def read_data():
long_pid, long_data, long_label = ReadData.ReadData('../../data1/long.csv')
# mat1 = [truncate_long(ts, 9000) for ts in long_data]
# mat2 = [truncate_long(ts, 6000) for ts in long_data]
mat3 = [truncate_long(ts, 3000) for ts in long_data]
# mat4 = [sample_long(ts, 10) for ts in mat1]
# mat5 = [sample_long(ts, 10) for ts in mat2]
# mat6 = [sample_long(ts, 10) for ts in mat3]
label_onehot = ReadData.Label2OneHot(long_label)
# plt.plot(mat1[0])
# plt.plot(mat4[0])
mat = mat3
all_feature = np.array(mat, dtype=np.float32)
all_label = np.array(label_onehot, dtype=np.float32)
kf = StratifiedKFold(n_splits=5, shuffle=True)
for train_index, test_index in kf.split(all_feature, long_label):
train_data = all_feature[train_index]
train_label = all_label[train_index]
test_data = all_feature[test_index]
test_label = all_label[test_index]
break
train_data = np.expand_dims(np.array(train_data, dtype=np.float32), axis=2)
test_data = np.expand_dims(np.array(test_data, dtype=np.float32), axis=2)
return train_data, train_label, test_data, test_label
def slide_and_cut(tmp_data, tmp_label, tmp_pid):
out_pid = []
out_data = []
out_label = []
window_size = 6000
cnter = {'N': 0, 'O': 0, 'A': 0, '~': 0}
for i in range(len(tmp_data)):
#print(tmp_label[i])
if cnter[tmp_label[i]] is not None:
cnter[tmp_label[i]] += len(tmp_data[i])
stride_N = 500
stride_O = int(stride_N // (cnter['N'] / cnter['O']))
stride_A = int(stride_N // (cnter['N'] / cnter['A']))
stride_P = int(0.85 * stride_N // (cnter['N'] / cnter['~']))
stride = {'N': stride_N, 'O': stride_O, 'A': stride_A, '~': stride_P}
for i in range(len(tmp_data)):
tmp_stride = stride[tmp_label[i]]
tmp_ts = tmp_data[i]
for j in range(0, len(tmp_ts) - window_size, tmp_stride):
out_pid.append(tmp_pid[i])
out_data.append(tmp_ts[j:j + window_size])
out_label.append(tmp_label[i])
out_label = ReadData.Label2OneHot(out_label)
out_data = np.expand_dims(np.array(out_data, dtype=np.float32), axis=2)
out_label = np.array(out_label, dtype=np.float32)
out_pid = np.array(out_pid, dtype=np.string_)
return out_data, out_label, out_pid
def slide_and_cut(tmp_data, tmp_label, tmp_pid):
'''
slide to get more samples from long data
Counter({'N': 5050, 'O': 2456, 'A': 738, '~': 284})
'''
out_pid = []
out_data = []
out_label = []
window_size = 6000
cnter = {'N': 0, 'O': 0, 'A': 0, '~': 0}
for i in range(len(tmp_data)):
cnter[tmp_label[i]] += len(tmp_data[i])
stride_N = 500
stride_O = int(stride_N // (cnter['N'] / cnter['O']))
stride_A = int(stride_N // (cnter['N'] / cnter['A']))
stride_P = int(0.85 * stride_N // (cnter['N'] / cnter['~']))
stride = {'N': stride_N, 'O': stride_O, 'A': stride_A, '~': stride_P}
print(stride)
for i in range(len(tmp_data)):
if i % 1000 == 0:
print(i)
tmp_stride = stride[tmp_label[i]]
tmp_ts = tmp_data[i]
for j in range(0, len(tmp_ts) - window_size, tmp_stride):
out_pid.append(tmp_pid[i])
out_data.append(tmp_ts[j:j + window_size])
out_label.append(tmp_label[i])
print(Counter(out_label))
idx = np.array(list(range(len(out_label))))
out_label = ReadData.Label2OneHot(out_label)
out_data = np.expand_dims(np.array(out_data, dtype=np.float32), axis=2)
out_label = np.array(out_label, dtype=np.float32)
out_pid = np.array(out_pid, dtype=np.string_)
idx_shuffle = np.random.permutation(idx)
out_data = out_data[idx_shuffle]
out_label = out_label[idx_shuffle]
out_pid = out_pid[idx_shuffle]
return out_data, out_label, out_pid
def read_data():
X = ReadData.read_centerwave('../../data1/centerwave_resampled.csv')
_, _, Y = ReadData.ReadData('../../data1/QRSinfo.csv')
all_feature = np.array(X)
print(all_feature.shape)
all_label = np.array(Y)
all_label_num = np.array(ReadData.Label2OneHot(Y))
kf = StratifiedKFold(n_splits=5, shuffle=True)
i_fold = 1
print('all feature shape: {0}'.format(all_feature.shape))
for train_index, test_index in kf.split(all_feature, all_label):
train_data = all_feature[train_index]
train_label = all_label_num[train_index]
test_data = all_feature[test_index]
test_label = all_label_num[test_index]
print('read data done')
return all_feature, all_label_num, train_data, train_label, test_data, test_label
def read_data():
long_pid, long_data, long_label = ReadData.ReadData( '../../data1/centerwave.csv' )
mat1 = [truncate_long(ts, 9000) for ts in long_data]
mat2 = [truncate_long(ts, 6000) for ts in long_data]
mat3 = [truncate_long(ts, 3000) for ts in long_data]
mat4 = [sample_long(ts, 10) for ts in mat1]
mat5 = [sample_long(ts, 10) for ts in mat2]
mat6 = [sample_long(ts, 10) for ts in mat3]
label_onehot = ReadData.Label2OneHot(long_label)
# plt.plot(mat1[0])
# plt.plot(mat4[0])
mat1 = np.expand_dims(np.array(mat1), axis=2)
label_onehot = np.array(label_onehot)
return mat1, label_onehot
def read_seq():
long_pid, long_data, long_label = ReadData.ReadData('../../data1/long.csv')
seq_pid = []
seq_data = []
seq_label = []
seq_len = 1000
for i in range(len(long_pid)):
ts = long_data[i]
for j in range(len(ts) // seq_len):
seq_data.append(ts[j * seq_len:(j + 1) * seq_len])
seq_pid.append(long_pid[i])
seq_label.append(long_label[i])
long_label = seq_label
seq_data = np.array(seq_data, dtype=np.float32)
seq_data = normalize(seq_data, axis=0)
seq_label = ReadData.Label2OneHot(seq_label)
seq_label = np.array(seq_label, dtype=np.float32)
all_feature = seq_data
all_label = seq_label
kf = StratifiedKFold(n_splits=5, shuffle=True)
for train_index, test_index in kf.split(all_feature, long_label):
train_data = all_feature[train_index]
train_label = all_label[train_index]
test_data = all_feature[test_index]
test_label = all_label[test_index]
break
train_data = np.expand_dims(np.array(train_data, dtype=np.float32), axis=2)
test_data = np.expand_dims(np.array(test_data, dtype=np.float32), axis=2)
return train_data, train_label, test_data, test_label
#-----------------------------------------------test--------------------------------------------
'''
train_data, train_label, val_data, val_label, test_data, test_label, test_pid = read_data_from_pkl(
)
long_pid, long_data, long_label = ReadData.ReadData('../../data1/long.csv')
new_test = []
new_pid = []
new_label = []
for j in range(len(long_pid)):
for i in range(len(test_pid)):
if long_pid[j] == test_pid[i]:
new_test.append(long_data[j])
new_pid.append(long_pid[j])
new_label.append(long_label[j])
out_label = ReadData.Label2OneHot(new_label)
out_label = np.array(out_label, dtype=np.float32)
new_test = np.array(new_test)
new_pid = np.array(new_pid)
test_data, test_label, test_pid = slide_and_cut(new_test,
np.array(test_label),
new_pid)
pid_map = {}
pid_set = set(new_pid)
pids = list(pid_set)
for i in range(len(pids)):
cur_pid = str(pids[i], 'utf-8')
pid_map[cur_pid] = i
if pred_1 != np.argmax(labels):
if pred_2 == np.argmax(labels):
y_pre = y_sec_pre
return y_pre
if __name__ == '__main__':
short_pid, short_data, short_label = ReadData.ReadData(
'../../data1/short.csv')
long_pid, long_data, long_label = ReadData.ReadData('../../data1/long.csv')
QRS_pid, QRS_data, QRS_label = ReadData.ReadData('../../data1/QRSinfo.csv')
print('=' * 60)
print('pred begin')
out_label = ReadData.Label2OneHot(long_label)
out_label = np.array(out_label, dtype=np.float32)
#res_pre = pred_resnet(long_data, long_label, long_pid)
#print(len(res_pre))
#MyEval.F1Score3_num(res_pre, out_label)
num_data = len(long_data)
pre = [[0. for j in range(4)] for i in range(num_data)]
#for i in range(num_data):
res = pred_one_sample(short_data[0:40], long_data[0:1], QRS_data[0:1],
long_pid[0:1], short_pid[0:40])
print(res)
labels = {'N': 0, 'A': 1, 'O': 2, '~': 3}
pre = [0., 0., 0., 0.]
pre[labels[res]] = 1