def run_kmeans():
# print(len(argv))
if len(argv) < 4:
print(
'Not enough arguments provided. Please provide 3 arguments: K, num_iterations, path_to_input'
)
exit(1)
k = int(argv[1])
num_iterations = int(argv[2])
input_path = argv[3]
if len(argv) == 5:
random_seed = int(argv[4])
else:
random_seed = 0
if k <= 1 or num_iterations <= 0:
print('Please provide correct parameters')
exit(1)
if not os.path.exists(input_path):
print('Input file does not exist')
exit(1)
points = load_data(input_path)
if k >= len(points):
print('Please set K less than size of dataset')
exit(1)
runner = KMeans(k, num_iterations)
runner.run(points, random_seed)
runner.print_results()
def run_kmeans():
list_seed = [1, 1, 1, 12, 12, 12]
list_k = [3, 4, 5, 3, 4, 5]
print("seed k sl1")
for index, value_seed in enumerate(list_seed):
k = list_k[index]
num_iterations = 10
input_path = "colors_dataset_ready.txt"
random_seed = value_seed
if k <= 1 or num_iterations <= 0:
print('Please provide correct parameters')
exit(1)
if not os.path.exists(input_path):
print('Input file does not exist')
exit(1)
points = load_data(input_path)
if k >= len(points):
print('Please set K less than size of dataset')
exit(1)
runner = KMeans(k, num_iterations)
runner.run(points, random_seed)
print(list_seed[index], end=" ")
print(list_k[index], end=" ")
runner.print_results()
def run_test(self):
test = KMeans(self.k, self.num_of_iters)
total_sse = []
total_sum = 0
for seed in range(self.max_seeds):
test.run(self.points, seed)
sse = test.compute_sse()
total_sse.append(sse)
total_sum += sse
minimal_sse = min(total_sse)
mean_sse = total_sum / 10
maximal_sse = max(total_sse)
return [
f"0-{self.max_seeds - 1}", self.k, self.num_of_iters, minimal_sse,
mean_sse, maximal_sse
]
class ClusteringGui(QMainWindow):
# ui
layout: QVBoxLayout # Main Layout in which everything else is contained
browse_btn: QPushButton # Load Dataset button
k_selector: QSpinBox # Selector for k value
repetitions_selector: QSpinBox # Select how many times K-Means is ran per dataset
run_btn: QPushButton # Run button
step_btn: QPushButton # Next button
dimensions_label: QLabel # Filled with vector dimensions found from dataset
recommended_k_label: QLabel # Filled with recommended K value as calculated using SSE / Elbow method
plot_canvas: FigureCanvas # Canvas containing matplotlib plot
path: str # Path of current loaded dataset
kmeans: KMeans
figure: plt.Figure
elbow_chart: QWidget
def __init__(self):
self.kmeans = KMeans()
super(ClusteringGui, self).__init__()
uic.loadUi(main_interface_file, self)
self.browse_btn = self.findChild(QPushButton, 'browse_button')
self.browse_btn.clicked.connect(self.on_browse_click)
self.k_selector = self.findChild(QSpinBox, 'k_val_selector')
self.k_selector.valueChanged.connect(self.on_update_k)
self.repetitions_selector = self.findChild(QSpinBox, 'k_repetitions_selector')
self.repetitions_selector.valueChanged.connect(self.on_set_repetitions)
self.run_btn = self.findChild(QPushButton, 'run_button')
self.run_btn.clicked.connect(self.on_run_click)
self.run_btn.setEnabled(False)
self.step_btn = self.findChild(QPushButton, 'step_button')
self.step_btn.clicked.connect(self.on_step_click)
self.step_btn.setEnabled(False)
self.elbow_btn = self.findChild(QPushButton, 'elbow_chart_button')
self.elbow_btn.clicked.connect(self.on_show_elbow)
self.elbow_btn.setEnabled(False)
self.layout = self.findChild(QVBoxLayout, 'layout')
self.dimensions_label = self.findChild(QLabel, 'dimensions_label')
self.dimensions_label.setText("")
self.show()
@pyqtSlot()
def on_browse_click(self):
self.path, _ = QFileDialog.getOpenFileName(self, "Open Dataset", "", "CSV Files (*.csv)")
try:
self.kmeans.open_dataset(filepath=self.path)
self.dimensions_label.setText("Dimensions: {}".format(self.kmeans.dimensions))
self.add_matplotlib_canvas()
self.setWindowTitle('K-Means Clustering: {}'.format(self.path))
self.elbow_btn.setEnabled(True)
self.run_btn.setEnabled(True)
self.step_btn.setEnabled(True)
except FileNotFoundError:
print("Exception")
error_dialog = QErrorMessage()
error_dialog.showMessage("File Not Found, try again")
error_dialog.exec()
@pyqtSlot()
def on_show_elbow(self):
sse = []
# Calculate SSE for values of K ranging from 1 to 10.
for i in range(1,10):
print("Calculating SSE for K =", i)
self.kmeans.update_k(i)
# Cluster and update centroids 3 times for each K value
self.kmeans.cluster_points()
self.kmeans.cluster_points()
self.kmeans.cluster_points()
sse.append(self.kmeans.calculate_sse())
self.elbow_chart = ElbowChartGui()
self.elbow_chart.plot(sse, self.path)
# Handles K value being changed
@pyqtSlot()
def on_update_k(self):
self.kmeans.update_k(self.k_selector.value())
# If there's data being displayed, update it now
if self.kmeans.data_displayed:
self.update_matplotlib()
@pyqtSlot()
def on_run_click(self):
self.kmeans.run()
self.update_matplotlib()
@pyqtSlot()
def on_set_repetitions(self):
self.kmeans.repetitions = self.repetitions_selector.value()
# Handles 'Next' button being pressed
@pyqtSlot()
def on_step_click(self):
self.kmeans.step()
self.update_matplotlib()
# Adds the matplotlib canvas to the UI
def add_matplotlib_canvas(self):
try:
self.figure.clear()
except AttributeError:
self.figure = plt.figure()
self.plot_canvas = FigureCanvas(self.figure)
self.layout.addWidget(self.plot_canvas)
ax = self.figure.add_subplot(1, 1, 1)
x = [point[0] for point in self.kmeans.vectors]
y = [point[1] for point in self.kmeans.vectors]
ax.scatter(x, y, alpha=0.8)
self.plot_canvas.draw()
# Updates the matplotlib UI
def update_matplotlib(self):
self.figure.clear()
ax = self.figure.add_subplot(1, 1, 1)
for cluster in self.kmeans.clusters:
x = [point[0] for point in cluster]
y = [point[1] for point in cluster]
ax.scatter(x, y, alpha=0.5)
for centroid in self.kmeans.centroids:
x, y = centroid[0], centroid[1]
ax.scatter(x, y, c='k', alpha=0.8)
self.plot_canvas.draw()
def itirate_kmeans(k, num_iterations, random_seed, points):
runner = KMeans(k, num_iterations)
runner.run(points, random_seed)
runner.print_distance(random_seed)
# Plot initial map
plot = Plot()
plot.plot(data_map, False)
# Run simulated annealing experiments
for i in range(1, 5):
print 'Running simulated annealing for type %d:' % i
SA = SimulatedAnnealing(i)
new_map = SA.anneal(data_map)
cost = SA_final.cost(new_map)
print 'Cost: %d' % cost
averages[i] += cost
plot.plot(new_map, False, i)
# Run k-means
dropoff_zones = data_map.dropoff_zones.keys()
K = len(dropoff_zones)
locations = data_map.coordinates.keys()
k_means = KMeans(K, dropoff_zones, locations, data_map)
print 'Running k-means clustering:'
kmeans_cost = k_means.run()
print 'Cost: %d' % kmeans_cost
averages[5] += kmeans_cost
# Print average costs
print map(lambda x: x / num_iterations, averages)