def main(argv):
dpath = os.environ["DeeprimerPATH"]
try:
opts, args = getopt.getopt(argv, "ht:w:o:p:c:")
except getopt.GetoptError:
print(
'Run_randomforest.py -t <n_estimator> -c <n_class> -w <fit/pred/eval> -o <preprocessed_object> -p <pred_input>'
)
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print(
"[Command]: Run_randomforest.py -t <n_estimator> -w <fit/pred/eval> -o <preprocessed_object> -p <pred_input>"
+ "\n\n" + "Example:" + "\n\n" + "1. Fit the model only:" +
"\n\n" +
"Run_randomforest.py -t 1000 -w fit -o <sample_pre.fit.pickled>"
+ "\n\n" + "2. Evaluate the model:" + "\n\n" +
"Run_randomforest.py -t 1000 -w eval -o <sample_split.eval.pickled>"
+ "\n\n" + "3. Make prediction:" + "\n\n" +
"Run_randomforest.py -t 1000 -w pred -o <sample_pre.fit_RF.machine> -p <pred_input>"
+ "\n")
sys.exit()
elif opt == "-t":
n_est = int(arg)
elif opt == "-w":
task = arg
elif opt == "-o":
obj = arg
elif opt == "-c":
nclass = int(arg)
elif opt == "-p":
pred_input = pd.read_csv(arg, delim_whitespace=True)
pred = pred_input.values
if 'nclass' not in locals():
nclass = 2
LW = 2
RANDOM_STATE = 42
tag = re.sub('\.pickled$', '', obj).split("/")[-1]
if task == "fit":
with open(obj, 'rb') as f:
pre_obj = pickle.load(f)
X_tr = pre_obj[0]
y_tr = pre_obj[1]
if sum(y_tr == 1) >= 2 * sum(y_tr == 0) or sum(
y_tr == 1) <= (1 / 2) * sum(y_tr == 0):
classifier = RandomForestClassifier(n_estimators=n_est)
sampler = RandomOverSampler(random_state=RANDOM_STATE)
clf = make_pipeline(sampler, classifier)
else:
clf = RandomForestClassifier(n_estimators=n_est)
fitted = clf.fit(X_tr, y_tr)
if nclass == 2:
with open(OBJpath + "/" + tag + "_RF.machine", 'wb') as f:
pickle.dump(fitted, f, pickle.HIGHEST_PROTOCOL)
elif nclass == 3:
with open(OBJpath + "/" + tag + "_3C_RF.machine", 'wb') as f:
pickle.dump(fitted, f, pickle.HIGHEST_PROTOCOL)
else:
print("Not support class over 3. Try Regress." + "\n")
sys.exit()
elif task == "eval":
with open(obj, 'rb') as f:
pre_obj = pickle.load(f)
X_tr = pre_obj[0]
y_tr = pre_obj[1]
X_te = pre_obj[2]
y_te = pre_obj[3]
if sum(y_tr == 1) >= 2 * sum(y_tr == 0) or sum(
y_tr == 1) <= (1 / 2) * sum(y_tr == 0):
classifier = RandomForestClassifier(n_estimators=n_est)
sampler = RandomOverSampler(random_state=RANDOM_STATE)
clf = make_pipeline(sampler, classifier)
else:
clf = RandomForestClassifier(n_estimators=n_est)
fitted = clf.fit(X_tr, y_tr)
if nclass == 2:
fpr, tpr, precision, recall, metrics = mev.performance_stat(
X_te, y_te, fitted)
mev.plot_eval(fpr, tpr, precision, recall, metrics, tag)
with open(REPpath + "/" + tag + "_RF.metrics", 'wb') as f:
for key, value in metrics.items():
f.write("%s %.3f" % (key, value) + '\n')
elif nclass == 3:
pred_p = fitted.predict_proba(X_te)
pred_c = fitted.predict(X_te)
cnf_matrix = confusion_matrix(y_te, pred_c)
np.set_printoptions(precision=2)
class_names = ["0", "1", "2"]
plot_confusion_matrix(cnf_matrix, class_names, True,
'Normalized confusion matrix', tag)
with open(REPpath + "/" + tag + "_3C_RF_eval.summay", 'wb') as f:
f.write(
classification_report(y_te,
pred_c,
target_names=class_names))
elif task == "pred":
tag1 = re.sub('\.machine$', '', obj).split("/")[-1]
with open(obj, 'rb') as f:
fitted_obj = pickle.load(f)
pred_p = fitted_obj.predict_proba(pred)
pred_c = fitted_obj.predict(pred)
if nclass == 2:
df = pd.DataFrame({
"Probability_1": pred_p[:, 1],
"Probability_0": pred_p[:, 0],
"Predited_class": pred_c
})
df.to_csv(REPpath + "/" + tag1 + ".2classification",
index=None,
sep='\t')
elif nclass == 3:
df = pd.DataFrame({
"Probability_2": pred_p[:, 2],
"Probability_1": pred_p[:, 1],
"Probability_0": pred_p[:, 0],
"Predited_class": pred_c
})
df.to_csv(REPpath + "/" + tag1 + ".3classification",
index=None,
sep='\t')
else:
print("Not support class over 3. Try Regression.")
sys.exit()
else:
print("Not supported task. Choose from fit, pred, eval" + "\n")
sys.exit()
def main(argv):
dpath = os.environ["DeeprimerPATH"]
try:
opts, args = getopt.getopt(argv, "hC:w:o:p:")
except getopt.GetoptError:
print(
'Run_SVM.py -C <penalty> -w <fit/pred/eval> -o <preprocessed_object> -p <pred_input>'
)
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print(
"[Command]: Run_SVM.py -C <penalty> -w <fit/pred/eval> -o <preprocessed_object> -p <pred_input>"
+ "\n\n" + "Example:" + "\n\n" + "1. Fit the model only:" +
"\n\n" +
"Run_SVM.py -C 1000 -w fit -o <sample_pre.fit.pickled>" +
"\n\n" + "2. Evaluate the model:" + "\n\n" +
"Run_SVM.py -C 1000 -w eval -o <sample_split.eval.pickled>" +
"\n\n" + "3. Make prediction:" + "\n\n" +
"Run_SVM.py -C 1000 -w pred -o <sample_pre.fit_SVM.machine> -p <pred_input>"
+ "\n")
sys.exit()
elif opt == "-C":
pty = int(arg)
elif opt == "-w":
task = arg
elif opt == "-o":
obj = arg
elif opt == "-p":
pred_input = pd.read_csv(arg, delim_whitespace=True)
pred = pred_input.values
LW = 2
RANDOM_STATE = 42
tag = re.sub('\.pickled$', '', obj).split("/")[-1]
if task == "fit":
with open(obj, 'rb') as f:
pre_obj = pickle.load(f)
X_tr = pre_obj[0]
y_tr = pre_obj[1]
if sum(y_tr == 1) >= 2 * sum(y_tr == 0) or sum(
y_tr == 1) <= (1 / 2) * sum(y_tr == 0):
classifier = svm.SVC(kernel='rbf', probability=True, C=pty)
sampler = RandomOverSampler(random_state=RANDOM_STATE)
clf = make_pipeline(sampler, classifier)
else:
clf = svm.SVC(kernel='rbf', probability=True, C=pty)
fitted = clf.fit(X_tr, y_tr)
with open(OBJpath + "/" + tag + "_SVM.machine", 'wb') as f:
pickle.dump(fitted, f, pickle.HIGHEST_PROTOCOL)
elif task == "eval":
with open(obj, 'rb') as f:
pre_obj = pickle.load(f)
X_tr = pre_obj[0]
y_tr = pre_obj[1]
X_te = pre_obj[2]
y_te = pre_obj[3]
if sum(y_tr == 1) >= 2 * sum(y_tr == 0) or sum(
y_tr == 1) <= (1 / 2) * sum(y_tr == 0):
classifier = svm.SVC(kernel='rbf', probability=True, C=pty)
sampler = RandomOverSampler(random_state=RANDOM_STATE)
clf = make_pipeline(sampler, classifier)
else:
clf = svm.SVC(kernel='rbf', probability=True, C=pty)
fitted = clf.fit(X_tr, y_tr)
fpr, tpr, precision, recall, metrics = mev.performance_stat(
X_te, y_te, fitted)
mev.plot_eval(fpr, tpr, precision, recall, metrics, tag)
with open(REPpath + "/" + tag + "_SVM.metrics", 'wb') as f:
for key, value in metrics.items():
f.write("%s %.3f" % (key, value) + '\n')
elif task == "pred":
tag1 = re.sub('\.machine$', '', obj).split("/")[-1]
with open(obj, 'rb') as f:
fitted_obj = pickle.load(f)
pred_p = fitted_obj.predict_proba(pred)
pred_c = fitted_obj.predict(pred)
df = pd.DataFrame({
"Probability_1": pred_p[:, 1],
"Probability_0": pred_p[:, 0],
"Predited_class": pred_c
})
df.to_csv(REPpath + "/" + tag1 + ".classification",
index=None,
sep='\t')
else:
print("Not supported task. Choose from fit, pred, eval" + "\n")
sys.exit()
def main(argv):
dpath = os.environ["DeeprimerPATH"]
try:
opts, args = getopt.getopt(argv, "hf:d:i:w:o:p:")
except getopt.GetoptError:
print(
'Run_CNN.py -f <n_feature> -d <drop_probability> -i <iterations> -w <fit/pred/eval> -o <preprocessed_object> -p <pred_input>'
)
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print(
"[Command]: Run_CNN.py -f <n_feature> -d <drop_probability> -i <iterations> -w <fit/pred/eval> -o <preprocessed_object> -p <pred_input>"
+ "\n\n" + "Example:" + "\n\n" + "1. Fit the model only:" +
"\n\n" +
"Run_CNN.py -f 415 -d 0.5 -i <iterations> -w fit -o <sample_pre.fit.pickled>"
+ "\n\n" + "2. Evaluate the model:" + "\n\n" +
"Run_CNN.py -f 415 -d 0.5 -i <iterations> -w eval -o <sample_split.eval.pickled>"
+ "\n\n" + "3. Make prediction:" + "\n\n" +
"Run_CNN.py -f 415 -w pred -o <sample_pre.fit_CNN.machine.meta> -p <pred_input>"
+ "\n")
sys.exit()
elif opt == "-f":
n_f = int(arg)
elif opt == "-d":
dp = float(arg)
elif opt == "-i":
it = int(arg)
elif opt == "-w":
task = arg
elif opt == "-o":
obj = arg
elif opt == "-p":
pred_input = pd.read_csv(arg, delim_whitespace=True)
Xpred = pred_input.values
LW = 2
tag = re.sub('\.pickled$', '', obj).split("/")[-1]
if task == "fit":
with open(obj, 'rb') as f:
pre_obj = pickle.load(f)
X_tr = pre_obj[0]
y_tr = pre_obj[1]
fit_CNN(X_tr, y_tr, n_f, dp, it, tag,
TF_CNN) #restores session in the TF_sessions folder
elif task == "eval":
with open(obj, 'rb') as f:
pre_obj = pickle.load(f)
X_tr = pre_obj[0]
y_tr = pre_obj[1]
X_te = pre_obj[2]
y_te = pre_obj[3]
fit_CNN(X_tr, y_tr, n_f, dp, it, tagi, TF_CNN)
meta = tag + "_CNN.machine.meta"
fpr, tpr, precision, recall, metrics = mev.performance_stat_nn(
X_te, y_te, "CNN", meta)
mev.plot_eval(fpr, tpr, precision, recall, metrics, tag)
with open(REPpath + "/" + tag + "_CNN.metrics", 'wb') as f:
for key, value in metrics.items():
f.write("%s %.3f" % (key, value) + '\n')
elif task == "pred":
meta = obj
tag1 = re.sub('\.machine\.meta$', '', obj).split("/")[-1]
X_te32 = Xpred.astype(np.float32)
sess = tf.Session()
saver = tf.train.import_meta_graph(obj)
saver.restore(sess, tf.train.latest_checkpoint(TF_CNN))
graph = tf.get_default_graph()
y_conv = graph.get_tensor_by_name("y_conv:0")
y_ = graph.get_tensor_by_name("y_:0")
x = graph.get_tensor_by_name("x:0")
keep_prob = graph.get_tensor_by_name("keep_prob:0")
feed_dict = {x: X_te32, keep_prob: 1.0}
probs = tf.nn.softmax(y_conv)
pred_p = sess.run(probs, feed_dict)
prediction = tf.argmax(y_conv, 1)
pred_c = prediction.eval(feed_dict, session=sess)
df = pd.DataFrame({
"Probability_1": pred_p[:, 1],
"Probability_0": pred_p[:, 0],
"Predited_class": pred_c
})
df.to_csv(REPpath + "/" + tag1 + ".classification",
index=None,
sep='\t')
else:
print("Not supported task. Choose from fit, pred, eval" + "\n")
sys.exit()