超参数调整 k 均值聚类
Hyperparameter Tuning k-means clustering
我正在尝试通过在带有决策树分类器的管道中使用它来对时空 K-Means 聚类执行超参数调整。其思想是使用 K-Means 聚类算法生成聚类距离 space 矩阵和聚类标签，然后将其传递给决策树分类器。对于超参数调整，只需使用 K-Means 算法的参数即可。
我正在使用 Python 3.8 和 sklearn 0.22.
我感兴趣的数据有3个columns/attributes：time、x和y（x和y是空间坐标）。
密码是：
class ST_KMeans():
"""
Note that the K-means clustering algorithm is designed for Euclidean distances.
It may stop converging with other distances when the mean is no longer a
best estimation for the cluster 'center'.
The 'mean' minimizes squared differences (or, squared Euclidean distance).
If you want a different distance function, you need to replace the mean with
an appropriate center estimation.
Parameters:
k: number of clusters
eps1 : float, default=0.5
The spatial density threshold (maximum spatial distance) between
two points to be considered related.
eps2 : float, default=10
The temporal threshold (maximum temporal distance) between two
points to be considered related.
metric : string default='euclidean'
The used distance metric - more options are
‘braycurtis’, ‘canberra’, ‘chebyshev’, ‘cityblock’, ‘correlation’,
‘cosine’, ‘dice’, ‘euclidean’, ‘hamming’, ‘jaccard’, ‘jensenshannon’,
‘kulsinski’, ‘mahalanobis’, ‘matching’, ‘rogerstanimoto’, ‘sqeuclidean’,
‘russellrao’, ‘seuclidean’, ‘sokalmichener’, ‘sokalsneath’, ‘yule’.
n_jobs : int or None, default=-1
The number of processes to start; -1 means use all processors (BE AWARE)
Attributes:
labels : array, shape = [n_samples]
Cluster labels for the data - noise is defined as -1
"""
def __init__(self, k, eps1 = 0.5, eps2 = 10, metric = 'euclidean', n_jobs = 1):
self.k = k
self.eps1 = eps1
self.eps2 = eps2
# self.min_samples = min_samples
self.metric = metric
self.n_jobs = n_jobs
def fit(self, X):
"""
Apply the ST K-Means algorithm
X : 2D numpy array. The first attribute of the array should be time attribute
as float. The following positions in the array are treated as spatial
coordinates.
The structure should look like this [[time_step1, x, y], [time_step2, x, y]..]
For example 2D dataset:
array([[0,0.45,0.43],
[0,0.54,0.34],...])
Returns:
self
"""
# check if input is correct
X = check_array(X)
# type(X)
# numpy.ndarray
# Check arguments for DBSCAN algo-
if not self.eps1 > 0.0 or not self.eps2 > 0.0:
raise ValueError('eps1, eps2, minPts must be positive')
# Get dimensions of 'X'-
# n - number of rows
# m - number of attributes/columns-
n, m = X.shape
# Compute sqaured form Euclidean Distance Matrix for 'time' and spatial attributes-
time_dist = squareform(pdist(X[:, 0].reshape(n, 1), metric = self.metric))
euc_dist = squareform(pdist(X[:, 1:], metric = self.metric))
'''
Filter the euclidean distance matrix using time distance matrix. The code snippet gets all the
indices of the 'time_dist' matrix in which the time distance is smaller than 'eps2'.
Afterward, for the same indices in the euclidean distance matrix the 'eps1' is doubled which results
in the fact that the indices are not considered during clustering - as they are bigger than 'eps1'.
'''
# filter 'euc_dist' matrix using 'time_dist' matrix-
dist = np.where(time_dist <= self.eps2, euc_dist, 2 * self.eps1)
# Initialize K-Means clustering model-
self.kmeans_clust_model = KMeans(
n_clusters = self.k, init = 'k-means++',
n_init = 10, max_iter = 300,
precompute_distances = 'auto', algorithm = 'auto')
# Train model-
self.kmeans_clust_model.fit(dist)
self.labels = self.kmeans_clust_model.labels_
self.X_transformed = self.kmeans_clust_model.fit_transform(X)
return self
def transform(self, X):
# print("\nX.shape = {0}\n".format(X.shape))
# pass
# return self.kmeans_clust_model.fit_transform(X)
return self.X_transformed
# Initialize ST-K-Means object-
st_kmeans_algo = ST_KMeans(
k = 5, eps1=0.6,
eps2=9, metric='euclidean',
n_jobs=1
)
# Train on a chunk of dataset-
st_kmeans_algo.fit(data.loc[:500, ['time', 'x', 'y']])
# Get clustered data points labels-
kmeans_labels = st_kmeans_algo.labels
kmeans_labels.shape
# (501,)
# Get labels for points clustered using trained model-
kmeans_transformed = st_kmeans_algo.X_transformed
kmeans_transformed.shape
# (501, 5)
dtc = DecisionTreeClassifier()
dtc.fit(kmeans_transformed, kmeans_labels)
y_pred = dtc.predict(kmeans_transformed)
# Get model performance metrics-
accuracy = accuracy_score(kmeans_labels, y_pred)
precision = precision_score(kmeans_labels, y_pred, average='macro')
recall = recall_score(kmeans_labels, y_pred, average='macro')
print("\nDT model metrics are:")
print("accuracy = {0:.4f}, precision = {1:.4f} & recall = {2:.4f}\n".format(
accuracy, precision, recall
))
# DT model metrics are:
# accuracy = 1.0000, precision = 1.0000 & recall = 1.0000
# Define steps of pipeline-
pipeline_steps = [
('st_kmeans_algo' ,ST_KMeans(k = 5, eps1=0.6, eps2=9, metric='euclidean', n_jobs=1)),
('dtc', DecisionTreeClassifier())
]
# Instantiate a pipeline-
pipeline = Pipeline(pipeline_steps)
# Train pipeline-
pipeline.fit(kmeans_transformed, kmeans_labels)
然而 pipeline.fit() 给出了以下错误：
> --------------------------------------------------------------------------- TypeError Traceback (most recent call
> last) <ipython-input-25-711d6dd8d926> in <module>
> ----> 1 pipeline = Pipeline(pipeline_steps)
>
> ~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in
> __init__(self, steps, memory, verbose)
> 134 self.memory = memory
> 135 self.verbose = verbose
> --> 136 self._validate_steps()
> 137
> 138 def get_params(self, deep=True):
>
> ~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in
> _validate_steps(self)
> 179 if (not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not
> 180 hasattr(t, "transform")):
> --> 181 raise TypeError("All intermediate steps should be "
> 182 "transformers and implement fit and transform "
> 183 "or be the string 'passthrough' "
>
> TypeError: All intermediate steps should be transformers and implement
> fit and transform or be the string 'passthrough' '<__main__.ST_KMeans
> object at 0x7f0971db5430>' (type <class '__main__.ST_KMeans'>) doesn't
怎么了？
您的错误消息说明了一切：所有中间步骤都应该是转换器并实现适合和转换。在您的情况下，您的 class ST_KMeans() 还必须实现 transform 函数才能在管道中使用。此外，最佳实践通常是从模块 sklearn.base:
继承 classes BaseEstimator 和 TransformerMixin
from sklearn.base import BaseEstimator, TransformerMixin
class ST_KMeans(BaseEstimator, TransformerMixin):
def fit(self, X, y=none):
...
return self
def transform(self, X):
return self.X_transformed
然后，您可以在管道中使用您的 class。
我正在尝试通过在带有决策树分类器的管道中使用它来对时空 K-Means 聚类执行超参数调整。其思想是使用 K-Means 聚类算法生成聚类距离 space 矩阵和聚类标签，然后将其传递给决策树分类器。对于超参数调整，只需使用 K-Means 算法的参数即可。 我正在使用 Python 3.8 和 sklearn 0.22.
我感兴趣的数据有3个columns/attributes：time、x和y（x和y是空间坐标）。
密码是：
class ST_KMeans():
"""
Note that the K-means clustering algorithm is designed for Euclidean distances.
It may stop converging with other distances when the mean is no longer a
best estimation for the cluster 'center'.
The 'mean' minimizes squared differences (or, squared Euclidean distance).
If you want a different distance function, you need to replace the mean with
an appropriate center estimation.
Parameters:
k: number of clusters
eps1 : float, default=0.5
The spatial density threshold (maximum spatial distance) between
two points to be considered related.
eps2 : float, default=10
The temporal threshold (maximum temporal distance) between two
points to be considered related.
metric : string default='euclidean'
The used distance metric - more options are
‘braycurtis’, ‘canberra’, ‘chebyshev’, ‘cityblock’, ‘correlation’,
‘cosine’, ‘dice’, ‘euclidean’, ‘hamming’, ‘jaccard’, ‘jensenshannon’,
‘kulsinski’, ‘mahalanobis’, ‘matching’, ‘rogerstanimoto’, ‘sqeuclidean’,
‘russellrao’, ‘seuclidean’, ‘sokalmichener’, ‘sokalsneath’, ‘yule’.
n_jobs : int or None, default=-1
The number of processes to start; -1 means use all processors (BE AWARE)
Attributes:
labels : array, shape = [n_samples]
Cluster labels for the data - noise is defined as -1
"""
def __init__(self, k, eps1 = 0.5, eps2 = 10, metric = 'euclidean', n_jobs = 1):
self.k = k
self.eps1 = eps1
self.eps2 = eps2
# self.min_samples = min_samples
self.metric = metric
self.n_jobs = n_jobs
def fit(self, X):
"""
Apply the ST K-Means algorithm
X : 2D numpy array. The first attribute of the array should be time attribute
as float. The following positions in the array are treated as spatial
coordinates.
The structure should look like this [[time_step1, x, y], [time_step2, x, y]..]
For example 2D dataset:
array([[0,0.45,0.43],
[0,0.54,0.34],...])
Returns:
self
"""
# check if input is correct
X = check_array(X)
# type(X)
# numpy.ndarray
# Check arguments for DBSCAN algo-
if not self.eps1 > 0.0 or not self.eps2 > 0.0:
raise ValueError('eps1, eps2, minPts must be positive')
# Get dimensions of 'X'-
# n - number of rows
# m - number of attributes/columns-
n, m = X.shape
# Compute sqaured form Euclidean Distance Matrix for 'time' and spatial attributes-
time_dist = squareform(pdist(X[:, 0].reshape(n, 1), metric = self.metric))
euc_dist = squareform(pdist(X[:, 1:], metric = self.metric))
'''
Filter the euclidean distance matrix using time distance matrix. The code snippet gets all the
indices of the 'time_dist' matrix in which the time distance is smaller than 'eps2'.
Afterward, for the same indices in the euclidean distance matrix the 'eps1' is doubled which results
in the fact that the indices are not considered during clustering - as they are bigger than 'eps1'.
'''
# filter 'euc_dist' matrix using 'time_dist' matrix-
dist = np.where(time_dist <= self.eps2, euc_dist, 2 * self.eps1)
# Initialize K-Means clustering model-
self.kmeans_clust_model = KMeans(
n_clusters = self.k, init = 'k-means++',
n_init = 10, max_iter = 300,
precompute_distances = 'auto', algorithm = 'auto')
# Train model-
self.kmeans_clust_model.fit(dist)
self.labels = self.kmeans_clust_model.labels_
self.X_transformed = self.kmeans_clust_model.fit_transform(X)
return self
def transform(self, X):
# print("\nX.shape = {0}\n".format(X.shape))
# pass
# return self.kmeans_clust_model.fit_transform(X)
return self.X_transformed
# Initialize ST-K-Means object-
st_kmeans_algo = ST_KMeans(
k = 5, eps1=0.6,
eps2=9, metric='euclidean',
n_jobs=1
)
# Train on a chunk of dataset-
st_kmeans_algo.fit(data.loc[:500, ['time', 'x', 'y']])
# Get clustered data points labels-
kmeans_labels = st_kmeans_algo.labels
kmeans_labels.shape
# (501,)
# Get labels for points clustered using trained model-
kmeans_transformed = st_kmeans_algo.X_transformed
kmeans_transformed.shape
# (501, 5)
dtc = DecisionTreeClassifier()
dtc.fit(kmeans_transformed, kmeans_labels)
y_pred = dtc.predict(kmeans_transformed)
# Get model performance metrics-
accuracy = accuracy_score(kmeans_labels, y_pred)
precision = precision_score(kmeans_labels, y_pred, average='macro')
recall = recall_score(kmeans_labels, y_pred, average='macro')
print("\nDT model metrics are:")
print("accuracy = {0:.4f}, precision = {1:.4f} & recall = {2:.4f}\n".format(
accuracy, precision, recall
))
# DT model metrics are:
# accuracy = 1.0000, precision = 1.0000 & recall = 1.0000
# Define steps of pipeline-
pipeline_steps = [
('st_kmeans_algo' ,ST_KMeans(k = 5, eps1=0.6, eps2=9, metric='euclidean', n_jobs=1)),
('dtc', DecisionTreeClassifier())
]
# Instantiate a pipeline-
pipeline = Pipeline(pipeline_steps)
# Train pipeline-
pipeline.fit(kmeans_transformed, kmeans_labels)
然而 pipeline.fit() 给出了以下错误：
> --------------------------------------------------------------------------- TypeError Traceback (most recent call
> last) <ipython-input-25-711d6dd8d926> in <module>
> ----> 1 pipeline = Pipeline(pipeline_steps)
>
> ~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in
> __init__(self, steps, memory, verbose)
> 134 self.memory = memory
> 135 self.verbose = verbose
> --> 136 self._validate_steps()
> 137
> 138 def get_params(self, deep=True):
>
> ~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in
> _validate_steps(self)
> 179 if (not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not
> 180 hasattr(t, "transform")):
> --> 181 raise TypeError("All intermediate steps should be "
> 182 "transformers and implement fit and transform "
> 183 "or be the string 'passthrough' "
>
> TypeError: All intermediate steps should be transformers and implement
> fit and transform or be the string 'passthrough' '<__main__.ST_KMeans
> object at 0x7f0971db5430>' (type <class '__main__.ST_KMeans'>) doesn't
怎么了？
您的错误消息说明了一切：所有中间步骤都应该是转换器并实现适合和转换。在您的情况下，您的 class ST_KMeans() 还必须实现 transform 函数才能在管道中使用。此外，最佳实践通常是从模块 sklearn.base:
BaseEstimator 和 TransformerMixin
from sklearn.base import BaseEstimator, TransformerMixin
class ST_KMeans(BaseEstimator, TransformerMixin):
def fit(self, X, y=none):
...
return self
def transform(self, X):
return self.X_transformed
然后，您可以在管道中使用您的 class。