Pushing the docs to dev/ for branch: main, commit b29438accd49f98c4a0…

…b625cf0a61e7da9271bec
skrub-data · Jan 23, 2024 · acbf991 · acbf991
1 parent 9845bda
commit acbf991
Show file tree

Hide file tree

Showing 62 changed files with 453 additions and 453 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: e65101e38a131eedb841b03c0c1c495b
+config: 1a1ba6b402fb86cc0386a59eccfbc0a2
 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 +847,43 @@ corresponding columns:
  .. code-block:: none
 
 
-    array(['gaithersburg, the, clarksburg', 'station, mc311, state',
-           'patrol, 5th, 4th', 'behavioral, health, school',
-           'division, animal, virtual',
-           'administration, battalion, operations', 'silver, spring, ride',
-           'protective, programs, program', 'automotive, equipment, budget',
-           'delivery, explosive, warehouse', 'human, ombudsman, juvenile',
-           'safety, collision, section', 'training, recruit, recruiting',
-           'highway, services, service', 'district, 3rd, 1st',
-           'communications, communication, commuter',
-           'welfare, children, childhood', 'rockville, twinbrook, library',
-           'maintenance, facilities, council',
-           'engineering, mangement, parking', 'supports, support, sports',
-           'technology, systems, telephone', 'personnel, family, crisis',
-           'eligibility, assistance, assisted', 'director, automated, office',
-           'nicholson, transit, taxicab', 'compliance, accounts, hampden',
-           'construction, building, design', 'security, custody, mcdc',
-           'investigative, inspections, investigations',
-           'operator, equipment, bus', 'manager, investigator, iii',
-           'officer, office, traffic', 'school, room, behavioral',
-           'master, registered, meter', 'liquor, clerk, store',
-           'information, recreation, technology', 'community, health, nurse',
-           'specialist, special, resource',
-           'coordinator, coordinating, services',
-           'supervisory, supervisor, therapist', 'lieutenant, captain, chief',
+    array(['special, programs, program', 'resources, resource, network',
+           'silver, spring, ride', 'station, state, estate',
+           'district, squad, payroll', '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',
-           'enforcement, inspector, force', 'technician, mechanic, supply',
-           'correctional, correction, corporal',
-           'firefighter, rescuer, recruit',
+           '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',
            'communications, telecommunications, safety',
-           'warehouse, welfare, caseworker',
-           'crossing, purchasing, background', 'planning, senior, engineer',
-           'income, assistance, client', 'sergeant, police, cadet',
-           'accountant, assistant, library', 'program, programs, projects',
-           'legislative, principal, executive',
-           'librarian, psychiatric, employee',
-           'customer, urban, representative', 'candidate, sheriff, deputy',
-           'environmental, budget, scientist'], dtype=object)
+           '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)
 
 
 
@@ -965,7 +965,7 @@ Let's look at the cross-validated R2 score of our model:
 
  .. code-block:: none
 
-    R2 score:  mean: 0.922; std: 0.014
+    R2 score:  mean: 0.919; std: 0.012
 
 
 
@@ -1505,7 +1505,7 @@ to plot the feature importances.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 8.940 seconds)
+   **Total running time of the script:** (1 minutes 29.145 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 1.618 seconds)
+   **Total running time of the script:** (0 minutes 2.488 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 4.129 seconds)
+   **Total running time of the script:** (0 minutes 5.359 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 20.409 seconds)
+   **Total running time of the script:** (0 minutes 24.406 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 4.789 seconds)
+   **Total running time of the script:** (0 minutes 5.798 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', 'companies', 'games', 'albums', 'all_entities', 'schools'}
+    {'movies', 'schools', 'all_entities', 'games', 'albums', 'companies'}
 
 
 
@@ -873,7 +873,7 @@ It helped significantly improve the prediction score.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (11 minutes 40.136 seconds)
+   **Total running time of the script:** (11 minutes 45.643 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(
 
-    0.5908
+    0.5864499999999999
 
 
 
@@ -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 59.788 seconds)
+   **Total running time of the script:** (11 minutes 43.985 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>0.054509</td>
-          <td>0.058128</td>
-          <td>0.071069</td>
-          <td>0.052660</td>
-          <td>0.052842</td>
+          <td>0.059505</td>
+          <td>0.032508</td>
+          <td>0.078928</td>
+          <td>0.069610</td>
+          <td>0.084291</td>
         </tr>
         <tr>
           <th>split2_test_score</th>
-          <td>0.069220</td>
-          <td>0.093858</td>
-          <td>0.092783</td>
-          <td>0.102946</td>
-          <td>0.094487</td>
+          <td>0.072540</td>
+          <td>0.081928</td>
+          <td>0.084433</td>
+          <td>0.097590</td>
+          <td>0.085638</td>
         </tr>
         <tr>
           <th>split3_test_score</th>
-          <td>0.045484</td>
-          <td>0.069533</td>
-          <td>0.059923</td>
-          <td>0.063730</td>
-          <td>0.078378</td>
+          <td>0.041792</td>
+          <td>0.063570</td>
+          <td>0.068268</td>
+          <td>0.068114</td>
+          <td>0.077827</td>
         </tr>
         <tr>
           <th>split4_test_score</th>
-          <td>0.129426</td>
-          <td>0.135126</td>
-          <td>0.142650</td>
-          <td>0.150611</td>
-          <td>0.156610</td>
+          <td>0.144257</td>
+          <td>0.121750</td>
+          <td>0.154879</td>
+          <td>0.154665</td>
+          <td>0.154509</td>
         </tr>
         <tr>
           <th>split5_test_score</th>
-          <td>0.109764</td>
-          <td>0.111292</td>
-          <td>0.109923</td>
-          <td>0.110233</td>
-          <td>0.115234</td>
+          <td>0.105915</td>
+          <td>0.112408</td>
+          <td>0.109866</td>
+          <td>0.108885</td>
+          <td>0.115138</td>
         </tr>
         <tr>
           <th>split6_test_score</th>
-          <td>0.083386</td>
-          <td>0.105465</td>
-          <td>0.105645</td>
-          <td>0.107080</td>
-          <td>0.105257</td>
+          <td>0.083759</td>
+          <td>0.098489</td>
+          <td>0.104181</td>
+          <td>0.110296</td>
+          <td>0.105656</td>
         </tr>
         <tr>
           <th>split7_test_score</th>
-          <td>0.069049</td>
-          <td>0.060614</td>
-          <td>0.059454</td>
-          <td>0.061911</td>
-          <td>0.081074</td>
+          <td>0.068791</td>
+          <td>0.066842</td>
+          <td>0.071446</td>
+          <td>0.064729</td>
+          <td>0.072894</td>
         </tr>
         <tr>
           <th>split8_test_score</th>
-          <td>0.101018</td>
-          <td>0.115044</td>
-          <td>0.116905</td>
-          <td>0.128505</td>
-          <td>0.118541</td>
+          <td>0.109317</td>
+          <td>0.113322</td>
+          <td>0.121739</td>
+          <td>0.127709</td>
+          <td>0.131357</td>
         </tr>
         <tr>
           <th>split9_test_score</th>
-          <td>0.118754</td>
-          <td>0.150841</td>
-          <td>0.169428</td>
-          <td>0.167694</td>
-          <td>0.177697</td>
+          <td>0.130825</td>
+          <td>0.161078</td>
+          <td>0.165871</td>
+          <td>0.164596</td>
+          <td>0.183170</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 21.403 seconds)
+   **Total running time of the script:** (0 minutes 18.508 seconds)
 
 
 .. _sphx_glr_download_auto_examples_08_join_aggregation.py: