def history(self,
param,
roll_window=None,
show_figure=True,
filename=None,
**kwargs):
"""
Return subset of summary and show a figure to show the history of all countries.
Args:
param (str): parameter/day parameter/Rt/OxCGRT score to show
roll_window (int or None): rolling average window if necessary
show_figure (bool): If True, show the result as a figure
filename (str): filename of the figure, or None (show figure)
kwargs: keword arguments of line_plot()
Returns:
pandas.DataFrame:
Index
Date (pd.Timestamp) date
Columns
(str) country names
Values:
parameter values
"""
# Get the parameter value of each date
df = self.track()
# Select the param
if param not in df.columns:
sel_param_str = ', '.join(df.columns.tolist())
raise KeyError(
f"@param must be selected from {sel_param_str}, but {param} was applied."
)
df = df.pivot_table(values=param,
index=self.DATE,
columns=self.COUNTRY,
aggfunc="last")
# Rolling mean
if roll_window is not None:
roll_window = self._ensure_natural_int(roll_window,
name="roll_window")
df = df.rolling(window=roll_window).mean()
# Show figure
if not show_figure:
return df
line_plot(df,
title=f"History of {param} in each country",
ylabel=param,
h=1 if param == self.RT else None,
filename=filename,
**kwargs)
return df
def positive_rate(self,
country,
province=None,
window=7,
last_date=None,
show_figure=True,
filename=None):
"""
Return the PCR rate of a country as a dataframe.
Args:
country(str): country name or ISO3 code
province(str or None): province name
window (int): window of moving average, >= 1
last_date (str or None): the last date of the total tests records or None (max date of main dataset)
show_figure (bool): if True, show the records as a line-plot.
filename (str): filename of the figure, or None (display figure)
Raises:
covsirphy.PCRIncorrectPreconditionError: the dataset has too many missing values
Returns:
pandas.DataFrame
Index
reset index
Columns
- Date (pandas.TimeStamp): Observation date
- Tests (int): the number of total tests performed
- Confirmed (int): the number of confirmed cases
- Tests_diff (int): daily tests performed
- Confirmed_diff (int): daily confirmed cases
- Test_positive_rate (float): positive rate (%) of the daily cases over the total daily tests performed
Note:
If non monotonic records were found for either confirmed cases or tests,
"with partially complemented tests data" will be added to the title of the figure.
"""
window = self._ensure_natural_int(window, name="window")
# Subset with area
country_alias = self.ensure_country_name(country)
province = province or self.UNKNOWN
try:
subset_df = self._subset_select(country_alias, province)
except PCRIncorrectPreconditionError:
raise PCRIncorrectPreconditionError(
country=country,
province=province,
message="Too many missing Tests records") from None
# Limit tests records to last date
if last_date is not None:
subset_df = subset_df.loc[
subset_df[self.DATE] <= pd.to_datetime(last_date)]
# Process PCR data
df, is_complemented = self._pcr_processing(subset_df, window)
# Calculate PCR values
df[self.PCR_RATE] = df[[self.C_DIFF, self.T_DIFF
]].apply(lambda x: x[0] / x[1] * 100
if x[1] > self.min_pcr_tests else 0,
axis=1)
if not show_figure:
return df
# Create figure
area = self.area_name(country, province=province)
comp_status = "\nwith partially complemented tests data" if is_complemented else ""
line_plot(
df.set_index(self.DATE)[self.PCR_RATE],
title=f"{area}: Test positive rate (%) over time {comp_status}",
ylabel="Test positive rate (%)",
y_integer=True,
filename=filename,
show_legend=False,
)
return df