Changeset 112c79 in git for machine_learning/predictor_runner.py

Timestamp:

Aug 2, 2019, 7:35:10 PM (5 years ago)

Author:

Murray Heymann <heymann.murray@…>

Branches:

(u'spielwiese', 'fe61d9c35bf7c61f2b6cbf1b56e25e2f08d536cc')

Children:

58603fd7faac3d049f61ca0b65d89e4be0a664f9

Parents:

fece1392f8e9ff07b64d0ed4e5ec57bfa6dbf258

git-author:

Murray Heymann <heymann.murray@gmail.com>2019-08-02 19:35:10+02:00

git-committer:

Murray Heymann <heymann.murray@gmail.com>2019-08-02 19:35:13+02:00

Message:

Use sklearn to count keyword occurances

File:

• machine_learning/predictor_runner.py (modified) (6 diffs)

machine_learning/predictor_runner.py

@@ -5 +5 @@
 import os
 import sys
+import time
 import numpy as np
-from model.predictor import *
+
+from model.predictor import HelpPagePredictor
+from common.keyword_vector import read_dictionary, count_occurances
+from common.lookuptable import create_table
+from common.constants import KEYWORDS_FILE
 
 def find_prediction(filename):
+    """
+    Given a file name as string, get the predicted help page name
+    """
     dictionary = read_dictionary(KEYWORDS_FILE)
+
     start = time.time()
     vectors, file_list = create_table(dictionary=dictionary)
@@ -15 +24 @@
     print(end - start, "seconds to create_table")
 
+    return _find_prediction(filename, dictionary, vectors, file_list)
+
+
+def _find_prediction(filename, dictionary, vectors, file_list):
+    """
+    Train a predictor, get the predicted help page name
+    """
     predictor = HelpPagePredictor()
     predictor.fit(vectors, file_list)
@@ -24 +40 @@
     print(end - start, "seconds to make prediction")
     return prediction
-    
+
 
 def main():
@@ -42 +58 @@
     predictor.fit(vectors, file_list)
 
-    start = time.time()
-    test_vec = count_occurances("extract.lib", dictionary)
-    prediction = predictor.predict(np.array([test_vec]))
-    end = time.time()
-    print(end - start, "seconds to make prediction")
-    print(prediction)
-    print()
-
     print("prediction for zero vector")
     start = time.time()
@@ -59 +67 @@
     print()
 
+    prediction = _find_prediction("extract.lib",
+                                  dictionary,
+                                  vectors,
+                                  file_list)
+    print(prediction)
+    print()
+
+
     if len(sys.argv) >= 2:
         for i in range(len(sys.argv)):
@@ -65 +81 @@
             if not os.path.isfile(sys.argv[i]):
                 continue
+
             print("predicting for file", sys.argv[i])
-            start = time.time()
-            test_vec = count_occurances(sys.argv[i], dictionary)
-            prediction = predictor.predict(np.array([test_vec]))
-            end = time.time()
-            print(end - start, "seconds to make prediction")
+            prediction = _find_prediction(sys.argv[i],
+                                          dictionary,
+                                          vectors,
+                                          file_list)
             print(prediction)
             print()