def read_data_sets_cf(user=None,
need_labels=False,
train_size=80,
validation_size=10,
test_size=10):
"""
1. Get all the user ids
2. For each user get their events
3. Call the parser
4. Return the results
"""
assert (train_size + validation_size + test_size) == 100
# Get the historical meetings of the user
db_client = CalendarDBClient()
events = db_client.list_all_events(user)
# Get the training objects saved using the system
training_objs = Training.objects.filter(user_id=user)
# Obtain a representation of the data
data, labels = parse_dataset_cf(events, training_objs)
t_max = len(data) * train_size / 100
v_max = len(data) * validation_size / 100
data_sets = DataSets()
data_sets.train = DataSet(data[:t_max],
labels[:t_max] if need_labels else [],
need_labels)
data_sets.validation = DataSet(data[t_max:v_max],
data[t_max:v_max] if need_labels else [],
need_labels)
data_sets.test = DataSet(data[v_max:],
labels[v_max:] if need_labels else [],
need_labels)
# , Do the math to return the total number of items
return data_sets, len(users)
def read_data_sets(user,
need_labels=False,
train_size=100,
validation_size=0,
test_size=0):
assert (train_size + validation_size + test_size) == 100
# Get the historical meetings of the user
db_client = CalendarDBClient()
events = db_client.list_all_events(user)
# Get the training objects saved using the system
training_objs = Training.objects.filter(user_id=user)
# Obtain a representation of the data
data, labels = parse_dataset(events, training_objs, need_labels)
t_max = len(data) * train_size / 100
v_max = len(data) * validation_size / 100
data_sets = DataSets()
data_sets.train = DataSet(data[:t_max],
labels[:t_max] if need_labels else [],
need_labels)
data_sets.validation = DataSet(data[t_max:v_max],
data[t_max:v_max] if need_labels else [],
need_labels)
data_sets.test = DataSet(data[v_max:],
labels[v_max:] if need_labels else [],
need_labels)
return data_sets