while time_spent <= time_budget - (
2 * time_one_loop) - TIME_RESIDUAL and is_bo and True:
vprint(
verbose, "=========== " + basename.capitalize() +
" Training cycle " + str(cycle) + " ================")
M = MyAutoML(D.info, verbose=False, debug_mode=debug_mode)
M.fit(X_train_train, Y_train_train)
vprint(
verbose, "[+] Fitting success, time spent so far %5.2f sec" %
(time.time() - start))
# Make predictions
# -----------------
pred_train_valid = M.predict(X_train_valid)
if 'classification' in D.info['task']:
performance = sklearn.metrics.roc_auc_score(
Y_train_valid, pred_train_valid)
performance = 2 * performance - 1
vprint(verbose,
"[+] AUC for X_train_valid, %5.4f" % (performance))
else:
preformance = 0.0
vprint(verbose, "[-] Performance cannot be measured")
list_hyps_all.append(cur_hyps)
list_measures_all.append([(1.0 - performance) * 10.0])
cur_hyps, _, _, _ = model_bo.optimize(np.array(list_hyps_all),
np.array(list_measures_all),
is_grid_optimized=False,
else:
# Make a learning curve by exponentially increasing the number of estimators
M.model.n_estimators = int(np.exp2(cycle))
M.model.n_estimators = min(max_estimators, M.model.n_estimators)
vprint( verbose, "[+] Number of estimators: %d" % (M.model.n_estimators))
last_n_estimators = M.model.n_estimators
# Fit base estimators
# -------------------
M.fit(D.data['X_train'], D.data['Y_train'])
vprint( verbose, "[+] Fitting success, time spent so far %5.2f sec" % (time.time() - start))
vprint( verbose, "[+] Size of trained model %5.2f bytes" % data_io.total_size(M))
# Make predictions
# -----------------
Y_valid = M.predict(D.data['X_valid'])
Y_test = M.predict(D.data['X_test'])
vprint( verbose, "[+] Prediction success, time spent so far %5.2f sec" % (time.time() - start))
# Write results
# -------------
if overwrite_output:
filename_valid = basename + '_valid.predict'
filename_test = basename + '_test.predict'
else:
filename_valid = basename + '_valid_' + str(cycle).zfill(3) + '.predict'
filename_test = basename + '_test_' + str(cycle).zfill(3) + '.predict'
data_io.write(os.path.join(output_dir,filename_valid), Y_valid)
data_io.write(os.path.join(output_dir,filename_test), Y_test)
vprint( verbose, "[+] Results saved, time spent so far %5.2f sec" % (time.time() - start))
# The model can also select its hyper-parameters based on other elements of info.
# Only instantiates class object
vprint( verbose, "======== Creating model ==========")
M = MyAutoML(D.info, verbose=False, debug_mode=debug_mode) # I turned off verbose to avoid tons of junk...
print M
# Does cross validation for all models and picks the best classifier
# Probably need to pass in the time remaining since timekeeping needs to be done in here
# -------------------
M.run_cycles(D.data['X_train'], D.data['Y_train'])
vprint( verbose, "[+] Fitting success, time spent so far %5.2f sec" % (time.time() - start))
vprint( verbose, "[+] Size of trained model %5.2f bytes" % data_io.total_size(M))
# Make predictions
# -----------------
Y_test = M.predict(D.data['X_test'])
vprint( verbose, "[+] Prediction success, time spent so far %5.2f sec" % (time.time() - start))
# Write results
# -------------
filename_test = basename + '_test.predict'
data_io.write(os.path.join(output_dir,filename_test), Y_test)