def main():
problem_dataset_dir = os.path.join('Problems', 'Problem6')
solution_dir = os.path.join("Problems", "Problem6Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
genome = case[0]
k = case[1][0]
l = case[1][1][0]
t = case[1][1][1]
dna = DNA(genome)
clumps_patterns = dna.get_clumps_patterns(int(k), int(t), int(l))
if clumps_patterns.sort() != case_output.sort():
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + clumps_patterns)
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
case = test_cases[test_i]
genome = case[0]
k = case[1][0]
l = case[1][1][0]
t = case[1][1][1]
dna = DNA(genome)
clumps_patterns = dna.get_clumps_patterns(int(k), int(t), int(l))
usage.end()
writer.write_data(test_i, clumps_patterns, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + genome + "\n" + str(k) + " " + str(l) + " " + str(t))
print("\n\nOutput")
print("=====")
for clump in clumps_patterns:
print(clump)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem2')
solution_dir = os.path.join("Problems", "Problem2Solution")
data_reader = DataReader(problem_dataset_dir)
training_data, testing_data = data_reader.get_data()
codons_table = data_reader.get_rna_codon_table()
for sample in training_data:
dna_string = sample[0][0]
amino_acid = sample[0][1]
output = sample[1]
dna = DNA(dna_string)
dna.set_codon_table(codons_table)
candidates = dna.get_dna_to_amino_acid_candidates(amino_acid)
if set(candidates) != set(output):
raise Exception("Output not matched!\nExpecting: " + str(output) +
"\nFound: " + str(candidates))
print("Passed training data..\n\n")
writer = DataWriter(solution_dir)
usage = Usage()
for sample in testing_data:
usage.start()
dna_string = sample[0][0]
amino_acid = sample[0][1]
dna = DNA(dna_string)
dna.set_codon_table(codons_table)
candidates = dna.get_dna_to_amino_acid_candidates(amino_acid)
usage.end()
writer.write_data((dna_string, amino_acid), candidates,
usage.get_execution_time(), usage.get_memory_usage())
print("DNA:\n" + dna_string)
print("Protein\n" + amino_acid)
print("\n\nOutput")
print("=====")
print(str(len(candidates)))
for substring in candidates:
print(substring)
print("\n\nExecution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Usage: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem3')
solution_dir = os.path.join("Problems", "Problem3Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
dna = DNA(case[0])
k_mers = dna.most_frequent_k_mer(int(case[1]))
if k_mers.sort() != case_output.sort():
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + str(k_mers))
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem11')
solution_dir = os.path.join("Problems", "Problem11Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
scoring_matrix = data_reader.get_BLOSUM62_data()
for train_i in range(0, len(output)):
alpha_dna, beta_dna = test_cases[train_i]
case_output = output[train_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
align = strings_algorithms.alignment(_type='global',
scoring_matrix=scoring_matrix)
if align != case_output:
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + str(align))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
alpha_dna, beta_dna = test_cases[test_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
align = strings_algorithms.alignment(_type='global',
scoring_matrix=scoring_matrix)
usage.end()
writer.write_data(test_i + 1, align, usage.get_execution_time(),
usage.get_memory_usage())
print("\n\nInput:\n" + alpha_dna + "\n" + beta_dna + "\n")
print("\n\nOutput")
print("=====")
print(align[0])
print(align[1][0])
print(align[1][1])
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem4')
solution_dir = os.path.join("Problems", "Problem4Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
dna = DNA(case)
reverse_complement = dna.reverse_complement()
if reverse_complement != case_output:
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " +
reverse_complement)
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem2')
solution_dir = os.path.join("Problems", "Problem2Solution")
data_reader = DataReader(problem_dataset_dir)
training_data, testing_data = data_reader.get_data()
codons_table = data_reader.get_rna_codon_table()
for sample in training_data:
dna_string = sample[0][0]
amino_acid = sample[0][1]
output = sample[1]
dna = DNA(dna_string)
dna.set_codon_table(codons_table)
candidates = dna.get_dna_to_amino_acid_candidates(amino_acid)
if set(candidates) != set(output):
raise Exception("Output not matched!\nExpecting: " + str(output) + "\nFound: " + str(candidates))
print("Passed training data..\n\n")
writer = DataWriter(solution_dir)
usage = Usage()
for sample in testing_data:
usage.start()
dna_string = sample[0][0]
amino_acid = sample[0][1]
dna = DNA(dna_string)
dna.set_codon_table(codons_table)
candidates = dna.get_dna_to_amino_acid_candidates(amino_acid)
usage.end()
writer.write_data((dna_string, amino_acid), candidates, usage.get_execution_time(), usage.get_memory_usage())
print("DNA:\n" + dna_string)
print("Protein\n" + amino_acid)
print("\n\nOutput")
print("=====")
print(str(len(candidates)))
for substring in candidates:
print(substring)
print("\n\nExecution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Usage: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem9')
solution_dir = os.path.join("Problems", "Problem9Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
genome = case[0]
k = case[1][0]
d = case[1][1]
dna = DNA(genome)
k_mers = dna.most_frequent_missmatched_k_mer(int(k), int(d))
if set(case_output) != set(k_mers):
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(k_mers))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output) + 1, len(test_cases)):
usage.start()
case = test_cases[test_i]
genome = case[0]
k = case[1][0]
d = case[1][1]
dna = DNA(genome)
k_mers = dna.most_frequent_missmatched_k_mer(int(k), int(d))
usage.end()
writer.write_data(test_i, k_mers, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + genome + "\n" + str(k) + "\n" + str(d))
print("\n\nOutput")
print("=====")
print('\n'.join(map(lambda v: str(v), k_mers)))
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem7')
solution_dir = os.path.join("Problems", "Problem7Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = np.array(output[train_i])
dna = DNA(case.strip())
min_skew_indices = dna.get_min_skew()
if not np.array_equal(case_output, min_skew_indices):
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " +
str(min_skew_indices))
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem5')
solution_dir = os.path.join("Problems", "Problem5Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
pattern = case[0]
genome = case[1]
dna = DNA(genome)
pattern_indices = dna.get_pattern_indices(pattern)
if pattern_indices != case_output:
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + pattern_indices)
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem5')
solution_dir = os.path.join("Problems", "Problem5Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
pattern = case[0]
genome = case[1]
dna = DNA(genome)
pattern_indices = dna.get_pattern_indices(pattern)
if pattern_indices != case_output:
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + pattern_indices)
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
case = test_cases[test_i]
pattern = case[0]
genome = case[1]
dna = DNA(genome)
pattern_indices = dna.get_pattern_indices(pattern)
usage.end()
writer.write_data(test_i + 1, pattern_indices, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + pattern + "\n" + genome)
print("\n\nOutput")
print("=====")
print(pattern_indices)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem10')
solution_dir = os.path.join("Problems", "Problem10Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
alpha_dna, beta_dna = test_cases[train_i]
case_output = output[train_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
lcs = strings_algorithms.lcs('dp')
print(len(lcs))
if len(case_output) != len(lcs):
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + str(lcs))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
alpha_dna, beta_dna = test_cases[test_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
lcs = strings_algorithms.lcs('dp')
print(len(lcs))
usage.end()
writer.write_data(test_i + 1, lcs, usage.get_execution_time(),
usage.get_memory_usage())
print("\n\nInput:\n" + alpha_dna + "\n" + beta_dna + "\n")
print("\n\nOutput")
print("=====")
print(lcs)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem9')
solution_dir = os.path.join("Problems", "Problem9Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
genome = case[0]
k = case[1][0]
d = case[1][1]
dna = DNA(genome)
k_mers = dna.most_frequent_missmatched_k_mer(int(k), int(d))
if set(case_output) != set(k_mers):
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + str(k_mers))
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem11')
solution_dir = os.path.join("Problems", "Problem11Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
scoring_matrix = data_reader.get_BLOSUM62_data()
for train_i in range(0, len(output)):
alpha_dna, beta_dna = test_cases[train_i]
case_output = output[train_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
align = strings_algorithms.alignment(_type='global', scoring_matrix=scoring_matrix)
if align != case_output:
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(align))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
alpha_dna, beta_dna = test_cases[test_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
align = strings_algorithms.alignment(_type='global', scoring_matrix=scoring_matrix)
usage.end()
writer.write_data(test_i + 1, align, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + alpha_dna + "\n" + beta_dna + "\n")
print("\n\nOutput")
print("=====")
print(align[0])
print(align[1][0])
print(align[1][1])
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem16')
solution_dir = os.path.join("Problems", "Problem16Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
k_mers = test_cases[train_i]
graph = Graph()
adj_list = graph.get_debruijn_graph(_type='k_mers', k_mers=k_mers)
case_output = output[train_i]
if sorted(adj_list.items()) != sorted(case_output.items()):
raise Exception("Output not matched!\nExpecting: " +
str(sorted(case_output.items())) + "\nFound: " +
str(sorted(adj_list.items())))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
k_mers = test_cases[test_i]
adj_list = Graph().get_debruijn_graph(_type='k_mers', k_mers=k_mers)
usage.end()
writer.write_data(test_i + 1, adj_list, usage.get_execution_time(),
usage.get_memory_usage())
print("\n\nInput:\n" + str(k_mers) + "\n")
print("\n\nOutput")
print("=====")
print(adj_list)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem13')
solution_dir = os.path.join("Problems", "Problem13Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
(k, genome) = test_cases[train_i]
case_output = output[train_i]
dna = DNA(genome)
k_mers = dna.get_k_mers(int(k))
if sorted(case_output) != sorted(k_mers):
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + str(k_mers))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
(k, genome) = test_cases[test_i]
dna = DNA(genome)
k_mers = dna.get_k_mers(int(k))
usage.end()
writer.write_data(test_i + 1, k_mers, usage.get_execution_time(),
usage.get_memory_usage())
print("\n\nInput:\n" + k + "\n" + genome + "\n")
print("\n\nOutput")
print("=====")
print(k_mers)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem17')
solution_dir = os.path.join("Problems", "Problem17Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
dna = test_cases[train_i][0]
k = test_cases[train_i][1][0]
score_matrix = test_cases[train_i][1][1]
case_output = output[train_i]
most_probable_k_mer = DNA(dna).get_most_probable_k_mer(int(k), score_matrix)
if most_probable_k_mer != case_output:
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(most_probable_k_mer))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output) - 1, len(test_cases)):
usage.start()
dna = test_cases[test_i][0]
k = test_cases[test_i][1][0]
score_matrix = test_cases[test_i][1][1]
most_probable_k_mer = DNA(dna).get_most_probable_k_mer(int(k), score_matrix)
usage.end()
writer.write_data(test_i + 1, most_probable_k_mer, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + str(dna) + "\n" + str(k) + "\n" + str(score_matrix))
print("\n\nOutput")
print("=====")
print(most_probable_k_mer)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem10')
solution_dir = os.path.join("Problems", "Problem10Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
alpha_dna, beta_dna = test_cases[train_i]
case_output = output[train_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
lcs = strings_algorithms.lcs('dp')
print(len(lcs))
if len(case_output) != len(lcs):
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(lcs))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
alpha_dna, beta_dna = test_cases[test_i]
strings_algorithms = StringsAlgorithms(alpha_dna, beta_dna)
lcs = strings_algorithms.lcs('dp')
print(len(lcs))
usage.end()
writer.write_data(test_i + 1, lcs, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + alpha_dna + "\n" + beta_dna + "\n")
print("\n\nOutput")
print("=====")
print(lcs)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem6')
solution_dir = os.path.join("Problems", "Problem6Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
genome = case[0]
k = case[1][0]
l = case[1][1][0]
t = case[1][1][1]
dna = DNA(genome)
clumps_patterns = dna.get_clumps_patterns(int(k), int(t), int(l))
if clumps_patterns.sort() != case_output.sort():
raise Exception("Output not matched!\nExpecting: " +
str(case_output) + "\nFound: " + clumps_patterns)
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem15')
solution_dir = os.path.join("Problems", "Problem15Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
k = test_cases[train_i][0]
dna = test_cases[train_i][1]
graph = Graph()
adj_list = graph.get_debruijn_graph(_type='string', k=int(k), dna_string=dna)
case_output = output[train_i]
if sorted(adj_list.items()) != sorted(case_output.items()):
raise Exception("Output not matched!\nExpecting: " + str(sorted(case_output.items())) + "\nFound: " + str(sorted(adj_list.items())))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
k = test_cases[test_i][0]
dna = test_cases[test_i][1]
adj_list = Graph().get_debruijn_graph(_type='string', k=int(k), dna_string=dna)
usage.end()
writer.write_data(test_i + 1, adj_list, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + str(k) + "\n" + dna + "\n")
print("\n\nOutput")
print("=====")
print(adj_list)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem7')
solution_dir = os.path.join("Problems", "Problem7Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = np.array(output[train_i])
dna = DNA(case.strip())
min_skew_indices = dna.get_min_skew()
if not np.array_equal(case_output, min_skew_indices):
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(min_skew_indices))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
case = test_cases[test_i]
dna = DNA(case.strip())
min_skew_indices = dna.get_min_skew()
usage.end()
writer.write_data(test_i + 1, min_skew_indices, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + case + "\n")
print("\n\nOutput")
print("=====")
print(list(min_skew_indices))
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem4')
solution_dir = os.path.join("Problems", "Problem4Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
case = test_cases[train_i]
case_output = output[train_i]
dna = DNA(case)
reverse_complement = dna.reverse_complement()
if reverse_complement != case_output:
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + reverse_complement)
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
case = test_cases[test_i]
dna = DNA(case)
reverse_complement = dna.reverse_complement()
usage.end()
writer.write_data(test_i + 1, reverse_complement, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + case)
print("\n\nOutput")
print("=====")
print(reverse_complement)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem13')
solution_dir = os.path.join("Problems", "Problem13Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
(k, genome) = test_cases[train_i]
case_output = output[train_i]
dna = DNA(genome)
k_mers = dna.get_k_mers(int(k))
if sorted(case_output) != sorted(k_mers):
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(k_mers))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
(k, genome) = test_cases[test_i]
dna = DNA(genome)
k_mers = dna.get_k_mers(int(k))
usage.end()
writer.write_data(test_i + 1, k_mers, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + k + "\n" + genome + "\n")
print("\n\nOutput")
print("=====")
print(k_mers)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem14')
solution_dir = os.path.join("Problems", "Problem14Solution")
data_reader = DataReader(problem_dataset_dir)
test_cases, output = data_reader.get_data()
for train_i in range(0, len(output)):
k_mers = test_cases[train_i]
case_output = output[train_i]
graph = Graph(k_mers)
adj_list = graph.get_overlap_graph()
if sorted(adj_list.items()) != sorted(case_output.items()):
raise Exception("Output not matched!\nExpecting: " + str(case_output) + "\nFound: " + str(adj_list))
print("Passed training data..")
writer = DataWriter(solution_dir)
usage = Usage()
for test_i in range(len(test_cases) - len(output), len(test_cases)):
usage.start()
k_mers = test_cases[test_i]
graph = Graph(k_mers)
adj_list = graph.get_overlap_graph()
usage.end()
writer.write_data(test_i + 1, adj_list, usage.get_execution_time(), usage.get_memory_usage())
print("\n\nInput:\n" + str(k_mers) + "\n")
print("\n\nOutput")
print("=====")
print(adj_list)
print("\n")
print("======")
print("Execution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Used: " + str(usage.get_memory_usage()) + " MB")
def main():
problem_dataset_dir = os.path.join('Problems', 'Problem1')
solution_dir = os.path.join("Problems", "Problem1Solution")
data_reader = DataReader(problem_dataset_dir)
training_data, testing_data = data_reader.get_data()
codons_table = data_reader.get_rna_codon_table()
for sample in training_data:
rna_string = sample[0]
output = sample[1]
rna = RNA(rna_string)
rna.set_codons_table(codons_table)
amino_acid = rna.to_amino_acid()
if amino_acid != output:
raise Exception("Output not matched!\nExpecting: " + output +
"\nFound: " + amino_acid)
print("Passed training data..\n\n")
writer = DataWriter(solution_dir)
usage = Usage()
for sample in testing_data:
usage.start()
rna_string = sample[0]
rna = RNA(rna_string)
rna.set_codons_table(codons_table)
amino_acid = rna.to_amino_acid()
usage.end()
writer.write_data(rna_string, amino_acid, usage.get_execution_time(),
usage.get_memory_usage())
print("RNA:\n" + rna_string)
print("Protein:\n" + amino_acid)
print("\n\nExecution Time: " + str(usage.get_execution_time()) + " s")
print("Memory Usage: " + str(usage.get_memory_usage()) + " MB")
from data_reader.reader import DataReader
from libs_utils.sklearn_util.sklearn_util import SklearnUtil
from libs_utils.nltk_util.nltk_util import NltkUtil
from preprocessing_util.preprocessing import Preprocessing
import pickle
file_path = "./data/train.csv"
reader = DataReader(file_path)
reader.get_all_train_data()
questions_pairs, labels = reader.get_train_data()
preprocessor = Preprocessing(questions_pairs)
questions_pairs = preprocessor.remove_extra_whitespaces()
print("End removing extra spaces")
preprocessor = Preprocessing(questions_pairs)
questions_pairs = preprocessor.remove_punctuation()
print("End removing punctuations")
preprocessor = Preprocessing(questions_pairs)
questions_pairs = preprocessor.normalize_text()
print("End normalization")
preprocessor = Preprocessing(questions_pairs)
tokenized_questions_pairs = preprocessor.tokenize()
print("End tokenization")
preprocessor = Preprocessing(questions_pairs)
stemmed_questions_pairs = preprocessor.tokenize_with_stemming()
print("End stemmed tokenization")