Added few comments and Regex Patterns

feature_extraction/features.py

@@ -1,13 +1,13 @@
-from utils.constants import REGEX_CONSTANTS
 import feature_extraction.lexicons as lexicons
-import re
+from utils.constants import REGEX_CONSTANTS
 
 """ List of supported features for feature extraction from Input String """
 FEATURE_LIST = ['COMPARE', 'CONTRAST', 'RESULT', 'USE', 'IMPORTANT', 'RESEARCH', 'APPROACH',
                 'PUBLIC', 'BEFORE', 'BETTER_SOLUTION', 'PROFESSIONALS', 'CITATION', 'ACRONYM',
-                'CONTAINS_YEAR', 'SEQUENCE', 'REFERENCE']
+                'CONTAINS_YEAR', 'SEQUENCE', 'REFERENCE', 'PERCENTAGE', 'URL']
 
-REGEX_FEATURES = ['ACRONYM', 'CONTAINS_YEAR', 'SEQUENCE', 'REFERENCE']
+""" Features with Regex Pattern Matching - For these features, get the regex pattern from constants"""
+REGEX_FEATURES = ['ACRONYM', 'CONTAINS_YEAR', 'SEQUENCE', 'REFERENCE', 'PERCENTAGE', 'URL']
 
 
 def extract_features_from_text(text: str):
@@ -25,11 +25,16 @@ def extract_features_from_text(text: str):
     # Iterate through the list features and get list of words from the lexicon dictionary,
     # for each word in the word list, check if it appears in input text and add it to the text feature list
     for feature in FEATURE_LIST:
+
+        # If the feature is Regex Pattern Match, get the pattern from :`~feature_extraction.lexicons.ALL_LEXICONS`
+        # and match it with the input text
         if feature in REGEX_FEATURES:
             pattern = REGEX_CONSTANTS[feature]
             if bool(pattern.match(text)):
                 text_feature_list.append(feature)
             continue
+
+        # If the feature is not a Regex Pattern Match, then get the list of dictionary words from lexicon dictionary
         word_list = lexicon_dict[feature]
         for word in word_list:
             if word in text:

feature_extraction/lexicons.py

@@ -1,3 +1,6 @@
+"""
+Dictionary of Lexicons used for Feature Extraction
+"""
 ALL_LEXICONS = {
 
     'COMPARE': ['compar' 'compet', 'evaluat', 'test', 'superior', 'inferior', 'better', 'best', 'worse', 'worst',

testing/eval_testing.py

@@ -28,6 +28,5 @@ train_file_path = project_root+'/data/tsv/train.tsv'
 print(train_file_path)
 
 data = read_csv_file(csv_file_path=train_file_path, delimiter='\t')
-for inst in data:
+for inst in data[:10]:
-    if len(inst.features) <= 0:
     inst.print()

utils/constants.py

@@ -5,8 +5,23 @@ AVG_MICRO = 'MICRO'
 AVG_MACRO = 'MACRO'
 
 REGEX_CONSTANTS = {
-    'ACRONYM': re.compile(r"\s*\b[A-Z.]{2,}s?\b\s*"),
+
-    'CONTAINS_YEAR': re.compile('.*([1-2][0-9]{3})'),
+    # Regex for matching Acronym Patterns -> COVID-19 / SEKA / SMY2 / EAP1 / SCP16 / ASC1 / DENV-2
-    'SEQUENCE': re.compile(r'\s+\((\d+,* *)*\)\s+'),
+    'ACRONYM': re.compile(r"\s*\b[A-Z.]{2,}s?\b\s*"),  # TODO :: (for Isaac)
-    'REFERENCE': re.compile(r"\s*\[(\d+,* *)*\]\s*")
+
+    # Regex for matching Years in the text - > 1995 / 2020 / 2019
+    'CONTAINS_YEAR': re.compile('.*([1-2][0-9]{3})'),  # TODO :: (for Isaac)
+
+    # Regex for matching Number Sequences in the text -> (15) / (10, 11, 112, 113) / (1,7,8,10-14)
+    'SEQUENCE': re.compile(r'\s+\((\d+,* *)*\)\s+'),  # TODO :: (for Isaac)
+
+    # Regex for matching References in the text -> [4] / [ 10-17, 19, 20] / [123, 500]
+    'REFERENCE': re.compile(r"\s*\[(\d+,* *)*\]\s*"),  # TODO :: (for Isaac)
+
+    # Regex for matching percentages in the text -> 99% / 99.99% / 10 % / 23.98% / 10-20% / 25%-30%
+    'PERCENTAGE': re.compile(r"\d+(\.\d+)?%"),  # TODO :: (for Isaac)
+
+    # Regex for matching URLs -> http://www.phrap.org/, http://www. , http://carcfordjournals. ,
+    # https://www.ims.uni-stuttgart.de/
+    'URL': re.compile(r"https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+")  # TODO :: (for Isaac)
 }

utils/models.py

@@ -3,7 +3,8 @@ from feature_extraction.features import extract_features_from_text
 
 class DataInstance:
     """
-    Model Class for carrying Training and Testing data from tsc/csv file
+    Model Class for carrying Training and Testing data from tsv/csv file.
+    Also carries the extracted features.
     """
 
     def __init__(self, r_id, text, true_label):