def run_decode_lcp_yuta(input_folder_path, output_folder_path):
e = experiment_data()
e.experiment_name = "DECODE-SAIS-LCP-YUTA"
input_filename = os.listdir(input_folder_path)
for f in input_filename:
input_file = os.path.join(input_folder_path, f)
output_file = os.path.join(output_folder_path, f + '-decode-yuta')
compressed_file = os.path.join(output_folder_path, f + '.gcis')
print("GCIS Compressing: ", f)
if (os.path.isfile(compressed_file)):
print(compressed_file, 'already exists, skipping')
else:
gcis.compress_gc_is(input_file, compressed_file)
print("GCIS Decoding and SAIS Yuta + LCP")
dt = []
st = []
tt = []
for i in range(number_of_samples):
(decode_time,
saca_time) = sais.decode_sais_lcp_yuta(compressed_file,
output_file)
dt.append(float(decode_time))
st.append(float(saca_time))
tt.append(float(decode_time) + float(saca_time))
print("Decode Time =", decode_time, 'seconds')
print("Saca LCP Yuta Time =", saca_time, 'seconds')
e.experiment_input.append(f)
e.experiment_time.append(('{:.2f}'.format(statistics.mean(dt)),
'{:.2f}'.format(statistics.mean(st)),
'{:.2f}'.format(statistics.mean(tt))))
return e
def run_decode(input_folder_path, output_folder_path):
e = experiment_data()
e.experiment_name = "GCIS-DECODE"
input_filename = os.listdir(input_folder_path)
for f in input_filename:
input_file = os.path.join(input_folder_path, f)
compressed_file = os.path.join(output_folder_path, f + '.gcis')
decompressed_file = os.path.join(output_folder_path, f + '.tmp.txt')
print("GCIS Compressing: ", f)
if (os.path.isfile(compressed_file)):
print(compressed_file, 'already exists, skipping')
else:
gcis.compress_gc_is(input_file, compressed_file)
print("GCIS Decoding")
tt = []
for i in range(number_of_samples):
total_time = gcis.decompress_gc_is(compressed_file,
decompressed_file)
tt.append(total_time)
print("Time Decode =", "{:.2f}".format(total_time))
print('Removing tmp file', decompressed_file)
os.remove(decompressed_file)
e.experiment_input.append(f)
e.experiment_time.append("{:.2f}".format(statistics.mean(tt)))
return e
def run_decode_saca_lcp(input_folder_path, output_folder_path):
e = experiment_data()
e.experiment_name = "GCIS-SACA-LCP"
input_filename = os.listdir(input_folder_path)
for f in input_filename:
input_file = os.path.join(input_folder_path, f)
compressed_file = os.path.join(output_folder_path, f + '.gcis')
output_file = os.path.join(output_folder_path, f + '-gcis')
print("GCIS Compressing: ", f)
if (os.path.isfile(compressed_file)):
print(compressed_file, 'already exists, skipping')
else:
gcis.compress_gc_is(input_file, compressed_file)
print("GCIS Decoding + SAIS + LCP: ", f)
tt = []
for i in range(number_of_samples):
start_time = time.perf_counter() # Start time
gcis.decompress_saca_lcp(compressed_file, output_file)
end_time = time.perf_counter() # End time
total_time = end_time - start_time
print("Time GCIS + LCP =", "{:.2f}".format(total_time))
tt.append(total_time)
e.experiment_input.append(f)
e.experiment_time.append("{:.2f}".format(statistics.mean(tt)))
return e
def run_decode_divsufsort_lcp(input_folder_path, output_folder_path):
e = experiment_data()
e.experiment_name = "DECODE-SAIS-DIVSUFSORT-LCP"
input_filename = os.listdir(input_folder_path)
for f in input_filename:
# Divsufsort + LCP have
# Terrible behaviour on artificial sequences, skip.
if (f == 'fib41' or f == 'rs.13' or f == 'tm29'):
print("Divsufort + LCP: Artificial Sequence", f, "skipping")
tt = [-1.0]
st = [-1.0]
dt = [-1.0]
e.experiment_input.append(f)
e.experiment_time.append(('{:.2f}'.format(statistics.mean(dt)),
'{:.2f}'.format(statistics.mean(st)),
'{:.2f}'.format(statistics.mean(tt))))
continue
input_file = os.path.join(input_folder_path, f)
output_file = os.path.join(output_folder_path,
f + '-decode-divsufsort')
compressed_file = os.path.join(output_folder_path, f + '.gcis')
print("GCIS Compressing: ", f)
if (os.path.isfile(compressed_file)):
print(compressed_file, 'already exists, skipping')
else:
gcis.compress_gc_is(input_file, compressed_file)
print("GCIS Decoding and Divsufsort + LCP")
dt = []
st = []
tt = []
for i in range(number_of_samples):
(decode_time, saca_time) = sais.decode_sais_divsufsort_lcp(
compressed_file, output_file)
dt.append(float(decode_time))
st.append(float(saca_time))
tt.append(float(decode_time) + float(saca_time))
print("Decode Time =", decode_time, 'seconds')
print("Saca Divsufsort Time =", saca_time, 'seconds')
e.experiment_input.append(f)
e.experiment_time.append(('{:.2f}'.format(statistics.mean(dt)),
'{:.2f}'.format(statistics.mean(st)),
'{:.2f}'.format(statistics.mean(tt))))
return e