def test_artificial_bouts():
start_a = datetime.strptime("01/01/2000", "%d/%m/%Y")
end_a = start_a + timedelta(hours=1)
bout_a = Bout.Bout(start_a, end_a)
# Hour long bout
assert (bout_a.length == timedelta(hours=1))
start_b = datetime.strptime("01/01/2000", "%d/%m/%Y")
end_b = start_a + timedelta(minutes=15)
bout_b = Bout.Bout(start_b, end_b)
# They share common time
assert (bout_a.overlaps(bout_b))
# 15 minutes, to be precise
intersection = bout_a.intersection(bout_b)
assert (intersection.length == timedelta(minutes=15))
start_c = datetime.strptime("01/02/2000", "%d/%m/%Y")
end_c = start_c + timedelta(days=1)
bout_c = Bout.Bout(start_c, end_c)
# No overlap of those bouts
assert (not bout_a.overlaps(bout_c))
# bout_a ends exactly as bout_d starts
# there should be no overlap (0 common time)
start_d = end_a
end_d = start_d + timedelta(minutes=1)
bout_d = Bout.Bout(start_d, end_d)
assert (not bout_a.overlaps(bout_d))
def summary_statistics(self, statistics=[("generic", "mean")], time_period=False, name=""):
if time_period == False:
windows = [Bout(self.timeframe[0], self.timeframe[1]+timedelta(days=1111))]
else:
windows = [Bout(time_period[0],time_period[1])]
return self.build_statistics_channels(windows, statistics, name=name)
def test_f():
# Case F
# Multiple deletions producing consistent results
origin = counts.timestamps[0]
# Delete first 2 hours
start = origin
end = origin + timedelta(hours=2)
# Summarise the data before deletion
summary_before = Time_Series.Time_Series("")
summary_before.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
counts.delete_windows([Bout.Bout(start, end)])
# Summarise the data after deletion
summary_after_a = Time_Series.Time_Series("")
summary_after_a.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
# Delete midday to 2pm
start = origin + timedelta(hours=12)
end = origin + timedelta(hours=14)
counts.delete_windows([Bout.Bout(start, end)])
# Summarise the data after deletion
summary_after_b = Time_Series.Time_Series("")
summary_after_b.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
# 20 hours left
assert (summary_after_b.get_channel("AG_Counts_n").data[0] == 20 * 60)
# 4 hours missing
assert (summary_after_b.get_channel("AG_Counts_missing").data[0] == 4 * 60)
# Sum data should be 20 1s
assert (summary_after_b.get_channel("AG_Counts_sum").data[0] == 20 * 60)
def piecewise_statistics(self, window_size, statistics=[("generic", "mean")], time_period=False, name=""):
if time_period == False:
start = self.timeframe[0] - timedelta(hours=self.timeframe[0].hour, minutes=self.timeframe[0].minute, seconds=self.timeframe[0].second, microseconds=self.timeframe[0].microsecond)
end = self.timeframe[1] + timedelta(hours=23-self.timeframe[1].hour, minutes=59-self.timeframe[1].minute, seconds=59-self.timeframe[1].second, microseconds=999999-self.timeframe[1].microsecond)
else:
start = time_period[0]
end = time_period[1]
#print("Piecewise statistics: {}".format(self.name))
windows = []
start_dts = start
end_dts = start + window_size
while start_dts < end:
window = Bout(start_dts, end_dts)
windows.append(window)
start_dts = start_dts + window_size
end_dts = end_dts + window_size
return self.build_statistics_channels(windows, statistics, name=name)
def test_a():
# Case A
# Both timestamps preceed data
origin = counts.timestamps[0]
start = origin - timedelta(days=2)
end = origin - timedelta(days=1)
# Summarise the data before deletion
summary_before = Time_Series.Time_Series("")
summary_before.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
counts.delete_windows([Bout.Bout(start, end)])
# Summarise the data after deletion
summary_after = Time_Series.Time_Series("")
summary_after.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
# All values should be identical, loop through them and assert equality
suffixes = "sum n missing 0_0 0_1 1_1".split(" ")
for suffix in suffixes:
assert (summary_before.get_channel("AG_Counts_" + suffix).data[0] ==
summary_after.get_channel("AG_Counts_" + suffix).data[0])
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(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_list_intersection([window],bouts)
cache_lengths(intersection)
sum_seconds = total_time(intersection).total_seconds()
output_row.append(sum_seconds)
elif val1 == "mean":
intersection = bout_list_intersection([window],bouts)
cache_lengths(intersection)
sum_seconds = 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 test_b():
# Case B
# First timestamp preceeds data, second doesn't
origin = counts.timestamps[0]
start = origin - timedelta(hours=12)
end = origin + timedelta(hours=12)
# Summarise the data before deletion
summary_before = Time_Series.Time_Series("")
summary_before.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
counts.delete_windows([Bout.Bout(start, end)])
# Summarise the data after deletion
summary_after = Time_Series.Time_Series("")
summary_after.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
# n should go down and missing should go up
assert (summary_before.get_channel("AG_Counts_n").data[0] >
summary_after.get_channel("AG_Counts_n").data[0])
assert (summary_before.get_channel("AG_Counts_missing").data[0] <
summary_after.get_channel("AG_Counts_missing").data[0])
# Should only be 12 hours left
assert (summary_after.get_channel("AG_Counts_n").data[0] == 12 * 60)
# And 12 hours missing
assert (summary_after.get_channel("AG_Counts_missing").data[0] == 12 * 60)
def test_c():
# Case C
# Both timestamps inside data
origin = counts.timestamps[0]
start = origin + timedelta(hours=6)
end = origin + timedelta(hours=7)
# Summarise the data before deletion
summary_before = Time_Series.Time_Series("")
summary_before.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
counts.delete_windows([Bout.Bout(start, end)])
# Summarise the data after deletion
summary_after = Time_Series.Time_Series("")
summary_after.add_channels(
counts.summary_statistics(statistics=[(
"generic",
["sum", "n", "missing"]), ("cutpoints",
[[0, 0], [0, 1], [1, 1]])]))
# n should go down and missing should go up
assert (summary_before.get_channel("AG_Counts_n").data[0] >
summary_after.get_channel("AG_Counts_n").data[0])
assert (summary_before.get_channel("AG_Counts_missing").data[0] <
summary_after.get_channel("AG_Counts_missing").data[0])
# Should only be 23 hours left
assert (summary_after.get_channel("AG_Counts_n").data[0] == 23 * 60)
# And 1 hours missing
assert (summary_after.get_channel("AG_Counts_missing").data[0] == 1 * 60)
def process_file(job_details):
id_num = str(job_details["pid"])
filename = job_details["filename"]
filename_short = os.path.basename(filename).split('.')[0]
meta = os.path.join(results_folder,
"metadata_{}.csv".format(filename_short))
# check if analysis_meta already exists...
if os.path.isfile(meta):
os.remove(meta)
battery_max = 0
if monitor_type == "GeneActiv":
battery_max = GA_battery_max
elif monitor_type == "Axivity":
battery_max = AX_battery_max
epochs = [timedelta(minutes=n) for n in epoch_minutes]
# Use 'epochs_minutes' variable to create the corresponding names to the epochs defined
names = []
plots_list = []
for n in epoch_minutes:
name = ""
if n % 60 == 0: # If the epoch is a multiple of 60, it will be named in hours, e.g. '1h'
name = "{}h".format(int(n / 60))
elif n % 60 != 0: # If the epoch is NOT a multiple of 60, it will be named in seconds, e.g. '15m'
name = "{}m".format(n)
names.append(name)
if n in epoch_plot:
plots_list.append(name)
# fast-load the data to identify any anomalies:
qc_ts, qc_header = data_loading.fast_load(filename, monitor_type)
qc_channels = qc_ts.get_channels(["X", "Y", "Z"])
anomalies = diagnostics.diagnose_fix_anomalies(qc_channels,
discrepancy_threshold=2)
# Load the data
ts, header = data_loading.load(filename, monitor_type, compress=False)
header["processed_file"] = os.path.basename(filename)
# some monitors have manufacturers parameters applied to them, let's preserve these but rename them:
var_list = [
"x_gain", "x_offset", "y_gain", "y_offset", "z_gain", "z_offset",
"calibration_date"
]
for var in var_list:
if var in header.keys():
header[("manufacturers_%s" % var)] = header[var]
header.pop(var)
x, y, z, battery, temperature, integrity = ts.get_channels(
["X", "Y", "Z", "Battery", "Temperature", "Integrity"])
initial_channels = [x, y, z, battery, temperature, integrity]
# create dictionary of anomalies total and types
anomalies_dict = {"QC_anomalies_total": len(anomalies)}
# check whether any anomalies have been found:
if len(anomalies) > 0:
anomalies_file = os.path.join(
results_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)
# if anomalies have been found, fix these anomalies
channels = diagnostics.fix_anomalies(anomalies, initial_channels)
else:
for type in anomaly_types:
anomalies_dict["QC_anomaly_{}".format(type)] = 0
# if no anomalies
channels = initial_channels
first_channel = channels[0]
# Convert timestamps to offsets from the first timestamp
start, offsets = Channel.timestamps_to_offsets(first_channel.timestamps)
# As timestamps are sparse, expand them to 1 per observation
offsets = Channel.interpolate_offsets(offsets, len(first_channel.data))
# For each channel, convert to offset timestamps
for c in channels:
c.start = start
c.set_contents(c.data, offsets, timestamp_policy="offset")
# find approximate first and last battery percentage values
first_battery_pct = round((battery.data[1] / battery_max) * 100, 2)
last_battery_pct = round((battery.data[-1] / battery_max) * 100, 2)
# 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)
# if the sampling frequency is greater than 40Hz
if x.frequency > 40:
# apply a low pass filter
x = pampro_fourier.low_pass_filter(x,
20,
frequency=x.frequency,
order=4)
x.name = "X" # because LPF^ changes the name, we want to override that
y = pampro_fourier.low_pass_filter(y,
20,
frequency=y.frequency,
order=4)
y.name = "Y"
z = pampro_fourier.low_pass_filter(z,
20,
frequency=z.frequency,
order=4)
z.name = "Z"
# find any bouts where data is "missing" BEFORE calibration
missing_bouts = []
if -111 in x.data:
# extract the bouts of the data channels where the data == -111 (the missing value)
missing = x.bouts(-111, -111)
# add a buffer of 2 minutes (120 seconds) to the beginning and end of each bout
for item in missing:
bout_start = max(item.start_timestamp - timedelta(seconds=120),
x.timeframe[0])
bout_end = min(item.end_timestamp + timedelta(seconds=120),
x.timeframe[1])
new_bout = Bout.Bout(start_timestamp=bout_start,
end_timestamp=bout_end)
missing_bouts.append(new_bout)
else:
pass
x.delete_windows(missing_bouts)
y.delete_windows(missing_bouts)
z.delete_windows(missing_bouts)
integrity.fill_windows(missing_bouts, fill_value=1)
################ CALIBRATION #######################
# extract still bouts
calibration_ts, calibration_header = triaxial_calibration.calibrate_stepone(
x, y, z, noise_cutoff_mg=noise_cutoff_mg)
# Calibrate the acceleration to local gravity
cal_diagnostics = triaxial_calibration.calibrate_steptwo(
calibration_ts, calibration_header, calibration_statistics=False)
# calibrate data
triaxial_calibration.do_calibration(x,
y,
z,
temperature=None,
cp=cal_diagnostics)
x.delete_windows(missing_bouts)
y.delete_windows(missing_bouts)
z.delete_windows(missing_bouts)
temperature.delete_windows(missing_bouts)
battery.delete_windows(missing_bouts)
# Derive some signal features
vm = channel_inference.infer_vector_magnitude(x, y, z)
vm.delete_windows(missing_bouts)
if "HPFVM" in stats:
vm_hpf = channel_inference.infer_vm_hpf(vm)
else:
vm_hpf = None
if "ENMO" in stats:
enmo = channel_inference.infer_enmo(vm)
else:
enmo = None
if "PITCH" and "ROLL" in stats:
pitch, roll = channel_inference.infer_pitch_roll(x, y, z)
else:
pitch = roll = None
# Infer nonwear and mask those data points in the signal
nonwear_bouts = channel_inference.infer_nonwear_triaxial(
x, y, z, noise_cutoff_mg=noise_cutoff_mg)
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, vm_hpf, pitch, roll, temperature, battery],
["ENMO", "HPFVM", "PITCH", "ROLL", "Temperature", "Battery"]):
if channel_name in stats:
# Collapse the sample data to a processing epoch (in seconds) so data is summarised
epoch_level_channel = channel.piecewise_statistics(
timedelta(seconds=processing_epoch), time_period=tp)[0]
epoch_level_channel.name = channel_name
if channel_name in ["Temperature", "Battery"]:
pass
else:
epoch_level_channel.delete_windows(nonwear_bouts)
epoch_level_channel.delete_windows(missing_bouts)
ts.add_channel(epoch_level_channel)
# collapse binary integrity channel
epoch_level_channel = integrity.piecewise_statistics(
timedelta(seconds=int(processing_epoch)),
statistics=[("binary", ["flag"])],
time_period=tp)[0]
epoch_level_channel.name = "Integrity"
epoch_level_channel.fill_windows(missing_bouts, fill_value=1)
ts.add_channel(epoch_level_channel)
# create and open results files
results_files = [
os.path.join(results_folder, "{}_{}.csv".format(name, filename_short))
for name in names
]
files = [open(file, "w") for file in results_files]
# Write the column headers to the created files
for f in files:
f.write(pampro_utilities.design_file_header(stats) + "\n")
# writing out and plotting results
for epoch, name, f in zip(epochs, names, files):
results_ts = ts.piecewise_statistics(epoch,
statistics=stats,
time_period=tp,
name=id_num)
results_ts.write_channels_to_file(file_target=f)
f.flush()
if name in plots_list:
# for each statistic in the plotting dictionary, produce a plot in the results folder
for stat, plot in plotting_dict.items():
try:
results_ts[stat].add_annotations(nonwear_bouts)
results_ts.draw([[stat]],
file_target=os.path.join(
results_folder,
plot.format(filename_short, name)))
except KeyError:
pass
header["processing_script"] = version
header["analysis_resolutions"] = names
header["noise_cutoff_mg"] = noise_cutoff_mg
header["processing_epoch"] = processing_epoch
header["QC_first_battery_pct"] = first_battery_pct
header["QC_last_battery_pct"] = last_battery_pct
metadata = {**header, **anomalies_dict, **cal_diagnostics}
# write metadata to file
pampro_utilities.dict_write(meta, id_num, metadata)
for c in ts:
del c.data
del c.timestamps
del c.indices
del c.cached_indices
