else:
sep = "/"
guide = CONFIG_PATH + sep + "Hui_SuperProject" + sep + "MovDict.json"
guide_dict = read_json(guide).to_dict()
example_path = CONFIG_PATH + sep + "Hui_SuperProject" + sep + "Data_Examples"
key = 15
features_path = "D:\PhD\Data\HuisData\Dataset1\FeatureExtracted\Features_tsfel_HuiData"
filename = "features_500_15.npz"
tag = 8
sub = 1
a = 10000
b = 45000
begin_feat = 5000
all_signals = loadH5(example_path + sep + guide_dict[key]["file"])[a:b:sub, :]
or_signal = all_signals[:, tag]
ref_signal = all_signals[:, -1]
ssts_distance(or_signal)
file = load_npz_featuresHui(features_path + sep + filename)
feature_set = load_featuresbydomain(file, features_tag=tag)
features_temp = np.array(feature_set["featurebydomain"]["temp"])[:, a:b:sub]
features_stat = np.array(feature_set["featurebydomain"]["stat"])[:, a:b:sub]
features_spec = np.array(feature_set["featurebydomain"]["spec"])[:, a:b:sub]
features_t_norm = StandardScaler().fit_transform(features_temp)
# # features_t_norm = matrix_norm(features_temp)
# # print(features_t_norm)
for i in range(len(corpus)):
# labels = np.append(labels, lda_model[corpus[i]][0][0])
topics = lda_model[corpus[i]]
topics.sort(key=get_key, reverse=True)
labels = np.append(labels, np.repeat(topics[0][0], win_size))
print(topics)
# print(lda_model[corpus_i])
return labels[:-ind_end]
guide = CONFIG_PATH + "/Hui_SuperProject/MovDict.json"
guide_dict = read_json(guide).to_dict()
example_path = CONFIG_PATH + "/Hui_SuperProject/Data_Examples/"
signal = loadH5(example_path + "arthrokinemat_2018_06_03_00_08_52.h5")
fs = 1000
b = 4
acc1 = signal[b * fs:, 0]
acc1_sm = mean_norm(acc1)
acc1_sm = smooth(abs(acc1_sm), 1000)
acc1_sm = acc1_sm[::50]
# plt.plot(acc1_sm)
# plt.show()
acc_str = Connotation2(acc1_sm)
print(acc_str)
# lsa_labels = movingLSA(acc_str)
lda_labels = movingLDA(acc_str, win_size=50)
wave3_conc_str_tpl = runLengthEncoding(wave3_str) # ax1 = plt.subplot(1,1,1) # # plot_textcolorized(wave3, wave3_conc_str_tpl[2], ax1) # plot_textcolorized(wave3, wave3_str, ax1) # plt.show() # ax1 = plt.subplot(1,1,1) # plot_textcolorized(wave3, wave3_str, ax1) # plt.show() #Exercise 4 - Test this new approach on other signals from tools.processing_tools import * example_path = r"D:\PhD\Code\Hui_SuperProject\Data_Examples\\" signalHui1 = loadH5(example_path + "arthrokinemat_2018_06_02_23_51_55.h5") #pre process ch1 = smooth(mean_norm(signalHui1[:, 5]), 2000) ch1 = ch1[1000:] amp_level = AmplitudeTrans(ch1, 2, string.ascii_uppercase, method="quantiles") ampdiff_str = AmpChange(ch1, 0.75, "absolute") speed_str = D1Speed(ch1, 0.75) sign_str = SignConnotation(ch1) wave3_str = addArrayofStrings([sign_str, ampdiff_str, speed_str])