def run_optimization(self):
# Disabling is needed since this function is not reentrant
# Fast clicking on, say, "To: " causes multiple calls
try:
self.controlArea.setDisabled(True)
self.optimization_runs = []
if self.check_data_size(self.k_to):
self.optimization_runs = []
kmeans = KMeans(
init=['random', 'k-means++'][self.smart_init],
n_init=self.n_init,
max_iter=self.max_iterations)
with self.progressBar(self.k_to - self.k_from + 1) as progress:
for k in range(self.k_from, self.k_to + 1):
progress.advance()
kmeans.params["n_clusters"] = k
self.optimization_runs.append((k, kmeans(self.data)))
finally:
self.controlArea.setDisabled(False)
self.show_results()
self.send_data()
def run_optimization(self):
# Disabling is needed since this function is not reentrant
# Fast clicking on, say, "To: " causes multiple calls
try:
self.controlArea.setDisabled(True)
self.optimization_runs = []
if not self.check_data_size(self.k_from, self.error):
return
self.check_data_size(self.k_to, self.warning)
k_to = min(self.k_to, len(self.data))
kmeans = KMeans(init=['random', 'k-means++'][self.smart_init],
n_init=self.n_init,
max_iter=self.max_iterations)
with self.progressBar(k_to - self.k_from + 1) as progress:
for k in range(self.k_from, k_to + 1):
progress.advance()
kmeans.params["n_clusters"] = k
self.optimization_runs.append((k, kmeans(self.data)))
finally:
self.controlArea.setDisabled(False)
self.show_results()
self.send_data()
def run_optimization(self):
# Disabling is needed since this function is not reentrant
# Fast clicking on, say, "To: " causes multiple calls
try:
self.controlArea.setDisabled(True)
self.optimization_runs = []
if self.check_data_size(self.k_to):
self.progressBarInit()
progress_steps = self.k_to - self.k_from + 1
self.optimization_runs = []
kmeans = KMeans(
init=["random", "k-means++"][self.smart_init], n_init=self.n_init, max_iter=self.max_iterations
)
for k in range(self.k_from, self.k_to + 1):
self.progressBarSet(100.0 * (k - self.k_from) / progress_steps)
kmeans.params["n_clusters"] = k
self.optimization_runs.append((k, kmeans(self.data)))
self.progressBarFinished()
finally:
self.controlArea.setDisabled(False)
self.show_results()
self.send_data()
def _compute_clustering(data, k, init, n_init, max_iter, silhouette,
random_state):
# type: (Table, int, str, int, int, bool) -> KMeansModel
if k > len(data):
raise NotEnoughData()
return KMeans(
n_clusters=k,
init=init,
n_init=n_init,
max_iter=max_iter,
compute_silhouette_score=silhouette,
random_state=random_state,
)(data)
def run_optimization(self):
# Disabling is needed since this function is not reentrant
# Fast clicking on, say, "To: " causes multiple calls
try:
self.controlArea.setDisabled(True)
self.optimization_runs = []
if not self.check_data_size(self.k_from, self.Error):
return
self.check_data_size(self.k_to, self.Warning)
k_to = min(self.k_to, len(self.data))
kmeans = KMeans(
init=['random', 'k-means++'][self.smart_init],
n_init=self.n_init, max_iter=self.max_iterations,
compute_silhouette_score=self.scoring == self.SILHOUETTE)
with self.progressBar(k_to - self.k_from + 1) as progress:
for k in range(self.k_from, k_to + 1):
progress.advance()
kmeans.params["n_clusters"] = k
self.optimization_runs.append((k, kmeans(self.data)))
finally:
self.controlArea.setDisabled(False)
self.show_results()
self.send_data()
def run_optimization(self):
# Disabling is needed since this function is not reentrant
# Fast clicking on, say, "To: " causes multiple calls
try:
self.controlArea.setDisabled(True)
self.optimization_runs = []
if self.check_data_size(self.k_to):
self.progressBarInit()
progress_steps = self.k_to - self.k_from + 1
self.optimization_runs = []
kmeans = KMeans(init=['random', 'k-means++'][self.smart_init],
n_init=self.n_init,
max_iter=self.max_iterations)
for k in range(self.k_from, self.k_to + 1):
self.progressBarSet(100.0 * (k - self.k_from) /
progress_steps)
kmeans.params["n_clusters"] = k
self.optimization_runs.append((k, kmeans(self.data)))
self.progressBarFinished()
finally:
self.controlArea.setDisabled(False)
self.show_results()
self.send_data()
def _compute_clustering(self, k):
# False positives (Setting is not recognized as int)
# pylint: disable=invalid-sequence-index
# pylint: disable=broad-except
try:
if k > len(self.data):
self.clusterings[k] = "not enough data"
else:
self.clusterings[k] = KMeans(
n_clusters=k,
init=['random', 'k-means++'][self.smart_init],
n_init=self.n_init,
max_iter=self.max_iterations,
compute_silhouette_score=True)(self.data)
except Exception as exc:
self.clusterings[k] = str(exc)
return False
else:
return True
def _compute_clustering(data, k, init, n_init, max_iter, random_state):
# type: (Table, int, str, int, int, bool) -> KMeansModel
if k > len(data):
raise NotEnoughData()
model = KMeans(n_clusters=k,
init=init,
n_init=n_init,
max_iter=max_iter,
random_state=random_state,
preprocessors=[]).get_model(data)
if data.X.shape[0] <= SILHOUETTE_MAX_SAMPLES:
model.silhouette_samples = silhouette_samples(data.X, model.labels)
model.silhouette = np.mean(model.silhouette_samples)
else:
model.silhouette_samples = None
model.silhouette = \
silhouette_score(data.X, model.labels,
sample_size=SILHOUETTE_MAX_SAMPLES,
random_state=RANDOM_STATE)
return model
