Pythonic, эквивалентный из несдвига или восстановления?

Вы можете построить графики выживаемости Каплана-Мейера для пациентов с риском с помощью Plotly, используя подзаговоры. Первый график имеет коэффициент выживаемости, второй график представляет собой точечный график, на котором показан только текст, то есть маркеры не показаны.

Оба графика имеют одинаковую ось Y, и пациенты в группе риска представлены с соответствующими значениями X.

Больше примеров здесь: https://github.com/Ashafix/Kaplan-Meier_Plotly

Пример 1 - Рак легких у женщин и мужчин [ 1110]

import pandas as pd
import lifelines
import plotly
import numpy as np
plotly.offline.init_notebook_mode()

df = pd.read_csv('http://www-eio.upc.edu/~pau/cms/rdata/csv/survival/lung.csv')

fig = plotly.tools.make_subplots(rows=2, cols=1, print_grid=False)
kmfs = []

dict_sex = {1: 'Male', 2: 'Female'}

steps = 5 # the number of time points where number of patients at risk which should be shown

x_min = 0 # min value in x-axis, used to make sure that both plots have the same range
x_max = 0 # max value in x-axis

for sex in df.sex.unique():
    T = df[df.sex == sex]["time"]
    E = df[df.sex == sex]["status"]
    kmf = lifelines.KaplanMeierFitter()

    kmf.fit(T, event_observed=E)
    kmfs.append(kmf)
    x_max = max(x_max, max(kmf.event_table.index))
    x_min = min(x_min, min(kmf.event_table.index))
    fig.append_trace(plotly.graph_objs.Scatter(x=kmf.survival_function_.index,
                                               y=kmf.survival_function_.values.flatten(),  
                                               name=dict_sex[sex]), 
                     1, 1)


for s, sex in enumerate(df.sex.unique()):
    x = []
    kmf = kmfs[s].event_table
    for i in range(0, int(x_max), int(x_max / (steps - 1))):
        x.append(kmf.iloc[np.abs(kmf.index - i).argsort()[0]].name)
    fig.append_trace(plotly.graph_objs.Scatter(x=x, 
                                               y=[dict_sex[sex]] * len(x), 
                                               text=[kmfs[s].event_table[kmfs[s].event_table.index == t].at_risk.values[0] for t in x], 
                                               mode='text', 
                                               showlegend=False), 
                     2, 1)

# just a dummy line used as a spacer/header
t = [''] * len(x)
t[1] = 'Patients at risk'
fig.append_trace(plotly.graph_objs.Scatter(x=x, 
                                           y=[''] * len(x), 
                                           text=t,
                                           mode='text', 
                                           showlegend=False), 
                 2, 1)


# prettier layout
x_axis_range = [x_min - x_max * 0.05, x_max * 1.05]
fig['layout']['xaxis2']['visible'] = False
fig['layout']['xaxis2']['range'] = x_axis_range
fig['layout']['xaxis']['range'] = x_axis_range
fig['layout']['yaxis']['domain'] = [0.4, 1]
fig['layout']['yaxis2']['domain'] = [0.0, 0.3]
fig['layout']['yaxis2']['showgrid'] = False
fig['layout']['yaxis']['showgrid'] = False

plotly.offline.iplot(fig)

Пример 2 - Рак толстой кишки при различных методах лечения

df = pd.read_csv('http://www-eio.upc.edu/~pau/cms/rdata/csv/survival/colon.csv')

fig = plotly.tools.make_subplots(rows=2, cols=1, print_grid=False)
kmfs = []

steps = 5 # the number of time points where number of patients at risk which should be shown

x_min = 0 # min value in x-axis, used to make sure that both plots have the same range
x_max = 0 # max value in x-axis

for rx in df.rx.unique():
    T = df[df.rx == rx]["time"]
    E = df[df.rx == rx]["status"]
    kmf = lifelines.KaplanMeierFitter()

    kmf.fit(T, event_observed=E)
    kmfs.append(kmf)
    x_max = max(x_max, max(kmf.event_table.index))
    x_min = min(x_min, min(kmf.event_table.index))
    fig.append_trace(plotly.graph_objs.Scatter(x=kmf.survival_function_.index,
                                               y=kmf.survival_function_.values.flatten(),
                                               name=rx), 
                     1, 1)


fig_patients = []
for s, rx in enumerate(df.rx.unique()):
    kmf = kmfs[s].event_table
    x = []
    for i in range(0, int(x_max), int(x_max / (steps - 1))):
        x.append(kmf.iloc[np.abs(kmf.index - i).argsort()[0]].name)
    fig.append_trace(plotly.graph_objs.Scatter(x=x, 
                                               y=[rx] * len(x), 
                                               text=[kmfs[s].event_table[kmfs[s].event_table.index == t].at_risk.values[0] for t in x], 
                                               mode='text', 
                                               showlegend=False), 
                     2, 1)

# just a dummy line used as a spacer/header
t = [''] * len(x)
t[1] = 'Patients at risk'
fig.append_trace(plotly.graph_objs.Scatter(x=x, 
                                           y=[''] * len(x), 
                                           text=t,
                                           mode='text', 
                                           showlegend=False), 
                 2, 1)


# prettier layout
x_axis_range = [x_min - x_max * 0.05, x_max * 1.05]
fig['layout']['xaxis2']['visible'] = False
fig['layout']['xaxis2']['range'] = x_axis_range
fig['layout']['xaxis']['range'] = x_axis_range
fig['layout']['yaxis']['domain'] = [0.4, 1]
fig['layout']['yaxis2']['domain'] = [0.0, 0.3]
fig['layout']['yaxis2']['showgrid'] = False
fig['layout']['yaxis']['showgrid'] = False

plotly.offline.iplot(fig)

[ 116]