def split(self, percentage):
'''
get a random splitting of data with a specified proportion of rows.
NOTE: it is recommended to use subdata_row method in get deterministic splits.
Parameters
----------
@param percentage: the percentage of data split.
Returns
----------
@return out: a list [data_split, data_split_comp, selidx_split, selidx_split_comp]
data_split: a Feedback data of percentage, whose index (in the full data set)
is given in selidx_split
data_split_comp: a Feedback data of 1- percentage, whose index is given
in data_split_comp. This is the complement part of data_split.
selidx_split: the index of rows in data_split.
selidx_split_comp: the index of rows in data_split_comp.
'''
# obtain the indices of the split / complement of the split.
[selidx_split, selidx_split_comp] = ds.split(self.num_row, percentage);
# acquire data from the splits.
data_split = self.subdata_row(selidx_split);
data_split_comp = self.subdata_row(selidx_split_comp);
return [data_split, data_split_comp, selidx_split, selidx_split_comp];
def split(self, percentage):
'''
get a random splitting of data with a specified proportion of rows.
NOTE: it is recommended to use subdata_row method in get deterministic splits.
Parameters
----------
@param percentage: the percentage of data split.
Returns
----------
@return out: a list [data_split, data_split_comp, selidx_split, selidx_split_comp]
data_split: a Feedback data of percentage, whose index (in the full data set)
is given in selidx_split
data_split_comp: a Feedback data of 1- percentage, whose index is given
in data_split_comp. This is the complement part of data_split.
selidx_split: the index of rows in data_split.
selidx_split_comp: the index of rows in data_split_comp.
'''
# obtain the indices of the split / complement of the split.
[selidx_split, selidx_split_comp] = ds.split(self.num_row, percentage)
# acquire data from the splits.
data_split = self.subdata_row(selidx_split)
data_split_comp = self.subdata_row(selidx_split_comp)
return [data_split, data_split_comp, selidx_split, selidx_split_comp]
def experiment_rand_split(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, training_prec, total_iteration):
'''
Parameters
----------
exp_name: a human-readable experiment name.
method_list: a list of matrix completion models
Returns
----------
'''
# define mcpl_log style.
mcpl_log = lambda msg: Logger.Log(msg, Logger.MSG_CATEGORY_EXP)
#mcpl_log('Data ID: ' + hash(daily_data_file));
# here we use a regular hash.
exp_id = exp_name + '_data' +str(hash(daily_data_file)) + '_mu' + str(min_occ_user) + '_mp' + str(min_occ_prog) \
+ '_trprec' + str(training_prec) + '_toiter' + str(total_iteration)
mcpl_log('Experiment ID: ' + exp_id)
# save experiment splitting as resources.
reader = UtilityDataReader()
data = reader.read_file_with_minval(daily_data_file, min_occ_user,
min_occ_prog)
# we normalize here before splitting.
mcpl_log('Normalizing data...')
data.normalize_row()
result = {}
for method in method_list:
# do for each method
perf_vect = []
for iteration in range(total_iteration):
# do for each iteration for each method;
mcpl_log('Method: ' + method.unique_str() + ' Iteration: ' +
str(iteration))
# data split of the current iteration.
split_resource_str = 'exp' + exp_id + '_split_iter' + str(
iteration)
split_dir = exp_id + '/split'
split = URM.LoadResource(URM.RTYPE_RESULT, split_resource_str,
split_dir)
if not split:
split = ds.split(data.num_row, training_prec)
URM.SaveResource(URM.RTYPE_RESULT, split_resource_str, split,
split_dir)
[split_tr, split_te] = split
data_tr = data.subdata_row(split_tr)
data_te = data.subdata_row(split_te)
iter_result = experiment_unit_rand_split(exp_id, method, data_tr,
data_te, iteration)
perf_vect.append(iter_result)
result[method.unique_str()] = perf_vect
mcpl_log('Experiment Done [' + exp_id + ']')
return result
def experiment_rand_split(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, training_prec, total_iteration):
'''
Parameters
----------
exp_name: a human-readable experiment name.
method_list: a list of matrix completion models
Returns
----------
'''
# define mcpl_log style.
mcpl_log = lambda msg: Logger.Log(msg, Logger.MSG_CATEGORY_EXP);
#mcpl_log('Data ID: ' + hash(daily_data_file));
# here we use a regular hash.
exp_id = exp_name + '_data' +str(hash(daily_data_file)) + '_mu' + str(min_occ_user) + '_mp' + str(min_occ_prog) \
+ '_trprec' + str(training_prec) + '_toiter' + str(total_iteration);
mcpl_log('Experiment ID: ' + exp_id);
# save experiment splitting as resources.
reader = DailyWatchTimeReader();
data = reader.read_file_with_minval(daily_data_file, min_occ_user, min_occ_prog);
# we normalize here before splitting.
mcpl_log('Normalizing data...');
data.normalize_row();
result = {};
for method in method_list:
# do for each method
perf_vect = [];
for iteration in range(total_iteration):
# do for each iteration for each method;
mcpl_log('Method: '+ method.unique_str() + ' Iteration: '+ str(iteration));
# data split of the current iteration.
split_resource_str = 'exp' + exp_id + '_split_iter' + str(iteration);
split_dir = exp_id + '/split';
split = URM.LoadResource(URM.RTYPE_RESULT, split_resource_str, split_dir);
if not split:
split = ds.split(data.num_row, training_prec);
URM.SaveResource(URM.RTYPE_RESULT, split_resource_str, split, split_dir);
[split_tr, split_te] = split;
data_tr = data.subdata_row(split_tr);
data_te = data.subdata_row(split_te);
iter_result = experiment_unit_rand_split(exp_id, method, data_tr, data_te, iteration);
perf_vect.append(iter_result);
result[method.unique_str()] = perf_vect;
mcpl_log('Experiment Done [' + exp_id + ']');
return result;
