completed 2 clustering parts of unsupervised learning section

2019-07-25 00:12:04 +01:00
parent 9648dfe7db
commit 15dfbd5d91
23 changed files with 5877 additions and 0 deletions
--- a/Clustering/dbscan_lab_helper.py
+++ b/Clustering/dbscan_lab_helper.py
@@ -0,0 +1,82 @@
+import matplotlib.pyplot as plt
+import numpy as np
+from itertools import cycle, islice
+from sklearn import cluster
+
+figsize = (10, 10)
+point_size = 150
+point_border = 0.8
+
+
+def plot_dataset(dataset, xlim=(-15, 15), ylim=(-15, 15)):
+    plt.figure(figsize=figsize)
+    plt.scatter(dataset[:, 0], dataset[:, 1], s=point_size,
+                color="#00B3E9", edgecolor='black', lw=point_border)
+    plt.xlim(xlim)
+    plt.ylim(ylim)
+    plt.show()
+
+
+def plot_clustered_dataset(dataset, y_pred, xlim=(-15, 15), ylim=(-15, 15), neighborhood=False, epsilon=0.5):
+
+    fig, ax = plt.subplots(figsize=figsize)
+
+    colors = np.array(list(islice(cycle(['#df8efd', '#78c465', '#ff8e34',
+                                         '#f65e97', '#a65628', '#984ea3',
+                                         '#999999', '#e41a1c', '#dede00']),
+                                  int(max(y_pred) + 1))))
+    colors = np.append(colors, '#BECBD6')
+
+    if neighborhood:
+        for point in dataset:
+            circle1 = plt.Circle(
+                point, epsilon, color='#666666', fill=False, zorder=0, alpha=0.3)
+            ax.add_artist(circle1)
+
+    ax.scatter(dataset[:, 0], dataset[:, 1], s=point_size,
+               color=colors[y_pred], zorder=10, edgecolor='black', lw=point_border)
+    plt.xlim(xlim)
+    plt.ylim(ylim)
+    plt.show()
+
+
+def plot_dbscan_grid(dataset, eps_values, min_samples_values):
+
+    fig = plt.figure(figsize=(16, 20))
+    plt.subplots_adjust(left=.02, right=.98, bottom=0.001, top=.96, wspace=.05,
+                        hspace=0.25)
+
+    plot_num = 1
+
+    for i, min_samples in enumerate(min_samples_values):
+        for j, eps in enumerate(eps_values):
+            ax = fig.add_subplot(len(min_samples_values),
+                                 len(eps_values), plot_num)
+
+            dbscan = cluster.DBSCAN(eps=eps, min_samples=min_samples)
+            y_pred_2 = dbscan.fit_predict(dataset)
+
+            colors = np.array(list(islice(cycle(['#df8efd', '#78c465', '#ff8e34',
+                                                 '#f65e97', '#a65628', '#984ea3',
+                                                 '#999999', '#e41a1c', '#dede00']),
+                                          int(max(y_pred_2) + 1))))
+            colors = np.append(colors, '#BECBD6')
+
+            for point in dataset:
+                circle1 = plt.Circle(
+                    point, eps, color='#666666', fill=False, zorder=0, alpha=0.3)
+                ax.add_artist(circle1)
+
+            ax.text(0, -0.03, 'Epsilon: {} \nMin_samples: {}'.format(eps,
+                                                                     min_samples), transform=ax.transAxes, fontsize=16, va='top')
+            ax.scatter(dataset[:, 0], dataset[:, 1], s=50,
+                       color=colors[y_pred_2], zorder=10, edgecolor='black', lw=0.5)
+
+            plt.xticks(())
+            plt.yticks(())
+            plt.xlim(-14, 5)
+            plt.ylim(-12, 7)
+
+            plot_num = plot_num + 1
+
+    plt.show()