ms762wu/EMG_Biometrics_2021
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

style: move things :)

Browse Source
This commit is contained in:
Skudalen 2021-06-28 20:32:00 +02:00
parent e0a1dfee71
commit 055ad434a3
3 changed files with 11 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Handle_emg_data.py
View File

@ -12,7 +12,7 @@ class Data_container:
self.data_dict_round2 = {'left': [None]*8, 'right': [None]*8}
self.data_dict_round3 = {'left': [None]*8, 'right': [None]*8}
self.data_dict_round4 = {'left': [None]*8, 'right': [None]*8}
self.dict_list = [self.data_dict_round1,
self.dict_list = [self.data_dict_round1,
self.data_dict_round2,
self.data_dict_round3,
self.data_dict_round4
@ -450,6 +450,8 @@ class CSV_handler:
return df
# HELP FUNCTIONS: ------------------------------------------------------------------------:
# Help: gets the str from emg nr
def get_emg_str(emg_nr):
return 'emg' + str(emg_nr)

6
Present_data.py
View File

@ -69,6 +69,7 @@ def plot_3_mfcc(mfcc_data1, data_label1:str, mfcc_data2, data_label2:str, mfcc_d
plt.show()
# DATA FUNCTIONS: --------------------------------------------------------------:
# The CSV_handler takes in data_type, but only for visuals.
@ -115,6 +116,7 @@ def mfcc_custom(df:DataFrame, samplesize, windowsize, stepsize):
y = get_xory_from_df('y', df)
return N, base.mfcc(y, samplesize, windowsize, stepsize)
# CASE FUNTIONS ----------------------------------------------------------------:
# Takes in a df and compares the FFT and the wavelet denoising of the FFT
@ -128,6 +130,9 @@ def compare_with_wavelet_filter(data_frame):
plot_compare_two_df(data_frame_freq, 'Original data', data_frame_freq_filt, 'Analyzed data')
# Loads three preset emg datasets, calculates mfcc for each and plots them.
# Input: CSV_handler
# Output: None --> Plot
def compare_mfcc_3_plots(csv_handler:CSV_handler):
df1, samplerate1 = get_data(csv_handler, 1, 'left', 1, 1)
df2, samplerate2 = get_data(csv_handler, 1, 'left', 2, 1)
@ -146,6 +151,7 @@ def compare_mfcc_3_plots(csv_handler:CSV_handler):
plot_3_mfcc(mfcc_feat1, label_1, mfcc_feat2, label_2, mfcc_feat3, label_3)
# MAIN: ------------------------------------------------------------------------:
def main():

22
Signal_prep.py
View File

@ -2,14 +2,11 @@ import numpy as np
from pandas.core.frame import DataFrame
from scipy.fft import fft, fftfreq
import pywt
#from pyhton_speech_features.base import mfcc
import sys
import Handle_emg_data as Handler
sys.path.insert(0, '/Users/Markus/Prosjekter git/Slovakia 2021/python_speech_features/python_speech_features')
from python_speech_features.python_speech_features import *
import Handle_emg_data as Handler
# Takes in a df and outputs np arrays for x and y values
def get_xory_from_df(x_or_y, df:DataFrame):
@ -42,14 +39,6 @@ def wavelet_db4(df:DataFrame):
N_trans = np.array(range(int(np.floor((y_values.size + wavelet.dec_len - 1) / 2))))
return N_trans, cA, cD
# Filters signal accordning to Stein's Unbiased Risk Estimate(SURE)
'''
def sure_threshold_filter(cA, cD):
cA_filt = pyyawt.theselect(cA, 'rigrsure')
cD_filt = cD
return cA_filt, cD_filt
'''
# soft filtering of wavelet trans with the a 1/2 std filter
def soft_threshold_filter(cA, cD):
cA_filt = pywt.threshold(cA, np.std(cA)/2)
@ -69,16 +58,9 @@ def inverse_wavelet(df, cA_filt, cD_filt):
old_len = len(get_xory_from_df('y', df))
return y_new_values
# NOT FINISHED
def cepstrum(df:DataFrame):
N = get_xory_from_df('x', df)
y = get_xory_from_df('y', df)
return None
def mfcc(df:DataFrame, samplesize, windowsize, stepsize):
N = get_xory_from_df('x', df)
y = get_xory_from_df('y', df)
return N, base.mfcc(y, samplesize, windowsize, stepsize)