# Chapter 4: Identifying aggregate attributes.
# First we focus on the time domain.
# Set the window sizes to the number of instances representing 1 seconds, 5 seconds and 3 minutes
window_sizes = [
int(float(1000) / milliseconds_per_instance),
int(float(5000) / milliseconds_per_instance),
int(float(0.3 * 60000) / milliseconds_per_instance)
]
NumAbs = NumericalAbstraction()
dataset_copy = copy.deepcopy(dataset)
for ws in window_sizes:
dataset_copy = NumAbs.abstract_numerical(dataset_copy,
['userAcceleration.x'], ws,
'mean')
dataset_copy = NumAbs.abstract_numerical(dataset_copy,
['userAcceleration.x'], ws, 'std')
DataViz.plot_dataset(dataset_copy, [
'userAcceleration.x', 'userAcceleration.x_temp_mean',
'userAcceleration.x_temp_std', 'label'
], ['exact', 'like', 'like', 'like'], ['line', 'line', 'line', 'points'])
ws = int(float(0.3 * 60000) / milliseconds_per_instance)
selected_predictor_cols = [c for c in dataset.columns if not 'label' in c]
dataset = NumAbs.abstract_numerical(dataset, selected_predictor_cols, ws,
'mean')
dataset = NumAbs.abstract_numerical(dataset, selected_predictor_cols, ws,
'std')
print('total window sizes', window_sizes)
NumAbs = NumericalAbstraction()
periodic_predictor_cols = [
'acc_x',
'acc_y',
'acc_z',
"gyr_x",
"gyr_y",
"gyr_z",
]
for ws in window_sizes:
dataset = NumAbs.abstract_numerical(dataset, periodic_predictor_cols, ws,
'mean')
dataset = NumAbs.abstract_numerical(dataset, periodic_predictor_cols, ws,
'std')
print('window size', ws)
print(dataset.columns)
DataViz.plot_dataset(dataset, ['acc_x', 'acc_y', 'acc_z', 'label'],
['exact', 'like', 'like', 'like'],
['line', 'line', 'line', 'points'])
# ws = int(float(0.5*60000)/milliseconds_per_instance)
# dataset = NumAbs.abstract_numerical(dataset, periodic_predictor_cols, ws, 'mean')
# dataset = NumAbs.abstract_numerical(dataset, periodic_predictor_cols, ws, 'std')
print('temporal', dataset.shape)
# Compute the number of milliseconds covered by an instane based on the first two rows
milliseconds_per_instance = (dataset.index[1] - dataset.index[0]).microseconds/1000
# Chapter 4: Identifying aggregate attributes.
# First we focus on the time domain.
# Set the window sizes to the number of instances representing 5 seconds, 30 seconds and 5 minutes
window_sizes = [int(float(5000)/milliseconds_per_instance), int(float(0.5*60000)/milliseconds_per_instance), int(float(5*60000)/milliseconds_per_instance)]
NumAbs = NumericalAbstraction()
dataset_copy = copy.deepcopy(dataset)
for ws in window_sizes:
dataset_copy = NumAbs.abstract_numerical(dataset_copy, ['acc_phone_x'], ws, 'mean')
dataset_copy = NumAbs.abstract_numerical(dataset_copy, ['acc_phone_x'], ws, 'std')
DataViz.plot_dataset(dataset_copy, ['acc_phone_x', 'acc_phone_x_temp_mean', 'acc_phone_x_temp_std', 'label'], ['exact', 'like', 'like', 'like'], ['line', 'line', 'line', 'points'])
ws = int(float(0.5*60000)/milliseconds_per_instance)
selected_predictor_cols = [c for c in dataset.columns if not 'label' in c]
dataset = NumAbs.abstract_numerical(dataset, selected_predictor_cols, ws, 'mean')
dataset = NumAbs.abstract_numerical(dataset, selected_predictor_cols, ws, 'std')
CatAbs = CategoricalAbstraction()
dataset = CatAbs.abstract_categorical(dataset, ['label'], ['like'], 0.03, int(float(5*60000)/milliseconds_per_instance), 2)
# Now we move to the frequency domain, with the same window size.
NumAbs = NumericalAbstraction()
dataset_copy = copy.deepcopy(dataset)
# for ws in window_sizes:
# dataset_copy = NumAbs.abstract_numerical(dataset_copy, ['acc_phone_X'], ws, 'mean')
# dataset_copy = NumAbs.abstract_numerical(dataset_copy, ['acc_phone_X'], ws, 'std')
#
# DataViz.plot_dataset(dataset_copy, ['acc_phone_X', 'acc_phone_X_temp_mean', 'acc_phone_X_temp_std', 'label'],
# ['exact', 'like', 'like', 'like'], ['line', 'line', 'line', 'points'])
# ws = int(float(0.5 * 60000) / milliseconds_per_instance) $ FIXME they only use one window size! We do multiple
# ws = int(float(8000) / milliseconds_per_instance)
ws = int(float(4000) / milliseconds_per_instance)
# for ws in window_sizes: #FIXME uncomment for multiple ws's
selected_predictor_cols = [c for c in dataset.columns if not 'label' in c]
dataset = NumAbs.abstract_numerical(dataset, selected_predictor_cols, ws,
'mean')
dataset = NumAbs.abstract_numerical(dataset, selected_predictor_cols, ws,
'std')
# DataViz.plot_dataset(dataset,
# ['acc_phone_X', 'gyr_phone_X', 'mag_phone_X', 'pca_1', 'label'],
# ['like', 'like', 'like', 'like', 'like'],
# ['line', 'line', 'line', 'line', 'points'])
#
# # support for labels is useless in our case
# CatAbs = CategoricalAbstraction()
# dataset = CatAbs.abstract_categorical(dataset, ['label'], ['like'], 0.03,
# int(float(8000) / milliseconds_per_instance), 2)
#
# Now we move to the frequency domain, with the same window size.
# Chapter 4: Identifying aggregate attributes.
# First we focus on the time domain.
# Set the window sizes to the number of instances representing 5 seconds, 30 seconds and 5 minutes
window_sizes = [
int(float(2000) / milliseconds_per_instance),
int(float(4000) / milliseconds_per_instance),
int(float(10000) / milliseconds_per_instance)
]
NumAbs = NumericalAbstraction()
dataset_copy = copy.deepcopy(dataset)
for ws in window_sizes:
dataset_copy = NumAbs.abstract_numerical(
dataset_copy, ['linacc_Linear Acceleration x (m/s^2)'], ws, 'mean')
dataset_copy = NumAbs.abstract_numerical(
dataset_copy, ['linacc_Linear Acceleration x (m/s^2)'], ws, 'std')
DataViz.plot_dataset(dataset_copy, [
'linacc_Linear Acceleration x (m/s^2)',
'linacc_Linear Acceleration x (m/s^2)_temp_mean',
'linacc_Linear Acceleration x (m/s^2)_temp_std', 'label'
], ['exact', 'like', 'like', 'like'], ['line', 'line', 'line', 'points'])
ws = int(float(4000) / milliseconds_per_instance)
selected_predictor_cols = [
'acc_Acceleration x (m/s^2)', 'acc_Acceleration y (m/s^2)',
'acc_Acceleration z (m/s^2)', 'press_Pressure (hPa)',
'gyr_Gyroscope x (rad/s)', 'gyr_Gyroscope y (rad/s)',
print('milliseconds per instance', milliseconds_per_instance)
window_sizes = [
int(float(5000) / milliseconds_per_instance),
int(float(0.5 * 60000) / milliseconds_per_instance),
int(float(5 * 60000) / milliseconds_per_instance)
]
print('window sizes', window_sizes)
NumAbs = NumericalAbstraction()
CatAbs = CategoricalAbstraction()
dataset_copy = copy.deepcopy(dataset)
for ws in window_sizes:
dataset_copy = NumAbs.abstract_numerical(dataset_copy, ['acc_phone_x'], ws,
'min')
dataset_copy = NumAbs.abstract_numerical(dataset_copy, ['acc_phone_x'], ws,
'max')
print('window size', ws)
DataViz.plot_dataset(dataset_copy,
['acc_phone_x', 'acc_phone_x_temp_min', 'label'],
['exact', 'like', 'like'], ['line', 'line', 'points'])
DataViz.plot_dataset(dataset_copy,
['acc_phone_x', 'acc_phone_x_temp_max', 'label'],
['exact', 'like', 'like'], ['line', 'line', 'points'])
DataViz.plot_dataset(
dataset_copy,
['acc_phone_x', 'acc_phone_x_temp_max', 'acc_phone_x_temp_min', 'label'],
['exact', 'like', 'like', 'like'], ['line', 'line', 'line', 'points'])
def main():
# Read the result from the previous chapter convert the index to datetime
try:
dataset = pd.read_csv(DATA_PATH / DATASET_FNAME, index_col=0)
dataset.index = pd.to_datetime(dataset.index)
except IOError as e:
print(
'File not found, try to run previous crowdsignals scripts first!')
raise e
# Create an instance of visualization class to plot the results
DataViz = VisualizeDataset(__file__)
# Compute the number of milliseconds covered by an instance based on the first two rows
milliseconds_per_instance = (dataset.index[1] -
dataset.index[0]).microseconds / 1000
# Create objects for feature abstraction
NumAbs = NumericalAbstraction()
CatAbs = CategoricalAbstraction()
FreqAbs = FourierTransformation()
if FLAGS.mode == 'time':
# Focus on the time domain first
# Set the window sizes to the number of instances representing 5 seconds, 30 seconds and 5 minutes
window_sizes = [
int(float(5000) / milliseconds_per_instance),
int(float(0.5 * 60000) / milliseconds_per_instance),
int(float(5 * 60000) / milliseconds_per_instance)
]
dataset_copy = copy.deepcopy(dataset)
for ws in window_sizes:
print(
f'Abstracting numerical features for window size {ws * milliseconds_per_instance / 1000}s.'
)
dataset_copy = NumAbs.abstract_numerical(
data_table=dataset_copy,
cols=['acc_phone_x'],
window_size=ws,
aggregation_function='mean')
dataset_copy = NumAbs.abstract_numerical(
data_table=dataset_copy,
cols=['acc_phone_x'],
window_size=ws,
aggregation_function='std')
DataViz.plot_dataset(data_table=dataset_copy,
columns=[
'acc_phone_x', 'acc_phone_x_temp_mean',
'acc_phone_x_temp_std', 'label'
],
match=['exact', 'like', 'like', 'like'],
display=['line', 'line', 'line', 'points'])
elif FLAGS.mode == 'frequency':
# Move to the frequency domain with the same window size
fs = 1000.0 / milliseconds_per_instance
ws = int(10000.0 / milliseconds_per_instance)
data_table = FreqAbs.abstract_frequency(
data_table=copy.deepcopy(dataset),
cols=['acc_phone_x'],
window_size=ws,
sampling_rate=fs)
# Spectral analysis
DataViz.plot_dataset(data_table=data_table,
columns=[
'acc_phone_x_max_freq',
'acc_phone_x_freq_weighted',
'acc_phone_x_pse', 'label'
],
match=['like', 'like', 'like', 'like'],
display=['line', 'line', 'line', 'points'])
elif FLAGS.mode == 'final':
ws = int(float(0.5 * 60000) / milliseconds_per_instance)
fs = 1000.0 / milliseconds_per_instance
# Abstract time domain features and plot the result
selected_predictor_cols = [
c for c in dataset.columns if 'label' not in c
]
print('Calculating mean and std for selected predictor cols.')
dataset = NumAbs.abstract_numerical(data_table=dataset,
cols=selected_predictor_cols,
window_size=ws,
aggregation_function='mean')
dataset = NumAbs.abstract_numerical(data_table=dataset,
cols=selected_predictor_cols,
window_size=ws,
aggregation_function='std')
DataViz.plot_dataset(data_table=dataset,
columns=[
'acc_phone_x', 'gyr_phone_x', 'hr_watch_rate',
'light_phone_lux', 'mag_phone_x',
'press_phone_', 'pca_1', 'label'
],
match=[
'like', 'like', 'like', 'like', 'like',
'like', 'like', 'like'
],
display=[
'line', 'line', 'line', 'line', 'line',
'line', 'line', 'points'
])
# Abstract categorical features
print('Abstracting categorical features.')
dataset = CatAbs.abstract_categorical(
data_table=dataset,
cols=['label'],
match=['like'],
min_support=0.03,
window_size=int(float(5 * 60000) / milliseconds_per_instance),
max_pattern_size=2)
# Abstract frequency domain features
periodic_predictor_cols = [
'acc_phone_x', 'acc_phone_y', 'acc_phone_z', 'acc_watch_x',
'acc_watch_y', 'acc_watch_z', 'gyr_phone_x', 'gyr_phone_y',
'gyr_phone_z', 'gyr_watch_x', 'gyr_watch_y', 'gyr_watch_z',
'mag_phone_x', 'mag_phone_y', 'mag_phone_z', 'mag_watch_x',
'mag_watch_y', 'mag_watch_z'
]
print('Abstracting frequency features.')
dataset = FreqAbs.abstract_frequency(data_table=dataset,
cols=periodic_predictor_cols,
window_size=ws,
sampling_rate=fs)
# Take a certain percentage of overlap in the windows, otherwise training examples will be too much alike
# Set the allowed percentage of overlap
window_overlap = FLAGS.overlap
skip_points = int((1 - window_overlap) * ws)
dataset = dataset.iloc[::skip_points, :]
# Plot the final dataset
DataViz.plot_dataset(data_table=dataset,
columns=[
'acc_phone_x', 'gyr_phone_x', 'hr_watch_rate',
'light_phone_lux', 'mag_phone_x',
'press_phone_', 'pca_1', 'label'
],
match=[
'like', 'like', 'like', 'like', 'like',
'like', 'like', 'like'
],
display=[
'line', 'line', 'line', 'line', 'line',
'line', 'line', 'points'
])
# Store the generated dataset
dataset.to_csv(DATA_PATH / RESULT_FNAME)