问题
I need to render at_risk numbers on a Kaplan Meier graph.
The end result should be similar to this:
The bit I am having trouble rendering is the No. of patients at risk at the bottom of the graph. The values displayed there, correspond to the values on the x-axis. So in essence, it's like a Y-axis rendered in parallel with the X.
I have been trying to replicate multiple-axis found here (https://plot.ly/python/multiple-axes/) without success, and also tried having a subplot and hide everything but the X-axis, but then its values do not align with the graph above.
What is the best approach for this?
回答1:
You could plot Kaplan-Meier survival graphs with patients at risk with Plotly by using subplots. The first plot has the survival rate, the second plot is a scatter plot where only the text is shown, i.e. the markers are not shown.
Both plots have the same y-axis and the patients at risk are plotted at the respective x-values.
More examples are here: https://github.com/Ashafix/Kaplan-Meier_Plotly
Example 1 - Lung cancer in female and male patients
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)
Example 2 - Colon cancer with different treatments
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)
回答2:
This is builtin to lifelines as well:
from lifelines import KaplanMeierFitter
ix = waltons['group'] == 'control'
ax = plt.subplot(111)
kmf_control = KaplanMeierFitter()
ax = kmf_control.fit(waltons.loc[ix]['T'], waltons.loc[ix]['E'], label='control').plot(ax=ax)
kmf_exp = KaplanMeierFitter()
ax = kmf_exp.fit(waltons.loc[~ix]['T'], waltons.loc[~ix]['E'], label='exp').plot(ax=ax)
from lifelines.plotting import add_at_risk_counts
add_at_risk_counts(kmf_exp, kmf_control, ax=ax)
https://lifelines.readthedocs.io/en/latest/Examples.html#displaying-multiple-at-risk-counts-below-plots
However, I'm not sure if this works well with plotly
来源：https://stackoverflow.com/questions/54232879/secondary-parallel-x-axis-on-plotly-charts-python