Skip to content

suport python3 #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

suport python3 #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions draw.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ def plot_data_list(wrong_files, wrong_data, figure_dir):
except Exception:
print("failed to create folder to store figures")
return
for i in xrange(len(wrong_files)):
for i in range(len(wrong_files)):
filename = wrong_files[i]
f = os.path.join(figure_dir, filename.strip('/').replace("/", "-") + ".png")
plot_data(wrong_data[i], f, filename[filename.rfind('/')+1:])
Expand All @@ -37,14 +37,14 @@ def plot_data(data, filename, title):
base_num = len(ALL_BASES)
cycles = len(data)/base_num
percents = {}
for b in xrange(base_num):
percents[ALL_BASES[b]]=[ 0.0 for c in xrange(cycles)]
for b in range(base_num):
percents[ALL_BASES[b]]=[ 0.0 for c in range(cycles)]

for c in xrange(cycles):
for c in range(cycles):
total = 0
for b in xrange(base_num):
for b in range(base_num):
total += data[c * base_num + b]
for b in xrange(base_num):
for b in range(base_num):
percents[ALL_BASES[b]][c] = float(data[c * base_num + b]) / float(total)

x = range(1, cycles+1)
Expand Down Expand Up @@ -80,7 +80,7 @@ def plot_benchmark(scores_arr, algorithms_arr, filename):
plt.ylim(0.97, 1.001)
plt.ylabel('Score', size=16, color='#333333')
plt.xlabel('Validation pass (sorted by score)', size=16, color='#333333')
for i in xrange(len(scores_arr)):
for i in range(len(scores_arr)):
plt.plot(x, scores_arr[i], color = colors[i%5], label=algorithms_arr[i], alpha=0.5, linewidth=2, linestyle = linestyles[i%3])
plt.legend(loc='lower left')
plt.savefig(filename)
Expand Down
21 changes: 12 additions & 9 deletions predict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,26 +60,29 @@ def load_model(options):
print("Error: the model file not found: " + options.model_file)
sys.exit(1)
f = open(filename, "rb")
model = pickle.load(f)
if sys.version_info.major >2:
model = pickle.load(f, encoding='latin1')
else:
model = pickle.load(f)
f.close()
return model

def main():
if sys.version_info.major >2:
print('python3 is not supported yet, please use python2')
sys.exit(1)

(options, args) = parseCommand()

data, samples = preprocess(options)

model = load_model(options)

labels = model.predict(data)

for i in xrange(len(samples)):
if options.quite == False or (labels[i] == 0 and "cfdna" in samples[i].lower()) or (labels[i] == 1 and "cfdna" not in samples[i].lower()):
print(get_type_name(labels[i]) + ": " + samples[i])
if sys.version_info.major >2:
for i in range(len(samples)):
if options.quite == False or (labels[i] == 0 and "cfdna" in samples[i].lower()) or (labels[i] == 1 and "cfdna" not in samples[i].lower()):
print(get_type_name(labels[i]) + ": " + samples[i])
else:
for i in xrange(len(samples)):
if options.quite == False or (labels[i] == 0 and "cfdna" in samples[i].lower()) or (labels[i] == 1 and "cfdna" not in samples[i].lower()):
print(get_type_name(labels[i]) + ": " + samples[i])

plot_data_list(samples, data, "predict_fig")

Expand Down
37 changes: 24 additions & 13 deletions train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,15 +135,26 @@ def bootstrap_split(data, label, samples):
validation_set["data"] = []
validation_set["label"] = []
validation_set["samples"] = []
for i in xrange(total_num):
if i in training_ids:
training_set["data"].append(data[i])
training_set["label"].append(label[i])
training_set["samples"].append(samples[i])
else:
validation_set["data"].append(data[i])
validation_set["label"].append(label[i])
validation_set["samples"].append(samples[i])
if sys.version_info.major >2:
for i in range(total_num):
if i in training_ids:
training_set["data"].append(data[i])
training_set["label"].append(label[i])
training_set["samples"].append(samples[i])
else:
validation_set["data"].append(data[i])
validation_set["label"].append(label[i])
validation_set["samples"].append(samples[i])
else:
for i in xrange(total_num):
if i in training_ids:
training_set["data"].append(data[i])
training_set["label"].append(label[i])
training_set["samples"].append(samples[i])
else:
validation_set["data"].append(data[i])
validation_set["label"].append(label[i])
validation_set["samples"].append(samples[i])

return training_set, validation_set

Expand All @@ -153,7 +164,7 @@ def train(model, data, label, samples, options, benchmark = False):
scores = []
wrong_files = []
wrong_data = []
for i in xrange(options.passes):
for i in range(options.passes):
print(str(i+1) + " / " + str(options.passes));
training_set, validation_set = bootstrap_split(data, label, samples)
model.fit(np.array(training_set["data"]), np.array(training_set["label"]))
Expand All @@ -166,7 +177,7 @@ def train(model, data, label, samples, options, benchmark = False):

# get wrongly predicted elements
arr = np.array(validation_set["data"])
for v in xrange(len(validation_set["data"])):
for v in range(len(validation_set["data"])):
result = model.predict(arr[v:v+1])
if result[0] != validation_set["label"][v]:
#print("Truth: " + str(validation_set["label"][v]) + ", predicted: " + str(result[0]) + ": " + validation_set["samples"][v])
Expand Down Expand Up @@ -238,10 +249,10 @@ def main():
GaussianNB(),
svm.SVC(kernel='rbf')]
scores_arr = []
for m in xrange(len(models)):
for m in range(len(models)):
print("\nbenchmark with: " + names[m])
scores_arr.append(train(models[m], data, label, samples, options, True))
for m in xrange(len(models)):
for m in range(len(models)):
print("\nbenchmark mean score with: " + names[m] + " mean " + str(np.mean(scores_arr[m])) + ", std " + str(np.std(scores_arr[m])))
print("\nploting benchmark result...")
plot_benchmark(scores_arr, names, "benchmark.png")
Expand Down