def run(transaction_file, flag_file, threshold, k, set_method, lcm_path, max_comb, log_file, alternative):
# read 2 files and get transaction list
sys.stderr.write( "Read input files ...\n" )
transaction_list = set()
try:
transaction_list, columnid2name = readFile.readFiles(transaction_file, flag_file, ",")
# If the alternative hypothesis is 'less',
# the positive and negative of observe values are reversed,
# and conduct the identical procedure to 'greater'.
if alternative < 0:
transaction_list = lamp.reverseValue( transaction_list, set_method )
max_comb = lamp.convertMaxComb( max_comb, len(columnid2name) )
except ValueError as e:
return
except KeyError as e:
return
trans4lcm = transaction_file + ".4lcm53" # the filename for outputting logs
# run multiple test
try:
outlog = open( log_file, 'w' )
except IOError as e:
outlog.close()
start_time = time.time()
# generate null distribution
sys.stderr.write( "Calculate the minimum p-value distribution using the permutation test ...\n" )
outlog.write("Calculate the minimum p-value distribution using the permutation test ...\n")
min_p_list, fre_pattern, func_f = \
generateMinPDist(transaction_list, trans4lcm, threshold, set_method, \
lcm_path, max_comb, k, outlog, alternative)
# adjusted significance level
outlog.write("Adjust significance level ...\n")
adjusted_threshold, sorted_min_p_list = adjustedThreshold( min_p_list, threshold, k )
outlog.write("Adjusted significance level: %s\n" % adjusted_threshold)
correction_term_time = time.time()
# enumerate combination whose P-value up to adjusted threshold
outlog.write("Calculate the p-values in the given data set ...\n")
enrich_lst, time_enumerate_freq, time_enumerate_total = \
enumerateSigComb( transaction_list, trans4lcm, fre_pattern, func_f, \
max_comb, adjusted_threshold, outlog )
finish_test_time = time.time()
# output the significant combinations
outputResult( transaction_file, flag_file, threshold, k, set_method, max_comb, columnid2name, \
enrich_lst, adjusted_threshold, transaction_list, func_f, sorted_min_p_list, alternative )
# output time cost
sys.stdout.write("Time (sec.): Computing correction factor %.3f, Enumerating significant combinations %.3f, Total %.3f\n" \
% (correction_term_time-start_time, time_enumerate_total, finish_test_time - start_time))
# output the minimum P-values
outputMinP( min_p_list )
outlog.close()
return enrich_lst, adjusted_threshold, columnid2name
def run(transaction_file, flag_file, threshold, set_method, lcm_path, max_comb, log_file, alternative): # read 2 files and get transaction list sys.stderr.write( "Read input files ...\n" ) transaction_list = set() try: transaction_list, columnid2name = readFile.readFiles(transaction_file, flag_file, ',') max_comb = lamp.convertMaxComb( max_comb, len(columnid2name) ) except ValueError, e: return
def run(transaction_file, flag_file, threshold, set_method, lcm_path, max_comb,
log_file, alternative):
# read 2 files and get transaction list
sys.stderr.write("Read input files ...\n")
transaction_list = set()
try:
transaction_list, columnid2name = readFile.readFiles(
transaction_file, flag_file, ',')
max_comb = lamp.convertMaxComb(max_comb, len(columnid2name))
except ValueError, e:
return
def run(transaction_file, flag_file, threshold, k, set_method, lcm_path, max_comb, log_file, alternative): # read 2 files and get transaction list sys.stderr.write( "Read input files ...\n" ) transaction_list = set() try: transaction_list, columnid2name = readFile.readFiles(transaction_file, flag_file, ",") # If the alternative hypothesis is 'less', # the positive and negative of observe values are reversed, # and conduct the identical procedure to 'greater'. if alternative < 0: transaction_list = lamp.reverseValue( transaction_list, set_method ) max_comb = lamp.convertMaxComb( max_comb, len(columnid2name) ) except ValueError, e: return
def run(transaction_file, flag_file, threshold, k, set_method, lcm_path,
max_comb, log_file, alternative):
# read 2 files and get transaction list
sys.stderr.write("Read input files ...\n")
transaction_list = set()
try:
transaction_list, columnid2name = readFile.readFiles(
transaction_file, flag_file, ",")
# If the alternative hypothesis is 'less',
# the positive and negative of observe values are reversed,
# and conduct the identical procedure to 'greater'.
if alternative < 0:
transaction_list = lamp.reverseValue(transaction_list, set_method)
max_comb = lamp.convertMaxComb(max_comb, len(columnid2name))
except ValueError, e:
return
