Documentation edits

Author: firefly-cpp

README.md

@@ -14,14 +14,13 @@
 ![GitHub commit activity](https://img.shields.io/github/commit-activity/w/firefly-cpp/niaarm.svg)
 [![Average time to resolve an issue](http://isitmaintained.com/badge/resolution/firefly-cpp/niaarm.svg)](http://isitmaintained.com/project/firefly-cpp/niaarm "Average time to resolve an issue")
 
-## General outline of framework
-NiaARM is a framework for Association Rule Mining based on nature-inspired algorithms for optimization. The framework is fully written in Python and runs on all platforms.
-NiaARM allows users to automatically preprocess the data in a transaction database, to search for association rules and provide pretty output of rules found. This framework also supports numerical and real-valued types of attributes besides the categorical ones. Mining the association rules is defined as an optimization problem and solved using the nature-inspired algorithms that comes from the related framework called [NiaPy](https://github.com/NiaOrg/NiaPy).
+## General outline of the framework
+NiaARM is a framework for Association Rule Mining based on nature-inspired algorithms for optimization. The framework is written fully in Python and runs on all platforms. NiaARM allows users to preprocess the data in a transaction database automatically, to search for association rules and provide a pretty output of the rules found. This framework also supports numerical and real-valued types of attributes besides the categorical ones. Mining the association rules is defined as an optimization problem, and solved using the nature-inspired algorithms that come from the related framework called [NiaPy](https://github.com/NiaOrg/NiaPy).
 
 ## Detailed insights
-Current version witholds (but is not limited to) following functions:
+The current version witholds (but is not limited to) the following functions:
 
-- loading dataset in CSV format,
+- loading datasets in CSV format,
 - preprocessing of data,
 - searching for association rules,
 - providing output of mined association rules,

datasets/README.md

@@ -1,5 +1,5 @@
 # References
 
-- Abalone dataset is downloaded from https://archive.ics.uci.edu/ml/index.php.
+- The Abalone dataset is downloaded from https://archive.ics.uci.edu/ml/index.php.
 
-- wiki_test_case dataset is composed from first Table found in: https://en.wikipedia.org/wiki/Lift_(data_mining)
+- The wiki_test_case dataset is composed from the first Table found in: https://en.wikipedia.org/wiki/Lift_(data_mining)

examples/basic_run.py

@@ -5,14 +5,14 @@
 
 
 if __name__ == '__main__':
-    # load and preprocess dataset from csv
+    # load and preprocess the dataset from csv
     data = Dataset("datasets/Abalone.csv")
 
     # Create a problem:::
-    # dimension represents dimension of the problem;
+    # dimension represents the dimension of the problem;
     # features represent the list of features, while transactions depicts the list of transactions
     # the following 4 elements represent weights (support, confidence, coverage, shrinkage)
-    # None defines that criteria is omitted and is therefore excluded from fitness function
+    # None defines that criteria are omitted and are, therefore, excluded from the fitness function
     problem = NiaARM(data.dimension, data.features, data.transactions, alpha=1.0, beta=1.0)
 
     # build niapy task

examples/feature_report.py

@@ -4,7 +4,7 @@
 # numerical features: min and max borders
 # categorical features: all categories
 if __name__ == '__main__':
-    # load and preprocess dataset from csv
+    # load and preprocess the dataset from csv
     data = Dataset("datasets/Abalone.csv")
     # get feature report
     data.feature_report()

niaarm/association_rule.py

@@ -20,10 +20,10 @@ def build_rule(self, vector):
             current_feature = self.permutation[i]
             feature = self.features[current_feature]
 
-            # set current position in vector
+            # set current position in the vector
             vector_position = self.feature_position(current_feature)
 
-            # get threshold for each feature
+            # get a threshold for each feature
             threshold_position = vector_position + self.threshold_move(current_feature)
 
             if vector[vector_position] > vector[threshold_position]:

niaarm/dataset.py

@@ -3,14 +3,14 @@
 
 
 class Dataset:
-    r"""Class for working with dataset.
+    r"""Class for working with a dataset.
 
     Attributes:
         data (pd.DataFrame): Data as a pandas Dataframe.
         transactions (np.ndarray): Transactional data.
         header (list[str]): Feature names.
         features (list[Feature]): List of features.
-        dimension (int): Dimension of the optimization problem for dataset.
+        dimension (int): Dimension of the optimization problem for the dataset.
 
     """
 
@@ -25,7 +25,7 @@ def __init__(self, path, delimiter=',', header=0, names=None):
         self.dimension = self.__problem_dimension()
 
     def __analyse_types(self):
-        r"""Extract data types for data in dataset."""
+        r"""Extract data types for the data in a dataset."""
         for head in self.header:
             col = self.data[head]
 

niaarm/feature.py

@@ -7,10 +7,10 @@ class Feature:
     r"""Class representing a feature.
 
     Attributes:
-       name (str): Name of feature.
-       dtype (str): Datatype of feature.
-       min_val (Optional[float]): Minimum value of feature in transaction database.
-       max_val (Optional[float]): Maximum value of feature in transaction database.
+       name (str): Name of the feature.
+       dtype (str): Datatype of the feature.
+       min_val (Optional[float]): Minimum value of the feature in the transaction database.
+       max_val (Optional[float]): Maximum value of the feature in the transaction database.
        categories (Optional[list[float]]): Possible categorical feature's values.
 
     """

niaarm/niaarm.py

@@ -23,7 +23,7 @@ class NiaARM(Problem):
 
     Attributes:
         features (list[Feature]): List of features.
-        transactions (np.ndarray): Data from transaction database.
+        transactions (np.ndarray): Data from the transaction database.
         rules (list[Rule]): Mined association rules.
 
     """
@@ -46,14 +46,14 @@ def __init__(self, dimension, features, transactions, alpha=0.0, beta=0.0, gamma
         super().__init__(dimension, 0.0, 1.0)
 
     def rule_exists(self, antecedent, consequent):
-        r"""Check if association rule already exists."""
+        r"""Check if the association rule already exists."""
         for rule in self.rules:
             if rule.antecedent == antecedent and rule.consequent == consequent:
                 return True
         return False
 
     def export_rules(self, path):
-        r"""Save all association rules found to csv file."""
+        r"""Save all association rules found to a csv file."""
         with open(path, 'w', newline='') as f:
             writer = csv.writer(f)
 
@@ -84,7 +84,7 @@ def _evaluate(self, sol):
         antecedent = rule[:cut]
         consequent = rule[cut:]
 
-        # check if rule is feasible
+        # check if the rule is feasible
         if _rule_feasible(antecedent, consequent):
             # get support and confidence of rule
             support, confidence = arm.support_confidence(antecedent, consequent, self.transactions)
@@ -126,8 +126,8 @@ def _evaluate(self, sol):
 
 
 def _fix_border(antecedent, consequent):
-    r"""In case lower and upper bounds of interval are the same.
-        We need this in order to provide clean output.
+    r"""In case the lower and the upper bounds of interval are the same.
+        We need this in order to provide a clean output.
 
         Arguments:
             antecedent (np.ndarray): .

niaarm/rule.py

@@ -7,13 +7,13 @@ class Rule:
     r"""Class representing an association rule.
 
     Attributes:
-        antecedent (list[str]): A list of antecedents of association rule.
-        consequent (list[str]): A list of consequents of association rule.
-        fitness (float): Value of fitness function.
-        support (float): Value of support.
-        confidence (float): Value of confidence.
-        shrink (Optional[float]): Value of shrink.
-        coverage (Optional[float]): Value of coverage.
+        antecedent (list[str]): A list of antecedents of the association rule.
+        consequent (list[str]): A list of consequents of the association rule.
+        fitness (float): Value of the fitness function.
+        support (float): Value of the support.
+        confidence (float): Value of the confidence.
+        shrink (Optional[float]): Value of the shrink.
+        coverage (Optional[float]): Value of the coverage.
 
     """
 

niaarm/tests/test_coverage.py

@@ -4,7 +4,7 @@
 
 
 class TestCoverage(TestCase):
-    # let's borrow test case from wikipedia:
+    # let's borrow a test case from wikipedia:
     # https://en.wikipedia.org/wiki/Lift_(data_mining)
 
     def setUp(self):