def feature_vector_generator (subject, t0, t1, sq=0):
'''Returns a generator of feature vectors
for subject between t0 and t1. All returned vectors
are guaranteed to be equal to or above signal quality sq.'''
# get all the readings for subject between t0 and t1
readings = querying.readings(subject, t0, t1)
# group readings into lists of length `vector_resolution`
groups = grouper(vector_resolution, readings)
for g in groups:
readings = filter(None, g)
# throw out readings with fewer signals than our desired resolution
if len(readings) == vector_resolution:
yield make_feature_vector(readings)
def feature_vector_generator(task, subject, position, sessionnum="", sq=""):
'''Returns a generator of feature vectors
for a specific task, subject, position, and session. All returned vectors
are guaranteed to be equal to or above signal quality sq.'''
# get all the readings for subject between t0 and t1
readings = querybytask.readings(task, subject, position, sessionnum, sq)
# group readings into lists of length `vector_resolution`
groups = grouper(vector_resolution, readings)
for g in groups:
readings = filter(None, g)
# throw out readings with fewer signals than our desired resolution
if len(readings) == vector_resolution:
yield make_feature_vector(readings)
def __init__(self, params):
self.size = params['size']
self.root = params['root']
self.sample_rate = 1.0 # this datasets not good for sampling, always use 100% samples.
self.x_cols = params['x_cols']
# [data engineering]
# time
self.train_test_split_time = params['train_test_split_time']
self.train_max_time = params.get('train_max_time')
self.train_min_time = params.get('train_min_time')
# place_id
self.place_min_checkin = params.get('place_min_checkin', 0)
self.place_min_last_checkin = params.get('place_min_last_checkin')
self.place_max_first_checkin = params.get('place_max_first_checkin')
# ctrl
self.remove_distance_outlier = params['remove_distance_outlier']
# special
self.grp = grouper.grouper(params)
def __init__(self, params):
self.size = params['size']
self.root = params['root']
self.sample_rate = 1.0 # this datasets not good for sampling, always use 100% samples.
self.x_cols = params['x_cols']
# [data engineering]
# time
self.train_test_split_time = params['train_test_split_time']
self.train_max_time = params.get('train_max_time')
self.train_min_time = params.get('train_min_time')
# place_id
self.place_min_checkin = params.get('place_min_checkin', 0)
self.place_min_last_checkin = params.get('place_min_last_checkin')
self.place_max_first_checkin = params.get('place_max_first_checkin')
# ctrl
self.remove_distance_outlier = params['remove_distance_outlier']
# special
self.grp = grouper.grouper(params)
