Pushing the docs to dev/ for branch: main, commit 12216ec8629e5765fbf…

…467456cec685e8aa2b9af
skrub-data · Dec 12, 2023 · 70dd600 · 70dd600
1 parent dbf9574
commit 70dd600
Show file tree

Hide file tree

Showing 62 changed files with 451 additions and 449 deletions.
diff --git a/dev/.buildinfo b/dev/.buildinfo
@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 2477e942aab9c78438a49ee8fb3d50a8
+config: e111dff184e2451e0a92cf034a83814e
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/dev/_images/sphx_glr_01_encodings_001.png b/dev/_images/sphx_glr_01_encodings_001.png
diff --git a/dev/_images/sphx_glr_01_encodings_thumb.png b/dev/_images/sphx_glr_01_encodings_thumb.png
diff --git a/dev/_images/sphx_glr_08_join_aggregation_003.png b/dev/_images/sphx_glr_08_join_aggregation_003.png
diff --git a/dev/_images/sphx_glr_09_interpolation_join_001.png b/dev/_images/sphx_glr_09_interpolation_join_001.png
diff --git a/dev/_images/sphx_glr_09_interpolation_join_002.png b/dev/_images/sphx_glr_09_interpolation_join_002.png
diff --git a/dev/_images/sphx_glr_09_interpolation_join_003.png b/dev/_images/sphx_glr_09_interpolation_join_003.png
diff --git a/dev/_images/sphx_glr_09_interpolation_join_thumb.png b/dev/_images/sphx_glr_09_interpolation_join_thumb.png
diff --git a/dev/_sources/auto_examples/01_encodings.rst.txt b/dev/_sources/auto_examples/01_encodings.rst.txt
@@ -440,44 +440,45 @@ corresponding columns:
  .. code-block:: none
 
 
-    array(['supports, support, recruit', 'shelters, centers, sheriff',
-           'rockville, fallsgrove, downtown', 'animal, individual, virtual',
-           'engineering, mangement, budgeting', 'station, state, estate',
-           'facilities, maintenance, accounts', 'silver, spring, ride',
-           'behavioral, health, school', 'equipment, management, automotive',
-           'patrol, 4th, 6th', 'safety, collision, section',
-           'communications, communication, telecommunications',
-           'warehouse, delivery, operations', 'highway, welfare, services',
-           'gaithersburg, the, clarksburg', 'nicholson, transit, taxicab',
-           'development, planning, stormwater',
-           'assessment, protective, process',
-           'construction, instruction, building',
-           'mechanical, special, commercial',
-           'technology, systems, telephone', 'district, urban, 3rd',
-           'family, sexual, crimes', 'security, mccf, unit',
-           'custody, members, customer',
+    array(['services, highway, service', 'engineering, training, planning',
+           'traffic, safety, alcohol', 'sexual, family, crimes',
+           'district, payroll, squad', 'construction, instruction, building',
+           'silver, spring, ride', 'behavioral, health, school',
+           'delivery, operations, special', 'gaithersburg, clarksburg, the',
+           'welfare, childhood, children', 'toddlers, custody, members',
+           'supports, support, network', 'station, state, estate',
+           'director, officers, projects', 'management, fleet, parking',
+           'maintenance, facilities, eligibility',
+           'processing, programs, accounting', 'security, mc311, mccf',
+           'communications, communication, immunization',
+           'administration, battalion, administrative', 'patrol, 4th, 6th',
+           'procurement, protective, fiscal',
+           'development, residential, stormwater',
            'investigative, investigations, criminal',
-           'administration, administrative, battalion',
-           'assistance, eligibility, emergency', 'automated, traffic, office',
-           'master, registered, firefighter', 'manager, budget, projects',
-           'specialist, special, environmental', 'candidate, police, cadet',
-           'officer, office, traffic', 'operator, bus, operations',
-           'income, assistance, client', 'liquor, clerk, store',
-           'rescuer, recruit, firefighter', 'technician, mechanic, supply',
-           'program, programs, procurement', 'lieutenant, captain, chief',
-           'community, nurse, unit', 'school, health, room',
+           'emergency, centers, center', 'nicholson, transit, taxicab',
+           'automotive, assessment, equipment',
+           'technology, systems, telephone', 'rockville, twinbrook, library',
+           'dietary, security, partnerships',
+           'operator, equipment, apprentice',
+           'recreation, planning, renovation',
+           'master, registered, firefighter', 'candidate, police, of',
+           'officer, office, police', 'specialist, special, procurement',
+           'program, programs, projects', 'technician, mechanic, supply',
+           'legislative, principal, executive',
+           'coordinator, coordinating, depot', 'sergeant, cadet, police',
+           'recruit, firefighter, rescuer', 'community, health, nurse',
+           'warehouse, welfare, caseworker',
+           'enforcement, permitting, inspector', 'manager, budget, engineer',
+           'school, room, behavioral', 'captain, rescue, chief',
+           'supervisory, supervisor, therapist',
            'communications, telecommunications, safety',
-           'coordinator, services, service', 'accountant, assistant, county',
-           'supervisor, supervisory, sergeant',
-           'craftsworker, customer, public', 'sheriff, deputy, autobody',
-           'enforcement, permitting, inspector',
-           'correctional, correction, records',
-           'information, technology, recreation',
-           'administrative, principal, executive',
-           'crossing, purchasing, engineer', 'warehouse, welfare, driver',
-           'corporal, erp, behavioral', 'worker, social, leader',
-           'librarian, library, telephone',
-           'equipment, investment, investigator'], dtype=object)
+           'liquor, clerk, store', 'librarian, crossing, library',
+           'sheriff, deputy, autobody',
+           'information, technology, technologist',
+           'lieutenant, attendant, facilities', 'services, service, urban',
+           'assistance, assistant, income',
+           'correctional, correction, corporal',
+           'administrative, administration, administrator'], dtype=object)
 
 
 
@@ -559,7 +560,7 @@ Let's look at the cross-validated R2 score of our model:
 
  .. code-block:: none
 
-    R2 score:  mean: 0.922; std: 0.013
+    R2 score:  mean: 0.919; std: 0.017
 
 
 
@@ -695,7 +696,7 @@ to plot the feature importances.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 16.726 seconds)
+   **Total running time of the script:** (1 minutes 20.106 seconds)
 
 
 .. _sphx_glr_download_auto_examples_01_encodings.py:

diff --git a/dev/_sources/auto_examples/02_feature_interpretation_with_gapencoder.rst.txt b/dev/_sources/auto_examples/02_feature_interpretation_with_gapencoder.rst.txt
@@ -504,7 +504,7 @@ as a set of latent topics.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 1.903 seconds)
+   **Total running time of the script:** (0 minutes 1.818 seconds)
 
 
 .. _sphx_glr_download_auto_examples_02_feature_interpretation_with_gapencoder.py:

diff --git a/dev/_sources/auto_examples/03_datetime_encoder.rst.txt b/dev/_sources/auto_examples/03_datetime_encoder.rst.txt
@@ -610,7 +610,7 @@ and transforms datetime columns by default.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 4.509 seconds)
+   **Total running time of the script:** (0 minutes 4.276 seconds)
 
 
 .. _sphx_glr_download_auto_examples_03_datetime_encoder.py:

diff --git a/dev/_sources/auto_examples/04_fuzzy_joining.rst.txt b/dev/_sources/auto_examples/04_fuzzy_joining.rst.txt
@@ -1711,7 +1711,7 @@ introduced into a grid search:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 19.485 seconds)
+   **Total running time of the script:** (0 minutes 20.298 seconds)
 
 
 .. _sphx_glr_download_auto_examples_04_fuzzy_joining.py:

diff --git a/dev/_sources/auto_examples/05_deduplication.rst.txt b/dev/_sources/auto_examples/05_deduplication.rst.txt
@@ -335,7 +335,7 @@ or |MinHash|.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 4.891 seconds)
+   **Total running time of the script:** (0 minutes 5.398 seconds)
 
 
 .. _sphx_glr_download_auto_examples_05_deduplication.py:

diff --git a/dev/_sources/auto_examples/06_ken_embeddings.rst.txt b/dev/_sources/auto_examples/06_ken_embeddings.rst.txt
@@ -305,7 +305,7 @@ We will start by checking out the available tables with
  .. code-block:: none
 
 
-    {'games', 'all_entities', 'companies', 'movies', 'albums', 'schools'}
+    {'games', 'all_entities', 'movies', 'schools', 'companies', 'albums'}
 
 
 
@@ -840,7 +840,7 @@ It helped significantly improve the prediction score.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (11 minutes 15.721 seconds)
+   **Total running time of the script:** (11 minutes 31.752 seconds)
 
 
 .. _sphx_glr_download_auto_examples_06_ken_embeddings.py:

diff --git a/dev/_sources/auto_examples/07_multiple_key_join.rst.txt b/dev/_sources/auto_examples/07_multiple_key_join.rst.txt
@@ -1225,7 +1225,7 @@ The results:
     /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/sklearn/preprocessing/_encoders.py:228: UserWarning: Found unknown categories in columns [1] during transform. These unknown categories will be encoded as all zeros
       warnings.warn(
 
-    0.58915
+    0.58585
 
 
 
@@ -1243,7 +1243,7 @@ Our final cross-validated accuracy score is 0.58.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (10 minutes 53.468 seconds)
+   **Total running time of the script:** (12 minutes 0.348 seconds)
 
 
 .. _sphx_glr_download_auto_examples_07_multiple_key_join.py:

diff --git a/dev/_sources/auto_examples/08_join_aggregation.rst.txt b/dev/_sources/auto_examples/08_join_aggregation.rst.txt
@@ -844,75 +844,75 @@ operation maximizing our validation score.
         </tr>
         <tr>
           <th>split1_test_score</th>
-          <td>0.045640</td>
-          <td>0.041599</td>
-          <td>0.064299</td>
-          <td>0.075415</td>
-          <td>0.082621</td>
+          <td>0.035662</td>
+          <td>0.053087</td>
+          <td>0.072071</td>
+          <td>0.066001</td>
+          <td>0.079685</td>
         </tr>
         <tr>
           <th>split2_test_score</th>
-          <td>0.071529</td>
-          <td>0.074321</td>
-          <td>0.089585</td>
-          <td>0.088302</td>
-          <td>0.092612</td>
+          <td>0.076336</td>
+          <td>0.082476</td>
+          <td>0.094569</td>
+          <td>0.091759</td>
+          <td>0.091283</td>
         </tr>
         <tr>
           <th>split3_test_score</th>
-          <td>0.040797</td>
-          <td>0.063690</td>
-          <td>0.069269</td>
-          <td>0.062119</td>
-          <td>0.069033</td>
+          <td>0.039651</td>
+          <td>0.067618</td>
+          <td>0.056371</td>
+          <td>0.073471</td>
+          <td>0.074189</td>
         </tr>
         <tr>
           <th>split4_test_score</th>
-          <td>0.138299</td>
-          <td>0.121267</td>
-          <td>0.140101</td>
-          <td>0.142540</td>
-          <td>0.140436</td>
+          <td>0.141117</td>
+          <td>0.125026</td>
+          <td>0.144522</td>
+          <td>0.144590</td>
+          <td>0.141754</td>
         </tr>
         <tr>
           <th>split5_test_score</th>
-          <td>0.106619</td>
-          <td>0.112459</td>
-          <td>0.104979</td>
-          <td>0.108407</td>
-          <td>0.114175</td>
+          <td>0.109087</td>
+          <td>0.110900</td>
+          <td>0.106453</td>
+          <td>0.109212</td>
+          <td>0.114790</td>
         </tr>
         <tr>
           <th>split6_test_score</th>
-          <td>0.077635</td>
-          <td>0.103037</td>
-          <td>0.107903</td>
-          <td>0.105183</td>
-          <td>0.106193</td>
+          <td>0.082496</td>
+          <td>0.102770</td>
+          <td>0.109770</td>
+          <td>0.110297</td>
+          <td>0.112940</td>
         </tr>
         <tr>
           <th>split7_test_score</th>
-          <td>0.074042</td>
-          <td>0.067023</td>
-          <td>0.070372</td>
-          <td>0.070241</td>
-          <td>0.076133</td>
+          <td>0.059398</td>
+          <td>0.066302</td>
+          <td>0.060979</td>
+          <td>0.064334</td>
+          <td>0.076729</td>
         </tr>
         <tr>
           <th>split8_test_score</th>
-          <td>0.110951</td>
-          <td>0.114420</td>
-          <td>0.117400</td>
-          <td>0.113873</td>
-          <td>0.132726</td>
+          <td>0.104940</td>
+          <td>0.111360</td>
+          <td>0.117624</td>
+          <td>0.120712</td>
+          <td>0.119874</td>
         </tr>
         <tr>
           <th>split9_test_score</th>
-          <td>0.121891</td>
-          <td>0.148754</td>
-          <td>0.175560</td>
-          <td>0.161689</td>
-          <td>0.180554</td>
+          <td>0.106619</td>
+          <td>0.155110</td>
+          <td>0.171715</td>
+          <td>0.164387</td>
+          <td>0.176994</td>
         </tr>
       </tbody>
     </table>
@@ -1003,7 +1003,7 @@ exhaustive histogram over all the possible values of ratings
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 16.742 seconds)
+   **Total running time of the script:** (0 minutes 17.713 seconds)
 
 
 .. _sphx_glr_download_auto_examples_08_join_aggregation.py: