Many small changes. Imports, uniqueness, etc.

ease/essay_set.py

@@ -3,7 +3,6 @@ Defines an essay set object, which encapsulates essays from training and test se
 Performs spell and grammar checking, tokenization, and stemming.
 """
 
-import numpy
 import nltk
 import sys
 import random

ease/feature_extractor.py

@@ -3,14 +3,12 @@ Extracts features from training set and test set essays
 """
 
 import numpy
-import re
 import nltk
 import sys
 from sklearn.feature_extraction.text import CountVectorizer
 import pickle
 import os
 from itertools import chain
-import copy
 import operator
 import logging
 

ease/grade.py

@@ -4,7 +4,6 @@ Functions to score specified data using specified ML models
 
 import sys
 import os
-import numpy
 import logging
 
 # Append sys to base path to import the following modules
@@ -13,12 +12,8 @@ sys.path.append(base_path)
 
 #Depend on base path to be imported
 from essay_set import EssaySet
-import util_functions
 from errors import *
 
-#Imports needed to unpickle grader data
-import math
-
 log = logging.getLogger(__name__)
 
 
@@ -51,7 +46,7 @@ def grade(grader_data, submission):
     feedback = {}
 
     # Retrieves the model and extractor we will be using
-    model, extractor = get_classifier_and_extractor(grader_data)
+    model, extractor = _get_classifier_and_extractor(grader_data)
 
     # Attempts to add the essay (text) to the essay set.
     try:
@@ -82,7 +77,7 @@ def grade(grader_data, submission):
     return results
 
 
-def get_classifier_and_extractor(grader_data):
+def _get_classifier_and_extractor(grader_data):
     """
     Finds the classifier and extractor from a completed training operation in order to perform the grading operation.
 

ease/util_functions.py

@@ -147,19 +147,6 @@ def ngrams(tokens, min_n, max_n):
     return all_ngrams
 
 
-def make_unique(sequence):
-    """
-    Makes a list of elements unique
-
-    Args:
-        sequence (list of any comparable): A sequence to make unique
-
-    Return:
-        the list without any duplicates.  May be out of order.
-    """
-    return list(set(sequence))
-
-
 def get_vocab(essays, scores, max_features_pass_1=750, max_features_pass_2=200):
     """
     Uses a fisher test to find words that are significant in that they separate
@@ -337,8 +324,12 @@ def histogram(ratings, min_rating=None, max_rating=None):
 def get_wordnet_syns(word):
     """
     Utilize wordnet (installed with nltk) to get synonyms for words
-    word is the input word
-    returns a list of unique synonyms
+
+    Args:
+        word (str): the word to generate synonyms for
+
+    Returns:
+        (list of str): Unique synonyms for the word
     """
     synonyms = []
     regex = r"_"
@@ -347,5 +338,6 @@ def get_wordnet_syns(word):
     for ss in synset:
         for swords in ss.lemma_names:
             synonyms.append(pat.sub(" ", swords.lower()))
-    synonyms = make_unique(synonyms)
+    # Makes the synonym list unique
+    synonyms = list(set(synonyms))
     return synonyms