plot_data, plot_datas, plot_mcf, plot_mcfs, plot_mcfdiff, plot_mcfdiffs, print_data
if __name__ == '__main__':
# Bladder Example
#raw_data = pd.read_csv('datas/bladder_recurrent.csv', sep=';')
raw_data = pd.read_csv('datas/T45.csv', sep=';')
raw_data.rename(columns={'Patient number': 'Sample', 'Event': 'Number', 'Censored': 'Event',
'Treatment group': 'Drug'}, inplace=True)
raw_data['Drug'] = raw_data['Drug'].map({1: 'Placebo', 2: 'Pyridoxine', 3: 'Thiotepa'})
raw_data['Event'] = 1 - raw_data['Event']
tb = print_data(raw_data)
print tb
df = transform_data(raw_data)
lt = mcf(df, robust=True, positive=False)
covariate = 'Drug'
cohort1, cohort2 = 'Placebo', 'Thiotepa'
group_df = df.set_index(covariate)
group_lt = df.groupby(covariate).apply(lambda sfr: mcf(sfr, robust=True, positive=False))
df1, df2 = group_df.ix[cohort1], group_df.ix[cohort2]
lt1, lt2 = group_lt.ix[cohort1], group_lt.ix[cohort2]
lt_diff = mcfdiff(lt1, lt2)
# Plot, no stratification
fig, (ax1, ax2) = plt.subplots(2, 1)
rows.append((i, t_ij, 1, cost))
t_ij += expon.rvs(scale=1. / rate)
rows.append((i, t_i, 0, np.nan))
return pd.DataFrame(rows, columns=['Sample', 'Time', 'Event', 'Cost'])
if __name__ == '__main__':
# Cook (2008, pg. 299) Example 8.1: Field Repair data
# This dataset (see Appendix D) gives simulated data on unscheduled repairs
# for a fleet of m = 134 large utility vehicles operated by a city. The data were
# collected over a three-year period on new vehicles which were purchased and
# placed in service over the first two years of the study. Time is measured in
# years from the start of the study, and costs are in hundreds of dollars.
raw_data = generate_data()
df = transform_data(raw_data)
# Table D.4.
# Marked point process (8.14) as mcf1 and cumulative cost process (8.12) as mcf2
lt1 = mcf(df, robust=True, positive=False)
mcf1 = mcfcost(df, mcf_compound=lt1, robust=False, positive=False)
mcf2 = mcfcost(df, robust=True, positive=False)
# Plot data
plot_data(df, alpha=0.5, marker='.', plot_costs=False)
# Plot MCFs
fig, (ax1, ax2) = plt.subplots(1, 2, sharex=True, sharey=False)
plot_mcf(mcf1, ax=ax1, cost=True, label='Events * Cost')
plot_mcf(mcf2, ax=ax2, cost=True, label='Cost')
raw_data.rename(columns={
'Patient number': 'Sample',
'Event': 'Number',
'Censored': 'Event',
'Treatment group': 'Drug'
},
inplace=True)
raw_data['Drug'] = raw_data['Drug'].map({
1: 'Placebo',
2: 'Pyridoxine',
3: 'Thiotepa'
})
raw_data['Event'] = 1 - raw_data['Event']
print raw_data.head()
df = transform_data(raw_data)
lt = mcf(df, robust=True, positive=False)
covariate = 'Drug'
cohort1, cohort2 = 'Placebo', 'Thiotepa'
group_df = df.set_index(covariate)
group_lt = df.groupby(covariate).apply(
lambda sfr: mcf(sfr, robust=True, positive=False))
df1, df2 = group_df.ix[cohort1], group_df.ix[cohort2]
lt1, lt2 = group_lt.ix[cohort1], group_lt.ix[cohort2]
lt_diff = mcfdiff(lt1, lt2)
# Plot, no stratification
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from data_operations import transform_data, mcf, mcfdiff, mcfequal,\
plot_data, plot_datas, plot_mcf, plot_mcfs, plot_mcfdiff, plot_mcfdiffs
if __name__ == '__main__':
# Transmission Example
data = pd.read_csv('datas/transmission_recurrent.csv', sep=';')
df = transform_data(data, format='recurrent')
lt = mcf(df, robust=True, positive=False)
print lt[['Time', 'Y', 'N', 'dE[N]', 'E[N]', 'E[N].lcl',
'E[N].ucl']].head()
covariate = 'Transmission'
cohort1, cohort2 = 'Automatic', 'Manual'
group_df = df.set_index(covariate)
group_lt = df.groupby(covariate).apply(
lambda sfr: mcf(sfr, robust=True, positive=True)) #, interval=True))
df1, df2 = group_df.ix[cohort1], group_df.ix[cohort2]
lt1, lt2 = group_lt.ix[cohort1], group_lt.ix[cohort2]
lt_diff = mcfdiff(lt1, lt2)
# Plot, no stratification
fig, (ax1, ax2) = plt.subplots(2, 1)
plot_data(df, ax=ax1)
T, columns=['Sample', 'Time', 'Event', 'Type', 'Cost'])
if __name__ == '__main__':
max_date = 180
play_rate, purchase_rate, churn_rate = 0.1, 0.004, 0.02
playtime_dist = stats.expon(scale=0.25)
purchase_dist = stats.rv_discrete(values=((1, 4, 10, 20), (0.80, 0.15,
0.04, 0.01)))
process = MarkovRecurrentTerminal(play_rate, purchase_rate, churn_rate,
playtime_dist, purchase_dist)
raw_data = process.Sample(300, max_date)
df_sessions = transform_data(raw_data[(raw_data['Type'] == 0) |
(raw_data['Event'] == 0)])
df_purchases = transform_data(raw_data[(raw_data['Type'] == 1) |
(raw_data['Event'] == 0)])
mcf_sessions = mcfcost(df_sessions, robust=True, positive=True)
mcf_purchases = mcfcost(df_purchases, robust=True, positive=True)
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2,
2,
sharex=True,
sharey=False)
plot_data(df_sessions, ax=ax1, marker='.', label='Session', alpha=0.2)
plot_data(df_purchases, ax=ax2, marker='*', label='Purchase', alpha=0.2)
plot_mcf(mcf_sessions, ax=ax3, cost=True).set_ylabel('Playtime')
plot_mcf(mcf_purchases, ax=ax4, cost=True).set_ylabel('Lifetime Value')