Я пытаюсь выполнить настройку гиперпараметров для кластеризации пространственно-временных K-средних, используя его в конвейере с классификатором дерева решений. Идея состоит в том, чтобы использовать алгоритм кластеризации K-средних для генерации пространственной матрицы кластерных расстояний и кластерных меток, которые затем будут переданы классификатору дерева решений. Для настройки гиперпараметров просто используйте параметры для алгоритма K-средних.
Я использую Python 3,8 и sklearn 0,22.
Интересующие меня данные имеют 3 столбца / атрибута: 'время ',' x 'и' y '(x и y - пространственные координаты).
Код:
class ST_KMeans(BaseEstimator, TransformerMixin):
# class ST_KMeans():
"""
Note that 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, Y = None):
"""
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):
if not isinstance(X, np.ndarray):
# Convert to numpy array-
X = X.values
# 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 'euc_dist' matrix using 'time_dist' matrix-
dist = np.where(time_dist <= self.eps2, euc_dist, 2 * self.eps1)
# return self.kmeans_clust_model.transform(X)
return self.kmeans_clust_model.transform(dist)
# Initialize ST-K-Means object-
st_kmeans_algo = ST_KMeans(
k = 5, eps1=0.6,
eps2=9, metric='euclidean',
n_jobs=1
)
Y = np.zeros(shape = (501,))
# Train on a chunk of dataset-
st_kmeans_algo.fit(data.loc[:500, ['time', 'x', 'y']], 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 = st_kmeans_algo.transform(data.loc[:500, ['time', 'x', 'y']])
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
# Hyper-parameter Tuning:
# 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)
kmeans_transformed.shape, kmeans_labels.shape
# ((501, 5), (501,))
# Train pipeline-
pipeline.fit(kmeans_transformed, kmeans_labels)
# Specify parameters to be hyper-parameter tuned-
params = [
{
'st_kmeans_algo__k': [3, 5, 7]
}
]
# Initialize GridSearchCV object-
grid_cv = GridSearchCV(estimator=pipeline, param_grid=params, cv = 2)
# Train GridSearch on computed data from above-
grid_cv.fit(kmeans_transformed, kmeans_labels)
Вызов' grid_cv.fit () 'дает следующая ошибка:
ValueError Traceback (последний вызов последним) в 5 6 # Обучить GridSearch по вычисленным данным из выше- ----> 7 grid_cv.fit (kmeans_transformed, kmeans_labels)
~ / .local / lib / python3 .8 / site-packages / sklearn / model_selection / _search.py in fit (self, X, y, groups, ** fit_params) 708 вернуть результаты 709 - -> 710 self._run_search (Assessment_candidates) 711 712 # Для мультиметрической c оценки сохранить best_index_, best_params_ и
~ / .local / lib / python3 .8 / site-packages / sklearn / model_selection / _search.py в _run_search (self, Assessment_candidates) 1149 def _run_search (self, Assessment_candidates): 1150 "" "Искать все ок. ndidates в param_grid "" "-> 1151 Assessment_candidates (ParameterGrid (self.param_grid)) 1152 1153
~ / .local / lib / python3 .8 / site-packages / sklearn / model_selection / _search.py в оценке_кандидатов (параметры_кандидата) 680 n_splits, n_candidates, n_candidates * n_splits)) 681 -> 682 out = parallel (delayed (_fit_and_score) (clone (base_estimator), 683 X, y, 684 train = train, test = test,
~ / .local / lib / python3 .8 / site-packages / joblib / parallel.py in call (self, iterable) 1002 # оставшиеся задания. 1003 self._iterating = False -> 1004 если self.dispatch_one_batch (iterator): 1005 self._iterating = self._original_iterator is not None 1006
~ / .local / lib / python3 .8 / site- пакеты / joblib / parallel.py в dispatch_one_batch (self, iterator) 833 return False 834 else: -> 835 self._dispatch (tasks) 836 return True 837
~ / .local / lib / python3 .8 / site-packages / joblib / parallel.py в _dispatch (self, batch) 752 с self._lock: 753 job_idx = len (self._jobs) -> 754 job = self._backend.apply_asyn c (batch , callback = cb) 755 # Задание может завершиться так быстро, что его обратный вызов 756 # вызывается до того, как мы сюда попали, в результате чего self._jobs принимает значение
~ / .local / lib / python3 .8 / site -packages / joblib / _parallel_backends.py в apply_asyn c (self, fun c, callback) 207 def apply_asyn c (self, fun c, callback = None): 208 "" "Запланировать развлечение c для запуска "" "-> 209 result = ImmediateResult (fun c) 210 если обратный вызов: 211 обратный вызов (результат)
~ / .local / lib / python3 .8 / site -пакеты / работа lib / _parallel_backends.py in init (self, batch) 588 # Не откладывайте приложение, чтобы не хранить входные 589 # аргументы в памяти -> 590 self.results = batch () 591 592 def get (self):
~ / .local / lib / python3 .8 / site-packages / joblib / parallel.py in call (self) 253 # изменить значение по умолчанию количество процессов до -1 254 с parallel_backend (self._backend, n_jobs = self._n_jobs): -> 255 return [fun c (* args, ** kwargs) 256 для развлечения c, args, kwargs в self.items] 257
~ / .local / lib / python3 .8 / site-packages / joblib / parallel.py in (.0) 253 # измените количество процессов по умолчанию на -1 254 с помощью parallel_backend (self._backend , n_jobs = self._n_jobs): -> 255 return [fun c (* args, ** kwargs) 256 для развлечения c, args, kwargs в self.items] 257
~ / .local / lib / python3 .8 / site-packages / sklearn / model_selection / _validation.py в _fit_and_score (оценка, X, y, счетчик, тренировка, тест, подробный, параметры, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times , return_estimator, error_score) 542 else: 543 fit_time = time.time () - start_time -> 544 test_scores = _score (оценка, X_test, y_test, scorer) 545 score_time = time.time () - start_time - fit_time 546 if return_train_score:
~ / .local / lib / python3 .8 / site-packages / sklearn / model_selection / _validati on.py в _score (оценка, X_test, y_test, scorer) 589 оценок = оценка (оценка, X_test) 590 иначе: -> 591 оценка = оценка (оценка, X_test, y_test) 592 593 error_msg = ("оценка должна возвращать число, получено% s (% s) "* 1045 *
~ / .local / lib / python3 .8 / site-packages / sklearn / metrics / _scorer.py в вызов (self , Estimator, * args, ** kwargs) 87 * args, ** kwargs) 88 else: ---> 89 score = scorer (Estimator, * args, ** kwargs) 90 scores [name] = score 91 return score
~ / .local / lib / python3 .8 / site-packages / sklearn / metrics / _scorer.py в _passthrough_scorer (оценка, * аргументы, ** kwargs) 369 def _passthrough_scorer (оценка, * аргументы, ** kwargs): 370 "" "Функция, которая обертывает Estimator.score" "" -> 371 return Estimator.score (* args, ** kwargs) 372 373
~ / .local / lib / python3 .8 / site-packages / sklearn / utils / metaestimators.py in (* args, ** kwargs) 114 115 # лямбда, но не частичная, позволяет help () работать с update_wrapper -> 116 out = lambda * аргументы, ** kwargs: self.fn (obj, * args, ** kwargs) 1 17 # обновить строку документации возвращаемой функции 118 update_wrapper (out, self.fn)
~ / .local / lib / python3 .8 / site-packages / sklearn / pipeline.py in score (self , X, y, sample_weight) 617 если sample_weight не равно None: 618 score_params ['sample_weight'] = sample_weight -> 619 return self.steps [-1] [- 1] .score (Xt, y, ** score_params) 620 621 @ свойство
~ / .local / lib / python3 .8 / site-packages / sklearn / base.py in score (self, X, y, sample_weight) 367 "" "368 с. метрики import precision_score -> 369 return precision_score (y, self.predict (X), sample_weight = sample_weight) 370371
~ / .local / lib / python3 .8 / site-packages / sklearn / metrics / _classification.py in precision_score (y_true, y_pred, normalize, sample_weight) 183 184 # Вычислить точность для каждого возможного представления -> 185 y_type, y_true, y_pred = _check_targets (y_true, y_pred) 186 check_consistent_length, y_pred_length (y_true) 187, если y_type.startswith ('multipleabel'):
~ / .local / lib / python3 .8 / site-packag es / sklearn / metrics / _classification.py в _check_targets (y_true, y_pred) 78 y_pred: массив или индикаторная матрица 79 "" "---> 80 check_consistent_length (y_true, y_pred) 81 type_true = type_of_target (y_true) тип 82 type_predget (y_true) 82 type_predget (y_true) 82 type_predget y_pred)
~ /. local / lib / python3 .8 / site-packages / sklearn / utils / validation.py в check_consistent_length (* массивы) 209 uniques = np.unique (lengths) 210 if len (uniques)> 1: -> 211 raise ValueError ("Найдены входные переменные с несогласованным количеством" 212 "выборок:% r"% [int (l) для l в длинах]) 213
ValueError: Найдены входные переменные с несогласованным количеством выборок: [251 , 250]
Различные размеры / формы:
kmeans_transformed.shape, kmeans_labels.shape, data.loc[:500, ['time', 'x', 'y']].shape
# ((501, 5), (501,), (501, 3))
Я не понимаю, как возникает ошибка в «samples: [251, 25]»?
Что не так?
Спасибо!