def merge_crossover(ind1, ind2):
"""Merge shapelets from one set with shapelets from the other"""
# Construct a pairwise similarity matrix using GAK
_all = list(ind1) + list(ind2)
similarity_matrix = cdist_gak(ind1, ind2, sigma=sigma_gak(_all))
# Iterate over shapelets in `ind1` and merge them with shapelets
# from `ind2`
for row_idx in range(similarity_matrix.shape[0]):
# Remove all elements equal to 1.0
mask = similarity_matrix[row_idx, :] != 1.0
non_equals = similarity_matrix[row_idx, :][mask]
if len(non_equals):
# Get the timeseries most similar to the one at row_idx
max_col_idx = np.argmax(non_equals)
ts1 = list(ind1[row_idx]).copy()
ts2 = list(ind2[max_col_idx]).copy()
# Merge them and remove nans
ind1[row_idx] = euclidean_barycenter([ts1, ts2])
ind1[row_idx] = ind1[row_idx][~np.isnan(ind1[row_idx])]
# Apply the same for the elements in ind2
for col_idx in range(similarity_matrix.shape[1]):
mask = similarity_matrix[:, col_idx] != 1.0
non_equals = similarity_matrix[:, col_idx][mask]
if len(non_equals):
max_row_idx = np.argmax(non_equals)
ts1 = list(ind1[max_row_idx]).copy()
ts2 = list(ind2[col_idx]).copy()
ind2[col_idx] = euclidean_barycenter([ts1, ts2])
ind2[col_idx] = ind2[col_idx][~np.isnan(ind2[col_idx])]
return ind1, ind2
def random_merge_crossover(ind1, ind2, p=0.25):
"""Merge shapelets from one set with shapelets from the other"""
# Construct a pairwise similarity matrix using GAK
new_ind1, new_ind2 = [], []
np.random.shuffle(ind1)
np.random.shuffle(ind2)
for shap1, shap2 in zip(ind1, ind2):
if len(shap1) > 4 and len(shap2) > 4 and np.random.random() < p:
max_size = min(len(shap1), len(shap2))
merge_len = np.random.randint(1, max_size)
shap1_start = np.random.randint(len(shap1) - merge_len)
shap2_start = np.random.randint(len(shap2) - merge_len)
shap1 = np.concatenate(
(shap1[:shap1_start].flatten(),
euclidean_barycenter([
shap1[shap1_start:shap1_start + merge_len],
shap2[shap2_start:shap2_start + merge_len]
]).flatten(), shap1[shap1_start + merge_len:].flatten()))
shap2 = np.concatenate(
(shap2[:shap2_start].flatten(),
euclidean_barycenter([
shap1[shap1_start:shap1_start + merge_len],
shap2[shap2_start:shap2_start + merge_len]
]).flatten(), shap2[shap2_start + merge_len:].flatten()))
new_ind1.append(shap1)
new_ind2.append(shap2)
return new_ind1, new_ind2
def merge(ts1, ts2):
if len(ts1) > len(ts2):
start = np.random.randint(len(ts1) - len(ts2))
centroid = euclidean_barycenter([ts1[start:start + len(ts2):],
ts2]).flatten()
elif len(ts2) > len(ts1):
start = np.random.randint(len(ts2) - len(ts1))
centroid = euclidean_barycenter([ts2[start:start + len(ts1):],
ts1]).flatten()
else:
start = 0
centroid = euclidean_barycenter([ts1, ts2]).flatten()
return centroid, start
def caculate_mid_centers(class_num, iter_num, input_len):
for i in range(class_num):
first_filename = "....\src\LSTM\start_point_0\class" + str(
i) + "_train.csv"
first_train_data = load_data(first_filename)
# 迭代的数据合并求簇心
# concat_data = []
# for j in range(iter_num):
# inter_filename = "....\src\LSTM\\result\\number"+str(j)+"_class"+str(i)+"_train.csv"
# inter_data = load_data(inter_filename)
# if j == 0:
# concat_data = np.vstack((first_train_data, inter_data))
# # concat_data = inter_data
# else:
# concat_data = np.vstack((concat_data, inter_data))
# # centers = softdtw_barycenter(concat_data, gamma=1.0, max_iter=5)
# centers = euclidean_barycenter(concat_data)
# centers = pd.DataFrame(np.reshape(centers, (1, len(centers))))
# centers.to_csv("D:\研究生\实验室\云环境下时间预测\代码\时间序列聚类\src\LSTM\\result\\number"+str(j)+"_class"+str(i)+"_centers.csv")
# 每次迭代的数据单独求簇心
for j in range(iter_num):
inter_filename = "....\src\LSTM\\result\\number" + str(
j) + "_class" + str(i) + "_train.csv"
inter_data = load_data(inter_filename)[:, :input_len]
print(inter_data.shape)
# centers = softdtw_barycenter(inter_data, gamma=1.0, max_iter=5)
centers = euclidean_barycenter(inter_data)
centers = pd.DataFrame(np.reshape(centers, (1, len(centers))))
centers.to_csv("....\src\LSTM\\result\\number" + str(j) +
"_class" + str(i) + "_centers.csv")
def _update_centroids(self, X):
if self.metric_params is None:
metric_params = {}
else:
metric_params = self.metric_params.copy()
if "gamma_sdtw" in metric_params.keys():
metric_params["gamma"] = metric_params["gamma_sdtw"]
del metric_params["gamma_sdtw"]
for k in range(self.n_clusters):
if self.metric == "dtw":
self.cluster_centers_[k] = dtw_barycenter_averaging(
X=X[self.labels_ == k],
barycenter_size=None,
init_barycenter=self.cluster_centers_[k],
metric_params=metric_params,
verbose=False)
elif self.metric == "softdtw":
self.cluster_centers_[k] = softdtw_barycenter(
X=X[self.labels_ == k],
max_iter=self.max_iter_barycenter,
init=self.cluster_centers_[k],
**metric_params)
else:
self.cluster_centers_[k] = euclidean_barycenter(
X=X[self.labels_ == k])
def calculate_test_mse_center(class_num):
root_path = '....\src\LSTM\\test_result'
for i in range(class_num):
filename = 'mse_test_' + str(i) + '.csv'
data = pd.read_csv(os.path.join(root_path, filename))
data = pd.DataFrame(data).values[:, 1:]
# center = softdtw_barycenter(data, gamma=1.0, max_iter=5)
center = euclidean_barycenter(data)
plt.plot(center)
plt.title('Cluster' + str(i))
plt.show()
def _update_centroids(self, X):
metric_params = self._get_metric_params()
for k in range(self.n_clusters):
if self.metric == "dtw":
self.cluster_centers_[k] = dtw_barycenter_averaging(
X=X[self.labels_ == k],
barycenter_size=None,
init_barycenter=self.cluster_centers_[k],
metric_params=metric_params,
verbose=False)
elif self.metric == "softdtw":
self.cluster_centers_[k] = softdtw_barycenter(
X=X[self.labels_ == k],
max_iter=self.max_iter_barycenter,
init=self.cluster_centers_[k],
**metric_params)
else:
self.cluster_centers_[k] = euclidean_barycenter(
X=X[self.labels_ == k])
import numpy
import matplotlib.pyplot as plt
from tslearn.barycenters import euclidean_barycenter, dtw_barycenter_averaging, softdtw_barycenter
from tslearn.datasets import CachedDatasets
numpy.random.seed(0)
X_train, y_train, X_test, y_test = CachedDatasets().load_dataset("Trace")
X = X_train[y_train == 2]
plt.figure()
plt.rcParams['font.sans-serif'] = ['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False #用来正常显示负号
plt.subplot(3, 1, 1)
for ts in X:
plt.plot(ts.ravel(), "k-", alpha=.2)
plt.plot(euclidean_barycenter(X).ravel(), "r-", linewidth=2)
plt.title("算数平均序列求解")
plt.subplot(3, 1, 2)
sdtw_bar = softdtw_barycenter(X, gamma=1., max_iter=100)
for ts in X:
plt.plot(ts.ravel(), "k-", alpha=.2)
plt.plot(sdtw_bar.ravel(), "r-", linewidth=2)
plt.title("DBA平均序列求解")
plt.tight_layout()
plt.show()
length_of_sequence = X.shape[1]
def plot_helper(barycenter):
# plot all points of the data set
for series in X:
plt.plot(series.ravel(), "k-", alpha=.2)
# plot the given barycenter of them
plt.plot(barycenter.ravel(), "r-", linewidth=2)
# plot the four variants with the same number of iterations and a tolerance of
# 1e-3 where applicable
ax1 = plt.subplot(4, 1, 1)
plt.title("Euclidean barycenter")
plot_helper(euclidean_barycenter(X))
plt.subplot(4, 1, 2, sharex=ax1)
plt.title("DBA (vectorized version of Petitjean's EM)")
plot_helper(dtw_barycenter_averaging(X, max_iter=50, tol=1e-3))
plt.subplot(4, 1, 3, sharex=ax1)
plt.title("DBA (subgradient descent approach)")
plot_helper(dtw_barycenter_averaging_subgradient(X, max_iter=50, tol=1e-3))
plt.subplot(4, 1, 4, sharex=ax1)
plt.title("Soft-DTW barycenter ($\gamma$=1.0)")
plot_helper(softdtw_barycenter(X, gamma=1., max_iter=50, tol=1e-3))
# clip the axes for better readability
ax1.set_xlim([0, length_of_sequence])