time_left_over = 0
for basename in datanames: # Loop over datasets
vprint( verbose, "************************************************")
vprint( verbose, "******** Processing dataset " + basename.capitalize() + " ********")
vprint( verbose, "************************************************")
# ======== Learning on a time budget:
# Keep track of time not to exceed your time budget. Time spent to inventory data neglected.
start = time.time()
# ======== Creating a data object with data, informations about it
vprint( verbose, "========= Reading and converting data ==========")
D = DataManager(basename, input_dir, replace_missing=True, filter_features=True, max_samples=max_samples, verbose=verbose)
print (D)
vprint( verbose, "[+] Size of uploaded data %5.2f bytes" % data_io.total_size(D))
# ======== Keeping track of time
if debug_mode<1:
time_budget = D.info['time_budget'] # <== HERE IS THE TIME BUDGET!
else:
time_budget = max_time
overall_time_budget = overall_time_budget + time_budget
vprint( verbose, "[+] Cumulated time budget (all tasks so far) %5.2f sec" % (overall_time_budget))
# We do not add the time left over form previous dataset: time_budget += time_left_over
vprint( verbose, "[+] Time budget for this task %5.2f sec" % time_budget)
time_spent = time.time() - start
vprint( verbose, "[+] Remaining time after reading data %5.2f sec" % (time_budget-time_spent))
if time_spent >= time_budget:
vprint( verbose, "[-] Sorry, time budget exceeded, skipping this task")
execution_success = False
pass
try:
os.remove(filename_test)
except:
pass
logger.info("************************************************")
logger.info("******** Processing dataset " + basename.capitalize() + "********")
logger.info("************************************************")
# ======== Creating a data object with data, informations about it
logger.info("========= Reading and converting data ==========")
D = DataManager(basename, data_dir, max_samples=max_samples)
logger.info(str(D))
logger.info("[+] Size of uploaded data %5.2f bytes" %
data_io.total_size(D))
overall_time_budget = min(max_time, D.info['time_budget'])
# ======== Create auto-sklearn model
new_info_object = {}
new_info_object['is_sparse'] = D.info['is_sparse']
new_info_object['task'] = STRING_TO_TASK_TYPES[D.info['task']]
new_info_object['metric'] = STRING_TO_METRIC[D.info['metric']]
configuration_space = get_configuration_space(new_info_object)
try:
config = ConfigSpace.Configuration(configuration_space, configuration)
except Exception as inst:
execution_success = False
logger.critical(inst)
continue
# ======== Learning on a time budget:
# Keep track of time not to exceed your time budget. Time spent to inventory data neglected.
start = time.time()
# ======== Creating a data object with data, informations about it
vprint(verbose, "========= Reading and converting data ==========")
D = DataManager(basename,
input_dir,
replace_missing=True,
filter_features=True,
max_samples=max_samples,
verbose=verbose)
print D
vprint(
verbose,
"[+] Size of uploaded data %5.2f bytes" % data_io.total_size(D))
# ======== Keeping track of time
if debug_mode < 1:
time_budget = D.info['time_budget'] # <== HERE IS THE TIME BUDGET!
else:
time_budget = max_time
overall_time_budget = overall_time_budget + time_budget
vprint(
verbose,
"[+] Cumulated time budget (all tasks so far) %5.2f sec" %
(overall_time_budget))
# We do not add the time left over form previous dataset: time_budget += time_left_over
vprint(verbose,
"[+] Time budget for this task %5.2f sec" % time_budget)
time_spent = time.time() - start
#### DEBUG MODE: Show dataset list and STOP
if debug_mode>=3:
data_io.show_version()
data_io.show_io(input_dir, output_dir)
exit(0)
vprint( verbose, "****************************************************")
vprint( verbose, "******** Processing spatio-temporal dataset ********")
vprint( verbose, "****************************************************")
#### Instanciate input data manager and load data
vprint( verbose, "========= Reading and converting data ==========")
Din = DataManager(datatype="input", verbose=verbose)
Din.loadData(input_dir)
vprint( verbose, Din)
vprint( verbose, "[+] Size of uploaded data {:5.2f} bytes".format(data_io.total_size(Din)))
#### Instanciate output data manager and load data
Dout = DataManager(datatype="output", verbose=verbose)
Dout.col_names = Din.col_names[Din.ycol0:]
Dout.horizon = Din.horizon
Dout.stride = Din.horizon
#### In debug mode, cheat and get the solution too
if debug_mode>1:
Dsol = DataManager(datatype="input", verbose=verbose)
Dsol.loadData(input_dir)
#### Instanciate predictive model
vprint( verbose, "======== Creating model ==========")
M = Model()
for basename in datanames: # Loop over datasets
vprint( verbose, "\n========== Ingestion program version " + str(version) + " ==========\n")
vprint( verbose, "************************************************")
vprint( verbose, "******** Processing dataset " + basename.capitalize() + " ********")
vprint( verbose, "************************************************")
# ======== Learning on a time budget:
# Keep track of time not to exceed your time budget. Time spent to inventory data neglected.
start = time.time()
# ======== Creating a data object with data, informations about it
vprint( verbose, "========= Reading and converting data ==========")
D = DataManager(basename, input_dir, replace_missing=True, filter_features=True, max_samples=max_samples, verbose=verbose)
print(D)
vprint( verbose, "[+] Size of uploaded data %5.2f bytes" % data_io.total_size(D))
# ======== Keeping track of time
if debug_mode<1:
time_budget = D.info['time_budget'] # <== HERE IS THE TIME BUDGET!
else:
time_budget = max_time
overall_time_budget = overall_time_budget + time_budget
vprint( verbose, "[+] Cumulated time budget (all tasks so far) %5.2f sec" % (overall_time_budget))
# We do not add the time left over form previous dataset: time_budget += time_left_over
vprint( verbose, "[+] Time budget for this task %5.2f sec" % time_budget)
time_spent = time.time() - start
vprint( verbose, "[+] Remaining time after reading data %5.2f sec" % (time_budget-time_spent))
if time_spent >= time_budget:
vprint( verbose, "[-] Sorry, time budget exceeded, skipping this task")
execution_success = False
continue
time_predict_value = time_to_predict(D)
time_budget = time_budget - time_spent # Remove time spent so far
start = time.time() # Reset the counter
time_spent = 0 # Initialize time spent learning
M.time_limit = time_budget * time_predict_value * 0.9
vprint(verbose, "[+] Time budget to train the model %5.2f sec" % M._time_limit)
Xtest = None
if D.info['test_num'] < 1000:
Xtest = np.array([x.hy.full_array() for x in read_data(test_fname)]).T
M.fit(X, y, test_set=Xtest)
# log_reg = LogisticRegression(random_state=0, class_weight='balanced')
# log_reg.fit(M.raw_decision_function(X), y)
vprint(verbose, "=========== " + basename.capitalize() + " Training cycle " + " ================")
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
# -----------------
if os.path.isfile(valid_fname):
Y_valid = M.predict_proba(read_data(valid_fname))[:, 1]
# Y_valid = log_reg.predict_proba(M.raw_decision_function(read_data(valid_fname)))[:, 1]
else:
Y_valid = None
if Xtest is None:
Xtest = read_data(test_fname)
Y_test = M.predict_proba(Xtest)[:, 1]
# Y_test = log_reg.predict_proba(M.raw_decision_function(read_data(test_fname)))[:, 1]
vprint(verbose, "[+] Prediction success, time spent so far %5.2f sec" % (time.time() - start))
# Write results
# -------------
filename_valid = basename + '_valid.predict'
time_left_over = 0
for basename in datanames: # Loop over datasets
vprint( verbose, "************************************************")
vprint( verbose, "******** Processing dataset " + basename.capitalize() + " ********")
vprint( verbose, "************************************************")
# ======== Learning on a time budget:
# Keep track of time not to exceed your time budget. Time spent to inventory data neglected.
start = time.time()
# ======== Creating a data object with data, informations about it
vprint( verbose, "========= Reading and converting data ==========")
D = DataManager(basename, input_dir, replace_missing=True, filter_features=True, max_samples=max_samples, verbose=verbose)
print D
vprint( verbose, "[+] Size of uploaded data %5.2f bytes" % data_io.total_size(D))
# ======== Keeping track of time
if debug_mode<1:
time_budget = D.info['time_budget'] # <== HERE IS THE TIME BUDGET!
else:
time_budget = max_time
overall_time_budget = overall_time_budget + time_budget
vprint( verbose, "[+] Cumulated time budget (all tasks so far) %5.2f sec" % (overall_time_budget))
# We do not add the time left over form previous dataset: time_budget += time_left_over
vprint( verbose, "[+] Time budget for this task %5.2f sec" % time_budget)
time_spent = time.time() - start
vprint( verbose, "[+] Remaining time after reading data %5.2f sec" % (time_budget-time_spent))
if time_spent >= time_budget:
vprint( verbose, "[-] Sorry, time budget exceeded, skipping this task")
execution_success = False
# ======== Learning on a time budget:
# Keep track of time not to exceed your time budget. Time spent to inventory data neglected.
start = time.time()
# ======== Creating a data object with data, informations about it
vprint(verbose, "========= Reading and converting data ==========")
D = DataManager(basename,
input_dir,
replace_missing=True,
filter_features=True,
max_samples=max_samples,
verbose=verbose)
print(D)
vprint(
verbose,
"[+] Size of uploaded data %5.2f bytes" % data_io.total_size(D))
# ======== Keeping track of time
if debug_mode < 1:
time_budget = D.info['time_budget'] # <== HERE IS THE TIME BUDGET!
else:
time_budget = max_time
#print overall_time_budget
#print time_budget
time_budget = float(time_budget)
overall_time_budget = overall_time_budget + time_budget
vprint(
verbose,
"[+] Cumulated time budget (all tasks so far) %5.2f sec" %
(overall_time_budget))
# We do not add the time left over form previous dataset: time_budget += time_left_over
