#variance
f11 = float(np.var(col1, ddof=1))
f12 = float(np.var(col2, ddof=1))
f13 = float(np.var(col3, ddof=1))
f14 = float(np.var(col4, ddof=1))
#max_freq
b1 = 1000 * myfeat.max_freq(col1)
b2 = 1000 * myfeat.max_freq(col2)
b3 = 1000 * myfeat.max_freq(col3)
b4 = 1000 * myfeat.max_freq(col4)
#RMS
f31 = myfeat.rms(col1)
f32 = myfeat.rms(col2)
f33 = myfeat.rms(col3)
f34 = myfeat.rms(col4)
#mean
f41 = np.mean(col1)
f42 = np.mean(col2)
f43 = np.mean(col3)
f44 = np.mean(col4)
#sum_peaks
f51 = sum(myfeat.peaks(col1, 2, 10))
f52 = sum(myfeat.peaks(col2, 2, 10))
my_feat[26] = std_m1
my_feat[27] = std_m2
#sum
sum_p1 = np.sum(arr_p1)
sum_p2 = np.sum(arr_p2)
sum_m1 = np.sum(arr_m1)
sum_m2 = np.sum(arr_m2)
my_feat[28] = sum_p1
my_feat[29] = sum_p2
my_feat[30] = sum_m1
my_feat[31] = sum_m2
#rms
rms_p1 = myfeat.rms(arr_p1)
rms_p2 = myfeat.rms(arr_p2)
rms_m1 = myfeat.rms(arr_m1)
rms_m2 = myfeat.rms(arr_m2)
my_feat[32] = rms_p1
my_feat[33] = rms_p2
my_feat[34] = rms_m1
my_feat[35] = rms_m2
result = model.predict(my_feat.T)
print(result)
print(h)
h = h + 1
#variance
feat_data[4] = float(np.var(col1, ddof=1))
feat_data[5] = float(np.var(col2, ddof=1))
feat_data[6] = float(np.var(col3, ddof=1))
feat_data[7] = float(np.var(col4, ddof=1))
#max_freq
feat_data[0] = 1000 * myfeat.max_freq(col1)
feat_data[1] = 1000 * myfeat.max_freq(col2)
feat_data[2] = 1000 * myfeat.max_freq(col3)
feat_data[3] = 1000 * myfeat.max_freq(col4)
#RMS
feat_data[8] = myfeat.rms(col1)
feat_data[9] = myfeat.rms(col2)
feat_data[10] = myfeat.rms(col3)
feat_data[11] = myfeat.rms(col4)
#mean
feat_data[17] = np.mean(col1)
feat_data[18] = np.mean(col2)
feat_data[19] = np.mean(col3)
feat_data[20] = np.mean(col4)
#sum_peaks
feat_data[21] = sum(myfeat.peaks(col1, 2, 10))
feat_data[22] = sum(myfeat.peaks(col2, 2, 10))