def fit(self, X, y):
self._check(X, y)
if dim(y) == 1:
raw_X = X
if self.fit_intercept:
X = hstack([ones(shape(X)[0], 1), X])
beta = zeros(shape(X)[1]) # row vector
X_T = matrix_transpose(X)
if self.fit_intercept:
beta[0] = sum(minus(reshape(y, -1), dot(
raw_X, beta[1:]))) / (shape(X)[0])
for _ in range(self.max_iter):
start = 1 if self.fit_intercept else 0
for j in range(start, len(beta)):
tmp_beta = [x for x in beta]
tmp_beta[j] = 0.0
r_j = minus(reshape(y, -1), dot(X, beta))
# r_j = minus(reshape(y,-1) , dot(X, tmp_beta))
arg1 = dot(X_T[j], r_j)
arg2 = self.alpha * shape(X)[0]
if sum(square(X_T[j])) != 0:
beta[j] = self._soft_thresholding_operator(
arg1, arg2) / sum(square(X_T[j]))
else:
beta[j] = 0
if self.fit_intercept:
beta[0] = sum(
minus(reshape(y, -1), dot(
raw_X, beta[1:]))) / (shape(X)[0])
# # add whatch
# self.beta = beta
# self._whatch(raw_X,y)
if self.fit_intercept:
self.intercept_ = beta[0]
self.coef_ = beta[1:]
else:
self.coef_ = beta
self.beta = beta
return self
elif dim(y) == 2:
if self.fit_intercept:
X = hstack([ones(shape(X)[0], 1), X])
y_t = matrix_transpose(y)
betas = []
for i in range(shape(y)[1]):
betas.append(self._fit(X, y_t[i]))
batas = matrix_transpose(betas)
self.betas = batas
def fit(self, X, y, weights=None):
X, y = self._check(X, y)
if self.fit_intercept:
m, n = shape(X)
bias = ones(m, 1)
X = hstack([bias, X])
eye = identity_matrix(shape(X)[1])
from linalg.matrix import diag
if not self.penalty_bias:
eye[0][0] = 0
# add weights
if weights != None:
assert (len(weights) == shape(X)[0])
X = matrix_matmul(diag(weights), X)
X_T = matrix_transpose(X)
self.W = matrix_matmul(
matrix_matmul(
matrix_inverse(
plus(matrix_matmul(X_T, X),
multiply(eye,
self.alpha * shape(X)[0]))
# plus(matrix_matmul(X_T,X),multiply(eye,self.alpha))
),
X_T),
y)
self.importance_ = sum(self.W, axis=1)
if self.fit_intercept:
self.importance_ = self.importance_[1:]
def predict(self, X):
assert (self.beta != None or self.betas != None)
if self.fit_intercept:
X = hstack([ones(shape(X)[0], 1), X])
if self.beta != None:
return dot(X, self.beta)
else:
return matrix_matmul(X, self.betas)
def predict(self, X):
assert (self.W != None)
if self.fit_intercept:
m, n = shape(X)
bias = ones(m, 1)
X = hstack([bias, X])
result = matrix_matmul(X, self.W)
if self.dim_Y == 1:
result = [x[0] for x in result]
return result
def fit(self, X, y):
X, y = self._check(X, y)
if self.fit_intercept:
m, n = shape(X)
bias = ones(m, 1)
X = hstack([bias, X])
X_T = matrix_transpose(X)
# print matrix_matmul(X_T,X)
self.W = matrix_matmul(
matrix_matmul(matrix_inverse(matrix_matmul(X_T, X)), X_T), y)
def fit(self, X, y):
X, y = self._check(X, y)
if self.fit_intercept:
m, n = shape(X)
bias = ones(m, 1)
X = hstack([bias, X])
eye = identity_matrix(shape(X)[1])
from linalg.matrix import diag
if self.penalty_loss:
eye = diag(self.penalty_loss)
X_T = matrix_transpose(X)
self.W = matrix_matmul(
matrix_matmul(
matrix_inverse(
plus(matrix_matmul(X_T, X),
multiply(eye,
self.alpha * shape(X)[0]))), X_T), y)
self.importance_ = sum(self.W, axis=1)
if self.fit_intercept:
self.importance_ = self.importance_[1:]
],
[
0.0, 2.0, 1.0, 1.0, 4.0, 3.0, 0.0, 7.0, 7.0, 0.0, 7.0, 5.0, 0.0, 1.0,
5.0
],
[
0.0, 0.0, 1.0, 0.0, 3.0, 1.0, 0.0, 4.0, 0.0, 0.0, 3.0, 1.0, 0.0, 8.0,
0.0
],
[
0.0, 2.0, 3.0, 0.0, 4.0, 8.0, 1.0, 14.0, 1.0, 0.0, 14.0, 0.0, 0.0,
4.0, 0.0
],
[
2.0, 4.0, 1.0, 1.0, 4.0, 0.0, 4.0, 12.0, 6.0, 0.0, 3.0, 9.0, 1.0, 4.0,
1.0
],
[
1.0, 2.0, 1.0, 0.0, 3.0, 3.0, 11.0, 28.0, 8.0, 4.0, 4.0, 1.0, 0.0,
0.0, 0.0
]]
# print(shift(A,1))
print(shape(vstack([A])))
print(shape(vstack([A, A, A])))
print(vstack([A, A, A]))
print(shape(hstack([A])))
print(shape(hstack([A, shift(A, 1), A])))
print(hstack([A, shift(A, 1), A]))
def features_building(ecs_logs,flavors_config,flavors_unique,training_start_time,training_end_time,predict_start_time,predict_end_time):
mapping_index = get_flavors_unique_mapping(flavors_unique)
predict_days = (predict_end_time-predict_start_time).days
sample = resampling(ecs_logs,flavors_unique,training_start_time,predict_start_time,frequency=predict_days,strike=1,skip=0)
def outlier_handling(sample,method='mean',max_sigma=3):
assert(method=='mean' or method=='zero' or method=='dynamic')
sample = matrix_copy(sample)
std_ = stdev(sample)
mean_ = mean(sample,axis=1)
for i in range(shape(sample)[0]):
for j in range(shape(sample)[1]):
if sample[i][j]-mean_[j] >max_sigma*std_[j]:
if method=='mean':
sample[i][j] = mean_[j]
elif method=='zero':
sample[i][j] = 0
elif method=='dynamic':
sample[i][j] = (sample[i][j] + mean_[j])/2.0
return sample
sample = outlier_handling(sample,method='mean',max_sigma=3)
# sample = exponential_smoothing(sample,alpha=0.2)
Ys = sample[1:]
def flavor_clustering(sample,k=3,variance_threshold=None):
corrcoef_sample = corrcoef(sample)
clustering_paths = []
for i in range(shape(sample)[1]):
col = corrcoef_sample[i]
col_index_sorted = argsort(col)[::-1]
if variance_threshold!=None:
col_index_sorted = col_index_sorted[1:]
index = [i for i in col_index_sorted if col[i]>variance_threshold]
else:
index = col_index_sorted[1:k+1]
clustering_paths.append(index)
return clustering_paths,corrcoef_sample
# adjustable # 1
variance_threshold = 0.6 #76.234
clustering_paths,coef_sample = flavor_clustering(sample,variance_threshold=variance_threshold)
def get_feature_grid(sample,i,fill_na='mean',max_na_rate=1,col_count=None,with_test=True):
assert(fill_na=='mean' or fill_na=='zero')
col = fancy(sample,None,i)
R = []
for j in range(len(col)):
left = [None for _ in range(len(col)-j)]
right = col[:j]
r = []
r.extend(left)
r.extend(right)
R.append(r)
def _mean_with_none(A):
if len(A)==0:
return 0
else:
count = 0
for i in range(len(A)):
if A[i]!=None:
count+=A[i]
return count/float(len(A))
means = []
for j in range(shape(R)[1]):
means.append(_mean_with_none(fancy(R,None,j)))
width = int((1-max_na_rate) * shape(R)[1])
R = fancy(R,None,(width,))
for _ in range(shape(R)[0]):
for j in range(shape(R)[1]):
if R[_][j]==None:
if fill_na=='mean':
R[_][j] = means[j]
elif fill_na=='zero':
R[_][j]=0
if with_test:
if col_count!=None:
return fancy(R,None,(-col_count,))
else:
return R
else:
if col_count!=None:
return fancy(R,(0,-1),(-col_count,))
else:
return R[:-1]
# def get_rate_X(sample,j):
# sum_row = sum(sample,axis=1)
# A = [sample[i][j]/float(sum_row[i]) if sum_row[i]!=0 else 0 for i in range(shape(sample)[0])]
# return A
# def get_cpu_rate_X(sample,i):
# cpu_config,mem_config = get_machine_config(flavors_unique)
# sample_copy = matrix_copy(sample)
# for i in range(shape(sample_copy)[0]):
# for j in range(shape(sample_copy)[1]):
# sample_copy[i][j] *= cpu_config[j]
# sample = sample_copy
# sum_row = sum(sample,axis=1)
# A = [sample[i][j]/float(sum_row[i]) if sum_row[i]!=0 else 0 for i in range(shape(sample)[0])]
# return A
# def get_men_rate_X(sample,i):
# cpu_config,mem_config = get_machine_config(flavors_unique)
# sample_copy = matrix_copy(sample)
# for i in range(shape(sample_copy)[0]):
# for j in range(shape(sample_copy)[1]):
# sample_copy[i][j] *= mem_config[j]
# sample = sample_copy
# sum_row = sum(sample,axis=1)
# A = [sample[i][j]/float(sum_row[i]) if sum_row[i]!=0 else 0 for i in range(shape(sample)[0])]
# return A
X_trainS,Y_trainS,X_test_S = [],[],[]
# adjustable # 2
col_count = 5 # n_feature
for f in flavors_unique:
X = get_feature_grid(sample,mapping_index[f],col_count=col_count,fill_na='mean',max_na_rate=1,with_test=True)
X_test = X[-1:]
X = X[:-1]
y = fancy(Ys,None,(mapping_index[f],mapping_index[f]+1))
clustering = True
# 1.data clustering
if clustering:
print(clustering_paths[mapping_index[f]])
# improve weights of X and y
X.extend(X)
y.extend(y)
for cluster_index in clustering_paths[mapping_index[f]]:
X_cluster = get_feature_grid(sample,mapping_index[f],col_count=col_count,fill_na='mean',max_na_rate=1,with_test=False)
y_cluster = fancy(Ys,None,(cluster_index,cluster_index+1))
w = coef_sample[mapping_index[f]][cluster_index]
# important
X_cluster = apply(X_cluster,lambda x:x*w)
y_cluster = apply(y_cluster,lambda x:x*w)
X.extend(X_cluster)
y.extend(y_cluster)
# do not delete
X.extend(X_test)
# --------------------------------------------------------- #
add_list= [X]
# add_list = []
# add_list.extend([sqrt(X)])
add_list.extend([apply(X,lambda x:math.log1p(x))]) # important
X = hstack(add_list)
# --------------------------------------------------------- #
def multi_exponential_smoothing(A,list_of_alpha):
R = A
for a in list_of_alpha:
R = exponential_smoothing(R,alpha=a)
return R
# #adjustable #3 smoothing degree
# # 77.291 3
# # 77.405 no.63
# depth = 3
# #adjustable #4 smoothing weights
# # base = [0.3,0.5,0.7,0.8] # 3.0.6,0.7,0.8 77.163
# # base = [0.1,0.3,0.5] # 3.0.6,0.7,0.8 77.163
base = [0.6,0.7,0.8]
depth = 3
# base = [0.7,0.8,0.9]
alphas = [[ base[i] for _ in range(depth)]for i in range(len(base))]
X_data_list = [multi_exponential_smoothing(X[:-1],a) for a in alphas]
Y_data_list = [multi_exponential_smoothing(y,a) for a in alphas]
X_data_list.extend([X])
Y_data_list.extend([y])
X = vstack(X_data_list)
y = vstack(Y_data_list)
# # # --------------------------------------------------------- #
# -----------------------------------------------------------#
y = flatten(y)
X = normalize(X,y=y,norm='l1')
assert(shape(X)[0]==shape(y)[0]+1)
X_trainS.append(X[:-1])
X_test_S.append(X[-1:])
Y_trainS.append(y)
return X_trainS,Y_trainS,X_test_S
def predict_flavors(ecs_logs, flavors_config, flavors_unique, training_start,
training_end, predict_start, predict_end):
predict_days = (predict_end - predict_start).days #check
hours = ((predict_end - predict_start).seconds / float(3600))
if hours >= 12:
predict_days += 1
skip_days = (predict_start - training_end).days
# print(skip_days) #checked
# print(predict_days) #checked
# sample = resampling(ecs_logs,flavors_unique,training_start,training_end,frequency=predict_days,strike=predict_days,skip=0)
sample = resampling(ecs_logs,
flavors_unique,
training_start,
training_end,
frequency=1,
strike=1,
skip=0)
def outlier_handling(sample, method='mean', max_sigma=3):
assert (method == 'mean' or method == 'dynamic')
std_ = stdev(sample)
mean_ = mean(sample, axis=0)
for i in range(shape(sample)[0]):
for j in range(shape(sample)[1]):
if sample[i][j] - mean_[j] > max_sigma * std_[j]:
if method == 'mean':
sample[i][j] = mean_[j]
elif method == 'dynamic':
if i < len(sample) / 2.0:
sample[i][j] = (mean_[j] + sample[i][j]) / 2.0
return sample
# sample = outlier_handling(sample,method='dynamic',max_sigma=3)
# sample = outlier_handling(sample,method='mean',max_sigma=3.5)
# from preprocessing import exponential_smoothing
# sample = exponential_smoothing(exponential_smoothing(sample,alpha=0.2),alpha=0.2)
skip_days -= 1
prediction = []
for i in range(shape(sample)[1]):
clf = Ridge(alpha=1, fit_intercept=True)
X = reshape(list(range(len(sample))), (-1, 1))
y = fancy(sample, None, (i, i + 1))
X_test = reshape(
list(range(len(sample),
len(sample) + skip_days + predict_days)), (-1, 1))
X_list = [X]
X = hstack(X_list)
X_test_list = [X_test]
X_test = hstack(X_test_list)
clf.fit(X, y)
p = clf.predict(X_test)
prediction.append(sum(flatten(p)))
prediction = [int(round(p)) if p > 0 else 0 for p in prediction]
return prediction
