idscrub 0.2.0__tar.gz → 0.2.1__tar.gz

{idscrub-0.2.0 → idscrub-0.2.1}/PKG-INFO

@@ -1,11 +1,12 @@
 Metadata-Version: 2.4
 Name: idscrub
-Version: 0.2.0
+Version: 0.2.1
 Author: Department for Business and Trade
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: ipykernel>=7.1.0
+Requires-Dist: ipywidgets
 Requires-Dist: numpy>=2.3.4
 Requires-Dist: pandas>=2.3.3
 Requires-Dist: phonenumbers>=9.0.18

{idscrub-0.2.0 → idscrub-0.2.1}/idscrub/scrub.py

@@ -906,11 +906,8 @@ class IDScrub:
 
         """
 
-        for i, scrub_method in enumerate(scrub_methods):
-            if i == len(scrub_methods) - 1:
-                self.call_scrub_method(scrub_method)
-            else:
-                self.call_scrub_method(scrub_method)
+        for scrub_method in scrub_methods:
+            self.call_scrub_method(scrub_method)
 
         return self.cleaned_texts
 

{idscrub-0.2.0 → idscrub-0.2.1}/idscrub.egg-info/PKG-INFO

@@ -1,11 +1,12 @@
 Metadata-Version: 2.4
 Name: idscrub
-Version: 0.2.0
+Version: 0.2.1
 Author: Department for Business and Trade
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: ipykernel>=7.1.0
+Requires-Dist: ipywidgets
 Requires-Dist: numpy>=2.3.4
 Requires-Dist: pandas>=2.3.3
 Requires-Dist: phonenumbers>=9.0.18

{idscrub-0.2.0 → idscrub-0.2.1}/idscrub.egg-info/requires.txt

@@ -1,4 +1,5 @@
 ipykernel>=7.1.0
+ipywidgets
 numpy>=2.3.4
 pandas>=2.3.3
 phonenumbers>=9.0.18

{idscrub-0.2.0 → idscrub-0.2.1}/notebooks/basic_usage.ipynb

@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -18,7 +18,7 @@
      "text": [
       "INFO: Texts loaded.\n",
       "INFO: Scrubbing names using SpaCy model `en_core_web_trf`...\n",
-      "100%|██████████| 2/2 [00:00<00:00, 44.29it/s]\n",
+      "100%|██████████| 2/2 [00:00<00:00, 28.72it/s]\n",
       "INFO: 3 spacy person scrubbed.\n",
       "INFO: Scrubbing phone numbers using regex...\n",
       "INFO: 1 uk phone numbers scrubbed.\n",
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -110,7 +110,7 @@
        "1           [+441111111111]            [AA11 1AA]  "
       ]
      },
-     "execution_count": 13,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -128,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -137,11 +137,11 @@
      "text": [
       "INFO: Texts loaded.\n",
       "INFO: Scrubbing using Presidio...\n",
-      "100%|██████████| 2/2 [00:00<00:00, 25.19it/s]\n",
+      "100%|██████████| 2/2 [00:00<00:00, 14.92it/s]\n",
       "INFO: 3 presidio person scrubbed.\n",
       "INFO: 1 presidio location scrubbed.\n",
       "INFO: Scrubbing names using SpaCy model `en_core_web_trf`...\n",
-      "100%|██████████| 2/2 [00:00<00:00, 48.66it/s]\n",
+      "100%|██████████| 2/2 [00:00<00:00, 49.69it/s]\n",
       "INFO: 0 spacy person scrubbed.\n",
       "INFO: Scrubbing GB phone numbers using Google's `phonenumbers`...\n",
       "INFO: 0 gb phone numbers scrubbed.\n",
@@ -184,7 +184,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -246,7 +246,7 @@
        "1                  [Lapland]           [+441111111111]            [AA11 1AA]  "
       ]
      },
-     "execution_count": 15,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -264,7 +264,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -273,7 +273,7 @@
      "text": [
       "INFO: Texts loaded.\n",
       "INFO: Scrubbing using Presidio...\n",
-      "100%|██████████| 2/2 [00:00<00:00, 23.03it/s]\n",
+      "100%|██████████| 2/2 [00:00<00:00, 29.00it/s]\n",
       "INFO: 3 presidio person scrubbed.\n",
       "INFO: Scrubbing GB phone numbers using Google's `phonenumbers`...\n",
       "INFO: 0 gb phone numbers scrubbed.\n",
@@ -324,7 +324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -389,7 +389,7 @@
        "1              [ACHILLES]           [+441111111111]            [AA11 1AA]  "
       ]
      },
-     "execution_count": 17,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -408,7 +408,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -417,7 +417,7 @@
      "text": [
       "INFO: Texts loaded.\n",
       "INFO: Scrubbing using Presidio...\n",
-      "100%|██████████| 2/2 [00:00<00:00, 23.38it/s]\n",
+      "100%|██████████| 2/2 [00:00<00:00, 24.48it/s]\n",
       "INFO: 3 presidio person scrubbed.\n",
       "INFO: 1 presidio iban code scrubbed.\n"
      ]
@@ -443,7 +443,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -499,7 +499,7 @@
        "1    [GB91BKEN10000041610008]  "
       ]
      },
-     "execution_count": 19,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -517,7 +517,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -623,7 +623,7 @@
        "4  They did not expected a reply from otis.reddin...  "
       ]
      },
-     "execution_count": 20,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -669,7 +669,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -678,12 +678,12 @@
      "text": [
       "  0%|          | 0/3 [00:00<?, ?it/s]INFO: Texts loaded.\n",
       "INFO: Scrubbing using Presidio...\n",
-      "100%|██████████| 5/5 [00:00<00:00, 18.99it/s]\n",
+      "100%|██████████| 5/5 [00:00<00:00, 31.94it/s]\n",
       "INFO: 4 presidio person scrubbed.\n",
       "INFO: 4 presidio person scrubbed.\n",
       "INFO: 4 presidio person scrubbed.\n",
       "INFO: Scrubbing names using SpaCy model `en_core_web_trf`...\n",
-      "100%|██████████| 5/5 [00:00<00:00, 67.00it/s]\n",
+      "100%|██████████| 5/5 [00:00<00:00, 71.88it/s]\n",
       "INFO: 0 spacy person scrubbed.\n",
       "INFO: Scrubbing GB phone numbers using Google's `phonenumbers`...\n",
       "INFO: 0 gb phone numbers scrubbed.\n",
@@ -699,13 +699,13 @@
       "INFO: 0 uk postcodes scrubbed.\n",
       "INFO: Scrubbing titles using regex...\n",
       "INFO: 2 titles scrubbed.\n",
-      " 33%|███▎      | 1/3 [00:03<00:06,  3.24s/it]INFO: Texts loaded.\n",
+      " 33%|███▎      | 1/3 [00:02<00:05,  2.55s/it]INFO: Texts loaded.\n",
       "INFO: Scrubbing using Presidio...\n",
-      "100%|██████████| 5/5 [00:00<00:00, 21.83it/s]\n",
+      "100%|██████████| 5/5 [00:00<00:00, 24.67it/s]\n",
       "INFO: 2 presidio person scrubbed.\n",
       "INFO: 2 presidio person scrubbed.\n",
       "INFO: Scrubbing names using SpaCy model `en_core_web_trf`...\n",
-      "100%|██████████| 5/5 [00:00<00:00, 84.69it/s]\n",
+      "100%|██████████| 5/5 [00:00<00:00, 86.96it/s]\n",
       "INFO: 0 spacy person scrubbed.\n",
       "INFO: Scrubbing GB phone numbers using Google's `phonenumbers`...\n",
       "INFO: 0 gb phone numbers scrubbed.\n",
@@ -721,15 +721,15 @@
       "INFO: 0 uk postcodes scrubbed.\n",
       "INFO: Scrubbing titles using regex...\n",
       "INFO: 0 titles scrubbed.\n",
-      " 67%|██████▋   | 2/3 [00:06<00:03,  3.24s/it]INFO: Texts loaded.\n",
+      " 67%|██████▋   | 2/3 [00:04<00:02,  2.39s/it]INFO: Texts loaded.\n",
       "INFO: Scrubbing using Presidio...\n",
-      "100%|██████████| 5/5 [00:00<00:00, 29.32it/s]\n",
+      "100%|██████████| 5/5 [00:00<00:00, 15.41it/s]\n",
       "INFO: 5 presidio url scrubbed.\n",
       "INFO: 2 presidio person scrubbed.\n",
       "INFO: 3 presidio email address scrubbed.\n",
       "INFO: 3 presidio email address scrubbed.\n",
       "INFO: Scrubbing names using SpaCy model `en_core_web_trf`...\n",
-      "100%|██████████| 5/5 [00:00<00:00, 66.37it/s]\n",
+      "100%|██████████| 5/5 [00:00<00:00, 64.25it/s]\n",
       "INFO: 0 spacy person scrubbed.\n",
       "INFO: Scrubbing GB phone numbers using Google's `phonenumbers`...\n",
       "INFO: 0 gb phone numbers scrubbed.\n",
@@ -745,7 +745,7 @@
       "INFO: 4 uk postcodes scrubbed.\n",
       "INFO: Scrubbing titles using regex...\n",
       "INFO: 0 titles scrubbed.\n",
-      "100%|██████████| 3/3 [00:08<00:00,  2.94s/it]\n"
+      "100%|██████████| 3/3 [00:07<00:00,  2.43s/it]\n"
      ]
     },
     {
@@ -851,7 +851,7 @@
        "4  They did not expected a reply from [EMAIL_ADDR...  "
       ]
      },
-     "execution_count": 21,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -866,7 +866,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -1050,7 +1050,7 @@
        "8             [EH8 8DX]  "
       ]
      },
-     "execution_count": 22,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }

{idscrub-0.2.0 → idscrub-0.2.1}/pyproject.toml

@@ -7,6 +7,7 @@ readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "ipykernel>=7.1.0",
+    "ipywidgets",
     "numpy>=2.3.4",
     "pandas>=2.3.3",
     "phonenumbers>=9.0.18",

{idscrub-0.2.0 → idscrub-0.2.1}/uv.lock

@@ -561,6 +561,7 @@ name = "idscrub"
 source = { editable = "." }
 dependencies = [
     { name = "ipykernel" },
+    { name = "ipywidgets" },
     { name = "numpy" },
     { name = "pandas" },
     { name = "phonenumbers" },
@@ -588,6 +589,7 @@ dev = [
 requires-dist = [
     { name = "en-core-web-trf", marker = "extra == 'trf'", url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_trf-3.8.0/en_core_web_trf-3.8.0-py3-none-any.whl" },
     { name = "ipykernel", specifier = ">=7.1.0" },
+    { name = "ipywidgets" },
     { name = "numpy", specifier = ">=2.3.4" },
     { name = "pandas", specifier = ">=2.3.3" },
     { name = "phonenumbers", specifier = ">=9.0.18" },
@@ -673,6 +675,22 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d9/33/1f075bf72b0b747cb3288d011319aaf64083cf2efef8354174e3ed4540e2/ipython_pygments_lexers-1.1.1-py3-none-any.whl", hash = "sha256:a9462224a505ade19a605f71f8fa63c2048833ce50abc86768a0d81d876dc81c", size = 8074, upload-time = "2025-01-17T11:24:33.271Z" },
 ]
 
+[[package]]
+name = "ipywidgets"
+version = "8.1.8"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "comm" },
+    { name = "ipython" },
+    { name = "jupyterlab-widgets" },
+    { name = "traitlets" },
+    { name = "widgetsnbextension" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/4c/ae/c5ce1edc1afe042eadb445e95b0671b03cee61895264357956e61c0d2ac0/ipywidgets-8.1.8.tar.gz", hash = "sha256:61f969306b95f85fba6b6986b7fe45d73124d1d9e3023a8068710d47a22ea668", size = 116739, upload-time = "2025-11-01T21:18:12.393Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/56/6d/0d9848617b9f753b87f214f1c682592f7ca42de085f564352f10f0843026/ipywidgets-8.1.8-py3-none-any.whl", hash = "sha256:ecaca67aed704a338f88f67b1181b58f821ab5dc89c1f0f5ef99db43c1c2921e", size = 139808, upload-time = "2025-11-01T21:18:10.956Z" },
+]
+
 [[package]]
 name = "jedi"
 version = "0.19.2"
@@ -726,6 +744,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e7/e7/80988e32bf6f73919a113473a604f5a8f09094de312b9d52b79c2df7612b/jupyter_core-5.9.1-py3-none-any.whl", hash = "sha256:ebf87fdc6073d142e114c72c9e29a9d7ca03fad818c5d300ce2adc1fb0743407", size = 29032, upload-time = "2025-10-16T19:19:16.783Z" },
 ]
 
+[[package]]
+name = "jupyterlab-widgets"
+version = "3.0.16"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/26/2d/ef58fed122b268c69c0aa099da20bc67657cdfb2e222688d5731bd5b971d/jupyterlab_widgets-3.0.16.tar.gz", hash = "sha256:423da05071d55cf27a9e602216d35a3a65a3e41cdf9c5d3b643b814ce38c19e0", size = 897423, upload-time = "2025-11-01T21:11:29.724Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ab/b5/36c712098e6191d1b4e349304ef73a8d06aed77e56ceaac8c0a306c7bda1/jupyterlab_widgets-3.0.16-py3-none-any.whl", hash = "sha256:45fa36d9c6422cf2559198e4db481aa243c7a32d9926b500781c830c80f7ecf8", size = 914926, upload-time = "2025-11-01T21:11:28.008Z" },
+]
+
 [[package]]
 name = "markupsafe"
 version = "3.0.3"
@@ -2205,6 +2232,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/24/6d/ea548150e8bd3727dbe9e39bec5b25e8cd40d984af8bb0a662cdef572ea2/weasel-0.4.2-py3-none-any.whl", hash = "sha256:47372460ff42ee89f59d8b6bc8ea07994600f7e88822a342b9771c72961f965e", size = 50752, upload-time = "2025-11-06T00:37:40.882Z" },
 ]
 
+[[package]]
+name = "widgetsnbextension"
+version = "4.0.15"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bd/f4/c67440c7fb409a71b7404b7aefcd7569a9c0d6bd071299bf4198ae7a5d95/widgetsnbextension-4.0.15.tar.gz", hash = "sha256:de8610639996f1567952d763a5a41af8af37f2575a41f9852a38f947eb82a3b9", size = 1097402, upload-time = "2025-11-01T21:15:55.178Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3f/0e/fa3b193432cfc60c93b42f3be03365f5f909d2b3ea410295cf36df739e31/widgetsnbextension-4.0.15-py3-none-any.whl", hash = "sha256:8156704e4346a571d9ce73b84bee86a29906c9abfd7223b7228a28899ccf3366", size = 2196503, upload-time = "2025-11-01T21:15:53.565Z" },
+]
+
 [[package]]
 name = "wrapt"
 version = "2.0.1"