def _run_lifelines(model: CoxTimeVaryingFitter,
data: pd.DataFrame) -> pd.DataFrame:
"""Retrieve the win probability.
Parameters
----------
model : CoxTimeVaryingFitter
The fitted model.
data : pd.DataFrame
The input dataset to be evaluated.
Returns
-------
pd.DataFrame
The updated dataset.
"""
# Get the cumulative hazard -- copying from ``lifelines.fitters.SemiParametericPHFitter``
vals = model.predict_partial_hazard(data[META["static"] +
META["dynamic"]])
c0 = interpolate_at_times(model.baseline_cumulative_hazard_,
data["stop"].values)
# Survival is the negative exponent of the cumulative hazard
new = data.copy()
new[META["survival"]] = 1 - np.exp(-(c0 * vals.values))
return new
def func(params):
model = CoxTimeVaryingFitter(**params, **kwargs)
model.fit(
train_data[[META["id"], META["event"]] + ["start", "stop"] +
META["static"] + META["dynamic"]],
id_col=META["id"],
event_col=META["event"],
start_col="start",
stop_col="stop",
)
metric: List[float] = []
for dataset in tune_data:
predt = model.predict_partial_hazard(dataset)
c0 = interpolate_at_times(model.baseline_cumulative_hazard_,
dataset["stop"].values)
metric.append(
roc_auc_score(
y_true=dataset[META["event"]],
y_score=1 - np.exp(-(c0 * predt.values)),
))
metric = -np.average(np.array(metric))
if metric < self.metric_:
self.metric_ = metric
self.best_.update(params)
self.logger.info(
f"New best metric value of {self.metric_} with \n\n{pformat(self.best_)}\n"
)
return {
"loss": metric,
"status": STATUS_OK,
}
event_col="Out",
start_col="Start",
stop_col="End",
show_progress=True)
ctv.print_summary()
#Get Hazards for specific episode
####EDIT THIS TO CHANGE WHICH SEASON/EPISODE YOU WANT TO APPLY THE MODEL TO#####
episode = 5
season = 13
predictData = allSeasonsByEpisode.loc[
(allSeasonsByEpisode["Episode"] == episode)
& (allSeasonsByEpisode["Season"] == season)]
## generate the relative risk with the model and merge it with the existing data
predictData["Partial Hazard"] = ctv.predict_partial_hazard(predictData)
predictData["Log Partial Hazard"] = ctv.predict_log_partial_hazard(predictData)
## clean up the data frame and display the ordered relative risks
predictData = predictData.sort_values(["Partial Hazard"], ascending=[True])
print("Model predictions for season " + str(season) + ", episode " +
str(episode))
print(predictData[[
"FirstName", "LastName", "Partial Hazard", "Log Partial Hazard"
]])
"""
What if we account for how many people are left in the competition
"""
ctv_compleft = CoxTimeVaryingFitter()
ctv_compleft.fit(trainData[[
"Age", "CompLeft", "QuickfireWins", "Wins", "Highs", "Lows", "Start",
"End", "ID", "Out"