def predict_diagonal(trainSet,
testSet,
dim=5,
tau=2,
epsilon=0.7,
lambd=3,
percent=0.6,
distNorm=1,
titleOfGraph='Pretty Girl',
figureName='GrilLikeYou',
pathSaveFigure=None):
# # vectors_train = data['train_data']
# dim = 5 #data['dim']
# tau = 2 #data['tau']
# percent = 0.6 #data['percent']
# # curve_number = data['curve_number']
# epsilon = 0.7 #data['epsilon']
# lambd = 2 #data['lambd']
vectors_train_1 = []
for i in range(len(trainSet) - (dim - 1) * tau):
vectors_train_1.append(state_phase(trainSet, i, dim, tau))
#tách statephases
vectors_test_1 = []
for i in range(len(testSet) - (dim - 1) * tau):
vectors_test_1.append(state_phase(testSet, i, dim, tau))
#ép kiểu về array
vectors_train_1 = np.array(vectors_train_1)
vectors_test_1 = np.array(vectors_test_1)
# print("train.shape: ", vectors_train_1.shape)
# r_dist là ma trận khoảng cách
# cdist là hàm trong numpy
# minkowski là cách tính
# p là norm
# y là train: đánh số từ trên xuống dưới
# x là test
r_dist = cdist(vectors_train_1, vectors_test_1, 'minkowski', p=distNorm)
# epsilon = r_dist.min()
# print("r_dist:",r_dist)
print('vectors_train.shape: ', vectors_train_1.shape) #in ra shape
print('vectors_test.shape: ', vectors_test_1.shape)
print('r_dist.shape: ', r_dist.shape)
print('r_dist min', r_dist.min())
print('epsilon: ', epsilon)
print('r_dist max', r_dist.max())
print('lambd: ', lambd)
# predict_label = np.zeros((testing_well_ts[:, -1].shape[0], ), dtype=int)
# indx_vectors_timeseries_test = indx_vectors_timeseries_test.reshape((vectors_test.shape[0], dim))
# predict_label = np.zeros(len(testSet),dtype=int)
#r1 là ma trận -2|-1 thay vì ma trận 01 như crp
#-2 là false
#-1 là true
#r_dist < epsilon trả về ma trận 01, 1 tại điểm r_dist < epsilon
#ma trận này trừ đi 2 thì thành ma trận -2|-1
r1 = np.array((r_dist < epsilon) - 2)
# r1 = np.array(r1 - 2)
f_crp = myCrpFunctions.crossRecurrencePlots("CRP", r1, dotSize=0.2)
plt.show()
len_r1 = int(np.size(r1[0]))
high_r1 = int(np.size(r1) / len_r1)
#x is an array whose each element is a diagonal of the crp matrix
#Đoạn này lấy ra những đoạn đường chéo có số lượng predict liền nhau lớn hơn lamdb
#Mỗi phần tử của diagonals_have_predict là một mảng chứa đúng 1 đoạn trùng với train tương ứng đúng vị trí
diagonals_have_predict = []
for index_diagonal in range(-(high_r1 - lambd + 1), len_r1 - lambd + 2, 1):
offset = index_diagonal
#---offset = x - y
y = -offset if (index_diagonal < 0) else 0
while (y < high_r1 and y + offset < len_r1):
if (r1[y][y + offset] == -1):
start = y
while (y + 1 < high_r1 and y + 1 + offset < len_r1
and r1[y + 1][y + 1 + offset] == -1):
y += 1
if (y - start + 1 >= lambd):
predicts = np.full(y + 1, -2)
for index in range(start, y + 1, 1):
predicts[index] = index + offset
diagonals_have_predict.append(predicts)
y += 1
#Mảng quy đổi về index của dữ liệu test từ index của statePhrase
#
indexSampleOrigin = diagonals_have_predict
for i_row in range(len(indexSampleOrigin)):
for i_in_1_State in range(len(indexSampleOrigin[i_row])):
if (indexSampleOrigin[i_row][i_in_1_State] >= 0):
#Chọn số index state cuối cùng
if ((i_in_1_State == len(indexSampleOrigin[i_row]) - 1)
or (indexSampleOrigin[i_row][i_in_1_State + 1] < 0)):
for j in range(((int(dim * percent)) - 1) * tau):
indexSampleOrigin[i_row] = np.insert(
indexSampleOrigin[i_row], i_in_1_State + j + 1,
indexSampleOrigin[i_row][i_in_1_State] + j + 1)
# Lấy giá trị từ index của sample trong testSet
valueOfSample = []
for i in range(len(indexSampleOrigin)):
arr = []
for j in range(len(indexSampleOrigin[i])):
if (indexSampleOrigin[i][j] < 0):
arr.append(None)
else:
arr.append(testSet[indexSampleOrigin[i][j]])
try:
shapePredict[indexSampleOrigin[i][j]] = shape
except (IndexError):
print(
"^v^v^v^v^v^v^v^v^v^v^v^v^v^v^indexError: {} ^v^v^v^v^v^v^v^v^v^v^v^v^v^v^"
% (indexSampleOrigin[i][j]))
valueOfSample.append(arr)
# print(valueOfSample)
# testSetPr = SyncPredictToTestArr(index_timeseries_test, testSet)
f_line = plt.figure(figureName, figsize=(12.8, 7.2), dpi=100)
print("_________num predict: ", len(valueOfSample))
if (len(valueOfSample) > 0):
# f_line.set_size_inches(1080, 720)
for i in range(0, len(valueOfSample)):
plt.plot(valueOfSample[i], ':', label=i)
plt.plot(trainSet, 'r', label='train')
plt.legend(loc=0)
plt.xlabel('index')
plt.ylabel('feature')
titleOfGraph = titleOfGraph + " - lamb_" + str(
lambd) + ' - minkowski_' + str(distNorm) + " - numPredict_" + str(
len(valueOfSample))
plt.title(titleOfGraph)
if (pathSaveFigure != None):
plt.savefig(pathSaveFigure, dpi=200)
# plt.ylim(ymin = min(trainSet) - 0.09)
# plt.show()
return f_line
def predict_diagonal(trainSet, testSet, dim=5, tau=2, epsilon=0.7, lambd=3, percent=0.6, titleOfGraph = 'Pretty Girl'):
# # vectors_train = data['train_data']
# dim = 5 #data['dim']
# tau = 2 #data['tau']
# percent = 0.6 #data['percent']
# # curve_number = data['curve_number']
# epsilon = 0.7 #data['epsilon']
# lambd = 2 #data['lambd']
vectors_train_1 = []
for i in range(len(trainSet)-(dim-1)*tau):
vectors_train_1.append(state_phase(trainSet, i, dim, tau))
#tách statephases
vectors_test_1 = []
for i in range(len(testSet)-(dim-1)*tau):
vectors_test_1.append(state_phase(testSet, i, dim, tau))
#ép kiểu về array
vectors_train_1 = np.array(vectors_train_1)
vectors_test_1 = np.array(vectors_test_1)
print("train.shape: ", vectors_train_1.shape)
# r_dist là ma trận khoảng cách
# cdist là hàm trong numpy
# minkowski là cách tính
# p là norm
# y là train: đánh số từ trên xuống dưới
# x là test
r_dist = cdist(vectors_train_1, vectors_test_1, 'minkowski', p=1)
# print("r_dist:",r_dist)
print('vectors_train.shape: ', vectors_train_1.shape) #in ra shape
print('vectors_test.shape: ', vectors_test_1.shape)
print('r_dist.shape: ', r_dist.shape)
print('r_dist min', r_dist.min())
print('epsilon: ', epsilon)
print('r_dist max', r_dist.max())
print('lambd: ', lambd)
# predict_label = np.zeros((testing_well_ts[:, -1].shape[0], ), dtype=int)
# indx_vectors_timeseries_test = indx_vectors_timeseries_test.reshape((vectors_test.shape[0], dim))
predict_label = np.zeros(len(testSet),dtype=int)
#r1 là ma trận 01
r1 = np.array(r_dist < epsilon)
# r1 = np.array(r1 - 2)
print(r1)
f_crp = myCrpFunctions.crossRecurrencePlots("CRP", r1, dotSize = 0.2)
len_r1 = int(np.size(r1[0]))
high_r1 = int(np.size(r1)/len_r1)
#x is an array whose each element is a diagonal of the crp matrix
diagonalsMatrix = []
for offset in range(-high_r1+1, len_r1):
diagonalsMatrix.append(np.array(np.diagonal(r1, offset), dtype=int))
print(diagonalsMatrix[len(diagonalsMatrix)-1])
# print(x)
f_crp = myCrpFunctions.crossRecurrencePlots("CRP2", diagonalsMatrix, dotSize = 0.2)
index_vecto = []
#index_vecto là index của các statePhase trong ma trận r_dist
#đoạn dưới là lấy vị trí statePhase test cho index_vecto từ ma trận đường chéo
for i_row in range(len(diagonalsMatrix)):
lenn = np.size(diagonalsMatrix[i_row])
i = 0
while i<lenn:
if (diagonalsMatrix[i_row][i] == 1):
start = i
while (i<lenn-1 and diagonalsMatrix[i_row][i+1] == 1 ):
i+=1
if (i-start+1 > lambd):
for temp in range(i-start+1):
if (i_row < high_r1):
index_vecto.append(start+temp)
else:
index_vecto.append(i_row - high_r1 + start + 1 + temp)
i+=1
print("------------------------------------------\n",
index_vecto,
"\n------------------------------------------")
#lọc y
index_vecto.sort()
index_vecto = filter_sort(index_vecto)
#index của cái feature ban đầu
index_timeseries_test = []
#đoạn này chuyển lại statephase thành feature
for i in index_vecto:
for j in range(((int(dim*percent))-1)*tau + 1):
index_timeseries_test.append(i+j)
#lọc
index_timeseries_test.sort()
index_timeseries_test = filter_sort(index_timeseries_test)
#khởi tạo label
for i in index_timeseries_test:
predict_label[i] = 1
print('predict_label:', predict_label)
print('num predict: ', np.sum(predict_label))
testSetPr = SyncPredictToTestArr(index_timeseries_test, testSet)
f_line = plt.figure("line")
for i in range(1, np.size(testSetPr)):
plt.plot(testSetPr[i], ':', label=i)
plt.plot(trainSet, 'r', label='train')
plt.legend(loc=0)
plt.xlabel('index')
plt.ylabel('feature')
plt.title(titleOfGraph)
# plt.show()
return predict_label.ravel().tolist()
def rqaCalculate(rpBinaryMatrix, keyDot = 1, lambd = 2, typeReturn = 'array', showCRP = 0):
import math
len_rpBinaryMatrix = int(np.size(rpBinaryMatrix[0]))
N = high_rpBinaryMatrix = int(np.size(rpBinaryMatrix)/len_rpBinaryMatrix)
content = []
for y in range(high_rpBinaryMatrix):
s = ";".join(str(i+2) for i in rpBinaryMatrix[y] )
s += "\n"
content.append(s)
myCrpFunctions.writeContentToFile('rqaOut.csv', content)
RR =0
DET = 0
LAM = 0
RATIO = 0
averageL = 0
averageH = 0
DIV = 0
ENTR = 0
TT = 0
# Duyệt các đường cao
Ph, Hmax, averageTime1, averageTime2 = getPverticalLengthDot(rpBinaryMatrix, high_rpBinaryMatrix, len_rpBinaryMatrix, keyDot = keyDot)
#Đếm số đường chéo theo độ dài
Pl, Lmax = getPdiagonalLengthDot(rpBinaryMatrix, high_rpBinaryMatrix, len_rpBinaryMatrix, keyDot = keyDot)
num_L = 0
num_H = 0
sum_Well_L = 0
sum_Well_H = 0
num_Well_L = 0
num_Well_H = 0
sumDot = Ph[0] # Đếm số điểm chấm theo đường thẳng, ph[0] là những đoạn chỉ có 1 chấm
lmin = lambd - 1
for i in range(1, N+1, 1):
sumDot += (i+1)*Ph[i]
num_L += Pl[i]
num_H += Ph[i]
if (i>=lmin):
sum_Well_L += Pl[i]*i
sum_Well_H += Ph[i]*i
num_Well_L += Pl[i]
num_Well_H += Ph[i]
RR = sumDot/(N**2)
if num_L*num_Well_L > 0:
DET = num_Well_L/num_L
averageL = sum_Well_L/num_Well_L
if (DET > 0):
RATIO = DET/RR
if num_H*num_Well_H > 0:
LAM = num_Well_H/num_H
averageH = sum_Well_H/num_Well_H
for i in range(lmin, N, 1):
if (Pl[i] > 0):
pl = Pl[i]/num_Well_L
ENTR -= pl*math.log(pl)
if Lmax > 0:
DIV = 1/Lmax
if (showCRP == 1):
import matplotlib.pyplot as plt
x = myCrpFunctions.crossRecurrencePlots("test", rpBinaryMatrix, keyDot = keyDot, dotSize = 10 )
plt.show()
print(RR)
print(DET)
print(LAM)
print("averageL, averageH", averageL, averageH)
print(Lmax, Hmax)
print(DIV)
print(ENTR)
print("averageTime1, averageTime2", averageTime1, averageTime2)
if (typeReturn == 'array'):
return [RR, DET, LAM, RATIO, averageL, averageH, Lmax, Hmax, DIV, ENTR, averageTime1, averageTime2]
if (typeReturn == 'dict'):
return {
"RR" : RR,
"DET" : DET,
"LAM" : LAM,
"RATIO" : RATIO,
"averageL" : averageL,
"averageH" : averageH,
"Lmax" : Lmax,
"Hmax" : Hmax,
"DIV" : DIV,
"ENTR" : ENTR,
"averageTime1" : averageTime1,
"averageTime2" : averageTime2
}