Preparing scripts for TP-Link plug.

[pingpong.git] / python_ml / plotting-dbscan.py

diff --git a/python_ml/plotting-dbscan.py b/python_ml/plotting-dbscan.py
index bdfc1d5302ac0c5442b7d8cd266c09ff049b3bcf..2202a8ef19894255d34eb24da996cad7754b851e 100644 (file)
--- a/python_ml/plotting-dbscan.py
+++ b/python_ml/plotting-dbscan.py
@@ -13,8 +13,10 @@ fig.set_size_inches(7, 7)
 # TODO: Just change the following path and filename 
 #      when needed to read from a different file
 path = "/scratch/July-2018/Pairs2/"
-device = "alexa2-off"
+device = "dlink-siren-device-off"
 filename = device + ".txt"
+plt.ylim(0, 2000)
+plt.xlim(0, 2000)
 
 # Number of triggers
 trig = 50
@@ -35,7 +37,9 @@ X = np.array(pairsArr);
 # Compute DBSCAN
 # eps = distances
 # min_samples = minimum number of members of a cluster
-db = DBSCAN(eps=20, min_samples=trig - 5).fit(X)
+#db = DBSCAN(eps=20, min_samples=trig - 5).fit(X)
+# TODO: This is just for seeing more clusters
+db = DBSCAN(eps=20, min_samples=trig - 45).fit(X)
 core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
 core_samples_mask[db.core_sample_indices_] = True
 labels = db.labels_
@@ -43,17 +47,18 @@ labels = db.labels_
 # Number of clusters in labels, ignoring noise if present.
 n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
 
-print('Estimated number of clusters: %d' % n_clusters_)
+#print('Estimated number of clusters: %d' % n_clusters_)
 
 import matplotlib.pyplot as plt
 
 # Black removed and is used for noise instead.
 unique_labels = set(labels)
-print("Labels: " + str(labels))
+#print("Labels: " + str(labels))
 
 colors = [plt.cm.Spectral(each)
           for each in np.linspace(0, 1, len(unique_labels))]
 for k, col in zip(unique_labels, colors):
+    cluster_col = [1, 0, 0, 1]
     if k == -1:
         # Black used for noise.
         col = [0, 0, 0, 1]
@@ -61,7 +66,7 @@ for k, col in zip(unique_labels, colors):
     class_member_mask = (labels == k)
 
     xy = X[class_member_mask & core_samples_mask]
-    plt.plot(xy[:, 0], xy[:, 1], 'o',
+    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(cluster_col),
              markeredgecolor='k', markersize=10)
 
     xy = X[class_member_mask & ~core_samples_mask]
@@ -79,11 +84,11 @@ for pair in pairsArr:
        else:
        # Only print the frequency when this is a real cluster
                plt.text(pair[0], pair[1], str(pair[0]) + ", " + str(pair[1]) + 
-                       "\nFreq: " + str(labels.tolist().count(labels[count])), fontsize=10)
+                       " : " + str(labels.tolist().count(labels[count])), fontsize=10)
        count = count + 1
 
        
-plt.title(device + ' - Estimated number of clusters: %d' % n_clusters_)
+plt.title(device + ' - Clusters: %d' % n_clusters_)
 plt.show()