SwapCase (#24)

Fixing pipeline documentation bug, 
adding SwapCase generator, 
fixing LeetSpeak bug,
Adding swapcase documentation + pipelines

Author: siebert-julien

badgers/generators/text/typos.py

@@ -32,10 +32,7 @@ class SwapLettersGenerator(TyposGenerator):
 
     def __init__(self, random_generator=default_rng(seed=0)):
         """
-
         :param random_generator: A random generator
-
-
         """
         super().__init__(random_generator)
 
@@ -110,10 +107,11 @@ def randomly_replace_letter(self, letter, replacement_proba):
         :param replacement_proba: the probability of replacing a letter with its leet counterpart
         :return:
         """
-        if self.random_generator.random() < replacement_proba:
-            return self.random_generator.choice(self.leet_speak_mapping[letter.upper()])
-        else:
-            return letter
+        if letter.upper() in self.leet_speak_mapping:
+            if self.random_generator.random() < replacement_proba:
+                letter = self.random_generator.choice(self.leet_speak_mapping[letter.upper()])
+
+        return letter
 
     def generate(self, X, y, replacement_proba: float = 0.1) -> Tuple:
         """
@@ -130,3 +128,32 @@ def generate(self, X, y, replacement_proba: float = 0.1) -> Tuple:
         ]
 
         return Xt, y
+
+class SwapCaseGenerator(TyposGenerator):
+
+    def __init__(self, random_generator=default_rng(seed=0)):
+        """
+        :param random_generator: A random generator
+        """
+        super().__init__(random_generator)
+
+    def randomly_swapcase_letter(self, letter, swapcase_proba):
+        """
+        Randomly swap case a letter
+        :param letter:
+        :param swapcase_proba: the probability of swapping case
+        :return:
+        """
+        if self.random_generator.random() < swapcase_proba:
+            letter = letter.swapcase()
+
+        return letter
+
+    def generate(self, X, y, swapcase_proba: float = 0.1) -> Tuple:
+        assert 0 <= swapcase_proba <= 1
+        Xt = [
+            ''.join([self.randomly_swapcase_letter(l, swapcase_proba=swapcase_proba) for l in word])
+            for word in X
+        ]
+
+        return Xt, y

docs/tutorials/tabular-data/Pipeline-Tabular-Data.ipynb renamed to docs/tutorials/Pipeline-Tabular-Data.ipynb

@@ -15,7 +15,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from badgers.generators.text.typos import SwapLettersGenerator, LeetSpeakGenerator"
+    "from badgers.generators.text.typos import SwapLettersGenerator, LeetSpeakGenerator, SwapCaseGenerator"
    ]
   },
   {
@@ -152,13 +152,104 @@
     "print('Transformed:\\t'+' '.join(Xt))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "180fe290-ed49-4027-9e59-c18cf89e5eb4",
+   "metadata": {},
+   "source": [
+    "## Swap case"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "9bcc0865-d9dd-4b95-ab4a-57feaad7c330",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "swap_case = SwapCaseGenerator()"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "04439b35-c84f-4dcf-ad73-0e6ba11518a7",
+   "execution_count": 11,
+   "id": "d947f6af-71fe-4913-90fa-4b37d929ea21",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "Xt, _ = swap_case.generate(X.copy(), y=None, swapcase_proba=0.25)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "ded6a17c-4e2c-483a-8894-99857a2132f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original:\tthe quick brown fox jumps over the lazy dog\n",
+      "Transformed:\tthE Quick broWn FoX jumpS Over the lazy Dog\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('Original:\\t'+' '.join(X))\n",
+    "print('Transformed:\\t'+' '.join(Xt))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0fdd30b-a223-4a35-9dab-4696238915a5",
+   "metadata": {},
+   "source": [
+    "## Using pipelines"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "90e5ca7b-c959-44de-aa8b-ebd4d09d24aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from badgers.core.pipeline import Pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "87f4d09e-8d89-4c3f-9640-6646f2082fa7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "generators = {'swap_letters': swap_letters, 'leet_speak': leet_speak, 'swap_case': swap_case}\n",
+    "params = {'swap_letters': {'swap_proba':0.5}, 'leet_speak': {'replacement_proba':0.25}, 'swap_case': {'swapcase_proba':0.25}}\n",
+    "pipeline = Pipeline(generators=generators)\n",
+    "Xt, _ = pipeline.generate(X.copy(), y=None, params=params)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "2b5fe819-9133-4038-bd25-189c3ef6a4a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original:\tthe quick brown fox jumps over the lazy dog\n",
+      "Transformed:\tthe quick /3®Ow^ vo)( Jv(v)|^eHS ov€R t|~|e lzay dog\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('Original:\\t'+' '.join(X))\n",
+    "print('Transformed:\\t'+' '.join(Xt))"
+   ]
   }
  ],
  "metadata": {
@@ -177,7 +268,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

docs/tutorials/text/Typos-Text.ipynb

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "badgers"
-version = "0.0.9"
+version = "0.0.10"
 keywords = ["data quality", "bad data", "data science"]
 authors = [
     { name = "Julien Siebert", email = "[email protected]" },

pyproject.toml

@@ -0,0 +1,15 @@
+numpy~=2.2.0
+scikit-learn~=1.6.0
+networkx~=3.4.2
+pandas~=2.2.3
+scipy~=1.14.1
+tox~=4.23.2
+mkdocs~=1.4.3
+mkdocstrings~=0.25.2
+mkdocstrings-python~=1.10.9
+mkdocs-gen-files~=0.5.0
+mkdocs-material~=9.1.12
+mkdocs-literate-nav~=0.6.0
+mkdocs-jupyter~=0.24.1
+jupyterlab~=4.3.4
+matplotlib~=3.10.0

requirements.txt

@@ -3,7 +3,7 @@
 
 from numpy.random import default_rng
 
-from badgers.generators.text.typos import SwapLettersGenerator, LeetSpeakGenerator
+from badgers.generators.text.typos import SwapLettersGenerator, LeetSpeakGenerator, SwapCaseGenerator
 
 
 class TestSwapLettersGenerator(unittest.TestCase):
@@ -43,11 +43,22 @@ def test_transform(self):
 class TestLeetSpeakGenerator(unittest.TestCase):
 
     def test_generate(self):
-        X = ['the', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'fox']
+        X = ['the', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'fox', ' <> ']
         trf = LeetSpeakGenerator()
         Xt, _ = trf.generate(X, None)
         self.assertEqual(len(X), len(Xt))
 
 
+class TestSwapCaseGenerator(unittest.TestCase):
+
+    def test_generate(self):
+        X = ['the', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'fox', ' <> ']
+        trf = SwapCaseGenerator()
+        Xt, _ = trf.generate(X, None, swapcase_proba=1.)
+        self.assertEqual(len(X), len(Xt))
+        for w1, w2 in zip(X, Xt):
+            self.assertEqual(w1.upper(), w2)
+
+
 if __name__ == '__main__':
     unittest.main()