X-Git-Url: http://plrg.eecs.uci.edu/git/?p=pingpong.git;a=blobdiff_plain;f=python_ml%2Fplotting-dbscan-complete.py;h=a2baa902c63104e52c02a2c6d24b07f4c5f60760;hp=d8c015be381c87dc9cfac252b5d1f8c67f924d41;hb=e97221aeee94e860ee4e090fdc84532bb874006d;hpb=301f34fb861dd5622d96bbbfe07bcd82b120fabf

diff --git a/python_ml/plotting-dbscan-complete.py b/python_ml/plotting-dbscan-complete.py
index d8c015b..a2baa90 100644
--- a/python_ml/plotting-dbscan-complete.py
+++ b/python_ml/plotting-dbscan-complete.py
@@ -12,9 +12,9 @@ fig.set_size_inches(7, 7)
 # Read from file
 # TODO: Just change the following path and filename 
 # 	when needed to read from a different file
-path = "/scratch/July-2018/Pairs/"
-device1 = "tplink-bulb-on"
-device2 = "tplink-bulb-off"
+path = "/scratch/July-2018/Pairs2/"
+device1 = "alexa2-on"
+device2 = "alexa2-off"
 filename1 = device1 + ".txt"
 filename2 = device2 + ".txt"
 
@@ -38,7 +38,7 @@ X = np.array(pairsArr);
 # Compute DBSCAN
 # eps = distances
 # min_samples = minimum number of members of a cluster
-db = DBSCAN(eps=30, min_samples=trig - 5).fit(X)
+db = DBSCAN(eps=10, min_samples=trig - 5).fit(X)
 core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
 core_samples_mask[db.core_sample_indices_] = True
 labels = db.labels_
@@ -55,8 +55,8 @@ colors = [plt.cm.Spectral(each)
 	      for each in np.linspace(0, 1, len(unique_labels))]
 for k, col in zip(unique_labels, colors):
 	if k == -1:
-	    # Black used for noise.
-	    col = [0, 0, 0, 1]
+	    # Red used for noise.
+	    col = [1, 0, 0, 1]
 
 	class_member_mask = (labels == k)
 
@@ -71,8 +71,12 @@ for k, col in zip(unique_labels, colors):
 
 count = 0
 for pair in pairsArr:
-	plt.text(pair[0], pair[1], str(pair[0]) + ", " + str(pair[1]) + 
-		"\nFreq: " + str(labels.tolist().count(labels[count])), fontsize=10)
+	if labels[count] == -1:
+		plt.text(pair[0], pair[1], str(pair[0]) + ", " + str(pair[1]), fontsize=10)
+	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)
 	count = count + 1
 
 #====================================================================================================
@@ -113,8 +117,8 @@ colors = [plt.cm.Spectral(each)
 	      for each in np.linspace(0, 1, len(unique_labels))]
 for k, col in zip(unique_labels, colors):
 	if k == -1:
-	    # Black used for noise.
-	    col = [0, 0, 0, 1]
+	    # Green used for noise.
+	    col = [0, 1, 0, 1]
 
 	class_member_mask = (labels == k)
 
@@ -129,13 +133,17 @@ for k, col in zip(unique_labels, colors):
 
 count = 0
 for pair in pairsArr:
-	plt.text(pair[0], pair[1], str(pair[0]) + ", " + str(pair[1]) + 
-		"\nFreq: " + str(labels.tolist().count(labels[count])), fontsize=10)
+	if labels[count] == -1:
+		plt.text(pair[0], pair[1], str(pair[0]) + ", " + str(pair[1]), fontsize=10)
+	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)
 	count = count + 1
 
 
 	
-plt.title(device1 + ' & ' + device2 + ' - Estimated number of clusters: %d' % n_clusters_)
+plt.title(device1 + ' & ' + device2)
 plt.show()