print(feature)
#ax = []
#ay = []
#plt.ion()
for k, v in order_dict[2:]:
temp = np.zeros(rows)
for q in range(rows):
temp[q] = sample[q][k]
feature = np.c_[feature, temp]
print(feature)
gram = np.zeros((rows, rows))
for i in range(rows):
for j in range(rows):
gram[i][j] = round(metrics_function.cosine(feature[i], feature[j]), 6)
print(gram)
#G = pd.DataFrame(gram)
#pd.DataFrame.to_csv(G, 'D:/Study/Bioinformatics/AFP/feature_matrix/Antifp_Main/188-bit/gram.csv')
clf = svm.SVC(kernel = 'precomputed', probability = False)
clf.fit(gram, y_train)
cv = model_selection.StratifiedKFold(n_splits = 5, shuffle = True, random_state = 0)
five_fold = model_selection.cross_validate(clf, gram, label, cv = cv, scoring = 'accuracy', n_jobs = -1)
ACC = np.mean(five_fold['test_score'])
print('ACC =', ACC)
if ACC > best_ACC:
best_ACC = ACC
best_feature = np.copy(feature)
#ax.append(k)
#ay.append(ACC)
file = np.loadtxt('D:/Study/Bioinformatics/QSP_new/' + name + '/train_' +
name + '.csv',
delimiter=',',
skiprows=1)
m = np.shape(file)[0]
n = np.shape(file)[1]
data = np.zeros((m, n - 1))
for index in range(m):
data[index] = file[index][1:]
np.set_printoptions(suppress=True)
K1 = np.zeros((m, m))
for i in range(m):
for j in range(m):
K1[i][j] = round(metrics_function.cosine(data[i], data[j]), 6)
print(K1)
with open(
'D:/Study/Bioinformatics/QSP_new/kernel_matrix/KM_train_cosine/KM_cosine_'
+ name + '_train.csv',
'w',
newline='') as csvfile:
writer = csv.writer(csvfile)
for row in K1:
writer.writerow(row)
csvfile.close()
K3 = np.zeros((m, m))
for i in range(m):
for j in range(m):
K3[i][j] = round(metrics_function.tanimoto(data[i], data[j]), 6)
file1 = np.loadtxt("D:/study/Bioinformatics/QSP/200p_200n/10_fold/" +
name + "/train/train_" + name + "_" + str(k) +
".csv",
delimiter=',')
p = np.shape(file1)[0]
q = np.shape(file1)[1]
X_train = np.zeros((p, q - 1))
for index in range(p):
X_train[index] = file1[index][1:]
K1 = np.zeros((p, p))
for i in range(p):
for j in range(p):
K1[i][j] = round(
metrics_function.cosine(X_train[i], X_train[j]), 6)
print(K1)
with open('D:/study/Bioinformatics/QSP/200p_200n/10_fold/' + name +
'/km_train/KM_cosine_' + name + '_train_' + str(k) + '.csv',
'w',
newline='') as csvfile:
writer = csv.writer(csvfile)
for row in K1:
writer.writerow(row)
csvfile.close()
K2 = np.zeros((m, p))
for i in range(m):
for j in range(p):
K2[i][j] = round(
metrics_function.cosine(X_test[i], X_train[j]), 6)
X_test[index] = f1[index][1:]
f2 = np.loadtxt('D:/study/Bioinformatics/AMP/' + name + '/train_' + name +
'.csv',
delimiter=',',
skiprows=1)
p = np.shape(f2)[0]
q = np.shape(f2)[1]
X_train = np.zeros((p, q - 1))
for index in range(p):
X_train[index] = f2[index][1:]
K1 = np.zeros((m, p))
for i in range(m):
for j in range(p):
K1[i][j] = round(metrics_function.cosine(X_test[i], X_train[j]), 6)
print(K1)
with open(
'D:/study/Bioinformatics/AMP/kernel_matrix/KM_test_cosine/KM_cosine_'
+ name + '_test.csv',
'w',
newline='') as csvfile:
writer = csv.writer(csvfile)
for row in K1:
writer.writerow(row)
csvfile.close()
K3 = np.zeros((m, p))
for i in range(m):
for j in range(p):
K3[i][j] = round(metrics_function.tanimoto(X_test[i], X_train[j]),
print(thresholds)
best_ACC = 0
best_train = X_train
best_test = X_test
for thres in thresholds:
print('threshold =', thres)
selector = SelectFromModel(model, threshold=thres, prefit=True)
X_train_selected = selector.transform(X_train)
print(np.shape(X_train_selected))
X_test_selected = selector.transform(X_test)
print(np.shape(X_test_selected))
gram_train = metrics_function.cosine(X_train_selected,
X_train_selected)
clf = svm.SVC(kernel='precomputed', probability=False)
try:
clf.fit(gram_train, y_train)
except ValueError as e:
print("ValueError Details : " + str(e))
continue
cv = model_selection.StratifiedKFold(n_splits=5, shuffle=False)
five_fold = model_selection.cross_validate(clf,
gram_train,
y_train,
cv=cv,
scoring='accuracy',
n_jobs=-1)
ACC = np.mean(five_fold['test_score'])