def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
kwargs:
print additional metadata in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
justify = string_justify(18)
print(self)
print("{} = {}".format(justify("number of subjects"), self.durations.shape[0]))
print("{} = {}".format(justify("number of events"), np.where(self.event_observed)[0].shape[0]))
print("{} = {:.3f}".format(justify("log-likelihood"), self._log_likelihood))
print("{} = {}".format(justify("hypothesis"), "lambda != 1, rho != 1"))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
print(df.to_string(float_format=format_floats(decimals), formatters={"p": format_p_value(decimals)}))
def to_html(self):
decimals = self.decimals
summary_df = self.model.summary
columns = summary_df.columns
headers = self.headers.copy()
headers.insert(0, ("model", "lifelines." + self.model._class_name))
header_df = pd.DataFrame.from_records(headers).set_index(0)
header_html = header_df.to_html(header=False,
notebook=True,
index_names=False)
summary_html = summary_df.to_html(
float_format=utils.format_floats(decimals),
formatters={
**{
c: utils.format_exp_floats(decimals)
for c in columns if "exp(" in c
},
**{
"p": utils.format_p_value(decimals)
},
},
)
if self.footers:
footer_df = pd.DataFrame.from_records(self.footers).set_index(0)
footer_html = footer_df.to_html(header=False,
notebook=True,
index_names=False)
else:
footer_html = ""
return header_html + summary_html + footer_html
def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
kwargs:
print additional meta data in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
# Print information about data first
justify = string_justify(18)
print(self)
print("{} = '{}'".format(justify("event col"), self.event_col))
if self.weights_col:
print("{} = '{}'".format(justify("weights col"), self.weights_col))
if self.strata:
print("{} = {}".format(justify("strata"), self.strata))
if self.penalizer > 0:
print("{} = {}".format(justify("penalizer"), self.penalizer))
print("{} = {}".format(justify("number of subjects"), self._n_unique))
print("{} = {}".format(justify("number of periods"), self._n_examples))
print("{} = {}".format(justify("number of events"), self.event_observed.sum()))
print("{} = {:.{prec}f}".format(justify("log-likelihood"), self._log_likelihood, prec=decimals))
print("{} = {} UTC".format(justify("time fit was run"), self._time_fit_was_called))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
# Significance codes last
print(
df.to_string(
float_format=format_floats(decimals),
formatters={"p": format_p_value(decimals), "exp(coef)": format_exp_floats(decimals)},
)
)
# Significance code explanation
print("---")
with np.errstate(invalid="ignore", divide="ignore"):
sr = self.log_likelihood_ratio_test()
print(
"Log-likelihood ratio test = {:.{prec}f} on {} df, -log2(p)={:.{prec}f}".format(
sr.test_statistic, sr.degrees_freedom, -np.log2(sr.p_value), prec=decimals
)
)
def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
kwargs:
print additional meta data in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
# Print information about data first
justify = string_justify(18)
print(self)
print("{} = '{}'".format(justify("event col"), self.event_col))
if self.weights_col:
print("{} = '{}'".format(justify("weights col"), self.weights_col))
if self.strata:
print("{} = {}".format(justify("strata"), self.strata))
if self.penalizer > 0:
print("{} = {}".format(justify("penalizer"), self.penalizer))
print("{} = {}".format(justify("number of subjects"), self._n_unique))
print("{} = {}".format(justify("number of periods"), self._n_examples))
print("{} = {}".format(justify("number of events"), self.event_observed.sum()))
print("{} = {:.{prec}f}".format(justify("log-likelihood"), self._log_likelihood, prec=decimals))
print("{} = {} UTC".format(justify("time fit was run"), self._time_fit_was_called))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
# Significance codes last
print(
df.to_string(
float_format=format_floats(decimals),
formatters={"p": format_p_value(decimals), "exp(coef)": format_exp_floats(decimals)},
)
)
# Significance code explanation
print("---")
with np.errstate(invalid="ignore", divide="ignore"):
sr = self.log_likelihood_ratio_test()
print(
"Log-likelihood ratio test = {:.{prec}f} on {} df, -log2(p)={:.{prec}f}".format(
sr.test_statistic, sr.degrees_freedom, -np.log2(sr.p_value), prec=decimals
)
)
def to_html(self):
decimals = self.decimals
summary_df = self.model.summary
columns = summary_df.columns
headers = self.headers.copy()
headers.insert(0, ("model", "lifelines." + self.model._class_name))
header_df = pd.DataFrame.from_records(headers).set_index(0)
header_html = header_df.to_html(header=False,
notebook=True,
index_names=False)
summary_html = summary_df.to_html(
float_format=utils.format_floats(decimals),
formatters={
**{
c: utils.format_exp_floats(decimals)
for c in columns if "exp(" in c
},
**{
"p": utils.format_p_value(decimals)
},
},
)
footers = []
with np.errstate(invalid="ignore", divide="ignore"):
try:
if utils.CensoringType.is_right_censoring(
self.model) and self.model._KNOWN_MODEL:
footers.append(
("Concordance", "{:.{prec}f}".format(self.model.score_,
prec=decimals)))
except AttributeError:
pass
try:
sr = self.model.log_likelihood_ratio_test()
footers.append((
"Log-likelihood ratio test",
"{:.{prec}f} on {} df, -log2(p)={:.{prec}f}".format(
sr.test_statistic,
sr.degrees_freedom,
-np.log2(sr.p_value),
prec=decimals),
))
except AttributeError:
pass
if footers:
footer_df = pd.DataFrame.from_records(footers).set_index(0)
footer_html = footer_df.to_html(header=False,
notebook=True,
index_names=False)
else:
footer_html = ""
return header_html + summary_html + footer_html
def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
alpha: float or iterable
specify confidence intervals to show
kwargs:
print additional metadata in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
# Print information about data first
justify = string_justify(18)
print(self)
print("{} = '{}'".format(justify("duration col"), self.duration_col))
if self.event_col:
print("{} = '{}'".format(justify("event col"), self.event_col))
if self.weights_col:
print("{} = '{}'".format(justify("weights col"), self.weights_col))
if self.penalizer > 0:
print("{} = {}".format(justify("penalizer"), self.penalizer))
if self.robust:
print("{} = {}".format(justify("robust variance"), True))
print("{} = {}".format(justify("number of subjects"), self._n_examples))
print("{} = {}".format(justify("number of events"), self.event_observed.sum()))
print("{} = {:.{prec}f}".format(justify("log-likelihood"), self._log_likelihood, prec=decimals))
print("{} = {}".format(justify("time fit was run"), self._time_fit_was_called))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
# Significance codes as last column
print(
df.to_string(
float_format=format_floats(decimals),
formatters={"p": format_p_value(decimals), "exp(coef)": format_exp_floats(decimals)},
)
)
# Significance code explanation
print("---")
print("Concordance = {:.{prec}f}".format(self.score_, prec=decimals))
print(
"Log-likelihood ratio test = {:.{prec}f} on {} df, -log2(p)={:.{prec}f}".format(
*self._compute_likelihood_ratio_test(), prec=decimals
)
)
def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
kwargs:
print additional meta data in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
# Print information about data first
justify = string_justify(18)
print(self)
print("{} = '{}'".format(justify("duration col"), self.duration_col))
print("{} = '{}'".format(justify("event col"), self.event_col))
if self.weights_col:
print("{} = '{}'".format(justify("weights col"), self.weights_col))
if self.coef_penalizer > 0:
print("{} = '{}'".format(justify("coef penalizer"),
self.coef_penalizer))
if self.smoothing_penalizer > 0:
print("{} = '{}'".format(justify("smoothing penalizer"),
self.smoothing_penalizer))
print("{} = {}".format(justify("number of subjects"),
self._n_examples))
print("{} = {}".format(justify("number of events"),
self.event_observed.sum()))
print("{} = {}".format(justify("time fit was run"),
self._time_fit_was_called))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
print(
df.to_string(
float_format=format_floats(decimals),
formatters={
"p": format_p_value(decimals),
"exp(coef)": format_exp_floats(decimals)
},
))
# Significance code explanation
print("---")
print("Concordance = {:.{prec}f}".format(self.score_, prec=decimals))
def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
kwargs:
print additional metadata in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
# Print information about data first
justify = string_justify(18)
print(self)
print("{} = '{}'".format(justify("event col"), self.event_col))
if self.weights_col:
print("{} = '{}'".format(justify("weights col"), self.weights_col))
if self.strata:
print("{} = {}".format(justify("strata"), self.strata))
print("{} = {}".format(justify("number of subjects"), self._n_unique))
print("{} = {}".format(justify("number of periods"), self._n_examples))
print("{} = {}".format(justify("number of events"),
self.event_observed.sum()))
print("{} = {:.{prec}f}".format(justify("log-likelihood"),
self._log_likelihood,
prec=decimals))
print("{} = {} UTC".format(justify("time fit was run"),
self._time_fit_was_called))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
# Significance codes last
df[""] = [significance_code(p) for p in df["p"]]
print(
df.to_string(float_format=format_floats(decimals),
formatters={"p": format_p_value(decimals)}))
# Significance code explanation
print("---")
print(significance_codes_as_text(), end="\n\n")
print(
"Likelihood ratio test = {:.{prec}f} on {} df, log(p)={:.{prec}f}".
format(*self._compute_likelihood_ratio_test(), prec=decimals))
def to_ascii(self, decimals=2, **kwargs):
extra_kwargs = dict(list(self._kwargs.items()) + list(kwargs.items()))
meta_data = self._stringify_meta_data(extra_kwargs)
df = self.summary
s = "<lifelines.StatisticalResult: {0}>".format(self.test_name)
s += "\n" + meta_data + "\n"
s += "---\n"
s += df.to_string(
float_format=format_floats(decimals), index=self.name is not None, formatters={"p": format_p_value(decimals)}
)
return s
def to_html(self, decimals=2, **kwargs):
extra_kwargs = dict(list(self._kwargs.items()) + list(kwargs.items()))
summary_df = self.summary
headers = []
for k, v in extra_kwargs.items():
headers.append((k, v))
header_df = pd.DataFrame.from_records(headers).set_index(0)
header_html = header_df.to_html(header=False, notebook=True, index_names=False)
summary_html = summary_df.to_html(float_format=format_floats(decimals), formatters={**{"p": format_p_value(decimals)}})
return header_html + summary_html
def print_summary(self, decimals=2, **kwargs):
"""
Print summary statistics describing the fit, the coefficients, and the error bounds.
Parameters
-----------
decimals: int, optional (default=2)
specify the number of decimal places to show
kwargs:
print additional meta data in the output (useful to provide model names, dataset names, etc.) when comparing
multiple outputs.
"""
# Print information about data first
justify = string_justify(18)
print(self)
print("{} = '{}'".format(justify("duration col"), self.duration_col))
print("{} = '{}'".format(justify("event col"), self.event_col))
if self.weights_col:
print("{} = '{}'".format(justify("weights col"), self.weights_col))
if self.coef_penalizer > 0:
print("{} = '{}'".format(justify("coef penalizer"), self.coef_penalizer))
if self.smoothing_penalizer > 0:
print("{} = '{}'".format(justify("smoothing penalizer"), self.smoothing_penalizer))
print("{} = {}".format(justify("number of subjects"), self._n_examples))
print("{} = {}".format(justify("number of events"), self.event_observed.sum()))
print("{} = {}".format(justify("time fit was run"), self._time_fit_was_called))
for k, v in kwargs.items():
print("{} = {}\n".format(justify(k), v))
print(end="\n")
print("---")
df = self.summary
print(
df.to_string(
float_format=format_floats(decimals),
formatters={"p": format_p_value(decimals), "exp(coef)": format_exp_floats(decimals)},
)
)
# Significance code explanation
print("---")
print("Concordance = {:.{prec}f}".format(self.score_, prec=decimals))
def to_ascii(self, decimals=2, **kwargs):
extra_kwargs = dict(list(self._kwargs.items()) + list(kwargs.items()))
meta_data = self._stringify_meta_data(extra_kwargs)
df = self.summary
df["-log2(p)"] = -utils.quiet_log2(df["p"])
s = self.__repr__()
s += "\n" + meta_data + "\n"
s += "---\n"
s += df.to_string(float_format=format_floats(decimals),
index=self.name is not None,
formatters={"p": format_p_value(decimals)})
return s
def to_ascii(self, decimals=2, **kwargs):
extra_kwargs = dict(list(self._kwargs.items()) + list(kwargs.items()))
meta_data = self._stringify_meta_data(extra_kwargs)
df = self.summary
with np.errstate(invalid="ignore", divide="ignore"):
df["-log2(p)"] = -np.log2(df["p"])
s = self.__repr__()
s += "\n" + meta_data + "\n"
s += "---\n"
s += df.to_string(
float_format=format_floats(decimals), index=self.name is not None, formatters={"p": format_p_value(decimals)}
)
return s
def _to_string(self, decimals=2, **kwargs):
extra_kwargs = dict(list(self._kwargs.items()) + list(kwargs.items()))
meta_data = self._stringify_meta_data(extra_kwargs)
df = self.summary
df["log(p)"] = np.log(df["p"])
df[""] = [significance_code(p) for p in df["p"]]
s = self.__repr__()
s += "\n" + meta_data + "\n"
s += "---\n"
s += df.to_string(
float_format=format_floats(decimals),
index=self.name is not None,
formatters={"p": format_p_value(decimals)},
)
s += "\n---"
s += "\n" + significance_codes_as_text()
return s
def ascii_print(self):
decimals = self.decimals
df = self.model.summary
justify = self.justify
print(self.model)
for string, value in self.headers:
print("{} = {}".format(justify(string), value))
print(end="\n")
print("---")
df.columns = utils.map_leading_space(df.columns)
columns = df.columns
if len(columns) <= 7:
# only need one row of display
first_row_set = [
"coef",
"exp(coef)",
"se(coef)",
"coef lower 95%",
"coef upper 95%",
"exp(coef) lower 95%",
"exp(coef) upper 95%",
"z",
"p",
"-log2(p)",
]
second_row_set = []
else:
first_row_set = [
"coef",
"exp(coef)",
"se(coef)",
"coef lower 95%",
"coef upper 95%",
"exp(coef) lower 95%",
"exp(coef) upper 95%",
]
second_row_set = ["z", "p", "-log2(p)"]
print(
df.to_string(
float_format=utils.format_floats(decimals),
formatters={
**{c: utils.format_exp_floats(decimals) for c in columns if "exp(" in c},
**{utils.leading_space("p"): utils.format_p_value(decimals)},
},
columns=[c for c in utils.map_leading_space(first_row_set) if c in columns],
)
)
if second_row_set:
print()
print(
df.to_string(
float_format=utils.format_floats(decimals),
formatters={
**{c: utils.format_exp_floats(decimals) for c in columns if "exp(" in c},
**{utils.leading_space("p"): utils.format_p_value(decimals)},
},
columns=utils.map_leading_space(second_row_set),
)
)
with np.errstate(invalid="ignore", divide="ignore"):
try:
print("---")
if utils.CensoringType.is_right_censoring(self.model) and self.model._KNOWN_MODEL:
print("Concordance = {:.{prec}f}".format(self.model.score_, prec=decimals))
except AttributeError:
pass
try:
sr = self.model.log_likelihood_ratio_test()
print(
"Log-likelihood ratio test = {:.{prec}f} on {} df, -log2(p)={:.{prec}f}".format(
sr.test_statistic, sr.degrees_freedom, -np.log2(sr.p_value), prec=decimals
)
)
except AttributeError:
pass
print()
def to_ascii(self):
df = self.model.summary
justify = self.justify
ci = 100 * (1 - self.model.alpha)
decimals = self.decimals
repr_string = ""
repr_string += repr(self.model) + "\n"
for string, value in self.headers:
repr_string += "{} = {}".format(justify(string), value) + "\n"
repr_string += "\n" + "---" + "\n"
df.columns = utils.map_leading_space(df.columns)
if self.columns is not None:
columns = df.columns.intersection(
utils.map_leading_space(self.columns))
else:
columns = df.columns
if len(columns) <= 7:
# only need one row of display
first_row_set = [
"coef",
"exp(coef)",
"se(coef)",
"coef lower %d%%" % ci,
"coef upper %d%%" % ci,
"exp(coef) lower %d%%" % ci,
"exp(coef) upper %d%%" % ci,
"z",
"p",
"-log2(p)",
]
second_row_set = []
else:
first_row_set = [
"coef",
"exp(coef)",
"se(coef)",
"coef lower %d%%" % ci,
"coef upper %d%%" % ci,
"exp(coef) lower %d%%" % ci,
"exp(coef) upper %d%%" % ci,
]
second_row_set = ["z", "p", "-log2(p)"]
repr_string += df[columns].to_string(
float_format=utils.format_floats(decimals),
formatters={
**{
c: utils.format_exp_floats(decimals)
for c in columns if "exp(coef)" in c
},
**{
utils.leading_space("p"): utils.format_p_value(decimals)
},
},
columns=[
c for c in utils.map_leading_space(first_row_set)
if c in columns
],
)
if second_row_set:
repr_string += "\n\n"
repr_string += df[
columns].to_string(
float_format=utils.format_floats(decimals),
formatters={
**{
c: utils.format_exp_floats(decimals)
for c in columns if "exp(" in c
},
**{
utils.leading_space("p"):
utils.format_p_value(decimals)
},
},
columns=utils.map_leading_space(second_row_set),
)
with np.errstate(invalid="ignore", divide="ignore"):
repr_string += "\n" + "---" + "\n"
for string, value in self.footers:
repr_string += "{} = {}".format(string, value) + "\n"
return repr_string
def ascii_print(self):
decimals = self.decimals
df = self.model.summary
justify = self.justify
print(self.model)
for string, value in self.headers:
print("{} = {}".format(justify(string), value))
print(end="\n")
print("---")
df.columns = utils.map_leading_space(df.columns)
columns = df.columns
if len(columns) <= 7:
# only need one row of display
first_row_set = [
"coef",
"exp(coef)",
"se(coef)",
"coef lower 95%",
"coef upper 95%",
"exp(coef) lower 95%",
"exp(coef) upper 95%",
"z",
"p",
"-log2(p)",
]
second_row_set = []
else:
first_row_set = [
"coef",
"exp(coef)",
"se(coef)",
"coef lower 95%",
"coef upper 95%",
"exp(coef) lower 95%",
"exp(coef) upper 95%",
]
second_row_set = ["z", "p", "-log2(p)"]
print(
df.to_string(
float_format=utils.format_floats(decimals),
formatters={
**{c: utils.format_exp_floats(decimals) for c in columns if "exp(coef)" in c},
**{utils.leading_space("p"): utils.format_p_value(decimals)},
},
columns=[c for c in utils.map_leading_space(first_row_set) if c in columns],
)
)
if second_row_set:
print()
print(
df.to_string(
float_format=utils.format_floats(decimals),
formatters={
**{c: utils.format_exp_floats(decimals) for c in columns if "exp(" in c},
**{utils.leading_space("p"): utils.format_p_value(decimals)},
},
columns=utils.map_leading_space(second_row_set),
)
)
with np.errstate(invalid="ignore", divide="ignore"):
print("---")
for string, value in self.footers:
print("{} = {}".format(string, value))