import numpy as np
import matplotlib.pyplot as plt
import cv2
from sklearn.cluster import DBSCAN
import os
os.chdir(
'/Users/ChrisErnst/Development/Perception-Challenge-Udacity-RoboticsND-Project3'
)
from extra_functions import cluster_gen
# Generate some clusters!
n_clusters = 50
clusters_x, clusters_y = cluster_gen(n_clusters)
# Convert to a single dataset in OpenCV format
data = np.float32(
(np.concatenate(clusters_x), np.concatenate(clusters_y))).transpose()
# Define max_distance (eps parameter in DBSCAN())
max_distance = 1
db = DBSCAN(eps=max_distance, min_samples=10).fit(data)
# Extract a mask of core cluster members
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
# Extract labels (-1 is used for outliers)
labels = db.labels_
n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
unique_labels = set(labels)
# Plot up the results!
min_x = np.min(data[:, 0])
max_x = np.max(data[:, 0])
min_y = np.min(data[:, 1])
import numpy as np
import matplotlib.pyplot as plt
import cv2
from sklearn.cluster import DBSCAN
import os
os.chdir('/Users/ChrisErnst/Development/Perception-Challenge-Udacity-RoboticsND-Project3')
from extra_functions import cluster_gen
# Generate some clusters!
n_clusters = 50
clusters_x, clusters_y = cluster_gen(n_clusters)
# Convert to a single dataset in OpenCV format
data = np.float32((np.concatenate(clusters_x), np.concatenate(clusters_y))).transpose()
# Define max_distance (eps parameter in DBSCAN())
max_distance = 1
db = DBSCAN(eps=max_distance, min_samples=10).fit(data)
# Extract a mask of core cluster members
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
# Extract labels (-1 is used for outliers)
labels = db.labels_
n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
unique_labels = set(labels)
# Plot up the results!
min_x = np.min(data[:, 0])
max_x = np.max(data[:, 0])
min_y = np.min(data[:, 1])
max_y = np.max(data[:, 1])
fig = plt.figure(figsize=(12,6))