Fixing scripts and adding a script to create diff plot between two lists of datapoints.

diff --git a/python_ml/plotting-dbscan-diff.py b/python_ml/plotting-dbscan-diff.py
new file mode 100644 (file)
index 0000000..ba89a15
--- /dev/null
+++ b/python_ml/plotting-dbscan-diff.py
@@ -0,0 +1,96 @@
+from sklearn.cluster import DBSCAN
+from sklearn import metrics
+import matplotlib.cm as cm
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Create a subplot with 1 row and 2 columns
+fig, (ax2) = plt.subplots(1, 1)
+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/Pairs2/"
+# TODO: Change the order of the files below to generate
+#              the diff plot reversedly
+device1 = "dlink-siren-device-off"
+device2 = "dlink-siren-device-on"
+filename1 = device1 + ".txt"
+filename2 = device2 + ".txt"
+plt.ylim(0, 2000)
+plt.xlim(0, 2000)
+
+# Number of triggers
+trig = 50
+
+# PLOTTING FOR DEVICE ON EVENT
+# Read and create an array of pairs
+with open(path + filename1, "r") as pairs:
+       pairsArr1 = list()
+       for line in pairs:
+               # We will see a pair and we need to split it into xpoint and ypoint
+               xpoint, ypoint = line.split(", ")
+               pair = [int(xpoint), int(ypoint)]
+               pairsArr1.append(pair)
+
+# PLOTTING FOR DEVICE ON EVENT
+# Read and create an array of pairs
+with open(path + filename2, "r") as pairs:
+       pairsArr2 = list()
+       for line in pairs:
+               # We will see a pair and we need to split it into xpoint and ypoint
+               xpoint, ypoint = line.split(", ")
+               pair = [int(xpoint), int(ypoint)]
+               pairsArr2.append(pair)
+
+diff12 = [i for i in pairsArr1 if i not in pairsArr2]
+
+X = np.array(diff12);
+
+# Compute DBSCAN
+# eps = distances
+# min_samples = minimum number of members of a cluster
+db = DBSCAN(eps=10, 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_
+
+# Number of clusters in labels, ignoring noise if present.
+n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
+
+# Black removed and is used for noise instead.
+unique_labels = set(labels)
+
+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]
+
+       class_member_mask = (labels == k)
+
+       # print("Unique label: " + str(k) + " with freq: " + str(labels.tolist().count(k)))
+       xy = X[class_member_mask & core_samples_mask]
+       plt.plot(xy[:, 0], xy[:, 1], 'o',
+                markeredgecolor='k', markersize=10)
+
+       xy = X[class_member_mask & ~core_samples_mask]
+       plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
+                markeredgecolor='k', markersize=6)
+
+count = 0
+for pair in diff12:
+       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]) + 
+                       " - Freq:" + str(labels.tolist().count(labels[count])), fontsize=10)
+       count = count + 1
+
+plt.title(device1 + ' - diff - ' + device2)
+plt.show()
+
+

diff --git a/python_ml/plotting-dbscan.py b/python_ml/plotting-dbscan.py
index bdfc1d5302ac0c5442b7d8cd266c09ff049b3bcf..9b5d1abb0e18ee3f1b7a4cea76f2a5b48eb87469 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/"
 # 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"
 filename = device + ".txt"

+plt.ylim(0, 2000)
+plt.xlim(0, 2000)

 
 # Number of triggers
 trig = 50
 
 # 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
 # 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_
 core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
 core_samples_mask[db.core_sample_indices_] = True
 labels = db.labels_


@@ -43,13 +47,13 @@ labels = db.labels_
 # Number of clusters in labels, ignoring noise if present.
 n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
 
 # 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)
 
 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))]
 
 colors = [plt.cm.Spectral(each)
           for each in np.linspace(0, 1, len(unique_labels))]


@@ -79,11 +83,11 @@ 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]) + 
        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)
+                       " - Freq: " + str(labels.tolist().count(labels[count])), fontsize=10)

        count = count + 1
 
        
        count = count + 1
 
        

-plt.title(device + ' - Estimated number of clusters: %d' % n_clusters_)
+plt.title(device + ' - Clusters: %d' % n_clusters_)

 plt.show()
 
 
 plt.show()