def distribution(self, x, mean, std):
"""
Gaussian Distribution Function
"""
numerator = R.square(x - mean)
denominator = R.Scalar(2) * R.square(std)
frac = R.div(numerator,denominator)
exponent = R.exp(R.Scalar(-1) * frac)
two_pi = R.Scalar(2) * R.pi()
gaussian_denominator = R.square_root(two_pi) * std
gaussian_func = R.div(exponent, gaussian_denominator)
return gaussian_func
def r2_score(y_true, y_pred):
if not isinstance(y_true, R.Tensor):
y_true = R.Tensor(y_true)
if not isinstance(y_pred, R.Tensor):
y_pred = R.Tensor(y_pred)
scalar1 = R.Scalar(1)
SS_res = R.sum(R.square(R.sub(y_true, y_pred)))
SS_tot = R.sum(R.square(R.sub(y_true, R.mean(y_true))))
return R.sub(scalar1, R.div(SS_res, R.add(SS_tot, R.epsilon())))
def distribution(self, x, mean, std):
"""
Gaussian Distribution Function
exponent = np.exp(-((x-mean)**2 / (2*std**2)))
gauss_func = exponent / (np.sqrt(2*np.pi)*std)
"""
numerator = R.square(x - mean)
denominator = R.Scalar(2) * R.square(std)
frac = R.div(numerator,denominator)
exponent = R.exp(R.Scalar(-1) * frac)
two_pi = R.Scalar(2) * R.Scalar(3.141592653589793)
gaussian_denominator = R.square_root(two_pi) * std
gaussian_func = R.div(exponent, gaussian_denominator)
return gaussian_func
def r2_score(y_true, y_pred):
if isinstance(y_true, R.Tensor) or isinstance(y_true, R.Op):
pass
else:
y_true = R.Tensor(y_true, name="y_true")
if isinstance(y_pred, R.Tensor) or isinstance(y_pred, R.Op):
pass
else:
y_pred = R.Tensor(y_pred, name="y_pred")
print(type(y_true), type(y_pred))
scalar1 = R.Scalar(1)
SS_res = R.sum(R.square(R.sub(y_pred, y_true)), name="ss_res")
SS_tot = R.sum(R.square(R.sub(y_true, R.mean(y_true))), name="ss_tot")
return R.sub(scalar1, R.div(SS_res, SS_tot), name="r2_score")
def pearson_correlation(x, y):
"""
Calculate linear correlation(pearson correlation)
"""
if not isinstance(x, R.Tensor):
x = R.Tensor(x)
if not isinstance(y, R.Tensor):
y = R.Tensor(y)
a = R.sum(R.square(x))
b = R.sum(R.square(y))
n = a.output.shape[0]
return R.div(
R.sub(R.multiply(R.Scalar(n), R.sum(R.multiply(x, y))),
R.multiply(R.sum(x), R.sum(y))),
R.multiply(
R.square_root(R.sub(R.multiply(R.Scalar(n), a), R.square(b))),
R.square_root(R.sub(R.multiply(R.Scalar(n), b), R.square(b)))))
def find_split(self, X, y):
ideal_col = None
ideal_threshold = None
num_observations = y.shape_().gather(R.Scalar(0))
while num_observations.status != 'computed':
pass
num_observations = int(num_observations.output)
if num_observations <= 1:
return ideal_col, ideal_threshold
y = y.reshape(shape=[num_observations])
count_in_parent = R.Tensor([])
for c in range(self.num_classes):
count_in_parent = count_in_parent.concat(
R.sum(R.equal(y, R.Scalar(c))).expand_dims())
gini = R.square(
count_in_parent.foreach(operation='div', params=num_observations))
best_gini = R.sub(R.Scalar(1.0), R.sum(gini))
temp_y = y.reshape(shape=[num_observations, 1])
for col in range(self.num_features):
temp_X = R.gather(
R.transpose(X),
R.Scalar(col)).reshape(shape=[num_observations, 1])
all_data = R.concat(temp_X, temp_y, axis=1)
column = R.gather(R.transpose(X), R.Scalar(col))
ind = column.find_indices(R.sort(R.unique(column)))
while ind.status != "computed":
pass
inform_server()
sorted_data = R.Tensor([])
for i in ind.output:
sorted_data = sorted_data.concat(all_data.gather(
R.Tensor(i))) # need to find another way to sort
sorted_data_tpose = sorted_data.transpose()
thresholds = sorted_data_tpose.gather(R.Scalar(0)).gather(
R.Scalar(0))
obs_classes = sorted_data_tpose.gather(R.Scalar(1)).gather(
R.Scalar(0))
num_left = R.Tensor([0] * self.num_classes) # need ops
num_right = count_in_parent
for i in range(1, num_observations):
class_ = R.gather(obs_classes, R.Tensor([i - 1]))
classencoding = R.one_hot_encoding(
class_, depth=self.num_classes).gather(R.Scalar(0))
num_left = num_left.add(classencoding)
num_right = num_right.sub(classencoding)
gini_left = R.sub(
R.Scalar(1),
R.sum(
R.square(R.foreach(num_left, operation='div',
params=i))))
gini_right = R.sub(
R.Scalar(1),
R.sum(
R.square(
R.foreach(num_right,
operation='div',
params=num_observations - i))))
gini = R.div(
R.add(
R.multiply(R.Scalar(i), gini_left),
R.multiply(R.Scalar(num_observations - i),
gini_right)), R.Scalar(num_observations))
decision1 = R.logical_and(thresholds.gather(R.Tensor([i])),
thresholds.gather(R.Tensor([i - 1])))
decision2 = gini.less(best_gini)
while decision2.status != "computed":
pass
print(decision2.output == 1)
if decision2.output == 1 and decision1 != 1:
best_gini = gini
ideal_col = col
ideal_threshold = R.div(
R.add(thresholds.gather(R.Tensor([i])),
thresholds.gather(R.Tensor([i - 1]))),
R.Scalar(2))
print(ideal_col, ideal_threshold)
return ideal_col, ideal_threshold
def closest_centroids(self, points, centroids):
centroids = R.expand_dims(centroids, axis=1)
return R.argmin(
R.square_root(R.sum(R.square(R.sub(points, centroids)), axis=2)))
def loss(out, Y):
# out and Y are both R.Tensor objects
s = R.square(out.sub(Y))
s = R.sum(s).div(R.Scalar(leny))
return (s)
def __compute_cost(self, y, y_pred, no_samples, name="cost"):
"""Cost function"""
return R.multiply(R.Scalar(1.0 / (2.0 * no_samples.output)),
R.sum(R.square(R.sub(y_pred, y))),
name=name)