def predict(self, X):
"""
Predict the output class
"""
MAPs = []
for index, row in enumerate(X):
joint_proba = {}
for class_name, features in self.class_summary.items():
total_features = len(features['summary'])
likelihood = R.Scalar(1)
for idx in range(total_features):
# print("feature: ", row[idx])
feature = R.Scalar(row[idx])
mean = features['summary'][idx]['mean']
stdev = features['summary'][idx]['std']
normal_proba = self.distribution(feature, mean, stdev)
likelihood = likelihood * normal_proba
prior_proba = R.Scalar(features['prior_proba'])
my_val = prior_proba * likelihood
joint_proba[class_name] = prior_proba * likelihood
MAPs.append(joint_proba)
return MAPs
def grow_tree(self, X, y, depth=0):
pop_per_class = R.Tensor([])
for c in range(self.num_classes):
pop_per_class = pop_per_class.concat(
R.sum(R.equal(y, R.Scalar(c))).expand_dims())
predicted_class = R.argmax(pop_per_class)
node = Node(predicted_class=predicted_class, depth=depth)
node.samples = R.shape(y).gather(R.Scalar(0))
if depth < self.max_depth:
#col, threshold = self.find_split(X, y)
col, threshold = 0, R.Tensor([12.895])
'''
'''
decision = R.Scalar(col).logical_and(threshold)
while decision.status != "computed":
pass
if decision.output == 1:
indices_left = X.transpose().gather(
R.Scalar(col)).less(threshold)
X_left, y_left = X.gather(indices_left), y.gather(indices_left)
indices_right = X.transpose().gather(
R.Scalar(col)).greater_equal(threshold)
X_right, y_right = X.gather(indices_right), y.gather(
indices_right)
node.feature_index = col
node.threshold = threshold
node.left = self.grow_tree(X_left, y_left, depth + 1)
node.left.leftbranch = True
node.right = self.grow_tree(X_right, y_right, depth + 1)
node.right.rightbranch = True
return node
def fit(self, X, y):
X = R.Tensor(X)
y = R.Tensor(y)
num_classes = y.unique().shape_().gather(R.Scalar(0))
num_features = X.shape_().gather(R.Scalar(1))
while num_features.status != 'computed':
pass
self.num_classes = int(num_classes.output)
self.num_features = int(num_features.output)
self.tree = self.grow_tree(X, y)
def categorical_hinge(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)
neg = R.max(R.elemul(R.sub(R.Scalar(-1), y_true), y_pred))
pos = R.sum(R.elemul(y_true, y_pred))
loss = R.max((R.sub(neg, pos), R.Scalar(1)), R.Scalar(0))
return loss
def one_hot_cross_entropy(y_true, y_pred, with_logit=True):
if with_logit:
y_pred = softmax(y_pred)
else:
pass
y_pred = R.clip(y_pred, R.epsilon(), R.div(R.Scalar(1), R.epsilon()))
N = y_pred.shape[0]
loss = R.div(R.elemul(R.Scalar(-1), R.mul(R.sum(y_true, R.natlog(R.add(y_pred, 1e-9))))), R.Scalar(N))
return loss
def log_loss(y_true, y_pred, with_logit=True):
if with_logit:
y_pred = sigmoid(y_pred)
else:
pass
y_pred = R.clip(y_pred, R.epsilon(), R.sub(R.Scalar(1), R.epsilon()))
loss = R.elemul(R.Scalar(-1), R.mean(R.elemul(y_true, R.natlog(y_pred)),
R.elemul((R.sub(R.Scalar(1), y_true)), R.natlog(R.sub(R.Scalar(1), y_pred)))))
return loss
def sparse_cross_entropy(y_true, y_pred, with_logit=True):
if with_logit:
y_pred = softmax(y_pred)
else:
pass
y_pred = R.clip(y_pred, R.epsilon(), R.div(R.Scalar(1), R.epsilon()))
N = y_pred.shape[0]
loss = R.elemul(R.Scalar(-1), R.div(R.sum(R.natlog(y_pred[R.len(y_pred), y_true])), R.Scalar(N)))
return loss
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 huber(y_true, y_pred, d):
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)
d = R.Scalar(d)
x = R.sub(y_true, y_pred)
if R.abs(x) <= d:
return R.elemul(R.Scalar(d), R.elemul(x, x))
if R.abs(x) > d:
return R.add(R.elemul(R.Scalar(d), R.mul(d, d)), R.elemul(d, R.sub(R.abs(x), d)))
def train(x, Y, w1, w2, alpha=0.01, epoch=10):
acc = []
losses = []
for j in range(epoch):
loss_sum = R.Scalar(0)
for i in range(len(x)):
out = f_forward(x[i], w1, w2)
loss_sum = loss_sum.add(loss(out, Y[i]))
w1, w2 = back_prop(x[i], y[i], w1, w2, alpha)
print('Epoch : ', j + 1)
acc.append(
R.Scalar(1).sub(loss_sum.div(R.Scalar(len(x)))).multiply(
R.Scalar(100)))
losses.append(loss_sum.div(R.Scalar(len(x))))
return (acc, losses, w1, w2)
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 __init__(self,x_points,y_points,theta):
self.raw_X = x_points
self.raw_y = y_points
self.m = R.Scalar(self.raw_y.shape[0])
self.X = R.Tensor(self.raw_X.tolist())
self.y = R.Tensor(self.raw_y.tolist())
self.theta = R.Tensor(theta.tolist())
def fit(self, X, y):
if self.fit_intercept:
X = self.__add_intercept(X)
self.leny = len(y)
Y = R.Tensor(y)
# weights initialization
self.theta = R.Tensor([0] * self.x_shape1)
for i in range(self.num_iter):
h = self.__sigmoid(X.dot(self.theta))
while h.status != 'computed':
pass
w = X.transpose()
while w.status != 'computed':
pass
self.theta = self.theta.sub(
self.lr.multiply((w.dot(h.sub(Y)).div(R.Scalar(self.leny)))))
while self.theta.status != 'computed':
pass
loss = self.__loss(self.__sigmoid(X.dot(self.theta)), Y)
while loss.status != 'computed':
pass
if (self.verbose == True):
self.losses.append(loss)
print('Iteration : ', i)
def grow_tree(self, X, y, depth=0):
pop_per_class = R.Tensor([])
for c in range(self.num_classes):
pop_per_class = pop_per_class.concat(
R.sum(R.equal(y, R.Scalar(c))).expand_dims())
predicted_class = R.argmax(pop_per_class)
while predicted_class.status != "computed":
pass
node = Node(predicted_class=predicted_class.output, depth=depth)
node.samples = R.shape(y).gather(R.Scalar(0))
if depth < self.max_depth:
col, threshold = self.find_split(X, y)
while threshold.status != "computed":
pass
z = X.shape_()
z1 = y.shape_()
while z1.status != "computed":
pass
if col is not None and threshold.output is not [None]:
indices_left = X.transpose().gather(
R.Scalar(col)).less(threshold)
X_left = X.gather(
R.find_indices(indices_left, R.Tensor(
[1])).reshape(shape=R.sum(indices_left).expand_dims()))
y_left = y.gather(
R.find_indices(indices_left, R.Tensor(
[1])).reshape(shape=R.sum(indices_left).expand_dims()))
indices_right = X.transpose().gather(
R.Scalar(col)).greater_equal(threshold)
X_right = X.gather(
R.find_indices(indices_right, R.Tensor([
1
])).reshape(shape=R.sum(indices_right).expand_dims()))
y_right = y.gather(
R.find_indices(indices_right, R.Tensor([
1
])).reshape(shape=R.sum(indices_right).expand_dims()))
node.feature_index = col
node.threshold = threshold
node.left = self.grow_tree(X_left, y_left, depth + 1)
node.left.leftbranch = True
node.right = self.grow_tree(X_right, y_right, depth + 1)
node.right.rightbranch = True
return node
def __init__(self, lr=0.01, num_iter=10, fit_intercept=True, verbose=True):
self.lr = R.Scalar(lr)
self.num_iter = num_iter
self.fit_intercept = fit_intercept
self.verbose = verbose
self.x_shape1 = None
self.losses = []
self.preds = None
def f1_score(true_labels, pred_labels):
if not isinstance(true_labels, R.Tensor):
y_true = R.Tensor(true_labels)
if not isinstance(pred_labels, R.Tensor):
pred_labels = R.Tensor(pred_labels)
pre = precision(true_labels, pred_labels)
rec = recall(true_labels, pred_labels)
return R.div(R.multiply(R.Scalar(2), R.multiply(pre, rec)),
R.add(pre, rec))
def mean_squared_error(y_true, y_pred):
"""
Mean Squared Error
"""
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)
return R.mean(R.pow(R.sub(y_true, y_pred), R.Scalar(2)))
def root_mean_squared_error(y_true, y_pred):
"""
Root Mean Squared Error
"""
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)
return R.pow(mean_squared_error(y_true, y_pred), R.Scalar(0.5))
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 fit(self, X_train, y_train, alpha=0.01, epoch=1):
self.x, self.y = self.preprocess(X_train, y_train)
self.leny = len(self.y)
print('Starting to Train...')
for j in range(epoch):
loss_sum = R.Scalar(0)
for i in range(len(self.x)):
out = self.f_forward(self.x[i], self.w1, self.w2)
loss_sum = loss_sum.add(self.loss(out, self.y[i]))
self.w1, self.w2 = self.back_prop(self.x[i], self.y[i],
self.w1, self.w2, alpha)
print('Epoch : ', j + 1)
self.acc.append(
R.Scalar(1).sub(loss_sum.div(R.Scalar(len(self.x)))).multiply(
R.Scalar(100)))
self.losses.append(loss_sum.div(R.Scalar(len(self.x))))
while self.w1.status != 'computed':
pass
while self.w2.status != 'computed':
pass
print('Training Complete!')
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 mean_squared_log_error(y_true, y_pred):
"""
Mean Squared Log Error
"""
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)
return R.mean(
R.pow(
R.sub(R.natlog(R.add(y_true, R.one())),
R.natlog(R.add(y_pred, R.one()))), R.Scalar(2)))
def back_prop(x, y, w1, w2, alpha):
# x,y are Tensors
# hiden layer
z1 = x.dot(w1) # input from layer 1
a1 = sigmoid(z1) # output of layer 2
# Output layer
z2 = a1.dot(w2) # input of out layer
a2 = sigmoid(z2) # output of out layer
# error in output layer
d2 = a2.sub(y)
d3 = a1.multiply(R.Scalar(1).sub(a1))
d4 = w2.dot(d2.transpose()).transpose()
d1 = d3.multiply(d4)
# Gradient for w1 and w2
w1_adj = x.transpose().dot(d1)
w2_adj = a1.transpose().dot(d2)
# Updating parameters
w1 = w1.sub(R.Scalar(alpha).multiply(w1_adj))
w2 = w2.sub(R.Scalar(alpha).multiply(w2_adj))
return (w1, w2)
def gradient_descent(self, alpha, num_iters):
alpha_ = R.Scalar(alpha)
for e in range(num_iters):
residual = self.X.dot(self.theta).sub(self.y)
while residual.status != 'computed':
pass
temp = self.theta.sub((alpha_.div(self.m)).multiply(self.X.transpose().dot(residual)))
while temp.status!='computed':
pass
self.theta = temp
print('Iteration : ',e)
op_theta = self.theta()
print('Theta found by gradient descent: intercept={0}, slope={1}'.format(op_theta[0],op_theta[1]))
return self.theta, op_theta[0], op_theta[1]
def __init__(self, id=None, **kwargs):
super().__init__(id=id, **kwargs)
self.__setup_logger()
# Define hyper-parameters
self.learning_rate = R.Scalar(kwargs.get("learning_rate", 0.01), name="learning_rate")
self.iterations = kwargs.get("iterations", 100)
self.X = None
self.y = None
self.W = None
self.b = None
self.no_samples = None
self.no_features = None
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")
import time import ravop.core as R from ravcom import inform_server a = R.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9, 0]) b = R.Scalar(10) c = R.add(a, b) d = R.sub(a, b) e = R.multiply(a, b) f = R.mean(a) g = R.median(a) inform_server() # Wait for 10 seconds time.sleep(10) print(c()) print(d()) print(e()) print(f()) print(g())
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
confusion = R.Tensor(confusion)
if average=='macro':
for i in confusion:
TP ,TN ,FP ,FN = i[0] ,i[1] ,i[2] ,i[3]
Recall = R.div(TP, R.add(TP, FN))
Precision = R.div(TP, R.add(TP, FP))
if Precision == 0 or Recall == 0
or Recall == np.nan or Precision == np.nan:
final.append(0)
else:
F1 = R.div(R.elemul(R.Scalar(2), R.elemul(Recall, Precision)),R.sum(Recall ,Precision))
final.append(F1)
return R.mean(final)
if average=='micro':
confusion = R.Tensor(confusion)
TP = R.sum(confusion ,axis=0)[0]
TN = R.sum(confusion ,axis=0)[1]
FP = R.sum(confusion ,axis=0)[2]
FN = R.sum(confusion ,axis=0)[3]
Recall = R.div(TP, R.add(TP, FN))
Precision = R.div(TP, R.add(TP, FP))
F1 = R.div(R.elemul(R.Scalar(2), R.elemul(Recall, Precision)),R.sum(Recall ,Precision))
def compute_cost(self):
residual = self.X.dot(self.theta).sub(self.y)
while residual.status != 'computed':
pass
return (R.Scalar(1).div(R.Scalar(2).multiply(self.m))).multiply(residual.dot(residual.transpose()))
