Lifelines categorical variables.

lifelines.py

from patsy import dmatrix
from lifelines import CoxPHFitter
import pandas as pd

df = pd.read_csv('/Users/camerondavidson-pilon/Downloads/prostate1.csv')
X = dmatrix('age + hg + sz + sg + rx + pf + status1 + dtime', df, return_type='dataframe')
print X.head()
"""
Notice patsy has removed the redundant variables: `0.2 mg estrogen` and `in bed < 50% daytime`. This is what R does too. 
Patsy has introduced an Intercept column, though. We don't want this.
"""
del X['Intercept']

cp = CoxPHFitter(normalize=False)
cp.fit(X, 'dtime', event_col='status1')
cp.print_summary() # values close to R.