Commit cce036f22feef37d6c05c4b0757afbcbc15de45c
1 parent
a79344696d
Exists in
master
Implementation of basic kmeans made by my hand
Showing 1 changed file with 85 additions and 0 deletions Inline Diff
bin/cluster_kmeans_ownmade.py
| File was created | 1 | ''' | |
| 2 | Un petit test pour faire du clustering | ||
| 3 | avec une distance de mahalanobis | ||
| 4 | ''' | ||
| 5 | |||
| 6 | import matplotlib.pyplot as plt | ||
| 7 | import numpy as np | ||
| 8 | from sklearn.manifold import TSNE | ||
| 9 | |||
| 10 | N = 18 # Number of individus | ||
| 11 | d = 2 # Number of dimensions | ||
| 12 | K = 3 # number of clusters | ||
| 13 | |||
| 14 | X = np.random.rand(N, d) # Features | ||
| 15 | |||
| 16 | C = np.random.random_sample((K, d)) # Model 0 | ||
| 17 | |||
| 18 | |||
| 19 | def dist(a, b): | ||
| 20 | ''' | ||
| 21 | Distance euclidienne | ||
| 22 | ''' | ||
| 23 | return np.sum(np.power(np.abs(a - b), 2)) | ||
| 24 | |||
| 25 | |||
| 26 | def plot_iteration(iteration, points, clusters, centers): | ||
| 27 | fig = plt.figure() | ||
| 28 | ax = fig.add_subplot(111) | ||
| 29 | scatter = ax.scatter(points[:, 0], points[:, 1], c=clusters, s=50) | ||
| 30 | for i, j in centers: | ||
| 31 | ax.scatter(i, j, s=50, c='red', marker='+') | ||
| 32 | ax.set_xlabel('x') | ||
| 33 | ax.set_ylabel('y') | ||
| 34 | plt.colorbar(scatter) | ||
| 35 | plt.ylim(0, 1) | ||
| 36 | plt.xlim(0, 1) | ||
| 37 | plt.savefig("test_" + str(iteration) + ".pdf") | ||
| 38 | |||
| 39 | |||
| 40 | end_algo = False | ||
| 41 | i = 0 | ||
| 42 | while not end_algo: | ||
| 43 | if i == 2000: | ||
| 44 | exit(1) | ||
| 45 | print("Iteration: ", i) | ||
| 46 | # Calcul matrix distance | ||
| 47 | distances = np.zeros((N, K)) | ||
| 48 | |||
| 49 | for n in range(N): | ||
| 50 | for k in range(K): | ||
| 51 | distances[n][k] = dist(X[n], C[k]) | ||
| 52 | closest_cluster = np.argmin(distances, axis=1) | ||
| 53 | |||
| 54 | if i % 1 == 0: | ||
| 55 | # -- Debug tool ---------------------- | ||
| 56 | # TSNE | ||
| 57 | X_embedded = np.concatenate((X, C), axis=0) | ||
| 58 | # X_embedded = TSNE(n_components=2).fit_transform(np.concatenate((X, C), axis=0)) | ||
| 59 | # Then plot | ||
| 60 | plot_iteration( | ||
| 61 | i, | ||
| 62 | X_embedded[:X.shape[0]], | ||
| 63 | closest_cluster, | ||
| 64 | X_embedded[X.shape[0]:] | ||
| 65 | ) | ||
| 66 | # ------------------------------------ | ||
| 67 | |||
| 68 | end_algo = True | ||
| 69 | for k in range(K): | ||
| 70 | # Find subset of X with values closed to the centroid c_k. | ||
| 71 | X_sub = np.where(closest_cluster == k) | ||
| 72 | X_sub = np.take(X, X_sub[0], axis=0) | ||
| 73 | np.mean(X_sub, axis=0) | ||
| 74 | C_new = np.mean(X_sub, axis=0) | ||
| 75 | if end_algo and (not (C[k] == C_new).all()): # If the same stop | ||
| 76 | end_algo = False | ||
| 77 | C[k] = C_new | ||
| 78 | i = i + 1 | ||
| 79 | |||
| 80 | plot_iteration( | ||
| 81 | i, | ||
| 82 | X_embedded[:X.shape[0]], | ||
| 83 | closest_cluster, | ||
| 84 | X_embedded[X.shape[0]:] | ||
| 85 | ) | ||
| 86 |