Sc 75 #bulk load

Solution Concept/Kernel idea.py

+""""This file contains my second idea for a solution concept to our problem.
+It is based on kernel methods as opposed to my last idea."""
+
+import numpy as np
+import re
+
+# Input sequences
+S1 = ["This", "is", "an", "example", "sequence", "This", "is", "the", "original"]
+S2 = ["This", "is", "another", "example", "sequence", "This", "is", "not", "the", "original"]
+
+# Algorithm constants
+avr_latency = 170 * 10**(-3)
+
+
+# Algorithm functions
+def in_time(w1, w2, threshold):
+    t1, t2 = w1.onset, w2.onset  # Get onsets for both words
+    delta = np.abs(t1 - t2)      # Get difference and use abs due to similarity of words before and after
+    penalty = np.sqrt(delta)/avr_latency  # Square root to not make penalty too large & normalize in terms of experiment
+
+    return penalty < threshold  # Return the decision of whether word 2 was in time of word 1
+
+
+def phi(w1, w2):  # String phi function for kernel methods, calculate how often w1 appears as substring of w2
+    return len([i.start() for i in re.finditer(w1, w2)])
+
+
+def similarity(w1, w2, seq1, threshold):
+    k = 0  # Kernel function answer
+    ws = 1  # hold all weights constant for now
+    for s in seq1:  # Calculate kernel function answer using feature mapping phi
+        k += ws * phi(s, w1) * phi(s, w2)
+
+    return k < threshold  # Return decision
+
+def alg(data1, data2, threshold1, threshold2):