from lifelines import CoxPHFitter import numpy as np import pandas as pd import lifelines path = './totalData.xlsx' data = pd.read_excel(path) col = list(data.columns) del col[0:5] cph = CoxPHFitter() cph.fit(data, 'totaltime', 'failure', strata=col) cph.print_summary() cph.predict_cumulative_hazard(data)
pheno = pheno.iloc[ib]
pheno = pheno.reset_index(drop=True)
geno_ia = geno[:,ia]
# Function for null model
logger.info('Generating Null models\n')
cph = CoxPHFitter()
cph.fit(pheno[[T_name, event_name] + covname], T_name, event_col=event_name)
# res_surv = cph.compute_residuals(pheno[[T_name, event_name] + covname], 'deviance').sort_index()['deviance']
res_surv = cph.compute_residuals(pheno[[T_name, event_name] + covname], 'martingale').sort_index()['martingale']
# This is the most memory intensive part. Might need to change if we are dealing with biobank scale data
if args.apr_flag == 'N':
logger.info('Calculating Null covariance matrix\n')
mat = cph.predict_cumulative_hazard(pheno)
P = np.diff(mat,axis=-0)
for isubj in range(P.shape[1]):
idx = np.abs(mat.index - pheno[T_name][isubj]).argmin()
P[idx::,isubj] = 0
V = da.diag(np.array(pheno[event_name] - res_surv)) - da.dot(P.transpose(),P)
X = np.array(pheno[covname])
C = V - da.matmul(da.matmul(da.matmul(V,X), da.linalg.inv(da.matmul(da.matmul(X.transpose(), V),X))), da.matmul(X.transpose(), V))
else:
logger.info('Using first order approximations for testing statistics\n')
# auto chunk to reduce the query time
chunk_array = [bim.i.values[i:i + chunk_size] for i in xrange(0, len(bim.i.values), chunk_size)]
nchunk = len(chunk_array)
chunk_ind = 1
sorted_y_test = np.sort(np.unique(y_test[:, 0]))
if sorted_y_test[0] != 0:
mesh_points = np.concatenate(([0.], sorted_y_test))
else:
mesh_points = sorted_y_test
surv = \
surv_model.predict_survival_function(X_test_standardized,
mesh_points)
surv = surv.values.T
# ---------------------------------------------------------------------
# compute c-index
#
if cindex_method == 'cum_haz':
cum_haz = \
surv_model.predict_cumulative_hazard(X_test_standardized,
sorted_y_test)
cum_haz = cum_haz.values.T
cum_hazard_scores = cum_haz.sum(axis=1)
test_cindex = concordance_index(y_test[:, 0],
-cum_hazard_scores,
y_test[:, 1])
elif cindex_method == 'cum_haz_from_surv':
surv_thresholded = np.maximum(surv,
np.finfo(float).eps)
cum_haz = -np.log(surv_thresholded)
cum_hazard_scores = cum_haz.sum(axis=1)
test_cindex = concordance_index(y_test[:, 0],
-cum_hazard_scores,
y_test[:, 1])
elif cindex_method == 'median':
predicted_medians = \