Pushing the docs to dev/ for branch: main, commit 80811edc8b03ee691ca…

…d71725ef3aa7f16ece1f6
skrub-data · Dec 14, 2023 · 3bb42d0 · 3bb42d0
1 parent 5bbefbb
commit 3bb42d0
Show file tree

Hide file tree

Showing 64 changed files with 453 additions and 451 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: 0419996a16f2a3c75464ed74042897b9
+config: 0630c51683edc6ca083cc9b7428c67b6
 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
@@ -440,45 +440,44 @@ corresponding columns:
  .. code-block:: none
 
 
-    array(['station, state, estate', 'services, highway, service',
-           'investigative, investigations, criminal',
-           'nicholson, transit, taxicab',
-           'communications, division, applications', 'silver, spring, ride',
-           'training, building, recruit', 'gaithersburg, clarksburg, the',
-           'patrol, 4th, 6th', 'director, automated, office',
-           'programs, program, preparedness',
-           'rockville, twinbrook, downtown',
-           'eligibility, assistance, assisted', 'safety, section, collision',
-           'management, equipment, automotive', 'security, mc311, mccf',
+    array(['gaithersburg, clarksburg, the', 'supports, support, sports',
+           'district, patrol, 3rd', 'telephone, automated, stormwater',
+           'special, section, labor', 'environmental, regulatory, behavioral',
+           'welfare, childhood, child', 'maintenance, facilities, finance',
+           'services, highway, service', 'station, state, estate',
+           'traffic, safety, alcohol', 'security, custody, mcdc',
+           'silver, spring, urban', 'family, crimes, major',
+           'training, recruit, recruiting',
+           'technology, systems, information',
+           'building, construction, instruction',
+           'nicholson, transit, transport',
+           'communications, communication, division',
+           'emergency, centers, center', 'delivery, warehouse, liquor',
+           'management, mangement, engineering',
            'administration, administrative, battalion',
-           'behavioral, health, school', 'welfare, children, childhood',
-           'protective, procurement, project',
-           'development, government, stormwater', 'supports, support, sports',
-           'family, animal, robbery', 'emergency, commuter, duplicating',
-           'custody, toddlers, mcdc', 'district, urban, 3rd',
-           'technology, systems, telephone', 'council, centers, members',
-           'delivery, special, operations',
-           'maintenance, facilities, finance', 'captain, chief, autobody',
-           'liquor, clerk, store', 'officer, office, police',
-           'master, registered, water', 'operator, bus, operations',
-           'administrative, legislative, principal',
-           'technician, mechanic, supply', 'manager, budget, engineer',
-           'recreation, renovation, resource', 'school, room, behavioral',
-           'coordinator, transit, coordinating',
-           'enforcement, permitting, inspector',
-           'information, technology, technologist',
-           'assistance, income, client', 'therapist, sheriff, plumber',
+           'investigative, explosive, investigations',
+           'eligibility, assistance, assisted', 'health, school, based',
+           'fleet, animal, bureau', 'downtown, rockville, library',
+           'accounts, toddlers, council', 'protective, programs, program',
+           'officer, office, traffic', 'warehouse, welfare, caseworker',
            'firefighter, rescuer, recruit',
-           'correctional, correction, regional',
-           'accountant, assistant, library',
+           'librarian, candidate, psychiatric', 'income, assistance, client',
+           'coordinator, services, service', 'manager, iii, management',
+           'equipment, investment, investigator', 'operator, bus, operations',
+           'specialist, special, quality',
+           'enforcement, inspector, permitting',
+           'technician, mechanic, supply',
            'communications, telecommunications, safety',
-           'services, service, aide', 'community, health, nurse',
-           'sergeant, cadet, emergency', 'craftsworker, worker, social',
-           'specialist, special, procurement',
-           'crossing, purchasing, planning', 'warehouse, welfare, driver',
-           'corporal, erp, behavioral', 'program, programs, projects',
-           'equipment, investment, investigator',
-           'lieutenant, attendant, shift'], dtype=object)
+           'crossing, parking, guard',
+           'administrative, legislative, principal',
+           'correctional, correction, corporal', 'school, room, behavioral',
+           'community, nurse, health', 'liquor, clerk, store',
+           'lieutenant, maintenance, client', 'sheriff, deputy, aide',
+           'accountant, assistant, library', 'sergeant, police, cadet',
+           'captain, chief, autobody', 'supervisor, supervisory, transit',
+           'program, programs, projects', 'environmental, therapist, budget',
+           'master, registered, meter', 'information, technology, renovation',
+           'planning, senior, background'], dtype=object)
 
 
 
@@ -560,7 +559,7 @@ Let's look at the cross-validated R2 score of our model:
 
  .. code-block:: none
 
-    R2 score:  mean: 0.921; std: 0.016
+    R2 score:  mean: 0.923; std: 0.013
 
 
 
@@ -696,7 +695,7 @@ to plot the feature importances.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 19.568 seconds)
+   **Total running time of the script:** (1 minutes 8.670 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 2.041 seconds)
+   **Total running time of the script:** (0 minutes 1.648 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 4.948 seconds)
+   **Total running time of the script:** (0 minutes 4.149 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 19.674 seconds)
+   **Total running time of the script:** (0 minutes 17.135 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 4.680 seconds)
+   **Total running time of the script:** (0 minutes 4.909 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
 
 
-    {'companies', 'games', 'all_entities', 'albums', 'schools', 'movies'}
+    {'all_entities', 'companies', 'movies', 'albums', 'games', 'schools'}
 
 
 
@@ -840,7 +840,7 @@ It helped significantly improve the prediction score.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (11 minutes 7.838 seconds)
+   **Total running time of the script:** (10 minutes 30.856 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
@@ -1226,7 +1226,7 @@ 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(
 
-    0.58995
+    0.5878500000000001
 
 
 
@@ -1244,7 +1244,7 @@ Our final cross-validated accuracy score is 0.58.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (11 minutes 29.384 seconds)
+   **Total running time of the script:** (10 minutes 56.053 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>0.047956</td>
-          <td>0.063122</td>
-          <td>0.082469</td>
-          <td>0.057066</td>
-          <td>0.062993</td>
+          <td>0.039475</td>
+          <td>0.047479</td>
+          <td>0.075629</td>
+          <td>0.065258</td>
+          <td>0.070249</td>
         </tr>
         <tr>
           <th>split2_test_score</th>
-          <td>0.077542</td>
-          <td>0.081570</td>
-          <td>0.094021</td>
-          <td>0.098690</td>
-          <td>0.097006</td>
+          <td>0.075227</td>
+          <td>0.083063</td>
+          <td>0.092384</td>
+          <td>0.096931</td>
+          <td>0.089502</td>
         </tr>
         <tr>
           <th>split3_test_score</th>
-          <td>0.043531</td>
-          <td>0.065571</td>
-          <td>0.048403</td>
-          <td>0.065745</td>
-          <td>0.069058</td>
+          <td>0.042883</td>
+          <td>0.060734</td>
+          <td>0.061950</td>
+          <td>0.070185</td>
+          <td>0.077840</td>
         </tr>
         <tr>
           <th>split4_test_score</th>
-          <td>0.146376</td>
-          <td>0.134605</td>
-          <td>0.134260</td>
-          <td>0.144846</td>
-          <td>0.146525</td>
+          <td>0.140699</td>
+          <td>0.133569</td>
+          <td>0.139557</td>
+          <td>0.152427</td>
+          <td>0.143822</td>
         </tr>
         <tr>
           <th>split5_test_score</th>
-          <td>0.106774</td>
-          <td>0.110818</td>
-          <td>0.108646</td>
-          <td>0.103209</td>
-          <td>0.118163</td>
+          <td>0.113387</td>
+          <td>0.114269</td>
+          <td>0.109349</td>
+          <td>0.106754</td>
+          <td>0.116180</td>
         </tr>
         <tr>
           <th>split6_test_score</th>
-          <td>0.087637</td>
-          <td>0.101564</td>
-          <td>0.106001</td>
-          <td>0.108448</td>
-          <td>0.104643</td>
+          <td>0.080712</td>
+          <td>0.095461</td>
+          <td>0.107454</td>
+          <td>0.107903</td>
+          <td>0.108229</td>
         </tr>
         <tr>
           <th>split7_test_score</th>
-          <td>0.069828</td>
-          <td>0.061365</td>
-          <td>0.063359</td>
-          <td>0.078356</td>
-          <td>0.087845</td>
+          <td>0.070899</td>
+          <td>0.067751</td>
+          <td>0.059840</td>
+          <td>0.069572</td>
+          <td>0.078243</td>
         </tr>
         <tr>
           <th>split8_test_score</th>
-          <td>0.103975</td>
-          <td>0.113042</td>
-          <td>0.124293</td>
-          <td>0.122794</td>
-          <td>0.134883</td>
+          <td>0.103105</td>
+          <td>0.112480</td>
+          <td>0.121120</td>
+          <td>0.124410</td>
+          <td>0.127232</td>
         </tr>
         <tr>
           <th>split9_test_score</th>
-          <td>0.119554</td>
-          <td>0.151334</td>
-          <td>0.162009</td>
-          <td>0.169056</td>
-          <td>0.191246</td>
+          <td>0.107526</td>
+          <td>0.157958</td>
+          <td>0.171831</td>
+          <td>0.164579</td>
+          <td>0.184743</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 18.997 seconds)
+   **Total running time of the script:** (0 minutes 21.351 seconds)
 
 
 .. _sphx_glr_download_auto_examples_08_join_aggregation.py: