def load(data_path):
device_map = _get_device_map(data_path)
activity_map = _get_activity_map(data_path)
df = _read_data(data_path, activity_map, device_map)
df_res1_act = _create_activity_df(df, 'Resident 1')
df_res2_act = _create_activity_df(df, 'Resident 2')
assert not _is_activity_overlapping(df_res1_act) \
or not _is_activity_overlapping(df_res2_act)
df_dev = _create_device_df(df)
df_dev = correct_devices(df_dev)
lst_res1_act = df_res1_act[ACTIVITY].unique()
lst_res2_act = df_res2_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(None, df_dev, activity_list=None, device_list=lst_dev)
data.df_dev_map = device_map
data.df_act_map = activity_map
data.df_activities_res1 = df_res1_act
data.lst_activities_res1 = lst_res1_act
data.df_activities_res2 = df_res2_act
data.lst_activities_res2 = lst_res2_act
return data
def load(dev_path, act_path, retain_corrections, subject):
"""
"""
assert subject in ['OrdonezA', 'OrdonezB']
df_act = _load_activities(act_path)
df_dev, df_loc = _load_devices(dev_path)
if subject == 'OrdonezB':
# the activity grooming is often overlapped by sleeping
# as I deem this activity as important i make it dominant
df_act, cor_lst = correct_activities(df_act, excepts=['Grooming'])
elif subject == 'OrdonezA':
df_act, cor_lst = correct_activities(df_act)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
df_dev = correct_devices(df_dev)
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
data.df_dev_rooms = df_loc
if retain_corrections:
data.correction_activities = cor_lst
return data
def load(data_path):
df = _load_df(data_path)
df_dev = _get_devices_df(df)
df_act = _get_activity_df(df)
dev_rep1, dev_rep3 = correct_devices(df_dev)
df_act, cor_lst = correct_activities(df_act)
data = Data(df_act, dev_rep1)
data.df_dev_rep3 = dev_rep3
return data
def load(data_path):
df = _load_df(data_path)
df_dev = _get_devices_df(df)
df_act = _get_activity_df(df)
df_dev = correct_devices(df_dev)
df_act, cor_lst = correct_activities(df_act)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
return data
def load(device_fp, activity_fp):
df_act = _load_activities(activity_fp)
df_dev = _load_devices(device_fp)
df_act, cor_lst = correct_activities(df_act)
df_dev = correct_devices(df_dev)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
data.correction_activities = cor_lst
return data
def load(dev_path, act_path, data_path):
df_dev_map = _load_device_map(dev_path)
df_act_map = _load_activity_map(act_path)
df_dev, df_act = _read_data(data_path, df_dev_map, df_act_map)
df_act, cor_lst = correct_activities(df_act)
df_dev_rep1, df_dev_rep3 = correct_devices(df_dev)
data = Data(df_act, df_dev_rep1)
data.df_dev_rep3 = df_dev_rep3
data.df_dev_map = df_dev_map
data.df_act_map = df_act_map
return data
def load(dev_path, act_path, data_path):
df_dev_map = _load_device_map(dev_path)
df_act_map = _load_activity_map(act_path)
df_dev, df_act = _read_data(data_path, df_dev_map, df_act_map)
df_act, cor_lst = correct_activities(df_act)
df_dev = correct_devices(df_dev)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
data.df_dev_map = df_dev_map
data.df_act_map = df_act_map
return data
def load_amsterdam(folder_path):
device_fp = os.path.join(folder_path, "kasterenSenseData.txt")
activity_fp = os.path.join(folder_path, "kasterenActData.txt")
df_act = _load_activities(activity_fp)
df_dev = _load_devices(device_fp)
df_act, cor_lst = correct_activities(df_act)
df_dev = correct_devices(df_dev)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
if retain_corrections:
data.correction_activities = cor_lst
return data
def load(folder_path, subjects):
"""
Loads a dataset generated by activity-assistant from a specified folder.
Parameters
----------
folder_path : str
The path to the folder where the dataset is located.
subjects : list of str
The subjecst names that are to be included. If the activity file
is named *activities_subject_foo.csv*, then *foo* is the corresponding name.
Examples
--------
The dataset ``my_dataset.zip`` is extracted in the folder ``/path/to/``.
>>> from pyadlml.dataset import load_act_assist
>>> data = load_act_assist('/path/to/my_dataset/', subjects=['chris'])
Returns
-------
data : object
"""
assert isinstance(folder_path, str)
assert isinstance(subjects, list)
df_dev = _read_devices(os.path.join(folder_path, DATA_NAME),
os.path.join(folder_path, DEV_MAP_NAME))
df_dev = correct_devices(df_dev)
# get mappings
lst_dev = _read_device_list(os.path.join(folder_path, DEV_MAP_NAME))
lst_act = _read_activity_list(os.path.join(folder_path, ACT_MAP_NAME))
data = Data(None, df_dev, activity_list=lst_act, device_list=lst_dev)
for subject in subjects:
df_act = _read_activities(
os.path.join(folder_path, ACT_NAME % (subject)))
# correct possible overlaps in activities
df_act, cor_lst = correct_activities(df_act)
setattr(data, 'df_activities_{}'.format(subject), df_act)
setattr(data, 'correction_activities_{}'.format(subject), cor_lst)
return data
def load(device_fp, activity_fp):
df_act = _load_activities(activity_fp)
df_dev = _load_devices(device_fp)
# correct overlapping activities as going to toilet is done in parallel
# for this dataset >:/
df_act, cor_lst = correct_activities(df_act)
# correct possible duplicates for representation 2
df_dev, df_dev_rep3 = correct_devices(df_dev)
data = Data(df_act, df_dev)
data.df_dev_rep3 = df_dev_rep3
data.correction_activities = cor_lst
return data
def load_casas_aruba(folder_path):
_fix_data(os.path.join(folder_path, "data"))
data_path = os.path.join(folder_path, 'corrected_data.csv')
df = _load_df(data_path)
df_dev = _get_devices_df(df)
df_act = _get_activity_df(df)
df_dev = correct_devices(df_dev)
df_act, cor_lst = correct_activities(df_act)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
return data
def load(data_path):
device_map = _get_device_map(data_path)
activity_map = _get_activity_map(data_path)
df = _read_data(data_path, activity_map, device_map)
df_res1_act = _create_activity_df(df, 'Resident 1')
df_res2_act = _create_activity_df(df, 'Resident 2')
assert not _is_activity_overlapping(
df_res1_act) or not _is_activity_overlapping(df_res2_act)
df_dev_rep3 = _create_device_df(df)
df_dev_rep1, df_dev_rep3 = correct_devices(df_dev_rep3)
data = Data(df_res1_act, df_dev_rep1)
data.df_dev_rep3 = df_dev_rep3
data.df_dev_map = device_map
data.df_act_map = activity_map
data.df_activities_res2 = df_res2_act
return data
def load(dev_path, act_path, subject):
"""
"""
assert subject in ['OrdonezA', 'OrdonezB']
df_act = _load_activities(act_path)
df_dev, df_loc = _load_devices(dev_path)
if subject == 'OrdonezB':
# the activity grooming is often overlapped by sleeping
# as I deem this activity as important i make it dominant
df_act, cor_lst = correct_activities(df_act, excepts=['Grooming'])
elif subject == 'OrdonezA':
df_act, cor_lst = correct_activities(df_act)
df_dev, df_dev_rep3 = correct_devices(df_dev)
data = Data(df_act, df_dev)
data.df_dev_rep3 = df_dev_rep3
data.correction_activities = cor_lst
data.df_dev_rooms = df_loc
return data
def load_mitlab(folder_path):
act_path = os.path.join(folder_path, subject, "Activities.csv")
dev_path = os.path.join(folder_path, subject, "sensors.csv")
data_path = os.path.join(folder_path, subject, "activities_data.csv")
df_dev_map = _load_device_map(dev_path)
df_act_map = _load_activity_map(act_path)
df_dev, df_act = _read_data(data_path, df_dev_map, df_act_map)
df_act, cor_lst = correct_activities(df_act)
df_dev = correct_devices(df_dev)
lst_act = df_act[ACTIVITY].unique()
lst_dev = df_dev[DEVICE].unique()
data = Data(df_act, df_dev, activity_list=lst_act, device_list=lst_dev)
data.df_dev_map = df_dev_map
data.df_act_map = df_act_map
if retain_corrections:
data.correction_activities = cor_lst
return data
