Changeset fece13 in git

Timestamp:

Aug 1, 2019, 2:31:25 PM (5 years ago)

Author:

Murray Heymann <heymann.murray@…>

Branches:

(u'spielwiese', 'fe61d9c35bf7c61f2b6cbf1b56e25e2f08d536cc')

Children:

112c79d4f91036791f523bcfbb261d1ba63c2d8f

Parents:

50e8722ce7219d67ee649c39300d30d2e9e90edd

Message:

Make python2 compatible

Files:

• .gitignore (modified) (1 diff)
• machine_learning/common/keyword_vector.py (modified) (3 diffs)
• machine_learning/common/lookuptable.py (modified) (1 diff)
• machine_learning/predictor_runner.py (modified) (1 diff)
• machine_learning/tests/common/test_keyword_vectors.py (modified) (3 diffs)

.gitignore

@@ -122 +122 @@
 *.npy
 .coverage
+*.pyc

machine_learning/common/keyword_vector.py

@@ -5 +5 @@
 import os
 import re
+import sys
 import numpy as np
 
@@ -18 +19 @@
         print("Please provide a valid input file as argument to read "
               "dictionary")
-        raise FileNotFoundError
+        if sys.version_info[0] == 3:
+            raise FileNotFoundError
+        else:
+            raise IOError
+
 
     dictionary = []
@@ -38 +43 @@
     if not os.path.isfile(filename):
         print("Please provide a valid input file as argument")
-        raise FileNotFoundError
+        if sys.version_info[0] == 3:
+            raise FileNotFoundError
+        else:
+            raise IOError
     assert dictionary is not None, \
             "Please provide a valid dictionary as argument"

machine_learning/common/lookuptable.py

@@ -28 +28 @@
         os.makedirs(data_path)
     tbz2_path = os.path.join(data_path, file_name)
+    urllib.request.urlcleanup()
     urllib.request.urlretrieve(tbz2_url, tbz2_path)
 

machine_learning/predictor_runner.py

@@ -7 +7 @@
 import numpy as np
 from model.predictor import *
+
+def find_prediction(filename):
+    dictionary = read_dictionary(KEYWORDS_FILE)
+    start = time.time()
+    vectors, file_list = create_table(dictionary=dictionary)
+    end = time.time()
+    print(end - start, "seconds to create_table")
+
+    predictor = HelpPagePredictor()
+    predictor.fit(vectors, file_list)
+
+    start = time.time()
+    test_vec = count_occurances(filename, dictionary)
+    prediction = predictor.predict(np.array([test_vec]))
+    end = time.time()
+    print(end - start, "seconds to make prediction")
+    return prediction
+    
 
 def main():

machine_learning/tests/common/test_keyword_vectors.py

@@ +1 @@
+import sys
 import unittest
 import numpy as np
@@ -13 +14 @@
 
         print("Non-existant file")
-        self.assertRaises(FileNotFoundError, read_dictionary, "asdfasdf")
+        if sys.version_info[0] == 3:
+            self.assertRaises(FileNotFoundError,
+                              read_dictionary,
+                              "asdfasdf")
+        else:
+            self.assertRaises(IOError,
+                              read_dictionary,
+                              "asdfasdf")
+
 
         print("Reading default file")
@@ -28 +37 @@
         dic = read_dictionary()
         print("Test non-existant file")
-        self.assertRaises(FileNotFoundError, count_occurances, "asdfasdf",
-                dic)
+        if sys.version_info[0] == 3:
+            self.assertRaises(FileNotFoundError,
+                              count_occurances,
+                              "asdfasdf",
+                              dic)
+        else:
+            self.assertRaises(IOError,
+                              count_occurances,
+                              "asdfasdf",
+                              dic)
 
         print("Count occurances with None dictionary:")