Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Refactoring pull_ozh.py #67

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Refactoring pull_ozh.py #67

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b501e65
refactoring
Apr 1, 2020
3f38a0e
further simplification
Apr 1, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
102 changes: 25 additions & 77 deletions pull_ozh.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,14 @@ def get_date_range(dfs):


def main():
dimensions = {
'cases': {'csv': 'ncumul_conf', 'xlsx': 'Cases'},
'fatalities': {'csv': 'ncumul_deceased', 'xlsx': 'Fatalities'},
'hospitalized': {'csv': 'ncumul_hosp', 'xlsx': 'Hospitalized'},
'icu': {'csv': 'ncumul_ICU', 'xlsx': 'ICU'},
'vent': {'csv': 'ncumul_vent', 'xlsx': 'Ventilated'},
'released': {'csv': 'ncumul_released', 'xlsx': 'Released'}
}
parser = ConfigParser()
parser.read("sources.ini")

Expand All @@ -41,61 +49,29 @@ def main():

# Append empty dates to all
dates = get_date_range(dfs)
df_cases = pd.DataFrame(float("nan"), index=dates, columns=cantons)
df_fatalities = pd.DataFrame(float("nan"), index=dates, columns=cantons)
df_hospitalized = pd.DataFrame(float("nan"), index=dates, columns=cantons)
df_icu = pd.DataFrame(float("nan"), index=dates, columns=cantons)
df_vent = pd.DataFrame(float("nan"), index=dates, columns=cantons)
df_released = pd.DataFrame(float("nan"), index=dates, columns=cantons)
df_by_dimension = {dimension: pd.DataFrame(float("nan"), index=dates, columns=cantons) for dimension in dimensions}

for canton, df in dfs.items():
for d in dates:
if d in df.index:
df_cases[canton][d] = df["ncumul_conf"][d]
df_fatalities[canton][d] = df["ncumul_deceased"][d]
df_hospitalized[canton][d] = df["ncumul_hosp"][d]
df_icu[canton][d] = df["ncumul_ICU"][d]
df_vent[canton][d] = df["ncumul_vent"][d]
df_released[canton][d] = df["ncumul_released"][d]
for dimension in dimensions:
df_by_dimension[dimension][canton][d] = df[dimensions[dimension]['csv']][d]

# Fill to calculate the correct totals for CH
df_cases_total = df_cases.fillna(method="ffill")
df_fatalities_total = df_fatalities.fillna(method="ffill")
df_hospitalized_total = df_hospitalized.fillna(method="ffill")
df_icu_total = df_icu.fillna(method="ffill")
df_vent_total = df_vent.fillna(method="ffill")
df_released_total = df_released.fillna(method="ffill")

df_cases["CH"] = df_cases_total.sum(axis=1)
df_fatalities["CH"] = df_fatalities_total.sum(axis=1)
df_hospitalized["CH"] = df_hospitalized_total.sum(axis=1)
df_icu["CH"] = df_icu_total.sum(axis=1)
df_vent["CH"] = df_vent_total.sum(axis=1)
df_released["CH"] = df_released_total.sum(axis=1)
df_total = {dimension: df.fillna(method="ffill") for dimension, df in df_by_dimension.items()}

for dimension in dimensions:
df_by_dimension[dimension]['CH'] = df_total[dimension].sum(axis=1)

# Create a summery with the most important values in json to allow web devs to grab it
summary = {
"totals": {
"cases": df_cases["CH"][-1],
"fatalities": df_fatalities["CH"][-1],
"hospitalized": df_hospitalized["CH"][-1],
"icu": df_icu["CH"][-1],
"vent": df_vent["CH"][-1],
"released": df_released["CH"][-1],
},
"changes": {
"cases": df_cases["CH"][-1] - df_cases["CH"][-2],
"fatalities": df_fatalities["CH"][-1] - df_fatalities["CH"][-2],
"hospitalized": df_hospitalized["CH"][-1] - df_hospitalized["CH"][-2],
"icu": df_icu["CH"][-1] - df_icu["CH"][-2],
"vent": df_vent["CH"][-1] - df_vent["CH"][-2],
"released": df_released["CH"][-1] - df_released["CH"][-2],
},
"totals": {dimension: df["CH"][-1] for dimension, df in df_by_dimension.items()},
"changes": {dimension: df["CH"][-1] - df["CH"][-2] for dimension, df in df_by_dimension.items()},
"updated_cantons": ",".join(
[
canton
for canton in df_cases
if canton != "CH" and not pd.np.isnan(float(df_cases[canton][-1]))
for canton in df_by_dimension['cases']
if canton != "CH" and not pd.np.isnan(float(df_by_dimension['cases'][canton][-1]))
]
),
}
Expand All @@ -104,44 +80,16 @@ def main():
json.dump(summary, f)

# Store as CSV
df_cases.to_csv("covid19_cases_switzerland_openzh.csv", index_label="Date")
df_fatalities.to_csv(
"covid19_fatalities_switzerland_openzh.csv", index_label="Date"
)
df_hospitalized.to_csv(
"covid19_hospitalized_switzerland_openzh.csv", index_label="Date"
)
df_icu.to_csv("covid19_icu_switzerland_openzh.csv", index_label="Date")
df_vent.to_csv("covid19_vent_switzerland_openzh.csv", index_label="Date")
df_released.to_csv("covid19_released_switzerland_openzh.csv", index_label="Date")
for dimension in dimensions:
df_by_dimension[dimension].to_csv(f"covid19_{dimension}_switzerland_openzh.csv", index_label="Date")

# Store as json
df_cases.to_json("covid19_cases_switzerland_openzh.json")
df_fatalities.to_json("covid19_fatalities_switzerland_openzh.json")
df_hospitalized.to_json("covid19_hospitalized_switzerland_openzh.json")
df_icu.to_json("covid19_icu_switzerland_openzh.json")
df_vent.to_json("covid19_vent_switzerland_openzh.json")
df_released.to_json("covid19_released_switzerland_openzh.json")
for dimension, df in df_by_dimension.items():
df.to_json(f"covid19_{dimension}_switzerland_openzh.json")

with pd.ExcelWriter("covid_19_data_switzerland.xlsx") as writer:
df_cases.to_excel(
writer, index_label="Date", sheet_name="Cases",
)
df_fatalities.to_excel(
writer, index_label="Date", sheet_name="Fatalities",
)
df_hospitalized.to_excel(
writer, index_label="Date", sheet_name="Hospitalized",
)
df_icu.to_excel(
writer, index_label="Date", sheet_name="ICU",
)
df_vent.to_excel(
writer, index_label="Date", sheet_name="Ventilated",
)
df_released.to_excel(
writer, index_label="Date", sheet_name="Released",
)
for dimension, df in df_by_dimension.items():
df.to_excel(writer, index_label="Date", sheet_name=dimensions[dimension]['xlsx'])


if __name__ == "__main__":
Expand Down