def fit_weibull(df, x_grid=None):
# Initialize the model and fit our data
wbf = WeibullFitter()
wbf.fit(df["offset"], df["observed"])
# Get weibull parameters
params = {"scale": wbf.lambda_, "shape": wbf.rho_}
# If x_grid is provided, return y
if x_grid is not None:
pdf = wbf.density_at_times(x_grid).to_numpy()
return params, pdf
else:
return params
# -*- coding: utf-8 -*-
# aalen additive
if __name__ == "__main__":
import pandas as pd
import numpy as np
import time
from lifelines import WeibullFitter
np.random.seed(1)
N = 250000
mu = 3 * np.random.randn()
sigma = np.random.uniform(0.1, 3.0)
X, C = np.exp(sigma * np.random.randn(N) +
mu), np.exp(np.random.randn(N) + mu)
E = X <= C
T = np.minimum(X, C)
wb = WeibullFitter()
start_time = time.time()
wb.fit(T, E)
print("--- %s seconds ---" % (time.time() - start_time))
wb.print_summary(5)
# -*- coding: utf-8 -*-
import numpy as np
from lifelines import WeibullFitter
lambda_, rho_ = 2, 0.5
N = 10000
T_actual = lambda_ * np.random.exponential(1, size=N) ** (1 / rho_)
T_censor = lambda_ * np.random.exponential(1, size=N) ** (1 / rho_)
T = np.minimum(T_actual, T_censor)
E = T_actual < T_censor
time = [1.0]
# lifelines computed confidence interval
wf = WeibullFitter()
print(wf.fit(T, E, timeline=time).confidence_interval_cumulative_hazard_)
bootstrap_samples = 10000
results = []
for _ in range(bootstrap_samples):
ix = np.random.randint(0, 10000, 10000)
wf = WeibullFitter().fit(T[ix], E[ix], timeline=time)
results.append(wf.cumulative_hazard_at_times(time).values[0])
print(np.percentile(results, [2.5, 97.5]))
kmf.plot(ax=ax)
# PURPOSE
ax = plt.subplot()
for purpose in df_cox.PURPOSE.unique():
is_pur = (df_cox.PURPOSE == purpose)
kmf.fit(T[is_pur], event_observed=E[is_pur], label=purpose)
kmf.plot(ax=ax)
############################################################
# WeibullFitter
############################################################
from lifelines import WeibullFitter
wf = WeibullFitter()
wf.fit(T, E)
print(wf.lambda_, wf.rho_)
wf.print_summary()
wf.plot()
############################################################
# NelsonAalenFitter
############################################################
from lifelines import NelsonAalenFitter
naf = NelsonAalenFitter()
naf.fit(T, event_observed=E)
naf.plot()
# univariate analysis: cum hazard
print(len('General Weibull distribution:') * '-')
# bool_up = (df.Type == 'RunTime')
# bool_down = ((df.Type == 'DownTime') & (df.ReasonId.isin(reasons_relative)))
# continue_obs = ((df.Type == 'DownTime') & (df.ReasonId.isin(reasons_absolute + reasons_not_considered + reasons_availability)))
# stop_obs = (df.Type == 'Break')
bool_up = (df_task['Type'] == 'RunTime') # List of all RunTimes
bool_down = (df_task['Type'].isin(['DownTime', 'Break'])) & (df_task['ReasonId'].isin(reasons_relative)) # List of all DownTimes in calculation
bool_ignore = (df_task['Type'].isin(['DownTime', 'Break'])) & (df_task['ReasonId'].isin(reasons_availability + reasons_absolute)) # List of all breaks to ignore
bool_break = (df_task['Type'].isin(['DownTime', 'Break'])) & (df_task['ReasonId'].isin(reasons_break)) # List of all breaks to stop observation
uptime, downtime, obs_up, obs_down = duration_run_down(list(df_task['Duration'] / 3600), list(bool_up), list(bool_down),
list(bool_ignore), list(bool_break), observation=True)
wf = WeibullFitter()
try:
wf.fit(uptime, obs_up)
weib = Weibull(wf.lambda_, wf.rho_)
except:
print(uptime)
raise
if print_all:
print(weib)
if export_all:
general_dist = ET.SubElement(root, 'general_dist')
general_dist.text = 'weibull'
general_dist.set("lambda", str(wf.lambda_))
general_dist.set("rho", str(wf.rho_))
general_dist.set("mean", str(weib.mean_time()))
plot_hist(uptime, obs_up, 99, weib)
plt.title(f'Probability of failure in time [general]'#, reasons: ' + ', '.join([str(x) for x in reasons_relative])
)