updated = updated.melt(id_vars=["data"],
var_name="Concelho",
value_name="Casos")
updated = updated.merge(
population[["Concelho", "2019"]],
how="left",
left_on="Concelho",
right_on="Concelho",
)
updated.fillna(0, inplace=True)
updated["ratio"] = round(
updated["Casos"] * 100 * 1000 / updated["2019"], 1)
updated = updated.pivot_table(values="ratio",
index="data",
columns="Concelho")
updated = updated.reset_index(level=0)
cols = [x for x in updated.columns if x != "data"]
updated[cols] = updated[cols].diff(2) # 14 days
updated = updated[2:]
func = convert_to_int if i == DATA_CONCELHOS_14DIAS_CSV else convert_to_float
updated = convert(updated, cols, func)
# sort by date
updated = updated.sort_values("data")
# convert back into dd-mm-yyyy
updated["data"] = updated["data"].dt.strftime("%d-%m-%Y")
updated.to_csv(i, index=False, line_terminator="\n")
Path(__file__).resolve().parents[2] / "data_concelhos_incidencia.csv")
PATH_TO_CSV_14DIAS = str(
Path(__file__).resolve().parents[2] / "data_concelhos_14dias.csv")
# Get list of municipalities
concelhos_df = get_list_municipalities()
# Get list of cases
casos_df = get_list_cases_long()
casos_df["confirmados_14"] = (casos_df["incidencia"] *
casos_df["population"] / 100000.0)
casos_df["confirmados_1"] = casos_df["confirmados_14"].div(14)
cols = ["confirmados_14", "confirmados_1"]
casos_df = convert(casos_df, cols, convert_to_int)
cols = ["incidencia"]
casos_df = convert(casos_df, cols, convert_to_float)
cols = [x for x in casos_df.columns if x.startswith("densidade")]
casos_df = convert(casos_df, cols, convert_to_float)
cols = [x for x in casos_df.columns if x.startswith("population")]
casos_df = convert(casos_df, cols, convert_to_int)
cols = list(casos_df.columns)
for i in ["data", "confirmados_14", "confirmados_1"]:
cols.remove(i)
cols.insert(cols.index("concelho") + 1, "confirmados_14")
cols.insert(cols.index("concelho") + 2, "confirmados_1")
cols.insert(0, "data")
casos_df = casos_df[cols]
casos_df = get_list_cases_long()
# Merge list of cases with list of municipalities
casos_df = concelhos_df.merge(casos_df, how="left", on="concelho")
# Helper for pivot table
casos_df.loc[casos_df.data.isna(), ["confirmados"]] = -1
casos_df.loc[casos_df.data.isna(), ["data"]] = "24-03-2020"
casos_df = casos_df.sort_values(by=["concelho"])
# Convert long table to wide table
casos_wide = pd.pivot_table(casos_df,
values="confirmados",
index="data",
columns="concelho")
casos_wide = casos_wide.reset_index()
casos_wide.data = pd.to_datetime(casos_wide.data, format="%d-%m-%Y")
casos_wide = casos_wide.sort_values(by="data").reset_index(drop=True)
casos_wide = casos_wide.replace(-1, np.nan)
casos_wide = patch_concelhos1(casos_wide)
casos_wide.data = casos_wide["data"].dt.strftime("%d-%m-%Y")
casos_wide = patch_concelhos2(casos_wide)
cols = [x for x in casos_wide.columns if not x.startswith("data")]
casos_wide = convert(casos_wide, cols, convert_to_int)
casos_wide.to_csv(PATH_TO_CSV, index=False, sep=",")