Pushing the docs to dev/ for branch: main, commit 14ca427b3eae6c4827a…

…c12a4370fc397e35eae26
skrub-data · Jan 23, 2024 · 0491589 · 0491589
1 parent acbf991
commit 0491589
Show file tree

Hide file tree

Showing 62 changed files with 455 additions and 452 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: 1a1ba6b402fb86cc0386a59eccfbc0a2
+config: 54a687fc1634dc02fbd9b5bd48544806
 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
@@ -847,43 +847,47 @@ corresponding columns:
  .. code-block:: none
 
 
-    array(['special, programs, program', 'resources, resource, network',
-           'silver, spring, ride', 'station, state, estate',
-           'district, squad, payroll', 'management, equipment, automotive',
+    array(['director, officers, officer',
+           'compensation, conservation, classification',
+           'silver, spring, urban', 'eligibility, accessibility, facilities',
+           'welfare, childhood, child', 'division, animal, major',
+           'abandoned, background, budget', 'district, patrol, squad',
+           'school, health, based', 'traffic, safety, alcohol',
+           'gaithersburg, clarksburg, the',
+           'management, equipment, automotive',
            'investigative, investigations, criminal',
-           'gaithersburg, clarksburg, the', 'engineering, parking, marking',
-           'rockville, downtown, library', 'services, highway, service',
-           'communications, communication, telecommunications',
-           'behavioral, health, school', 'director, automated, office',
-           'safety, division, section', 'technology, telephone, systems',
-           'welfare, child, childhood', 'nicholson, transit, taxicab',
-           'sexual, family, crimes', 'eligibility, assistance, medical',
-           'security, mccf, unit', '4th, 6th, 5th',
-           'delivery, warehouse, liquor',
-           'environmental, regulatory, adolescent',
-           'training, administration, recruit', '3rd, patrol, 2nd',
-           'maintenance, facilities, council', 'supports, support, sports',
-           'building, construction, instruction',
-           'toddlers, custody, members', 'warehouse, welfare, driver',
-           'program, programs, projects',
-           'administrative, administration, administrator',
-           'operator, equipment, apprentice', 'officer, office, police',
-           'candidate, attendant, master', 'firefighter, rescuer, recruit',
-           'school, room, behavioral', 'information, recreation, technology',
-           'liquor, clerk, store', 'specialist, special, planning',
-           'manager, engineer, investigator', 'worker, social, leader',
-           'community, health, nurse', 'technician, mechanic, systems',
-           'enforcement, permitting, inspector',
-           'coordinator, coordinating, legislative',
-           'crossing, library, librarian',
-           'correctional, correction, corporal', 'sheriff, deputy, autobody',
+           'services, highway, service', 'technology, systems, telephone',
+           'security, custody, mcdc', 'supports, support, council',
+           'station, state, estate', 'training, building, planning',
+           'nicholson, transit, taxicab', 'outreach, assault, family',
+           'communications, communication, commuter',
+           'inspections, collection, inspection',
+           'warehouse, delivery, liquor',
+           'administration, battalion, administrative',
+           'development, assessment, stormwater',
+           'environmental, regulatory, behavioral',
+           'rockville, downtown, fallsgrove', 'emergency, crossing, programs',
+           'engineering, projects, parking',
+           'recreation, correctional, correction',
+           'master, registered, water', 'manager, investigator, iii',
+           'officer, office, police', 'coordinator, transit, coordinating',
+           'captain, rescue, battalion', 'operator, equipment, apprentice',
+           'school, room, behavioral',
+           'information, technology, technologist',
+           'community, security, nurse', 'technician, mechanic, supply',
+           'income, assistance, client', 'enforcement, permitting, inspector',
+           'liquor, clerk, store',
            'communications, telecommunications, safety',
-           'lieutenant, shift, commander', 'income, assistance, client',
-           'sergeant, emergency, energy', 'principal, executive, examiner',
-           'environmental, budget, ombudsman', 'services, service, urban',
-           'accountant, assistant, attorney',
-           'supervisory, supervisor, therapist', 'captain, rescue, battalion'],
-          dtype=object)
+           'legislative, principal, executive',
+           'firefighter, recruit, rescuer', 'corporal, pfc, private',
+           'lieutenant, attendant, maintenance',
+           'specialist, special, quality', 'warehouse, worker, truck',
+           'assistant, library, librarian', 'sergeant, cadet, emergency',
+           'plumber, engineer, auditor', 'program, programs, projects',
+           'administrative, administration, administrator',
+           'services, service, urban', 'therapist, sheriff, deputy',
+           'crossing, planning, purchasing',
+           'environmental, budget, enviromental'], dtype=object)
 
 
 
@@ -965,7 +969,7 @@ Let's look at the cross-validated R2 score of our model:
 
  .. code-block:: none
 
-    R2 score:  mean: 0.919; std: 0.012
+    R2 score:  mean: 0.919; std: 0.015
 
 
 
@@ -1505,7 +1509,7 @@ to plot the feature importances.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 29.145 seconds)
+   **Total running time of the script:** (1 minutes 21.755 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 2.488 seconds)
+   **Total running time of the script:** (0 minutes 2.014 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 5.359 seconds)
+   **Total running time of the script:** (0 minutes 5.414 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
@@ -1732,7 +1732,7 @@ introduced into a grid search:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 24.406 seconds)
+   **Total running time of the script:** (0 minutes 25.014 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 5.798 seconds)
+   **Total running time of the script:** (0 minutes 6.666 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
 
 
-    {'movies', 'schools', 'all_entities', 'games', 'albums', 'companies'}
+    {'all_entities', 'games', 'movies', 'schools', 'companies', 'albums'}
 
 
 
@@ -873,7 +873,7 @@ It helped significantly improve the prediction score.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (11 minutes 45.643 seconds)
+   **Total running time of the script:** (10 minutes 45.188 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
@@ -1256,7 +1256,7 @@ The results:
     /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/sklearn/preprocessing/_encoders.py:241: UserWarning: Found unknown categories in columns [1] during transform. These unknown categories will be encoded as all zeros
       warnings.warn(
 
-    0.5864499999999999
+    0.5923
 
 
 
@@ -1274,7 +1274,7 @@ Our final cross-validated accuracy score is 0.58.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (11 minutes 43.985 seconds)
+   **Total running time of the script:** (11 minutes 14.788 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
@@ -1284,75 +1284,75 @@ operation maximizing our validation score.
         </tr>
         <tr>
           <th>split1_test_score</th>
-          <td>0.059505</td>
-          <td>0.032508</td>
-          <td>0.078928</td>
-          <td>0.069610</td>
-          <td>0.084291</td>
+          <td>0.045179</td>
+          <td>0.061203</td>
+          <td>0.078924</td>
+          <td>0.087615</td>
+          <td>0.083643</td>
         </tr>
         <tr>
           <th>split2_test_score</th>
-          <td>0.072540</td>
-          <td>0.081928</td>
-          <td>0.084433</td>
-          <td>0.097590</td>
-          <td>0.085638</td>
+          <td>0.071170</td>
+          <td>0.073612</td>
+          <td>0.101680</td>
+          <td>0.091776</td>
+          <td>0.089107</td>
         </tr>
         <tr>
           <th>split3_test_score</th>
-          <td>0.041792</td>
-          <td>0.063570</td>
-          <td>0.068268</td>
-          <td>0.068114</td>
-          <td>0.077827</td>
+          <td>0.048284</td>
+          <td>0.061595</td>
+          <td>0.060951</td>
+          <td>0.069888</td>
+          <td>0.063253</td>
         </tr>
         <tr>
           <th>split4_test_score</th>
-          <td>0.144257</td>
-          <td>0.121750</td>
-          <td>0.154879</td>
-          <td>0.154665</td>
-          <td>0.154509</td>
+          <td>0.141585</td>
+          <td>0.130055</td>
+          <td>0.150162</td>
+          <td>0.160109</td>
+          <td>0.156362</td>
         </tr>
         <tr>
           <th>split5_test_score</th>
-          <td>0.105915</td>
-          <td>0.112408</td>
-          <td>0.109866</td>
-          <td>0.108885</td>
-          <td>0.115138</td>
+          <td>0.108540</td>
+          <td>0.111022</td>
+          <td>0.106934</td>
+          <td>0.106461</td>
+          <td>0.115973</td>
         </tr>
         <tr>
           <th>split6_test_score</th>
-          <td>0.083759</td>
-          <td>0.098489</td>
-          <td>0.104181</td>
-          <td>0.110296</td>
-          <td>0.105656</td>
+          <td>0.086493</td>
+          <td>0.104097</td>
+          <td>0.104905</td>
+          <td>0.110491</td>
+          <td>0.114162</td>
         </tr>
         <tr>
           <th>split7_test_score</th>
-          <td>0.068791</td>
-          <td>0.066842</td>
-          <td>0.071446</td>
-          <td>0.064729</td>
-          <td>0.072894</td>
+          <td>0.066208</td>
+          <td>0.070801</td>
+          <td>0.053547</td>
+          <td>0.057299</td>
+          <td>0.083411</td>
         </tr>
         <tr>
           <th>split8_test_score</th>
-          <td>0.109317</td>
-          <td>0.113322</td>
-          <td>0.121739</td>
-          <td>0.127709</td>
-          <td>0.131357</td>
+          <td>0.114660</td>
+          <td>0.112979</td>
+          <td>0.111356</td>
+          <td>0.129530</td>
+          <td>0.130324</td>
         </tr>
         <tr>
           <th>split9_test_score</th>
-          <td>0.130825</td>
-          <td>0.161078</td>
-          <td>0.165871</td>
-          <td>0.164596</td>
-          <td>0.183170</td>
+          <td>0.112268</td>
+          <td>0.152847</td>
+          <td>0.164347</td>
+          <td>0.162349</td>
+          <td>0.182173</td>
         </tr>
       </tbody>
     </table>
@@ -1472,7 +1472,7 @@ exhaustive histogram over all the possible values of ratings
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 18.508 seconds)
+   **Total running time of the script:** (0 minutes 22.544 seconds)
 
 
 .. _sphx_glr_download_auto_examples_08_join_aggregation.py: