp(datetime.date.today()) - pd.DateOffset(days=1)
 
-# folder where divi and case data can be found after downloading with default out_folder
-data_folder = os.path.join(dd.defaultDict['out_folder'], "pydata", "Germany")
+# folder where divi and case data can be found after downloading
+data_folder = os.path.join(os.getcwd(), 'data', 'pydata')
+data_folder_germany = os.path.join(data_folder, "pydata", "Germany")
 
 
 def get_Data(endday_divi=yesterday, moving_average=True):
@@ -44,11 +45,11 @@ def get_Data(endday_divi=yesterday, moving_average=True):
     @param moving_average Defines if moving average is used"""
     print('Download case data from the Internet, takes some time')
     getCaseData.get_case_data(
-        out_folder=dd.defaultDict['out_folder'],
+        data_folder,
         moving_average=moving_average)
     print('Download DIVI Data from the Internet, takes some time')
     getDIVIData.get_divi_data(
-        out_folder=dd.defaultDict['out_folder'],
+        data_folder,
         end_date=endday_divi)
 
 
@@ -60,7 +61,7 @@ def plot_cases(
         @param daystart Day at which should be started in timestamp format
         @param simulationperiod number in integer format of days for which data should be plotted
         @param saveplot boolean value; says if plot should be saved """
-    df = pd.read_json(os.path.join(data_folder, "cases_infected.json"))
+    df = pd.read_json(os.path.join(data_folder_germany, "cases_infected.json"))
     if not (daystart + pd.DateOffset(days=simulationperiod) <= yesterday):
         simulationperiod = (yesterday - daystart).days
     mask = (
@@ -81,7 +82,7 @@ def plot_cases(
         plt.savefig(os.path.join('Plots', fig_name+".png"))
 
     if moving_average:
-        df = pd.read_json(os.path.join(data_folder, "cases_infected_ma7.json"))
+        df = pd.read_json(os.path.join(data_folder_germany, "cases_infected_ma7.json"))
         mask = (
             df['Date'] >= daystart) & (
             df['Date'] <= daystart + pd.DateOffset(days=simulationperiod))
@@ -98,7 +99,7 @@ def plot_cases(
         if saveplot:
             plt.savefig('Plots/plot_cases_confirmed_infections_ma7.png')
 
-    df = pd.read_json(os.path.join(data_folder, "cases_deaths.json"))
+    df = pd.read_json(os.path.join(data_folder_germany, "cases_deaths.json"))
     mask = (
         df['Date'] >= daystart) & (
         df['Date'] <= daystart + pd.DateOffset(days=simulationperiod))
@@ -117,7 +118,7 @@ def plot_cases(
         plt.savefig(os.path.join('Plots', fig_name+".png"))
 
     if moving_average:
-        df = pd.read_json(os.path.join(data_folder, "cases_deaths_ma7.json"))
+        df = pd.read_json(os.path.join(data_folder_germany, "cases_deaths_ma7.json"))
         mask = (
             df['Date'] >= daystart) & (
             df['Date'] <= daystart + pd.DateOffset(days=simulationperiod))
@@ -145,7 +146,7 @@ def plot_cases_age(
     @param saveplot boolean value; says if plot should be saved """
     if not (daystart + pd.DateOffset(days=simulationperiod) <= yesterday):
         simulationperiod = (yesterday - daystart).days
-    df = pd.read_json(os.path.join(data_folder, "cases_all_age.json"))
+    df = pd.read_json(os.path.join(data_folder_germany, "cases_all_age.json"))
     mask = (
         df['Date'] >= daystart) & (
         df['Date'] <= daystart + pd.DateOffset(days=simulationperiod))
@@ -183,7 +184,7 @@ def plot_cases_age(
         plt.savefig(os.path.join('Plots', fig_name+".png"))
 
     if moving_average:
-        df = pd.read_json(os.path.join(data_folder, "cases_all_age_ma7.json"))
+        df = pd.read_json(os.path.join(data_folder_germany, "cases_all_age_ma7.json"))
         mask = (
             df['Date'] >= daystart) & (
             df['Date'] <= daystart + pd.DateOffset(days=simulationperiod))
@@ -233,7 +234,7 @@ def plot_cases_county(
     @param saveplot boolean value; says if plot should be saved """
     if not (daystart + pd.DateOffset(days=simulationperiod) <= yesterday):
         simulationperiod = (yesterday - daystart).days
-    df = pd.read_json(os.path.join(data_folder, "cases_all_county.json"))
+    df = pd.read_json(os.path.join(data_folder_germany, "cases_all_county.json"))
     mask = (df['Date'] >= daystart) & (
         df['Date'] <= daystart + pd.DateOffset(days=simulationperiod)) & (df["County"] == county)
     fig_name = 'cases_confirmed_infections_county_' + county.replace(" ", "_")
@@ -264,7 +265,7 @@ def plot_cases_county(
 
     if moving_average:
         df = pd.read_json(os.path.join(
-            data_folder, "cases_all_county_ma7.json"))
+            data_folder_germany, "cases_all_county_ma7.json"))
         mask = (df['Date'] >= daystart) & (
             df['Date'] <= daystart + pd.DateOffset(days=simulationperiod)) & (df["County"] == county)
         fig_name = 'cases_confirmed_infections_county_' + county.replace(" ", "_") + '_ma7'
@@ -308,7 +309,7 @@ def plot_DIVI_data(
             + daystart.strftime("%d.%m.%Y") +
             ". Data for this date is not available.")
     else:
-        df = pd.read_json(os.path.join(data_folder, "germany_divi.json"))
+        df = pd.read_json(os.path.join(data_folder_germany, "germany_divi.json"))
         if not (daystart + pd.DateOffset(days=simulationperiod) <= endday_divi):
             simulationperiod = (endday_divi - daystart).days
         mask = (

pycode/memilio-epidata/memilio/epidata/README.rst

@@ -76,10 +76,7 @@ optional arguments working for all are:
 +---------------------------------------------+-----------------------------------------------------------+
 | -h, --help                                  | show this help message and exit                           |
 +---------------------------------------------+-----------------------------------------------------------+
-| -r, --read-data                             | Reads the data from file "json" instead of downloading it.|
-+---------------------------------------------+-----------------------------------------------------------+
-| -o OUT_FOLDER,                              | Defines folder for output.                                |
-| --out-folder OUT_FOLDER                     |                                                           |
+| -r, --read-data                             | Reads the data from file "json" instead of downloading it.|               |                                                           |
 +---------------------------------------------+-----------------------------------------------------------+
 | -ff {json,hdf5,json_timeasstring}           | Defines output format for data files.                     |
 | --file-format {json,hdf5,json_timeasstring} | Default is "json_timeasstring".                           |

pycode/memilio-epidata/memilio/epidata/cleanData.py

@@ -211,10 +211,8 @@ def cli():
     - delete all
     - delete just cases, jh, population, divi, vaccination, commuter or testing
     - choose file format: json or hdf5
-    - define path to files
     """
 
-    out_path_default = dd.defaultDict['out_folder']
 
     parser = argparse.ArgumentParser()
 
@@ -247,24 +245,21 @@ def cli():
                         action='store_true')
     parser.add_argument('-tx', '--txt', help='Deletes txt files.', 
                         action='store_true')
-    parser.add_argument(
-        '-o', '--out_path', type=str, default=out_path_default,
-        help='Defines folder for output.')
-
     args = parser.parse_args()
 
     return_args = [args.all_data, args.cases, args.john_hopkins, args.population,
                    args.divi, args.vaccination, args.commuter, args.testing, 
-                   args.json, args.hdf5, args.txt, args.out_path]
+                   args.json, args.hdf5, args.txt]
 
     return return_args
 
 
 def main():
     """! Main program entry."""
 
+    out_path = os.path.join(os.getcwd(), 'data', 'pydata')
     [all_data, cases, john_hopkins, population, divi,
-        vaccination, commuter, testing, json, hdf5, txt, out_path] = cli()
+        vaccination, commuter, testing, json, hdf5, txt] = cli()
 
     clean_data(all_data, cases, john_hopkins, population, divi,
                vaccination, commuter, testing, json, hdf5, txt, out_path)

pycode/memilio-epidata/memilio/epidata/defaultDict.py

@@ -32,16 +32,9 @@
 import os
 from datetime import date
 
-default_file_path = os.path.dirname(os.path.abspath(__file__))
-dfp_vec = default_file_path.split('memilio')
-if len(dfp_vec) > 0:
-    default_file_path = os.path.join(
-        dfp_vec[0], os.path.join('memilio', 'data/pydata'))
-
 defaultDict = {
     'read_data': False,
     'make_plot': False,
-    'out_folder': default_file_path,
     'start_date': date(2020, 4, 24),
     'end_date': date.today(),
     'split_berlin': False,

pycode/memilio-epidata/memilio/epidata/getCaseData.py

@@ -60,9 +60,9 @@ def check_for_completeness(df, merge_berlin=False, merge_eisenach=True):
     return False
 
 
-def get_case_data(read_data=dd.defaultDict['read_data'],
+def get_case_data(data_folder,
+                  read_data=dd.defaultDict['read_data'],
                   file_format=dd.defaultDict['file_format'],
-                  out_folder=dd.defaultDict['out_folder'],
                   no_raw=dd.defaultDict['no_raw'],
                   impute_dates=dd.defaultDict['impute_dates'],
                   make_plot=dd.defaultDict['make_plot'],
@@ -76,7 +76,7 @@ def get_case_data(read_data=dd.defaultDict['read_data'],
     If the data is read from the internet, before changing anything the data is stored in CaseDataFull.json.
     If data should be downloaded, it is checked if data contains all counties.
     If not a different source is tried.
-    The file is read in or stored at the folder "out_folder"/Germany/.
+    The file is read in or stored at the folder "data_folder"/Germany/.
     To store and change the data we use pandas.
 
     While working with the data
@@ -105,9 +105,9 @@ def get_case_data(read_data=dd.defaultDict['read_data'],
         - Infected, deaths and recovered split for state and age are stored in "cases_all_state_age"
         - Infected, deaths and recovered split for county and age are stored in "cases_all_county_age(_split_berlin)"
 
+    @param data_folder Path to folder where data is written in folder data_folder/Germany.
     @param read_data False [Default] or True. Defines if data is read from file or downloaded.
     @param file_format File format which is used for writing the data. Default defined in defaultDict.
-    @param out_folder Path to folder where data is written in folder out_folder/Germany.
     @param no_raw True or False [Default]. Defines if unchanged raw data is saved or not.
     @param impute_dates False [Default] or True. Defines if values for dates without new information are imputed.
     @param make_plot False [Default] or True. Defines if plots are generated with matplotlib.
@@ -116,7 +116,7 @@ def get_case_data(read_data=dd.defaultDict['read_data'],
     @param split_berlin True or False [Default]. Defines if Berlin's disctricts are kept separated or get merged.
     """
 
-    directory = os.path.join(out_folder, 'Germany/')
+    directory = os.path.join(data_folder, 'Germany/')
     gd.check_dir(directory)
     filename = "CaseDataFull"
 
@@ -684,8 +684,9 @@ def get_case_data(read_data=dd.defaultDict['read_data'],
 def main():
     """! Main program entry."""
 
+    path = os.path.join(os.getcwd(), 'data', 'pydata')
     arg_dict = gd.cli("cases")
-    get_case_data(**arg_dict)
+    get_case_data(path, **arg_dict)
 
 
 if __name__ == "__main__":

pycode/memilio-epidata/memilio/epidata/getCaseDatawithEstimations.py

@@ -37,9 +37,9 @@
 from memilio.epidata import getJHData as gjd
 
 
-def get_case_data_with_estimations(read_data=dd.defaultDict['read_data'],
+def get_case_data_with_estimations(data_folder,
+                                   read_data=dd.defaultDict['read_data'],
                                    file_format=dd.defaultDict['file_format'],
-                                   out_folder=dd.defaultDict['out_folder'],
                                    no_raw=dd.defaultDict['no_raw'],
                                    make_plot=dd.defaultDict['make_plot']):
     """! Function to estimate recovered and deaths from combination of case data from RKI and JH data
@@ -49,14 +49,14 @@ def get_case_data_with_estimations(read_data=dd.defaultDict['read_data'],
     With this fraction every existing case data from RKI is scaled.
     The new columns recovered_estimated and deaths_estimated are added.
 
+    @param data_folder Folder where data is written to.
     @param read_data False [Default] or True. Defines if data is read from file or downloaded.
     @param file_format json [Default]
-    @param out_folder Folder where data is written to.
     @param no_raw True or False [Default]. Defines if unchanged raw data is saved or not.
     @param make_plot [Optional] case data from RKI and estimated data can be compared by plots
     """
 
-    data_path = os.path.join(out_folder, 'Germany/')
+    data_path = os.path.join(data_folder, 'Germany/')
 
     if not read_data:
         impute_dates = False
@@ -66,11 +66,11 @@ def get_case_data_with_estimations(read_data=dd.defaultDict['read_data'],
 
         # get case data
         gcd.get_case_data(
-            read_data, file_format, out_folder, no_raw, impute_dates,
+            data_path, read_data, file_format, no_raw, impute_dates,
             make_plot_cases, moving_average, no_raw, split_berlin)
 
         # get data from John Hopkins University
-        gjd.get_jh_data(read_data, file_format, out_folder, no_raw)
+        gjd.get_jh_data(data_path, read_data, file_format, no_raw)
 
     # Now we now which data is generated and we can use it
     # read in jh data
@@ -379,8 +379,9 @@ def download_weekly_deaths_numbers(data_path):
 def main():
     """! Main program entry."""
 
+    path = os.path.join(os.getcwd(), 'data', 'pydata')
     arg_dict = gd.cli("cases_est")
-    get_case_data_with_estimations(**arg_dict)
+    get_case_data_with_estimations(path, **arg_dict)
 
 
 if __name__ == "__main__":