Changeset c1b9aba in git

Timestamp:

Jul 29, 2019, 8:11:02 PM (4 years ago)

Author:

Murray Heymann <heymann.murray@…>

Branches:

(u'spielwiese', '828514cf6e480e4bafc26df99217bf2a1ed1ef45')

Children:

8d8fefe7898bd9e2156488544587049b7107d0c1

Parents:

05dbb13ce9ff25aa2c15fa96fa9a3b3b4c4bc09e

Message:

Do more tests

File:

• machine_learning/model/predictor.py (modified) (3 diffs)

machine_learning/model/predictor.py

@@ -4 +4 @@
 
 import cProfile
+import os
+import sys
 import time
 
@@ -52 +54 @@
             i = 0
             for vec in self.vectors:
-                dist = vector_distance(x, vec)
+                # dist = vector_distance(x, vec)
+                # Dot product is much faster
+                dist = -np.dot(x, vec)
                 if dist < min_val:
                     min_val = dist
@@ -116 +120 @@
     print(end - start, "seconds to make prediction")
     print(prediction)
+    print()
 
-
-    test_vec = count_occurances("test.txt", dictionary)
+    print("prediction for zero vector")
+    zerovec = np.zeros(len(dictionary) - 2)
+    print(len(zerovec))
     start = time.time()
-    prediction = predictor.predict(np.array([test_vec]))
+    prediction = predictor.predict(np.array([zerovec]))
     end = time.time()
     print(end - start, "seconds to make prediction")
     print(prediction)
+    print()
+
+    if len(sys.argv) >= 2:
+        for i in range(len(sys.argv)):
+            if i == 0:
+                continue
+            if not os.path.isfile(sys.argv[i]):
+                continue
+            print ("predicting for file", sys.argv[i])
+            test_vec = count_occurances(sys.argv[i], dictionary)
+            start = time.time()
+            prediction = predictor.predict(np.array([test_vec]))
+            end = time.time()
+            print(end - start, "seconds to make prediction")
+            print(prediction)
+            print()
+
 
 if __name__ == '__main__':
-    cProfile.run("main()")
+    #cProfile.run("main()")
+    main()