def test_survival_table_from_events_raises_value_error_if_too_early_births():
n = 10
T = np.arange(0, n)
C = [True] * n
min_obs = T.copy()
min_obs[1] = min_obs[1] + 10
with pytest.raises(ValueError):
utils.survival_table_from_events(T, C, min_obs)
def test_survival_table_from_events_with_non_trivial_censorship_column():
T = np.random.exponential(5, size=50)
malformed_C = np.random.binomial(2, p=0.8) # set to 2 on purpose!
proper_C = malformed_C > 0 # (proper "boolean" array)
table1 = utils.survival_table_from_events(T, malformed_C, np.zeros_like(T))
table2 = utils.survival_table_from_events(T, proper_C, np.zeros_like(T))
assert_frame_equal(table1, table2)
def test_survival_table_from_events_raises_value_error_if_too_early_births():
n = 10
T = np.arange(0, n)
C = [True] * n
min_obs = T.copy()
min_obs[1] = min_obs[1] + 10
with pytest.raises(ValueError):
utils.survival_table_from_events(T, C, min_obs)
def preprocess_inputs(durations, event_observed, timeline, entry):
n = len(durations)
durations = np.asarray(durations).reshape((n, ))
# set to all observed if event_observed is none
if event_observed is None:
event_observed = np.ones(n, dtype=int)
else:
event_observed = np.asarray(event_observed).reshape(
(n, )).copy().astype(int)
if entry is None:
entry = np.zeros(n)
else:
entry = np.asarray(entry).reshape((n, ))
event_table = survival_table_from_events(durations, event_observed, entry)
if timeline is None:
timeline = event_table.index.values
else:
timeline = np.asarray(timeline)
return durations, event_observed, timeline.astype(
float), entry, event_table
def test_survival_events_from_table_with_ties():
T, C = np.array([1, 2, 3, 4, 4, 5]), np.array([1, 0, 1, 1, 1, 1])
d = utils.survival_table_from_events(T, C)
T_, C_, W_ = utils.survival_events_from_table(d[["censored", "observed"]])
npt.assert_array_equal([1, 2, 3, 4, 5], T_)
npt.assert_array_equal([1, 0, 1, 1, 1], C_)
npt.assert_array_equal([1, 1, 1, 2, 1], W_)
def test_survival_table_from_events_at_risk_column():
df = load_waltons()
# from R
expected = [163.0, 162.0, 160.0, 157.0, 154.0, 152.0, 151.0, 148.0, 144.0, 139.0, 134.0, 133.0, 130.0, 128.0, 126.0, 119.0, 118.0,
108.0, 107.0, 99.0, 96.0, 89.0, 87.0, 69.0, 65.0, 49.0, 38.0, 36.0, 27.0, 24.0, 14.0, 1.0]
df = utils.survival_table_from_events(df['T'], df['E'])
assert list(df['at_risk'][1:]) == expected # skip the first event as that is the birth time, 0.
def test_survival_table_from_events_at_risk_column():
df = load_waltons()
# from R
expected = [163.0, 162.0, 160.0, 157.0, 154.0, 152.0, 151.0, 148.0, 144.0, 139.0, 134.0, 133.0, 130.0, 128.0, 126.0, 119.0, 118.0,
108.0, 107.0, 99.0, 96.0, 89.0, 87.0, 69.0, 65.0, 49.0, 38.0, 36.0, 27.0, 24.0, 14.0, 1.0]
df = utils.survival_table_from_events(df['T'], df['E'])
assert list(df['at_risk'][1:]) == expected # skip the first event as that is the birth time, 0.
def test_survival_table_from_events_will_collapse_if_asked():
T, C = np.array([1, 3, 4, 5]), np.array([True, True, True, True])
table = utils.survival_table_from_events(T, C, collapse=True)
assert table.index.tolist() == [
pd.Interval(0, 3.5089999999999999, closed="right"),
pd.Interval(3.5089999999999999, 7.0179999999999998, closed="right"),
]
def test_survival_events_from_table_no_ties():
T, C = np.array([1, 2, 3, 4, 4, 5]), np.array([1, 0, 1, 1, 0, 1])
d = utils.survival_table_from_events(T, C)
T_, C_, W_ = utils.survival_events_from_table(d[["censored", "observed"]])
npt.assert_array_equal(T, T_)
npt.assert_array_equal(C, C_)
npt.assert_array_equal(W_, np.ones_like(T))
def test_survival_table_to_events_casts_to_float():
T, C = (np.array([1, 2, 3, 4, 4,
5]), np.array([True, False, True, True, True, True]))
d = utils.survival_table_from_events(T, C, np.zeros_like(T))
npt.assert_array_equal(d["censored"].values,
np.array([0.0, 0.0, 1.0, 0.0, 0.0, 0.0]))
npt.assert_array_equal(d["removed"].values,
np.array([0.0, 1.0, 1.0, 1.0, 2.0, 1.0]))
def test_survival_table_from_events_with_non_negative_T_and_no_lagged_births():
n = 10
T = np.arange(n)
C = [True] * n
min_obs = [0] * n
df = utils.survival_table_from_events(T, C, min_obs)
assert df.iloc[0]["entrance"] == n
assert df.index[0] == T.min()
assert df.index[-1] == T.max()
def test_survival_table_from_events_with_negative_T_and_lagged_births():
n = 10
T = np.arange(-n / 2, n / 2)
C = [True] * n
min_obs = np.linspace(-n / 2, 2, n)
df = utils.survival_table_from_events(T, C, min_obs)
assert df.iloc[0]["entrance"] == 1
assert df.index[0] == T.min()
assert df.index[-1] == T.max()
def test_survival_table_from_events_with_negative_T_and_lagged_births():
n = 10
T = np.arange(-n / 2, n / 2)
C = [True] * n
min_obs = np.linspace(-n / 2, 2, n)
df = utils.survival_table_from_events(T, C, min_obs)
assert df.iloc[0]['entrance'] == 1
assert df.index[0] == T.min()
assert df.index[-1] == T.max()
def test_survival_table_from_events_with_non_negative_T_and_no_lagged_births():
n = 10
T = np.arange(n)
C = [True] * n
min_obs = [0] * n
df = utils.survival_table_from_events(T, C, min_obs)
assert df.iloc[0]['entrance'] == n
assert df.index[0] == T.min()
assert df.index[-1] == T.max()
def test_survival_table_from_events_will_collapse_to_desired_bins():
T, C = np.array([1, 3, 4, 5]), np.array([True, True, True, True])
table = utils.survival_table_from_events(T,
C,
collapse=True,
intervals=[0, 4, 8])
assert table.index.tolist() == [
pd.Interval(0, 4, closed="right"),
pd.Interval(4, 8, closed="right")
]
def _compute_baseline_hazard(self, data, durations, event_observed, name):
# http://courses.nus.edu.sg/course/stacar/internet/st3242/handouts/notes3.pdf
ind_hazards = self.predict_partial_hazard(data)
ind_hazards['event_at'] = durations
ind_hazards_summed_over_durations = ind_hazards.groupby('event_at')[0].sum().sort_index(ascending=False).cumsum()
ind_hazards_summed_over_durations.name = 'hazards'
event_table = survival_table_from_events(durations, event_observed)
event_table = event_table.join(ind_hazards_summed_over_durations)
baseline_hazard = pd.DataFrame(event_table['observed'] / event_table['hazards'], columns=[name]).fillna(0)
return baseline_hazard
def _compute_baseline_hazard(self, data, durations, event_observed, name):
# http://courses.nus.edu.sg/course/stacar/internet/st3242/handouts/notes3.pdf
ind_hazards = self.predict_partial_hazard(data)
ind_hazards['event_at'] = durations
ind_hazards_summed_over_durations = ind_hazards.groupby('event_at')[0].sum().sort_index(ascending=False).cumsum()
ind_hazards_summed_over_durations.name = 'hazards'
event_table = survival_table_from_events(durations, event_observed)
event_table = event_table.join(ind_hazards_summed_over_durations)
baseline_hazard = pd.DataFrame(event_table['observed'] / event_table['hazards'], columns=[name]).fillna(0)
return baseline_hazard
def _compute_baseline_hazard(self, data, durations, event_observed, name):
# https://stats.stackexchange.com/questions/46532/cox-baseline-hazard
ind_hazards = self.predict_partial_hazard(data)
ind_hazards['event_at'] = durations.values
ind_hazards_summed_over_durations = ind_hazards.groupby('event_at')[0].sum().sort_index(ascending=False).cumsum()
ind_hazards_summed_over_durations.name = 'hazards'
event_table = survival_table_from_events(durations, event_observed)
event_table = event_table.join(ind_hazards_summed_over_durations)
baseline_hazard = pd.DataFrame(event_table['observed'] / event_table['hazards'], columns=[name]).fillna(0)
return baseline_hazard
def fit(self, event_times, censorship=None, timeline=None, label='NA-estimate', alpha=None, insert_0=True):
"""
Parameters:
event_times: an array, or pd.Series, of length n of times that the death event occured at
timeline: return the best estimate at the values in timelines (postively increasing)
censorship: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if censorship==None
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
insert_0: add a leading 0 (if not present) in the timeline.
Returns:
self, with new properties like 'survival_function_'.
"""
if censorship is None:
self.censorship = np.ones(len(event_times), dtype=bool)
else:
self.censorship = np.array(censorship).copy().astype(bool)
self.event_times = survival_table_from_events(event_times, self.censorship)
if alpha is None:
alpha = self.alpha
if timeline is None:
self.timeline = self.event_times.index.values.copy().astype(float)
if insert_0 and self.timeline[0] > 0:
self.timeline = np.insert(self.timeline, 0, 0.)
else:
self.timeline = np.array(timeline).copy().astype(float)
cumulative_hazard_, cumulative_sq_ = _additive_estimate(self.event_times, self.timeline,
self._additive_f, self._variance_f)
# esimates
self.cumulative_hazard_ = pd.DataFrame(cumulative_hazard_, columns=[label])
self.confidence_interval_ = self._bounds(cumulative_sq_[:, None], alpha)
self._cumulative_sq = cumulative_sq_
# estimation functions
self.predict = _predict(self, "cumulative_hazard_", label)
self.subtract = _subtract(self, "cumulative_hazard_")
self.divide = _divide(self, "cumulative_hazard_")
# plotting
self.plot = plot_dataframes(self, "cumulative_hazard_")
self.plot_cumulative_hazard = self.plot
self.plot_hazard = plot_dataframes(self, 'hazard_')
return self
def _compute_slopes(self):
def _univariate_linear_regression_without_intercept(X, Y, weights):
# normally (weights * X).dot(Y) / X.dot(weights * X), but we have a slightly different form here.
beta = X.dot(Y) / X.dot(weights * X)
errors = Y.values - np.outer(X, beta)
var = (errors ** 2).sum(0) / (Y.shape[0] - 2) / X.dot(weights * X)
return beta, np.sqrt(var)
weights = survival_table_from_events(self.durations, self.event_observed).loc[self._index, "at_risk"].values
y = (weights[:, None] * self.hazards_).cumsum()
X = self._index.values
betas, se = _univariate_linear_regression_without_intercept(X, y, weights)
return pd.Series(betas, index=y.columns), pd.Series(se, index=y.columns)
def _compute_slopes(self):
def _univariate_linear_regression_without_intercept(X, Y, weights):
# normally (weights * X).dot(Y) / X.dot(weights * X), but we have a slightly different form here.
beta = X.dot(Y) / X.dot(weights * X)
errors = Y.values - np.outer(X, beta)
var = (errors ** 2).sum(0) / (Y.shape[0] - 2) / X.dot(weights * X)
return beta, np.sqrt(var)
weights = survival_table_from_events(self.durations, self.event_observed).loc[self._index, "at_risk"].values
y = (weights[:, None] * self.hazards_).cumsum()
X = self._index.values
betas, se = _univariate_linear_regression_without_intercept(X, y, weights)
return pd.Series(betas, index=y.columns), pd.Series(se, index=y.columns)
def _compute_baseline_hazard(self):
# http://courses.nus.edu.sg/course/stacar/internet/st3242/handouts/notes3.pdf
ind_hazards = exp(np.dot(self.data, self.hazards_.T))
event_table = survival_table_from_events(self.durations.values,
self.event_observed.values,
np.zeros_like(self.durations))
n, d = event_table.shape
baseline_hazard_ = pd.DataFrame(np.zeros((n, 1)),
index=event_table.index,
columns=['baseline hazard'])
for t, s in event_table.iterrows():
baseline_hazard_.ix[t] = (s['observed'] /
ind_hazards[self.durations <= t].sum())
return baseline_hazard_
def _compute_baseline_hazard(self):
# http://courses.nus.edu.sg/course/stacar/internet/st3242/handouts/notes3.pdf
ind_hazards = exp(np.dot(self.data, self.hazards_.T))
event_table = survival_table_from_events(self.durations.values,
self.event_observed.values,
np.zeros_like(self.durations))
n, d = event_table.shape
baseline_hazard_ = pd.DataFrame(np.zeros((n, 1)),
index=event_table.index,
columns=['baseline hazard'])
for t, s in event_table.iterrows():
baseline_hazard_.ix[t] = (s['observed'] /
ind_hazards[self.durations <= t].sum())
return baseline_hazard_
def _summarize_survival(df, time_col, event_col, evaluate_at=None):
## prepare survival table
table = survival_table_from_events(df[time_col], df[event_col])
table.reset_index(inplace=True)
## normalize survival as fraction of initial_n
table['initial_n'] = table.loc[table['event_at'] == 0.0,'at_risk'][0]
table['survival'] = table.apply(lambda row: row['at_risk']/row['initial_n'], axis=1)
## handle timepoints if given
if evaluate_at is not None:
evaluate_times = pd.DataFrame({'event_at': evaluate_at})
table = pd.merge(evaluate_times, table, on='event_at', how='outer')
table = table.sort_values('event_at').fillna(method='ffill')
table['keep'] = table['event_at'].apply(lambda x: x in evaluate_at)
else:
table['keep'] = True
table = table.loc[table['keep'] == True,['event_at','survival']]
table.rename(columns={'event_at': time_col}, inplace=True)
return table
def fit(self, event_times, censorship=None, timeline=None, columns=['KM-estimate'], alpha=None, insert_0=True):
"""
Parameters:
event_times: an (n,1) array of times that the death event occured at
timeline: return the best estimate at the values in timelines (postively increasing)
censorship: an (n,1) array of booleans -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if censorship==None
columns: a length 1 array to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
insert_0: add a leading 0 (if not present) in the timeline.
Returns:
DataFrame with index either event_times or timelines (if not None), with
values under column_name with the KaplanMeier estimate
"""
#set to all observed if censorship is none
if censorship is None:
self.censorship = np.ones(event_times.shape[0], dtype=bool) #why boolean?
else:
self.censorship = np.array(censorship).copy()
if not alpha:
alpha = self.alpha
self.event_times = survival_table_from_events(event_times, self.censorship)
if timeline is None:
self.timeline = self.event_times.index.values.copy().astype(float)
if insert_0 and self.timeline[0]>0:
self.timeline = np.insert(self.timeline,0,0.)
else:
self.timeline = timeline.astype(float)
log_survival_function, cumulative_sq_ = _additive_estimate(self.event_times, self.timeline,
self._additive_f, self._additive_var)
self.survival_function_ = pd.DataFrame(np.exp(log_survival_function), columns=columns)
#self.median_ = median_survival_times(self.survival_function_)
self.confidence_interval_ = self._bounds(cumulative_sq_[:,None],alpha)
self.plot = plot_dataframes(self, "survival_function_")
self.plot_survival_function = self.plot
self.median_ = median_survival_times(self.survival_function_)
return self
def _summarize_survival(df, time_col, event_col, evaluate_at=None):
## prepare survival table
table = survival_table_from_events(df[time_col], df[event_col])
table.reset_index(inplace=True)
## normalize survival as fraction of initial_n
table['initial_n'] = max(table.at_risk)
table['survival'] = table.apply(
lambda row: row['at_risk'] / row['initial_n'], axis=1)
## handle timepoints if given
if evaluate_at is not None:
evaluate_times = pd.DataFrame({'event_at': evaluate_at})
table = pd.merge(evaluate_times, table, on='event_at', how='outer')
table = table.sort_values('event_at').fillna(method='ffill')
table['keep'] = table['event_at'].apply(lambda x: x in evaluate_at)
else:
table['keep'] = True
table = table.loc[table['keep'] == True, ['event_at', 'survival']]
table.rename(columns={'event_at': time_col}, inplace=True)
return table
def _compute_baseline_hazard(self, data, durations, event_observed,
weights, name):
# https://stats.stackexchange.com/questions/46532/cox-baseline-hazard
ind_hazards = self.predict_partial_hazard(data) * weights[:, None]
ind_hazards["event_at"] = durations.values
ind_hazards_summed_over_durations = (
ind_hazards.groupby("event_at")[0].sum().sort_index(
ascending=False).cumsum())
ind_hazards_summed_over_durations.name = "hazards"
event_table = survival_table_from_events(durations,
event_observed,
weights=weights)
event_table = event_table.join(ind_hazards_summed_over_durations)
baseline_hazard = pd.DataFrame(event_table["observed"] /
event_table["hazards"],
columns=[name]).fillna(0)
return baseline_hazard
def fit(self, event_times,censorship=None, timeline=None, columns=['NA-estimate'], alpha=None, insert_0=True):
"""
Parameters:
event_times: an (n,1) array of times that the death event occured at
timeline: return the best estimate at the values in timelines (postively increasing)
columns: a length 1 array to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
insert_0: add a leading 0 (if not present) in the timeline.
Returns:
DataFrame with index either event_times or timelines (if not None), with
values as the NelsonAalen estimate
"""
if censorship is None:
self.censorship = np.ones(event_times.shape[0], dtype=bool) #why boolean?
else:
self.censorship = np.array(censorship).copy().astype(bool)
self.event_times = survival_table_from_events(event_times, self.censorship)
if alpha is None:
alpha = self.alpha
if timeline is None:
self.timeline = self.event_times.index.values.copy().astype(float)
if insert_0 and self.timeline[0]>0:
self.timeline = np.insert(self.timeline,0,0.)
else:
self.timeline = timeline.astype(float)
cumulative_hazard_, cumulative_sq_ = _additive_estimate(self.event_times, self.timeline,
self._additive_f, self._variance_f )
self.cumulative_hazard_ = pd.DataFrame(cumulative_hazard_, columns=columns)
self.confidence_interval_ = self._bounds(cumulative_sq_[:,None],alpha)
self.plot = plot_dataframes(self, "cumulative_hazard_")
self.plot_cumulative_hazard = self.plot
self.plot_hazard = plot_dataframes(self, 'hazard_')
self._cumulative_sq = cumulative_sq_
return self
def _compute_baseline_hazard(self):
# http://courses.nus.edu.sg/course/stacar/internet/st3242/handouts/notes3.pdf
ind_hazards = self.predict_partial_hazard(self.data).values
event_table = survival_table_from_events(self.durations.values,
self.event_observed.values)
baseline_hazard_ = pd.DataFrame(np.zeros((event_table.shape[0], 1)),
index=event_table.index,
columns=['baseline hazard'])
for t, s in event_table.iterrows():
less = np.array(self.durations >= t)
if ind_hazards[less].sum() == 0:
v = 0
else:
v = (s['observed'] / ind_hazards[less].sum())
baseline_hazard_.ix[t] = v
return baseline_hazard_
def _compute_baseline_hazard(self):
# http://courses.nus.edu.sg/course/stacar/internet/st3242/handouts/notes3.pdf
ind_hazards = self.predict_partial_hazard(self.data).values
event_table = survival_table_from_events(self.durations.values,
self.event_observed.values)
baseline_hazard_ = pd.DataFrame(np.zeros((event_table.shape[0], 1)),
index=event_table.index,
columns=['baseline hazard'])
for t, s in event_table.iterrows():
less = np.array(self.durations >= t)
if ind_hazards[less].sum() == 0:
v = 0
else:
v = (s['observed'] / ind_hazards[less].sum())
baseline_hazard_.ix[t] = v
return baseline_hazard_
def preprocess_inputs(durations, event_observed, timeline, entry):
n = len(durations)
durations = np.asarray(durations).reshape((n,))
# set to all observed if event_observed is none
if event_observed is None:
event_observed = np.ones(n, dtype=int)
else:
event_observed = np.asarray(event_observed).reshape((n,)).copy().astype(int)
if entry is None:
entry = np.zeros(n)
else:
entry = np.asarray(entry).reshape((n,))
event_table = survival_table_from_events(durations, event_observed, entry)
if timeline is None:
timeline = event_table.index.values
else:
timeline = np.asarray(timeline)
return durations, event_observed, timeline.astype(float), entry, event_table
df = df[df['Site'] == "glottic"] df = df[df['Ethnicity'] == "white"] from lifelines.utils import survival_table_from_events df1 = df[df['Tcategory'] == 'T3'] df1['Censor'][df['Censor'] == 0] = 1 df1['Censor'][df['Censor'] == 1] = 0 df2 = df[df['Tcategory'] == 'T4'] df2['Censor'][df['Censor'] == 0] = 1 df2['Censor'][df['Censor'] == 1] = 0 T = df1['OS'] E = df1['Censor'] table = survival_table_from_events(df1['OS'], df1['Censor']) table2 = survival_table_from_events(df2['OS'], df2['Censor']) print table.head() from lifelines import KaplanMeierFitter kmf = KaplanMeierFitter() kmf.fit(T, event_observed=E, label="T3") # more succiently, kmf.fit(T,E) print kmf.survival_function_ ax = kmf.plot() T = df2['OS'] E = df2['Censor'] kmf.fit(T, event_observed=E, label="T4") # more succiently, kmf.fit(T,E) kmf.plot(ax=ax)
def test_survival_table_from_events_binned_with_empty_bin():
df = load_waltons()
ix = df["group"] == "miR-137"
event_table = utils.survival_table_from_events(
df.loc[ix]["T"], df.loc[ix]["E"], intervals=[0, 10, 20, 30, 40, 50])
assert not pd.isnull(event_table).any().any()
def test_survival_table_from_events_will_collapse_if_asked():
T, C = np.array([1, 3, 4, 5]), np.array([True, True, True, True])
table = utils.survival_table_from_events(T, C, collapse=True)
assert table.index.tolist() == [pd.Interval(0, 3.5089999999999999, closed='right'), pd.Interval(3.5089999999999999, 7.0179999999999998, closed='right')]
def test_survival_table_from_events_will_collapse_to_desired_bins():
T, C = np.array([1, 3, 4, 5]), np.array([True, True, True, True])
table = utils.survival_table_from_events(T, C, collapse=True, intervals=[0, 4, 8])
assert table.index.tolist() == [pd.Interval(0, 4, closed='right'), pd.Interval(4, 8, closed='right')]
"""
removed observed censored entrance at_risk
event_at
0 0 0 0 163 163
6 1 1 0 0 163
7 2 1 1 0 162
9 3 3 0 0 160
13 3 3 0 0 157
"""
# start_times is a vector of datetime objects
# end_times is a vector of (possibly missing) datetime objects.
import numpy as np
# traditional way to gen survival time
# gen xS fro survival time and xC for censor time
# compare two of them if xS < xC implies that event happen else not
xS = np.random.exponential(1,10)
xC = np.random.exponential(1,10)
obsE = xS<xC
obsT = []
for i in range(0,10):
if obsE[i]:
obsT.append(xS[i])
else :
obsT.append(xC[i])
table = survival_table_from_events(obsT,obsE)
print(table.head())
def test_survival_table_to_events():
T, C = np.array([1, 2, 3, 4, 4, 5]), np.array([1, 0, 1, 1, 1, 1])
d = utils.survival_table_from_events(T, C, np.zeros_like(T))
T_, C_ = utils.survival_events_from_table(d[['censored', 'observed']])
npt.assert_array_equal(T, T_)
npt.assert_array_equal(C, C_)
xlabel='Days of follow-up',
legend_labels=['Male', 'Female'],
ylabel='Survival probability',
title='Overall survival in lung cancer patients')
# Cox PH regression
from lifelines import CoxPHFitter
cph = CoxPHFitter()
lungdata['age_grp'] = np.where(lungdata['age'] >= 65, 1, 0)
lungdata['sex'] = np.where(lungdata['sex'] == 1, 1, 2)
lung_cph = lungdata[['time', 'status_km', 'sex', 'age',
'wt.loss']] # only keep vars needed for model
lung_cph = lung_cph[
lung_cph['wt.loss'].notna()] # drop nan values so the model can converge
cph.fit(lung_cph, 'time', event_col='status_km')
cph.print_summary()
# extract stats for the multivariate table & save as .csv format
cph.summary.to_csv(results_folder + 'multivariate_table.csv')
# miscellaneous ...
# look at the survival table
from lifelines.utils import survival_table_from_events
table = survival_table_from_events(T, E)
print(table.head())
def test_survival_table_to_events():
T, C = np.array([1, 2, 3, 4, 4, 5]), np.array([1, 0, 1, 1, 1, 1])
d = utils.survival_table_from_events(T, C, np.zeros_like(T))
T_, C_ = utils.survival_events_from_table(d[['censored', 'observed']])
npt.assert_array_equal(T, T_)
npt.assert_array_equal(C, C_)
def test_survival_table_to_events_casts_to_float():
T, C = np.array([1, 2, 3, 4, 4, 5]), np.array([True, False, True, True, True, True])
d = utils.survival_table_from_events(T, C, np.zeros_like(T))
npt.assert_array_equal(d['censored'].values, np.array([0., 0., 1., 0., 0., 0.]))
npt.assert_array_equal(d['removed'].values, np.array([0., 1., 1., 1., 2., 1.]))
