def test_extracted_bouts():
one_bouts = counts.bouts(1,1)
zero_bouts = counts.bouts(0,0)
# Bouts where counts == 0 and counts == 1 should be mutually excluse
# So there should be no intersections between them
intersections = Bout.bout_list_intersection(one_bouts, zero_bouts)
assert(len(intersections) == 0)
# A bout that spans the whole time period should completely intersect with bouts where counts == 1
one_big_bout = Bout.Bout(counts.timestamps[0]-timedelta(days=1), counts.timestamps[-1]+timedelta(days=1))
one_intersections = Bout.bout_list_intersection(one_bouts, [one_big_bout])
assert(Bout.total_time(one_intersections) == Bout.total_time(one_bouts))
# Same for zeros
zero_intersections = Bout.bout_list_intersection(zero_bouts, [one_big_bout])
assert(Bout.total_time(zero_intersections) == Bout.total_time(zero_bouts))
# Filling in the bout gaps of one bouts should recreate the zero bouts
inverse_of_one_bouts = Bout.time_period_minus_bouts((counts.timeframe[0], counts.timeframe[1]+timedelta(minutes=1)), one_bouts)
# They should have the same n
assert(len(inverse_of_one_bouts) == len(zero_bouts))
# Same total amount of time
assert(Bout.total_time(inverse_of_one_bouts) == Bout.total_time(zero_bouts))
def test_extracted_bouts():
one_bouts = counts.bouts(1, 1)
zero_bouts = counts.bouts(0, 0)
# Bouts where counts == 0 and counts == 1 should be mutually excluse
# So there should be no intersections between them
intersections = Bout.bout_list_intersection(one_bouts, zero_bouts)
assert (len(intersections) == 0)
# A bout that spans the whole time period should completely intersect with bouts where counts == 1
one_big_bout = Bout.Bout(counts.timestamps[0] - timedelta(days=1),
counts.timestamps[-1] + timedelta(days=1))
one_intersections = Bout.bout_list_intersection(one_bouts, [one_big_bout])
assert (Bout.total_time(one_intersections) == Bout.total_time(one_bouts))
# Same for zeros
zero_intersections = Bout.bout_list_intersection(zero_bouts,
[one_big_bout])
assert (Bout.total_time(zero_intersections) == Bout.total_time(zero_bouts))
# Filling in the bout gaps of one bouts should recreate the zero bouts
inverse_of_one_bouts = Bout.time_period_minus_bouts(
(counts.timeframe[0], counts.timeframe[1] + timedelta(minutes=1)),
one_bouts)
# They should have the same n
assert (len(inverse_of_one_bouts) == len(zero_bouts))
# Same total amount of time
assert (
Bout.total_time(inverse_of_one_bouts) == Bout.total_time(zero_bouts))
def window_statistics(self, start_dts, end_dts, statistics):
window = Bout.Bout(start_dts, end_dts)
bouts = self.bouts_involved(window)
output_row = []
if (len(bouts) > 0):
for stat in statistics:
if stat[0] == "generic":
for val1 in stat[1]:
if val1 == "sum":
intersection = Bout.bout_list_intersection([window],bouts)
Bout.cache_lengths(intersection)
sum_seconds = Bout.total_time(intersection).total_seconds()
output_row.append(sum_seconds)
elif val1 == "mean":
intersection = Bout.bout_list_intersection([window],bouts)
Bout.cache_lengths(intersection)
sum_seconds = Bout.total_time(intersection).total_seconds()
if sum_seconds >0 and len(bouts) > 0:
output_row.append( sum_seconds / len(bouts) )
else:
output_row.append(0)
elif val1 == "n":
output_row.append( len(bouts) )
else:
print("nooooooooo")
print(stat)
print(statistics)
output_row.append(-1)
elif stat[0] == "sdx":
# ("sdx", [10,20,30,40,50,60,70,80,90])
sdx_results = sdx(bouts, stat[1])
for r in sdx_results:
output_row.append(r)
else:
# No bouts in this Bout_Collection overlapping this window
# There was no data for the time period
# Output -1 for each missing variable
for i in range(self.expected_results(statistics)):
output_row.append(-1)
return output_row
def infer_valid_days(channel, wear_bouts, valid_criterion=timedelta(hours=10)):
#Generate day-long windows
start = time_utilities.start_of_day(channel.timestamps[0])
day_windows = []
while start < channel.timeframe[1]:
day_windows.append(Bout.Bout(start, start+timedelta(days=1)))
start += timedelta(days=1)
valid_windows = []
invalid_windows = []
for window in day_windows:
#how much does all of wear_bouts intersect with window?
intersections = Bout.bout_list_intersection([window], wear_bouts)
total = Bout.total_time(intersections)
# If the amount of overlap exceeds the valid criterion, it is valid
if total >= valid_criterion:
#window.draw_properties={"lw":0, "facecolor":[1,0,0], "alpha":0.25}
valid_windows.append(window)
else:
invalid_windows.append(window)
return(invalid_windows, valid_windows)
def infer_still_bouts_triaxial(x, y, z, window_size=timedelta(seconds=10), noise_cutoff_mg=13, minimum_length=timedelta(seconds=10)):
# Get windows of standard deviation in each axis
x_std = x.piecewise_statistics(window_size, statistics=[("generic", ["std"])], time_period=x.timeframe)[0]
y_std = y.piecewise_statistics(window_size, statistics=[("generic", ["std"])], time_period=y.timeframe)[0]
z_std = z.piecewise_statistics(window_size, statistics=[("generic", ["std"])], time_period=z.timeframe)[0]
# Find bouts where standard deviation is below threshold for long periods
x_bouts = x_std.bouts(0, float(noise_cutoff_mg)/1000.0)
y_bouts = y_std.bouts(0, float(noise_cutoff_mg)/1000.0)
z_bouts = z_std.bouts(0, float(noise_cutoff_mg)/1000.0)
x_bouts = Bout.limit_to_lengths(x_bouts, min_length=minimum_length)
y_bouts = Bout.limit_to_lengths(y_bouts, min_length=minimum_length)
z_bouts = Bout.limit_to_lengths(z_bouts, min_length=minimum_length)
# Get the times where those bouts overlap
x_intersect_y = Bout.bout_list_intersection(x_bouts, y_bouts)
x_intersect_y_intersect_z = Bout.bout_list_intersection(x_intersect_y, z_bouts)
return x_intersect_y_intersect_z
def qc_analysis(job_details):
id_num = str(job_details["pid"])
filename = job_details["filename"]
filename_short = os.path.basename(filename).split('.')[0]
battery_max = 0
if filetype == "GeneActiv":
battery_max = GA_battery_max
elif filetype == "Axivity":
battery_max = AX_battery_max
# Load the data from the hdf5 file
ts, header = data_loading.fast_load(filename, filetype)
header["QC_filename"] = os.path.basename(filename)
x, y, z, battery, temperature = ts.get_channels(["X", "Y", "Z", "Battery", "Temperature"])
# create a channel of battery percentage, based on the assumed battery maximum value
battery_pct = Channel.Channel.clone(battery)
battery_pct.data = (battery.data / battery_max) * 100
channels = [x, y, z, battery, temperature, battery_pct]
anomalies = diagnostics.diagnose_fix_anomalies(channels, discrepancy_threshold=2)
# create dictionary of anomalies types
anomalies_dict = dict()
# check whether any anomalies have been found:
if len(anomalies) > 0:
anomalies_file = os.path.join(anomalies_folder, "{}_anomalies.csv".format(filename_short))
df = pd.DataFrame(anomalies)
for type in anomaly_types:
anomalies_dict["QC_anomaly_{}".format(type)] = (df.anomaly_type.values == type).sum()
df = df.set_index("anomaly_type")
# print record of anomalies to anomalies_file
df.to_csv(anomalies_file)
else:
for type in anomaly_types:
anomalies_dict["QC_anomaly_{}".format(type)] = 0
# check for axis anomalies
axes_dict = diagnostics.diagnose_axes(x, y, z, noise_cutoff_mg=13)
axis_anomaly = False
for key, val in axes_dict.items():
anomalies_dict["QC_{}".format(key)] = val
if key.endswith("max"):
if val > axis_max:
axis_anomaly = True
elif key.endswith("min"):
if val < axis_min:
axis_anomaly = True
# create a "check battery" flag:
check_battery = False
# calculate first and last battery percentages
first_battery_pct = round((battery_pct.data[1]),2)
last_battery_pct = round((battery_pct.data[-1]),2)
header["QC_first_battery_pct"] = first_battery_pct
header["QC_last_battery_pct"] = last_battery_pct
# calculate lowest battery percentage
# check if battery.pct has a missing_value, exclude those values if they exist
if battery_pct.missing_value == "None":
lowest_battery_pct = min(battery_pct.data)
else:
test_array = np.delete(battery_pct.data, np.where(battery_pct.data == battery_pct.missing_value))
lowest_battery_pct = min(test_array)
header["QC_lowest_battery_pct"] = round(lowest_battery_pct,2)
header["QC_lowest_battery_threshold"] = battery_minimum
# find the maximum battery discharge in any 24hr period:
max_discharge = battery_pct.channel_max_decrease(time_period=timedelta(hours=discharge_hours))
header["QC_max_discharge"] = round(max_discharge, 2)
header["QC_discharge_time_period"] = "{} hours".format(discharge_hours)
header["QC_discharge_threshold"] = discharge_pct
# change flag if lowest battery percentage dips below battery_minimum at any point
# OR maximum discharge greater than discharge_pct over time period "hours = discharge_hours"
if lowest_battery_pct < battery_minimum or max_discharge > discharge_pct:
check_battery = True
header["QC_check_battery"] = str(check_battery)
header["QC_axis_anomaly"] = str(axis_anomaly)
# Calculate the time frame to use
start = time_utilities.start_of_day(x.timeframe[0])
end = time_utilities.end_of_day(x.timeframe[-1])
tp = (start, end)
results_ts = Time_Series.Time_Series("")
# Derive some signal features
vm = channel_inference.infer_vector_magnitude(x, y, z)
enmo = channel_inference.infer_enmo(vm)
enmo.minimum = 0
enmo.maximum = enmo_max
# Infer nonwear
nonwear_bouts = channel_inference.infer_nonwear_for_qc(x, y, z, noise_cutoff_mg=noise_cutoff_mg)
# Use nonwear bouts to calculate wear bouts
wear_bouts = Bout.time_period_minus_bouts(enmo.timeframe, nonwear_bouts)
# Use wear bouts to calculate the amount of wear time in the file in hours, save to meta data
total_wear = Bout.total_time(wear_bouts)
total_seconds_wear = total_wear.total_seconds()
total_hours_wear = round(total_seconds_wear/3600)
header["QC_total_hours_wear"] = total_hours_wear
# Split the enmo channel into lists of bouts for each quadrant:
''' quadrant_0 = 00:00 -> 06: 00
quadrant_1 = 06:00 -> 12: 00
quadrant_2 = 12:00 -> 18: 00
quadrant_3 = 18:00 -> 00: 00 '''
q_0, q_1, q_2, q_3 = channel_inference.create_quadrant_bouts(enmo)
# calculate the intersection of each set of bouts with wear_bouts, then calculate the wear time in each quadrant.
sum_quadrant_wear = 0
for quadrant, name1, name2 in ([q_0, "QC_hours_wear_quadrant_0", "QC_pct_wear_quadrant_0"],
[q_1, "QC_hours_wear_quadrant_1", "QC_pct_wear_quadrant_1"],
[q_2, "QC_hours_wear_quadrant_2", "QC_pct_wear_quadrant_2"],
[q_3, "QC_hours_wear_quadrant_3", "QC_pct_wear_quadrant_3"]):
quadrant_wear = Bout.bout_list_intersection(quadrant, wear_bouts)
seconds_wear = Bout.total_time(quadrant_wear).total_seconds()
hours_wear = round(seconds_wear / 3600)
header[name1] = hours_wear
header[name2] = round(((hours_wear / total_hours_wear) * 100), 2)
for bout in nonwear_bouts:
# Show non-wear bouts in purple
bout.draw_properties = {'lw': 0, 'alpha': 0.75, 'facecolor': '#764af9'}
for channel, channel_name in zip([enmo, battery_pct],["ENMO", "Battery_percentage"]):
channel.name = channel_name
results_ts.add_channel(channel)
if PLOT == "YES":
# Plot statistics as subplots in one plot file per data file
results_ts["ENMO"].add_annotations(nonwear_bouts)
results_ts.draw_qc(plotting_df, file_target=os.path.join(charts_folder,"{}_plots.png".format(filename_short)))
header["QC_script"] = version
# file of metadata from qc process
qc_output = os.path.join(results_folder, "qc_meta_{}.csv".format(filename_short))
# check if qc_output already exists...
if os.path.isfile(qc_output):
os.remove(qc_output)
metadata = {**header, **anomalies_dict}
# write metadata to file
pampro_utilities.dict_write(qc_output, id_num, metadata)
for c in ts:
del c.data
del c.timestamps
del c.indices
del c.cached_indices
def calibrate(x,y,z, allow_overwrite=True, budget=1000, noise_cutoff_mg=13):
""" Use still bouts in the given triaxial data to calibrate it and return the calibrated channels """
calibration_diagnostics = OrderedDict()
vm = channel_inference.infer_vector_magnitude(x,y,z)
# Get a list of bouts where standard deviation in each axis is below given threshold ("still")
still_bouts = channel_inference.infer_still_bouts_triaxial(x,y,z, noise_cutoff_mg=noise_cutoff_mg, minimum_length=timedelta(minutes=1))
num_still_bouts = len(still_bouts)
num_still_seconds = Bout.total_time(still_bouts).total_seconds()
# Summarise VM in 10s intervals
vm_windows = vm.piecewise_statistics(timedelta(seconds=10), [("generic", ["mean"])], time_period=vm.timeframe)[0]
# Get a list where VM was between 0.5 and 1.5g ("reasonable")
reasonable_bouts = vm_windows.bouts(0.5, 1.5)
num_reasonable_bouts = len(reasonable_bouts)
num_reasonable_seconds = Bout.total_time(reasonable_bouts).total_seconds()
# We only want still bouts where the VM level was within 0.5g of 1g
# Therefore insersect "still" time with "reasonable" time
still_bouts = Bout.bout_list_intersection(reasonable_bouts, still_bouts)
# And we only want bouts where it was still and reasonable for 10s or longer
still_bouts = Bout.limit_to_lengths(still_bouts, min_length = timedelta(seconds=10))
num_final_bouts = len(still_bouts)
num_final_seconds = Bout.total_time(still_bouts).total_seconds()
# Get the average X,Y,Z for each still bout (inside which, by definition, XYZ should not change)
still_x, num_samples = x.build_statistics_channels(still_bouts, [("generic", ["mean", "n"])])
still_y = y.build_statistics_channels(still_bouts, [("generic", ["mean"])])[0]
still_z = z.build_statistics_channels(still_bouts, [("generic", ["mean"])])[0]
# Get the octant positions of the points to calibrate on
occupancy = octant_occupancy(still_x.data, still_y.data, still_z.data)
# Are they fairly distributed?
comparisons = {"x<0":[0,1,2,3], "x>0":[4,5,6,7], "y<0":[0,1,4,5], "y>0":[2,3,6,7], "z<0":[0,2,4,6], "z>0":[1,3,5,7]}
for axis in ["x", "y", "z"]:
mt = sum(occupancy[comparisons[axis + ">0"]])
lt = sum(occupancy[comparisons[axis + "<0"]])
calibration_diagnostics[axis + "_inequality"] = abs(mt-lt)/sum(occupancy)
# Calculate the initial error without doing any calibration
start_error = evaluate_solution(still_x, still_y, still_z, num_samples, [0,1,0,1,0,1])
# Do offset and scale calibration by default
offset_only_calibration = False
calibration_diagnostics["calibration_method"] = "offset and scale"
# If we have less than 500 points to calibrate with, or if more than 2 octants are empty
if len(still_x.data) < 500 or sum(occupancy == 0) > 2:
offset_only_calibration = True
calibration_diagnostics["calibration_method"] = "offset only"
# Search for the correct way to calibrate the data
calibration_parameters = find_calibration_parameters(still_x.data, still_y.data, still_z.data, offset_only=offset_only_calibration)
for param,value in zip("x_offset,x_scale,y_offset,y_scale,z_offset,z_scale".split(","), calibration_parameters):
calibration_diagnostics[param] = value
for i,occ in enumerate(occupancy):
calibration_diagnostics["octant_"+str(i)] = occ
# Calculate the final error after calibration
end_error = evaluate_solution(still_x, still_y, still_z, num_samples, calibration_parameters)
calibration_diagnostics["start_error"] = start_error
calibration_diagnostics["end_error"] = end_error
calibration_diagnostics["num_final_bouts"] = num_final_bouts
calibration_diagnostics["num_final_seconds"] = num_final_seconds
calibration_diagnostics["num_still_bouts"] = num_still_bouts
calibration_diagnostics["num_still_seconds"] = num_still_seconds
calibration_diagnostics["num_reasonable_bouts"] = num_reasonable_bouts
calibration_diagnostics["num_reasonable_seconds"] = num_reasonable_seconds
if allow_overwrite:
# If we do not need to preserve the original x,y,z values, we can just calibrate that data
# Apply the best calibration factors to the data
do_calibration(x, y, z, calibration_parameters)
return (x, y, z, calibration_diagnostics)
else:
# Else we create an independent copy of the raw data and calibrate that instead
cal_x = copy.deepcopy(x)
cal_y = copy.deepcopy(y)
cal_z = copy.deepcopy(z)
# Apply the best calibration factors to the data
do_calibration(cal_x, cal_y, cal_z, calibration_parameters)
return (cal_x, cal_y, cal_z, calibration_diagnostics)
