def btnPreprocessPushed(self): # ASKS FOR THE DATA TO BE PROCESSED AND CALLS TO THE PIPELINE FUNCTIONS
import global_variables
import filter_files as filt
import feature_extraction as feat
import svm_classification as classif
import plots
import online_predict_test as onl_pred
mainRoot = tk.Tk()
mainRoot.withdraw()
mainRoot.update()
files_to_process = tkfiledialog.askopenfilenames(parent =mainRoot, initialdir = "./data",title = "Select file(s)",filetypes = (("txt files","*.txt"),("all files","*.*")))
print("\nSelected Files: ", files_to_process, "\n")
if files_to_process:
global_variables.set_files_to_process(files_to_process)
mainRoot.destroy()
# Processing
trial_hor, trial_ver, trial_lab = filt.filter()
# Feature Extraction
features = []
features = feat.features(trial_hor, trial_ver)
# Classification
classif.classification(features, trial_lab)
# PLOTTING FUNCTIONS (FOR TESTING PURPOSES)
# plots.feature3d_plot(features, trial_lab)
# plots.feature2d_plot(features, trial_lab)
# plots.trial_plot(trial_hor, trial_ver, trial_lab)
# plots.derivative_signal(trial_hor, trial_ver, trial_lab)
# plots.derivative_plots(trial_hor, trial_ver, trial_lab)
# plots.feature_plot(features, trial_lab)
# plots.movement_plot(trial_hor, trial_ver, trial_lab, "'Up'")
saveRoot = tk.Tk()
saveRoot.withdraw()
saveRoot.update()
save_wdw = SaveWindow(saveRoot)
saveRoot.mainloop()
def online_calculations(online_data_hor, online_data_ver):
"""
# FUNCTION: online_calculations(online_data_hor, online_data_ver)
# INPUT: Horizontal and Vertical data
# OUTPUT: None
# DESCRIPTION: Performs all the desired calculations over the data
# and predicts the label
# AUTHOR: Jayro Martinez Cervero
"""
samples_per_trial = global_variables.get_samples_per_trial()
lab = global_variables.get_lab()
model_name = global_variables.get_model()
model = pickle.load(open(model_name, 'rb'))
# Pre-processing
filtered_hor = filt.online_filter(online_data_hor)
filtered_ver = filt.online_filter(online_data_ver)
# Feature Extraction
features = feat.features([filtered_hor], [filtered_ver])
# Check if there's a movement or not
probs = model.predict_proba(features)
lab.sort()
max_pos = int(np.where(probs[0] == np.max(probs[0]))[0])
movement = lab[max_pos]
print("\n********************************************")
if np.max(probs) > 0.5:
print(lab)
print(np.max(probs))
print("MOVEMENT DETECTED: ", movement)
file_name = global_variables.get_online_data_file()
new_file_name = "./data/" + file_name + ".txt"
file = open(new_file_name, 'a')
str_write = str([online_data_hor, online_data_ver]) + "\n"
file.write(str_write)
file.close()
def read_flute(self):
sigs = []
i = 1
if (self.flute):
print('start flute feature extraction')
os.chdir(os.getcwd() + '\\flute')
for path in os.listdir():
if (i % 100 == 0):
print("flute : ", i, "/", np.size(os.listdir()))
# y, sr = lr.load(path)
signal = sig()
audio = mpe.AudioFileClip(path)
signal.y = np.mean(audio.to_soundarray(buffersize=200), 1)
signal.sr = audio.fps # sampling rate
feat = feature_extraction.features(signal.y, signal.sr)
feat_vec = feat.get_feature_vectors()
self.X.append(feat_vec.tolist())
self.Y.append(2) #2 for flute
sigs.append(signal)
i = i + 1
os.chdir("..")
return sigs
def menu():
os.system('clear')
# We show the main menu
print("*******************************************************")
print("*******************************************************")
print("********* *********")
print("*** WELCOME TO OUR FANTASTIC EOG PROGRAM ***")
print("********* *********")
print("*******************************************************")
print("*******************************************************")
print("\nYou can perform the following actions:\n")
print(" 1. Acquire New Data")
print(" 2. Pre-process Data, Extract Features & Classify")
print(" 3. Online Classification")
print(" 0. EXIT\n")
option = input("What would you like to do?: ")
if option == '1': # Acquire new data
os.system('clear')
files_in_data = [x for x in os.listdir('./data') if x.endswith(".txt")]
files_in_data = natsorted(files_in_data)
print("Select the file to save the new data: \n")
print(" 0 : Create a New File")
for i in range(0, len(files_in_data)):
print(" ", i + 1, ": Add to File ", files_in_data[i])
target_file = int(input("\nYour selection: "))
if target_file == 0:
os.system('clear')
file_name = input(
"Please write the name of the file (without extension): ")
global_variables.set_save_file(file_name + ".txt")
elif target_file <= len(files_in_data):
file_name = files_in_data[target_file - 1]
global_variables.set_save_file(file_name)
else:
os.system('clear')
print("Wrong Option, sorry.")
time.sleep(2)
menu()
# Connection, Data Acquisition & Data Storage
con.connect()
elif option == '2': # Pre-process data, extract features & classify
os.system('clear')
all_files = []
files_to_process = []
all_files = [x for x in os.listdir('./data') if x.endswith(".txt")]
all_files = natsorted(all_files)
print("Select the file/s to pre-process\n")
for i in range(0, len(all_files)):
print(" ", i, " : ", all_files[i])
selected_files = input(
"\nSelect desired files (you can use '-' to select ranges and/or ',' to select multiple datasets): "
)
selected_files = selected_files.split(',')
aux = []
for j in range(0, len(selected_files)):
aux = selected_files[j].split('-')
for k in range(int(aux[0]), int(aux[-1]) + 1):
files_to_process.append("./data/" + all_files[k])
global_variables.set_files_to_process(files_to_process)
time.sleep(1)
os.system('clear')
# Data Load, Filtering & Trial Split
print("Pre-processing & extracting features from files : ",
files_to_process)
trial_hor, trial_ver, trial_lab = filt.filter()
# Feature Extraction
features = []
features = feat.features(trial_hor, trial_ver)
print(
"\nPre-processing & Feature extraction done. Now we are going to perform classification."
)
# Classification
classif.classification(features, trial_lab)
save = input("\nDo you want to save the model?? [y/n]: ")
if save == 'y' or save == 'Y':
model_name = input("Write model name: ")
model_file_name = "./models/" + model_name + ".sav"
model = global_variables.get_model()
pickle.dump(model, open(model_file_name, 'wb'))
print("Model saved in " + model_file_name)
time.sleep(3)
menu()
elif option == '3': # Online classification
models_list = []
models_list = [x for x in os.listdir('./models') if x.endswith(".sav")]
models_list = natsorted(models_list)
os.system('clear')
print("Available models:\n")
for l in range(0, len(models_list)):
print(" ", l, " : ", models_list[l])
model = input("\nSelect the model for classification: ")
global_variables.set_model(models_list[int(model)])
os.system('clear')
print("Online classification started. \nModel selected: ",
global_variables.get_model(), "\n")
# Online Classification
online.online_classif()
elif option == '0': # EXIT
os.system('clear')
print("###############################")
print("## SEE YOU SOON!!!!!! ##")
print("###############################")
time.sleep(3)
os.system('clear')
sys.exit()
else: # Wrong option
print("\nYou selected a wrong option. ARE YOU KIDDING ME?")
time.sleep(2)
menu()