def _check_values(df, T, E):
pass_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_nans_or_infs(df)
check_low_var(df)
check_complete_separation(df, E, T)
def _check_values(self, df, T, E, weights, entries):
check_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(df)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_positivity(T)
check_complete_separation(df, E, T, self.event_col)
if self.weights_col:
if (weights.astype(int) != weights).any() and not self.robust:
warnings.warn(
dedent(
"""It appears your weights are not integers, possibly propensity or sampling scores then?
It's important to know that the naive variance estimates of the coefficients are biased. Instead a) set `robust=True` in the call to `fit`, or b) use Monte Carlo to
estimate the variances. See paper "Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis"""
),
StatisticalWarning,
)
if (weights <= 0).any():
raise ValueError(
"values in weight column %s must be positive." %
self.weights_col)
if self.entry_col:
count_invalid_rows = (entries > T).sum()
if count_invalid_rows:
warnings.warn(
"""There exist %d rows where entry > duration.""")
def _check_values(self, df, T, E, event_col):
check_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_nans_or_infs(df)
check_complete_separation(df, E, T, event_col)
if self.fit_intercept:
check_low_var(df)
def _check_values(df, E):
# check_for_overlapping_intervals(df) # this is currenty too slow for production.
check_low_var(df)
check_complete_separation(df, E)
pass_for_numeric_dtypes_or_raise(df)
def _check_values(df, E):
check_low_var(df)
check_complete_separation(df, E)
pass_for_numeric_dtypes_or_raise(df)
def _check_values(df, E):
check_low_var(df)
check_complete_separation(df, E)
pass_for_numeric_dtypes_or_raise(df)
def _check_values(df, E):
# check_for_overlapping_intervals(df) # this is currenty too slow for production.
check_low_var(df)
check_complete_separation(df, E)
pass_for_numeric_dtypes_or_raise(df)
