def create_wine(data_to_create=WINE_RED):
red_file = "wine/winequality-red.csv"
white_file = "wine/winequality-white.csv"
field_names, red_data = load_csv(red_file, delim=";")
white_data = load_csv(white_file, delim=";")[1]
if data_to_create == WINE_TRANSFER:
red_ids = np.zeros((red_data.shape[0], 1))
white_ids = np.ones((white_data.shape[0], 1))
red_data = np.hstack((red_data, red_ids))
white_data = np.hstack((white_data, white_ids))
wine_data = np.vstack((red_data, white_data))
ids = wine_data[:, -1]
x = wine_data[:, :-2]
y = wine_data[:, -2]
used_field_names = field_names[:-1]
viz = True
if viz:
learner = make_learner()
# learner = None
viz_features(x, y, ids, used_field_names, alpha=0.01, learner=learner)
suffix = "transfer"
else:
if data_to_create == WINE_RED:
wine_data = red_data
suffix = "red"
elif data_to_create == WINE_WHITE:
wine_data = white_data
suffix = "white"
else:
assert False
ids = None
x = wine_data[:, :-1]
y = wine_data[:, -1]
used_field_names = field_names[:-1]
data = data_class.Data()
data.x = data.x = array_functions.standardize(x)
if data_to_create == WINE_TRANSFER:
pass
# feat_idx = 1
# data.x = array_functions.vec_to_2d(x[:,feat_idx])
data.y = y
data.set_train()
data.set_target()
data.set_true_y()
data.data_set_ids = ids
data.is_regression = True
"""
data = data.rand_sample(.25, data.data_set_ids == 0)
data = data.rand_sample(.1, data.data_set_ids == 1)
s = wine_file % ('-small-' + str(data.p))
"""
s = wine_file % ("-" + suffix)
helper_functions.save_object(s, data)
def create_energy():
file = 'energy/ENB2012_data.csv'
field_names, energy_data = load_csv(file)
domain_ids = energy_data[:, 4]
x = energy_data
y = energy_data[:, -2]
from methods import method
#learner = method.NadarayaWatsonMethod()
learner = None
viz_features(x, y, domain_ids, field_names, learner=learner)
pass
def create_energy():
file = "energy/ENB2012_data.csv"
field_names, energy_data = load_csv(file)
domain_ids = energy_data[:, 4]
x = energy_data
y = energy_data[:, -2]
from methods import method
# learner = method.NadarayaWatsonMethod()
learner = None
viz_features(x, y, domain_ids, field_names, learner=learner)
pass
def create_pair(i, j, y_col):
file = pair_file(i, j)
data_i = load_pair(i)
data_j = load_pair(j)
data_all = np.vstack((data_i, data_j))
x = data_all[:, 1 - y_col]
y = data_all[:, y_col]
domain_ids = np.zeros(data_i.shape[0] + data_j.shape[0])
domain_ids[data_i.shape[0] :] = 1
# viz_features(x,y,domain_ids,learner=make_learner())
viz_features(x, y, domain_ids, learner=None)
create_and_save_data(x, y, domain_ids, file)
def create_pair(i, j, y_col):
file = pair_file(i, j)
data_i = load_pair(i)
data_j = load_pair(j)
data_all = np.vstack((data_i, data_j))
x = data_all[:, 1 - y_col]
y = data_all[:, y_col]
domain_ids = np.zeros(data_i.shape[0] + data_j.shape[0])
domain_ids[data_i.shape[0]:] = 1
#viz_features(x,y,domain_ids,learner=make_learner())
viz_features(x, y, domain_ids, learner=None)
create_and_save_data(x, y, domain_ids, file)
def create_forest_fires():
months = {
'jan': 1,
'feb': 2,
'mar': 3,
'apr': 4,
'may': 5,
'jun': 6,
'jul': 7,
'aug': 8,
'sep': 9,
'oct': 10,
'nov': 11,
'dec': 12
}
days = {
'sun': 1,
'mon': 2,
'tue': 3,
'wed': 4,
'thu': 5,
'fri': 6,
'sat': 7
}
#month_to_season = lambda x : (months[x]-1)/3
month_to_season = lambda x: months[x]
day_to_int = lambda x: days[x]
file = 'forest_fires/forestfires.csv'
converters = {2: month_to_season, 3: day_to_int}
field_names, forest_data = load_csv(file,
dtype='float',
converters=converters)
x = forest_data
y = forest_data[:, -1]
i = field_names == 'month'
domain_ids = forest_data[:, i]
months_to_use = np.asarray([6, 7, 8])
#months_to_use = np.asarray([1,2,3,4,5,6,7,8,9,10,11,12])
to_use = array_functions.find_set(domain_ids, months_to_use)
x = x[to_use, :]
y = y[to_use]
domain_ids = domain_ids[to_use]
x = x[:, 4:]
field_names = field_names[4:]
I = (y > 0) & (y < 700)
x = x[I, :]
y = y[I]
domain_ids = domain_ids[I]
from methods import method
learner = method.NadarayaWatsonMethod()
viz_features(x, y, domain_ids, field_names, learner=learner)
pass
def create_mpg():
file = "mpg/auto-mpg.data.txt"
# field_names, mpg_data = load_csv(file,has_field_names=False,dtype='string',delim=' ')
data = pd.read_csv(file, skiprows=0, delim_whitespace=True, dtype="string")
data = np.asarray(data)[:, 0:-1]
has_missing_values = (data == "?").any(1)
data = data[~has_missing_values, :]
data = data.astype("float")
domain_ids = data[:, 1]
x = data
y = data[:, 0]
viz_features(x, y, domain_ids)
pass
def create_mpg():
file = 'mpg/auto-mpg.data.txt'
#field_names, mpg_data = load_csv(file,has_field_names=False,dtype='string',delim=' ')
data = pd.read_csv(file, skiprows=0, delim_whitespace=True, dtype='string')
data = np.asarray(data)[:, 0:-1]
has_missing_values = (data == '?').any(1)
data = data[~has_missing_values, :]
data = data.astype('float')
domain_ids = data[:, 1]
x = data
y = data[:, 0]
viz_features(x, y, domain_ids)
pass
def create_concrete(transfer=False):
file = 'concrete/Concrete_Data.csv'
used_field_names, concrete_data = load_csv(file)
data = data_class.Data()
t = ''
if transfer:
feat_ind = 0
domain_ind = (used_field_names == 'age').nonzero()[0][0]
ages = concrete_data[:, domain_ind]
domain_ids = np.zeros(ages.shape)
domain_ids[ages < 10] = 1
domain_ids[(ages >= 10) & (ages <= 28)] = 2
domain_ids[ages > 75] = 3
data.x = concrete_data[:, 0:(concrete_data.shape[1] - 2)]
#0,3,5
#data.x = preprocessing.scale(data.x)
if concrete_num_feats == 1:
data.x = array_functions.vec_to_2d(data.x[:, feat_ind])
t = '-feat=' + str(feat_ind)
elif concrete_num_feats >= data.x.shape[1]:
t = '-' + str(min(data.x.shape[1], concrete_num_feats))
else:
assert False
data.data_set_ids = domain_ids
else:
data.x = concrete_data[:, 0:-1]
data.y = concrete_data[:, -1]
data.set_train()
data.set_target()
data.set_true_y()
data.is_regression = True
viz = False
if viz:
to_use = domain_ids > 0
domain_ids = domain_ids[to_use]
concrete_data = concrete_data[to_use, :]
np.delete(concrete_data, domain_ind, 1)
viz_features(concrete_data, concrete_data[:, -1], domain_ids,
used_field_names)
return
data.x = array_functions.standardize(data.x)
#viz_features(data.x,data.y,data.data_set_ids)
s = concrete_file % t
helper_functions.save_object(s, data)
def create_concrete(transfer=False):
file = "concrete/Concrete_Data.csv"
used_field_names, concrete_data = load_csv(file)
data = data_class.Data()
t = ""
if transfer:
feat_ind = 0
domain_ind = (used_field_names == "age").nonzero()[0][0]
ages = concrete_data[:, domain_ind]
domain_ids = np.zeros(ages.shape)
domain_ids[ages < 10] = 1
domain_ids[(ages >= 10) & (ages <= 28)] = 2
domain_ids[ages > 75] = 3
data.x = concrete_data[:, 0 : (concrete_data.shape[1] - 2)]
# 0,3,5
# data.x = preprocessing.scale(data.x)
if concrete_num_feats == 1:
data.x = array_functions.vec_to_2d(data.x[:, feat_ind])
t = "-feat=" + str(feat_ind)
elif concrete_num_feats >= data.x.shape[1]:
t = "-" + str(min(data.x.shape[1], concrete_num_feats))
else:
assert False
data.data_set_ids = domain_ids
else:
data.x = concrete_data[:, 0:-1]
data.y = concrete_data[:, -1]
data.set_train()
data.set_target()
data.set_true_y()
data.is_regression = True
viz = False
if viz:
to_use = domain_ids > 0
domain_ids = domain_ids[to_use]
concrete_data = concrete_data[to_use, :]
np.delete(concrete_data, domain_ind, 1)
viz_features(concrete_data, concrete_data[:, -1], domain_ids, used_field_names)
return
data.x = array_functions.standardize(data.x)
# viz_features(data.x,data.y,data.data_set_ids)
s = concrete_file % t
helper_functions.save_object(s, data)
def create_forest_fires():
months = {
"jan": 1,
"feb": 2,
"mar": 3,
"apr": 4,
"may": 5,
"jun": 6,
"jul": 7,
"aug": 8,
"sep": 9,
"oct": 10,
"nov": 11,
"dec": 12,
}
days = {"sun": 1, "mon": 2, "tue": 3, "wed": 4, "thu": 5, "fri": 6, "sat": 7}
# month_to_season = lambda x : (months[x]-1)/3
month_to_season = lambda x: months[x]
day_to_int = lambda x: days[x]
file = "forest_fires/forestfires.csv"
converters = {2: month_to_season, 3: day_to_int}
field_names, forest_data = load_csv(file, dtype="float", converters=converters)
x = forest_data
y = forest_data[:, -1]
i = field_names == "month"
domain_ids = forest_data[:, i]
months_to_use = np.asarray([6, 7, 8])
# months_to_use = np.asarray([1,2,3,4,5,6,7,8,9,10,11,12])
to_use = array_functions.find_set(domain_ids, months_to_use)
x = x[to_use, :]
y = y[to_use]
domain_ids = domain_ids[to_use]
x = x[:, 4:]
field_names = field_names[4:]
I = (y > 0) & (y < 700)
x = x[I, :]
y = y[I]
domain_ids = domain_ids[I]
from methods import method
learner = method.NadarayaWatsonMethod()
viz_features(x, y, domain_ids, field_names, learner=learner)
pass
def create_bike_sharing():
file = "bike_sharing/day.csv"
columns = [0] + range(2, 16)
all_field_names = pd.read_csv(file, nrows=1, dtype="string")
all_field_names = np.asarray(all_field_names.keys())
used_field_names = all_field_names[columns]
bike_data = np.loadtxt(file, skiprows=1, delimiter=",", usecols=columns)
domain_ind = used_field_names == "yr"
domain_ids = np.squeeze(bike_data[:, domain_ind])
# inds_to_keep = (used_field_names == 'temp') | (used_field_names == 'atemp')
# bike_data = bike_data[:,inds_to_keep]
# used_field_names = used_field_names[inds_to_keep]
viz = True
to_use = np.asarray([8, 9, 10, 11])
x = bike_data[:, to_use]
used_field_names = used_field_names[to_use]
y = bike_data[:, -1]
if viz:
# learner = make_learner()
learner = None
viz_features(x, y, domain_ids, used_field_names, learner=learner)
field_to_use = 1
x = x[:, field_to_use]
data = data_class.Data()
data.is_regression = True
data.x = array_functions.vec_to_2d(x)
data.x = array_functions.standardize(data.x)
data.y = y
data.y = array_functions.normalize(data.y)
data.set_defaults()
data.data_set_ids = domain_ids
s = bike_file % ("-feat=" + str(field_to_use))
helper_functions.save_object(s, data)
pass
def create_bike_sharing():
file = 'bike_sharing/day.csv'
columns = [0] + range(2, 16)
all_field_names = pd.read_csv(file, nrows=1, dtype='string')
all_field_names = np.asarray(all_field_names.keys())
used_field_names = all_field_names[columns]
bike_data = np.loadtxt(file, skiprows=1, delimiter=',', usecols=columns)
domain_ind = used_field_names == 'yr'
domain_ids = np.squeeze(bike_data[:, domain_ind])
#inds_to_keep = (used_field_names == 'temp') | (used_field_names == 'atemp')
#bike_data = bike_data[:,inds_to_keep]
#used_field_names = used_field_names[inds_to_keep]
viz = True
to_use = np.asarray([8, 9, 10, 11])
x = bike_data[:, to_use]
used_field_names = used_field_names[to_use]
y = bike_data[:, -1]
if viz:
#learner = make_learner()
learner = None
viz_features(x, y, domain_ids, used_field_names, learner=learner)
field_to_use = 1
x = x[:, field_to_use]
data = data_class.Data()
data.is_regression = True
data.x = array_functions.vec_to_2d(x)
data.x = array_functions.standardize(data.x)
data.y = y
data.y = array_functions.normalize(data.y)
data.set_defaults()
data.data_set_ids = domain_ids
s = bike_file % ('-feat=' + str(field_to_use))
helper_functions.save_object(s, data)
pass
def create_wine(data_to_create=WINE_RED):
red_file = 'wine/winequality-red.csv'
white_file = 'wine/winequality-white.csv'
field_names, red_data = load_csv(red_file, delim=';')
white_data = load_csv(white_file, delim=';')[1]
if data_to_create == WINE_TRANSFER:
red_ids = np.zeros((red_data.shape[0], 1))
white_ids = np.ones((white_data.shape[0], 1))
red_data = np.hstack((red_data, red_ids))
white_data = np.hstack((white_data, white_ids))
wine_data = np.vstack((red_data, white_data))
ids = wine_data[:, -1]
x = wine_data[:, :-2]
y = wine_data[:, -2]
used_field_names = field_names[:-1]
viz = True
if viz:
learner = make_learner()
#learner = None
viz_features(x,
y,
ids,
used_field_names,
alpha=.01,
learner=learner)
suffix = 'transfer'
else:
if data_to_create == WINE_RED:
wine_data = red_data
suffix = 'red'
elif data_to_create == WINE_WHITE:
wine_data = white_data
suffix = 'white'
else:
assert False
ids = None
x = wine_data[:, :-1]
y = wine_data[:, -1]
used_field_names = field_names[:-1]
data = data_class.Data()
data.x = data.x = array_functions.standardize(x)
if data_to_create == WINE_TRANSFER:
pass
#feat_idx = 1
#data.x = array_functions.vec_to_2d(x[:,feat_idx])
data.y = y
data.set_train()
data.set_target()
data.set_true_y()
data.data_set_ids = ids
data.is_regression = True
'''
data = data.rand_sample(.25, data.data_set_ids == 0)
data = data.rand_sample(.1, data.data_set_ids == 1)
s = wine_file % ('-small-' + str(data.p))
'''
s = wine_file % ('-' + suffix)
helper_functions.save_object(s, data)
