def _curve_fitting(self, phase, start_date, end_date):
"""
Perform curve fitting for the phase.
Args:
phase (str): phase name
start_date (str): start date of the phase
end_date (str): end date of the phase
Returns:
tuple
(pandas.DataFrame): Result of curve fitting
Index: reset index
Columns:
- (phase name)_predicted: predicted value of Susceptible
- (phase_name)_actual: actual value of Susceptible
- (phase_name)_Recovered: Recovered
(int): minimum value of R, which is the change point of the curve
"""
sr_df = self.sr_df.copy()
sta = self.date_obj(start_date)
end = self.date_obj(end_date)
sr_df = sr_df.loc[(sr_df.index >= sta) & (sr_df.index <= end), :]
trend = Trend(sr_df)
df = trend.run()
if trend.rmsle() > self.max_rmsle:
df[f"{self.S}{self.P}"] = None
# Get min value for vline
r_value = int(df[self.R].min())
# Rename the columns
phase = self.INITIAL if phase == "0th" else phase
df = df.rename({f"{self.S}{self.P}": f"{phase}{self.P}"}, axis=1)
df = df.rename({f"{self.S}{self.A}": f"{phase}{self.A}"}, axis=1)
df = df.rename({f"{self.R}": f"{phase}_{self.R}"}, axis=1)
return (df, r_value)
def error_f(self, start_dates, end_dates):
"""
Definition of error score to minimize in the study.
This is weighted average of RMSLE scores.
@start_dates <list[str]>: list of start date of phases (candidates)
@end_dates <list[str]>: list of end date of phases (candidates)
@return <float> : score of the error function to minimize
"""
scores = list()
for (start_date, end_date) in zip(start_dates, end_dates):
population = self.pop_dict[start_date]
trend = Trend(self.clean_df,
population,
self.country,
province=self.province,
start_date=start_date,
end_date=end_date)
trend.analyse()
scores.append(trend.rmsle())
return np.average(scores, weights=range(1, len(scores) + 1))
def _curve_fitting(self, phase, info):
"""
Perform curve fitting for the phase.
Args:
phase (str): phase name
info (dict[str]): start date, end date and population
Returns:
(tuple)
(pandas.DataFrame): Result of curve fitting
Index: reset index
Columns:
- (phase name)_predicted: predicted value of Susceptible
- (phase_name)_actual: actual value of Susceptible
- (phase_name)_Recovered: Recovered
(int): minimum value of R, which is the change point of the curve
"""
start_date = info[self.START]
end_date = info[self.END]
population = info[self.N]
trend = Trend(
self.jhu_data, population, self.country, province=self.province,
start_date=start_date, end_date=end_date
)
trend.analyse()
df = trend.result()
if trend.rmsle() > self.max_rmsle:
df[f"{self.S}{self.P}"] = None
# Get min value for vline
r_value = int(df[self.R].min())
# Rename the columns
phase = self.INITIAL if phase == "0th" else phase
df = df.rename({f"{self.S}{self.P}": f"{phase}{self.P}"}, axis=1)
df = df.rename({f"{self.S}{self.A}": f"{phase}{self.A}"}, axis=1)
df = df.rename({f"{self.R}": f"{phase}_{self.R}"}, axis=1)
return (df, r_value)