def experiment_leave_k_out(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, leave_k_out, total_iteration, top_n, binary = False):
'''
Parameters
----------
@param exp_name: the experiment name (prefix)
@param daily_datafile:
@param min_occ_user:
@param method_list:
@param leave_k_out: leave k out for each user. The k must be strict less than
min_occ_user
@param binary: if this is set to true then the binary data is used (non-zero set to 1).
Returns
----------
@return out
'''
if leave_k_out >= min_occ_user:
raise ValueError('The k in the leave k out should be strictly less than min_occ_user.');
# define lko_log style.
lko_log = lambda msg: Logger.Log(msg, Logger.MSG_CATEGORY_EXP);
# construct exp_id
if binary:
exp_id = 'lko_bi_' + exp_name + '_data' +str(hash(daily_data_file)) + '_mu' + str(min_occ_user) + '_mp' + str(min_occ_prog) \
+ '_k' + str(leave_k_out) + '_toiter' + str(total_iteration);
else:
exp_id = 'lko_' + exp_name + '_data' +str(hash(daily_data_file)) + '_mu' + str(min_occ_user) + '_mp' + str(min_occ_prog) \
+ '_k' + str(leave_k_out) + '_toiter' + str(total_iteration);
lko_log('Experiment ID: ' + exp_id);
# load data.
lko_log('Read data...');
reader = UtilityDataReader();
data = reader.read_file_with_minval(daily_data_file, min_occ_user, min_occ_prog);
lko_log('Data loaded: ' + str(data));
if binary:
lko_log('Binarizing data...');
data.binarize();
else:
# normalize
lko_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.
lko_log('Method: '+ method.unique_str() + ' Iteration: '+ str(iteration));
# data split of the current iteration.
split_resource_str = 'exp' + exp_id + '_lvidx_iter' + str(iteration);
split_dir = exp_id + '/lv_idx';
leave_k_out_idx = URM.LoadResource(URM.RTYPE_RESULT, split_resource_str, split_dir);
if not leave_k_out_idx:
# randomly generate k items from each row/user.
leave_k_out_idx = ds.leave_k_out(data, leave_k_out);
URM.SaveResource(URM.RTYPE_RESULT, split_resource_str, leave_k_out_idx, split_dir);
# split the k items as a separate.
[data_left, data_tr] = data.leave_k_out(leave_k_out_idx);
iter_result = experiment_unit_leave_k_out(exp_id, method, \
data_tr, data_left, iteration, top_n);
perf_vect.append(iter_result);
result[method.unique_str()] = perf_vect;
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 = 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_tr_te_map(exp_name, train_data_file, test_data_file, \
train_item_feature_file, test_item_feature_file, \
max_rank, binary = False):
'''
Parameters
----------
@param exp_name:
@param train_data_file:
@param test_data_file:
@param train_content_file:
@param test_content_file:
@param max_rank: the maximal N in the computation.
Returns
----------
@return out
'''
# initialize utilities
trte_log = lambda msg: Logger.Log(msg, Logger.MSG_CATEGORY_EXP)
# processing file name hashing (used for cache string).
# create hash for single file or a list of files.
if isinstance(train_data_file, list):
hash_file_tr_data_str = str(hash(tuple(train_data_file)))
else:
hash_file_tr_data_str = str(hash(train_data_file))
if isinstance(test_data_file, list):
hash_file_te_data_str = str(hash(tuple(test_data_file)))
else:
hash_file_te_data_str = str(hash(test_data_file))
if train_item_feature_file:
if isinstance(train_item_feature_file, list):
hash_file_tr_item_feature_str = str(
hash(tuple(train_item_feature_file)))
else:
hash_file_tr_item_feature_str = str(hash(train_item_feature_file))
else:
hash_file_tr_item_feature_str = ''
if test_item_feature_file:
if isinstance(test_item_feature_file, list):
hash_file_te_item_feature_str = str(
hash(tuple(test_item_feature_file)))
else:
hash_file_te_item_feature_str = str(hash(test_item_feature_file))
else:
hash_file_te_item_feature_str = ''
# display information
print 'Training data file', train_data_file, ' [hash:', hash_file_tr_data_str, ']'
if train_item_feature_file:
print 'Training content feature provided: ', train_item_feature_file, \
' [hash:', hash_file_tr_item_feature_str, ']'
else:
print 'Training content feature not provided.'
print 'Testing data file ', test_data_file, ' [hash:', hash_file_te_data_str, ']'
if test_item_feature_file:
print 'Testing content feature provided: ', test_item_feature_file, \
' [hash:', hash_file_te_item_feature_str, ']'
else:
print 'Testing content feature not provided.'
if binary:
exp_id_prefix = 'trte_bi_'
else:
exp_id_prefix = 'trte_'
exp_id = exp_id_prefix + exp_name + '_trdata_' + hash_file_tr_data_str \
+ '_tedata_' + hash_file_te_data_str \
+ '_tritemf_' + hash_file_tr_item_feature_str \
+ '_tritemf_' + hash_file_te_item_feature_str
trte_log('Experiment ID: ' + exp_id)
# load utility data and feature data.
trte_log('Read training data...')
reader = UtilityDataReader(fieldDelimiter='\t')
tr_data = reader.read_file_with_minval(train_data_file, 0, 0)
trte_log('Training data loaded: ' + str(tr_data))
te_data = reader.read_file_with_minval(test_data_file, 0, 0)
trte_log('Testing data loaded: ' + str(te_data))
# load item feature data
if binary:
trte_log('Binarizing data...')
tr_data.binarize()
te_data.binarize()
result = {}
#from StringIO import StringIO
from rs.data.utility_data import UtilityDataReader
from rs.data.recdata import FeedbackData
from copy import deepcopy
if __name__ == '__main__':
#txt = "U1\tD1\t44\n"+"U2\tD2\t10\n"+"U2\tD1\t20\n"
#for line in StringIO(txt):
# print line
data_file = '../../datasample/agg_duid_pid_watchtime_genre/toy_small_day1'
reader = UtilityDataReader();
feedback = reader.readFile(data_file);
print feedback.col_mapping
col_feature_map= {};
col_feature_map['P0001'] = 'feature1'
col_feature_map['P0002'] = 'feature2'
col_feature_map['P0003'] = 'feature3'
col_feature_map['P0004'] = 'feature4'
feedback2 = deepcopy(feedback)
feedback.attach_col_feature(col_feature_map)
print feedback.meta[FeedbackData.METAKEY_COL_FEATURE]
def experiment_tr_te_map(exp_name, train_data_file, test_data_file, \
train_item_feature_file, test_item_feature_file, \
max_rank, binary = False):
'''
Parameters
----------
@param exp_name:
@param train_data_file:
@param test_data_file:
@param train_content_file:
@param test_content_file:
@param max_rank: the maximal N in the computation.
Returns
----------
@return out
'''
# initialize utilities
trte_log = lambda msg: Logger.Log(msg, Logger.MSG_CATEGORY_EXP)
# processing file name hashing (used for cache string).
# create hash for single file or a list of files.
if isinstance(train_data_file, list):
hash_file_tr_data_str = str(hash(tuple(train_data_file)));
else:
hash_file_tr_data_str = str(hash(train_data_file));
if isinstance(test_data_file, list):
hash_file_te_data_str = str(hash(tuple(test_data_file)));
else:
hash_file_te_data_str = str(hash(test_data_file));
if train_item_feature_file:
if isinstance(train_item_feature_file, list):
hash_file_tr_item_feature_str = str(hash(tuple(train_item_feature_file)))
else:
hash_file_tr_item_feature_str = str(hash(train_item_feature_file))
else:
hash_file_tr_item_feature_str = '';
if test_item_feature_file:
if isinstance(test_item_feature_file, list):
hash_file_te_item_feature_str = str(hash(tuple(test_item_feature_file)))
else:
hash_file_te_item_feature_str = str(hash(test_item_feature_file))
else:
hash_file_te_item_feature_str = '';
# display information
print 'Training data file', train_data_file, ' [hash:', hash_file_tr_data_str, ']'
if train_item_feature_file:
print 'Training content feature provided: ', train_item_feature_file, \
' [hash:', hash_file_tr_item_feature_str, ']'
else:
print 'Training content feature not provided.'
print 'Testing data file ', test_data_file, ' [hash:', hash_file_te_data_str, ']'
if test_item_feature_file:
print 'Testing content feature provided: ', test_item_feature_file, \
' [hash:', hash_file_te_item_feature_str, ']'
else:
print 'Testing content feature not provided.'
if binary:
exp_id_prefix = 'trte_bi_'
else:
exp_id_prefix = 'trte_'
exp_id = exp_id_prefix + exp_name + '_trdata_' + hash_file_tr_data_str \
+ '_tedata_' + hash_file_te_data_str \
+ '_tritemf_' + hash_file_tr_item_feature_str \
+ '_tritemf_' + hash_file_te_item_feature_str;
trte_log('Experiment ID: ' + exp_id)
# load utility data and feature data.
trte_log('Read training data...')
reader = UtilityDataReader(fieldDelimiter = '\t');
tr_data = reader.read_file_with_minval(train_data_file, 0, 0);
trte_log('Training data loaded: '+ str(tr_data))
te_data = reader.read_file_with_minval(test_data_file, 0, 0);
trte_log('Testing data loaded: '+ str(te_data))
# load item feature data
if binary:
trte_log('Binarizing data...');
tr_data.binarize();
te_data.binarize();
result = {};