Changeset 2a4516e in git for machine_learning/common/keyword_vector.py

Timestamp:

Jul 25, 2019, 4:01:14 PM (5 years ago)

Author:

Murray Heymann <heymann.murray@…>

Branches:

(u'spielwiese', 'fe61d9c35bf7c61f2b6cbf1b56e25e2f08d536cc')

Children:

dd499fe3f7367342e4f0cf3495cdab72a21c2280

Parents:

1a034b64ea0141af657c8bd605ec28fcfe0d1d8b

Message:

Cleanup and test predictor.py

File:

• machine_learning/common/keyword_vector.py (modified) (12 diffs)

machine_learning/common/keyword_vector.py

@@ -1 +1 @@
 #!/usr/bin/python3
+
+"""Some vector logic"""
 
 import math
@@ -9 +11 @@
 
 def read_dictionary(filename):
+    """
+    Read a dictionary saved as a textfile
+    """
     if not os.path.isfile(filename):
         print("Please provide a valid input file as argument")
@@ -25 +30 @@
 
 def count_occurances(filename, dictionary):
+    """
+    Create a vector from a dictionary and populate the counts according to
+    a specified file
+    """
     if not os.path.isfile(filename):
         print("Please provide a valid input file as argument")
@@ -32 +41 @@
         return {}
     vector = create_vector(dictionary)
-    with open(filename, "r+") as file: 
+    with open(filename, "r+") as file:
         line = file.readline()
 
@@ -38 +47 @@
             # DONE: replace all non-alphanumeric characters with space
             # words = line.split()
-            words = re.sub('[^0-9a-zA-Z\-\_]', ' ', line).split()
+            words = re.sub('[^0-9a-zA-Z\-\_]', ' ', line).split() # pylint: disable=anomalous-backslash-in-string
             for word in words:
                 if word in vector.keys():
@@ -49 +58 @@
 
 def copy_dictionary(dictionary):
+    """
+    Return an identical copy of a dictionary
+    """
     new_dic = []
     for word in dictionary:
@@ -56 +68 @@
 
 def copy_vector(vector):
+    """
+    Return an identical copy of a vector
+    """
     new_vector = {}
     for key in vector.keys():
@@ -65 +80 @@
 
 def create_vector(dictionary):
-    vector={}
+    """
+    Create a zero vector for a given dictionary
+    """
+    vector = {}
     for word in dictionary:
         vector[word] = 0
@@ -72 +90 @@
 
 def vector_distance(vec1, vec2):
+    """
+    Calculate the Euclidean distance between two vectors.
+    """
     if not set(vec1.keys()) == set(vec2.keys()):
         print("Dictionaries don't have the same keys")
@@ -82 +103 @@
 
     dist = 0
-    for key in nvec1.keys():
+    for key in nvec1:
         dist = dist + (nvec1[key] - nvec2[key]) ** 2
 
     dist = math.sqrt(dist)
-    
+
     return dist
 
 
 def normalise_vector(vec):
-    sum = 0
+    """
+    Take a given vector and normalise each entry to get a Euclidean
+    distance of 1 between the zero vector and the vector itself.
+    """
+    sum_vals = 0
     for key in vec.keys():
-        sum = sum + (vec[key] * vec[key])
-    
-    sum = math.sqrt(sum)
+        sum_vals = sum_vals + (vec[key] * vec[key])
+
+    sum_vals = math.sqrt(sum_vals)
 
     for key in vec.keys():
-        vec[key] = (vec[key] + 0.0) / sum
+        vec[key] = (vec[key] + 0.0) / sum_vals
 
 
@@ -107 +132 @@
         sys.exit(1)
 
-    dic = read_dictionary(sys.argv[1])
+    dic = read_dictionary(sys.argv[1]) # pylint: disable=invalid-name
 
-    vector = {"hello":3, "bye":4}
-    normalise_vector(vector)
-    print("normalised vector: " + str(vector))
+    testvector = {"hello":3, "bye":4} # pylint: disable=invalid-name
+    normalise_vector(testvector)
+    print("normalised vector: " + str(testvector))
 
-    vector1 = {"hello":3, "bye":4}
-    vector2 = {"hello":4, "bye":3}
+    vector1 = {"hello":3, "bye":4} # pylint: disable=invalid-name
+    vector2 = {"hello":4, "bye":3} # pylint: disable=invalid-name
     print("distance same vector: " + str(vector_distance(vector1, vector1)))
     print("distance different vector: " + str(vector_distance(vector1, vector2)))
@@ -120 +145 @@
     print(vector2)
 
-    print(count_occurances("Singular/table.h", dic))
+    print(count_occurances("../Singular/table.h", dic))