Changeset 872089 in git

Timestamp:

Jul 26, 2019, 4:13:00 PM (4 years ago)

Author:

Murray Heymann <heymann.murray@…>

Branches:

(u'spielwiese', 'd1ba061a762c62d3a25159d8da8b6e17332291fa')

Children:

55a5abbd0397943b2c98a4492b27ecbc050c20ef

Parents:

746d3db65a7b75cbc29407ee9382332483801f1d

Message:

Reorganize source tree, make test prediction

Files:

• .gitignore (modified) (1 diff)
• machine_learning/__init__.py (added)
• machine_learning/common/lookuptable.py (modified) (3 diffs)
• machine_learning/model/__init__.py (added)
• machine_learning/model/predictor.py (moved) (moved from machine_learning/common/predictor.py) (2 diffs)

.gitignore

@@ -120 +120 @@
 keywords.txt
 helpfiles
+*.npy

machine_learning/common/lookuptable.py

@@ -1 +1 @@
 """
+j
 A Module for fetching helpfiles, creating vectors for each and bundling
 these up in a lookup table.
@@ -13 +14 @@
 
 # local imports
-from keyword_vector import count_occurances, read_dictionary
-from constants import HELP_FILE_URL, HELP_FILE_PATH, SINGULAR_BIN, \
+from common.keyword_vector import count_occurances, read_dictionary
+from common.constants import HELP_FILE_URL, HELP_FILE_PATH, SINGULAR_BIN, \
                         EXTRACT_SCRIPT, KEYWORDS_FILE, HELPFILE_NPY, \
                         VECTORS_NPY
@@ -51 +52 @@
 
 
-def create_table():
+def create_table(dictionary=read_dictionary(KEYWORDS_FILE)):
     """
     Get a list of helpfiles, and generate a word occurance vector for each.
     """
-    vectors = []
-    dictionary = read_dictionary(KEYWORDS_FILE)
+    vectors = [] 
 
     if not os.path.isfile(VECTORS_NPY) or not os.path.isfile(HELPFILE_NPY):

machine_learning/model/predictor.py

@@ -8 +8 @@
 
 # Local imports
-from keyword_vector import vector_distance
+from common.keyword_vector import vector_distance, count_occurances, \
+                                    read_dictionary
+from common.lookuptable import create_table
+from common.constants import KEYWORDS_FILE
 
 
@@ -89 +92 @@
     print(prediction)
 
+    dictionary = read_dictionary(KEYWORDS_FILE)
+    vectors, file_list = create_table(dictionary=dictionary)
+    test_vec = count_occurances("extract.lib", dictionary)
+    predictor.fit(vectors, file_list)
+    prediction = predictor.predict(np.array([test_vec]))
+    print(prediction)
+
 if __name__ == '__main__':
     main()