diff --git a/modules/.datapipeline.py.swp b/modules/.datapipeline.py.swp
deleted file mode 100644
index 4213d68c350303ec5029eb85195c3fa423f0fba4..0000000000000000000000000000000000000000
Binary files a/modules/.datapipeline.py.swp and /dev/null differ
diff --git a/regress_rr.py b/regress_rr.py
index 38d987f233c251975852fc812933cf267aa6ec6d..a5376e4ba236a48c1af7bc0c8a32e08d9b820ed9 100644
--- a/regress_rr.py
+++ b/regress_rr.py
@@ -22,6 +22,7 @@ from itertools import repeat, chain, combinations
from multiprocessing import Pool, cpu_count
import tensorflow as tf
+from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.preprocessing import PolynomialFeatures, LabelEncoder
from sklearn.model_selection import KFold, train_test_split
@@ -35,6 +36,7 @@ from modules.datapipeline import get_file_list, load_and_snip, load_data, \
load_split_data, load_harness_data
from modules.digitalsignalprocessing import vectorized_slide_win as vsw
from modules.digitalsignalprocessing import imu_signal_processing
+from modules.digitalsignalprocessing import hernandez_sp, reject_artefact
from modules.digitalsignalprocessing import do_pad_fft,\
pressure_signal_processing, infer_frequency
from modules.utils import *
@@ -64,7 +66,8 @@ from sktime.transformations.panel.rocket import (
MiniRocketMultivariateVariable,
)
-from config import WINDOW_SIZE, WINDOW_SHIFT, IMU_FS, DATA_DIR, BR_FS
+from config import WINDOW_SIZE, WINDOW_SHIFT, IMU_FS, DATA_DIR, BR_FS\
+ , FS_RESAMPLE
IMU_COLS = ['acc_x', 'acc_y', 'acc_z', 'gyr_x', 'gyr_y', 'gyr_z']
@@ -453,7 +456,6 @@ def load_and_sync_xsens(subject):
return xsens_df
-
def load_tsfresh(subject, project_dir,
window_size=12, window_shift=0.2, fs=IMU_FS,
overwrite=False):
@@ -556,6 +558,55 @@ def get_test_data(cal_df, activity_df, xsens_df, test_standing):
return pd.DataFrame(activity_list)
+def dsp_win_func(w_inds, df, i, cols):
+ time = df['sec'].values
+ if w_inds[-1] == 0: return
+ w_df = df.iloc[w_inds]
+ t0, t1 = time[w_inds][0], time[w_inds][-1]
+ diff = time[w_inds[1:]] - time[w_inds[0:-1]]
+ mask = np.abs(diff)>20
+ diff_chk = np.any(mask)
+ if diff_chk:
+ return
+
+ # cols = ['acc_x', 'acc_y', 'acc_z',
+ # 'gyr_x', 'gyr_y', 'gyr_z']
+
+ data = w_df[cols].values
+
+ if reject_artefact((data-np.mean(data,axis=0))/np.std(data,axis=0)):
+ return
+
+ # DSP
+ pca = PCA(n_components=1, random_state=3)
+
+ # do hernandez sp on datacols for df
+ filt = hernandez_sp(data=data, fs=IMU_FS)[1]
+
+ # pca
+ pca_out = pca.fit_transform(filt)
+
+ std = StandardScaler().fit_transform(pca_out)
+
+ pred = get_max_frequency(std, fs=FS_RESAMPLE)
+
+ # get pss / br estimates
+ # x_time median, pss max_freq, br median
+ sm_out = w_df['BR'].values
+ ps_out = w_df['PSS'].values
+
+ x_vec_time = np.median(time[w_inds])
+
+ fs = 1/np.mean(diff)
+ ps_freq = int(get_max_frequency(ps_out, fs=IMU_FS))
+
+ y_tmp = np.array([x_vec_time, np.nanmedian(sm_out), ps_freq])
+
+ y_hat = pd.DataFrame([ {'sec': x_vec_time, 'pred': pred} ])
+ y_out = pd.DataFrame([y_tmp], columns=['sec', 'br', 'pss'])
+
+ return y_hat, y_out
+
# save evaluation metrics in single file that handles the models for the
# subject and config
class EvalHandler():
@@ -616,18 +667,21 @@ def imu_rr_model(subject,
feature_method='tsfresh',
train_len:int=3,
test_standing=False,
+ data_input:str='imu+bvp',
):
# window_size, window_shift, intra, inter
cal_str = 'cpm'
fs = IMU_FS
tmp = []
imu_cols = ['acc_x', 'acc_y', 'acc_z', 'gyro_x', 'gyro_y', 'gyro_z']
- bvp_cols= ['bvp']
+ bvp_cols = ['bvp']
- # TODO:
- # implement and input args config by data cols
- # implement and input args config with test_standing
- data_cols = imu_cols + bvp_cols
+ if 'imu' in data_input and 'bvp' in data_input:
+ data_cols = imu_cols + bvp_cols
+ elif 'imu' in data_input and not 'bvp' in data_input:
+ data_cols = imu_cols
+ elif not 'imu' in data_input and 'bvp' in data_input:
+ data_cols = bvp_cols
do_minirocket = False
use_tsfresh = False
@@ -680,7 +734,37 @@ def imu_rr_model(subject,
# include standing or not
test_df_tmp = get_test_data(cal_df, activity_df, xsens_df, test_standing)
test_df = pd.concat([df for df in test_df_tmp['data']], axis=0)
-
+ x_test_df, y_test_df = get_df_windows(test_df,
+ imu_df_win_task,
+ window_size=window_size,
+ window_shift=window_shift,
+ fs=fs,
+ )
+
+ acc_dsp_df, acc_y_dsp_df = get_df_windows(test_df, dsp_win_func,
+ window_size=window_size,
+ window_shift=window_shift,
+ fs=fs,
+ cols=['acc_x', 'acc_y', 'acc_z'])
+ gyr_dsp_df, gyr_y_dsp_df = get_df_windows(test_df, dsp_win_func,
+ window_size=window_size,
+ window_shift=window_shift,
+ fs=fs,
+ cols=['gyr_x', 'gyr_y', 'gyr_z'])
+
+ acc_evals = Evaluation(acc_y_dsp_df[lbl_str], acc_dsp_df['pred'])
+ gyr_evals = Evaluation(gyr_y_dsp_df[lbl_str], gyr_dsp_df['pred'])
+ print("acc evals: \n", acc_evals.get_evals())
+ print("gyr evals: \n", gyr_evals.get_evals())
+ plt.subplot(211)
+ plt.plot(acc_y_dsp_df[lbl_str]); plt.plot(acc_dsp_df['pred'])
+ plt.subplot(212)
+ plt.plot(acc_y_dsp_df[lbl_str]); plt.plot(acc_dsp_df['pred'])
+ plt.show()
+
+ # TODO implement evals from dsp to results
+ ipdb.set_trace()
+
for combi in combinations(cal_df[cal_str].values, train_len):
combi_str = "-".join([str(x) for x in combi])
pfh.config[cal_str] = combi_str
@@ -707,17 +791,12 @@ def imu_rr_model(subject,
window_shift=window_shift,
fs=fs,
)
- x_test_df, y_test_df = get_df_windows(test_df,
- imu_df_win_task,
- window_size=window_size,
- window_shift=window_shift,
- fs=fs,
- )
x_train = make_windows_from_id(x_train_df, imu_cols)
- x_test = make_windows_from_id(x_test_df, imu_cols)
y_train = y_train_df[lbl_str].values.reshape(-1, 1)
+ x_test = make_windows_from_id(x_test_df, imu_cols)
y_test = y_test_df[lbl_str].values.reshape(-1, 1)
+
print("minirocket transforming...")
x_train = np.swapaxes(x_train, 1, 2)
@@ -731,19 +810,6 @@ def imu_rr_model(subject,
x_test = test_df.iloc[:, 3:].values
y_test = test_df[lbl_str].values.reshape(-1, 1)
else:
- x_train_df, y_train_df = get_df_windows(train_df,
- imu_df_win_task,
- window_size=window_size,
- window_shift=window_shift,
- fs=fs,
- )
- x_test_df, y_test_df = get_df_windows(test_df,
- imu_df_win_task,
- window_size=window_size,
- window_shift=window_shift,
- fs=fs,
- )
-
x_train = make_windows_from_id(x_train_df, imu_cols)
x_test = make_windows_from_id(x_test_df, imu_cols)
y_train = y_train_df[lbl_str].values.reshape(-1, 1)
@@ -814,6 +880,15 @@ def arg_parser():
default=3,
help='minutes of data to use for calibration'
)
+ parser.add_argument('-d', '--data_input', type=str,
+ default='imu',
+ help='imu, bvp, imu+bvp: select data cols for input'
+ )
+ parser.add_argument('-ts', '--test_standing', type=int,
+ default=0,
+ help='1 or 0 input, choose if standing data will be '\
+ 'recorded or not'
+ )
args = parser.parse_args()
return args
@@ -832,6 +907,8 @@ if __name__ == '__main__':
lbl_str = args.lbl_str
train_len = args.train_len
overwrite = args.overwrite
+ data_input = args.data_input
+ test_standing = args.test_standing
print(args)
assert train_len>0,"--train_len must be an integer greater than 0"
@@ -855,7 +932,9 @@ if __name__ == '__main__':
mdl_str=mdl_str,
overwrite=overwrite,
feature_method=feature_method,
- train_len=train_len
+ train_len=train_len,
+ data_input=data_input,
+ test_standing=test_standing,
)
if mdl_str in ['fnn', 'lstm', 'cnn1d', 'elastic', 'ard', 'xgboost']: