Adds a num_classes parameter to the mock_categorical_data function.

cityseer/util/mock.py

@@ -3,7 +3,7 @@
 '''
 import logging
 from typing import Tuple
-import json
+import string
 
 import networkx as nx
 import numpy as np
@@ -223,13 +223,16 @@ def mock_data_dict(G: nx.Graph, length: int = 50, random_seed: int = None) -> di
     return data_dict
 
 
-def mock_categorical_data(length: int, random_seed: int = None) -> np.ndarray:
+def mock_categorical_data(length: int, num_classes: int = 10, random_seed: int = None) -> np.ndarray:
     if random_seed is not None:
         np.random.seed(seed=random_seed)
 
-    random_class_str = 'abcdefghijk'
-    d = []
+    random_class_str = string.ascii_lowercase
+    if num_classes > len(random_class_str):
+        raise ValueError(f'The requested {num_classes} classes exceeds the max available categorical classes: {len(random_class_str)}')
+    random_class_str = random_class_str[:num_classes]
 
+    d = []
     for i in range(length):
         d.append(random_class_str[np.random.randint(0, len(random_class_str) - 1)])
 

docs/util/mock.md

@@ -72,7 +72,7 @@ A dictionary where each entry consists of a `key` representing a distinct data p
 
 mock\_categorical\_data
 -----------------------
-<FuncSignature>mock_categorical_data(length, random_seed=None)</FuncSignature>
+<FuncSignature>mock_categorical_data(length, num_classes=10, random_seed=None)</FuncSignature>
 
 Generates a `numpy` array containing mock categorical data for testing or experimentation purposes.
 
@@ -84,6 +84,12 @@ The number of categorical elements to return in the array.
 
 </FuncElement>
 
+<FuncElement name="num_classes" type="int">
+
+The maximum number of unique classes to return in the randomly assigned categorical data. The classes are randomly generated from a pool of unique class labels of length `num_classes`. The number of returned unique classes will be less than or equal to `num_classes`.
+
+</FuncElement>
+
 <FuncElement name="random_seed" type="int">
 
 For the use of a specified random seed.

setup.py

@@ -16,7 +16,7 @@
 
 setup (
     name = 'cityseer',
-    version='0.8.16',
+    version='0.8.17',
     packages=['cityseer', 'cityseer.algos', 'cityseer.metrics', 'cityseer.util'],
     description = 'Computational tools for urban analysis',
     url='https://github.com/cityseer/cityseer-api',

tests/util/test_mock.py

@@ -1,5 +1,7 @@
 import networkx as nx
 import numpy as np
+import pytest
+import string
 
 from cityseer.util import mock
 
@@ -57,10 +59,20 @@ def test_mock_data_dict():
 def test_mock_categorical_data():
     cat_d = mock.mock_categorical_data(50)
     assert len(cat_d) == 50
+    # classes are generated randomly from max number of classes
+    # i.e. situations do exist where the number of classes will be less than the max permitted
+    assert len(set(cat_d)) <= 10
 
     for c in cat_d:
         assert isinstance(c, str)
-        assert c in 'abcdefghijk'
+        assert c in string.ascii_lowercase
+
+    cat_d = mock.mock_categorical_data(50, num_classes=3)
+    assert len(set(cat_d)) <= 3
+
+    # test that an error is raised when requesting more than available max classes per asii_lowercase
+    with pytest.raises(ValueError):
+        mock.mock_categorical_data(50, num_classes=len(string.ascii_lowercase) + 1)
 
 
 def test_mock_numerical_data():