Pushing the docs to dev/ for branch: main, commit 7b363193d5f27c91a8e…

…03b3903e52263fc8c9c69
skrub-data · Jan 23, 2024 · 4f906f6 · 4f906f6
1 parent 0491589
commit 4f906f6
Show file tree

Hide file tree

Showing 62 changed files with 749 additions and 871 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: 54a687fc1634dc02fbd9b5bd48544806
+config: a92bca774470079cb82aaf8a5a866351
 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
@@ -847,47 +847,42 @@ corresponding columns:
  .. code-block:: none
 
 
-    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',
-           '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',
+    array(['administration, administrative, battalion',
+           'services, highway, service', 'station, state, estate',
+           'patrol, 5th, 6th', 'investigative, investigations, criminal',
+           'toddlers, custody, members', 'nicholson, transit, taxicab',
+           'management, mangement, budget', 'rockville, twinbrook, downtown',
+           'traffic, safety, alcohol', 'eligibility, assistance, assisted',
+           'personnel, family, crisis', 'supports, support, sports',
+           'behavioral, health, school', 'delivery, operations, emergency',
+           'gaithersburg, the, clarksburg',
+           'maintenance, facilities, finance',
+           'technology, systems, information', 'district, squad, 3rd',
+           'programs, program, accounts', 'processing, building, structural',
+           'division, animal, virtual', 'welfare, children, childhood',
+           'warehouse, liquor, labor', 'duplicating, regulation, educational',
+           'director, training, recruit',
+           'inspections, special, communications', 'silver, spring, urban',
+           'development, automotive, equipment', 'security, mc311, mccf',
+           'supervisor, supervisory, mcfrs', 'sergeant, cadet, emergency',
+           'correctional, correction, corporal', 'operator, bus, operations',
+           'officer, office, police', 'specialist, special, financial',
+           'firefighter, rescuer, rescue', 'lieutenant, captain, chief',
+           'warehouse, welfare, caseworker',
+           'enforcement, inspector, abandoned', 'community, health, nurse',
+           'coordinator, coordinating, services', 'manager, engineer, iii',
            'information, technology, technologist',
-           'community, security, nurse', 'technician, mechanic, supply',
-           'income, assistance, client', 'enforcement, permitting, inspector',
+           'purchasing, crossing, parking', 'technician, mechanic, supply',
+           'school, room, behavioral', 'legislative, principal, executive',
+           'assistance, income, client', 'sheriff, telephone, deputy',
+           'equipment, investment, investigator',
+           'therapist, administrator, estate',
+           'environmental, analyst, budget', 'accountant, assistant, library',
+           'program, programs, projects', 'recruit, crew, recreation',
            'liquor, clerk, store',
            'communications, telecommunications, safety',
-           '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)
+           'planning, permitting, resources', 'master, registered, meter'],
+          dtype=object)
 
 
 
@@ -969,7 +964,7 @@ Let's look at the cross-validated R2 score of our model:
 
  .. code-block:: none
 
-    R2 score:  mean: 0.919; std: 0.015
+    R2 score:  mean: 0.921; std: 0.012
 
 
 
@@ -1509,7 +1504,7 @@ to plot the feature importances.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 21.755 seconds)
+   **Total running time of the script:** (1 minutes 10.985 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 2.014 seconds)
+   **Total running time of the script:** (0 minutes 1.853 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 5.414 seconds)
+   **Total running time of the script:** (0 minutes 4.591 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
@@ -239,13 +239,6 @@ We extract the table containing GDP per capita by country:
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-    /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/skrub/datasets/_fetching.py:678: UserWarning: Could not find the dataset 'NY.GDP.PCAP.CD' locally. Downloading it from the World Bank; this might take a while... If it is interrupted, some files might be invalid/incomplete: if on the following run, the fetching raises errors, you can try fixing this issue by deleting the directory /home/circleci/skrub_data/world_bank/NY.GDP.PCAP.CD.csv.
-      info = _fetch_world_bank_data(dataset_id, data_directory)
-
 
 .. raw:: html
 
@@ -310,13 +303,6 @@ Then another table, with life expectancy by country:
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-    /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/skrub/datasets/_fetching.py:678: UserWarning: Could not find the dataset 'SP.DYN.LE00.IN' locally. Downloading it from the World Bank; this might take a while... If it is interrupted, some files might be invalid/incomplete: if on the following run, the fetching raises errors, you can try fixing this issue by deleting the directory /home/circleci/skrub_data/world_bank/SP.DYN.LE00.IN.csv.
-      info = _fetch_world_bank_data(dataset_id, data_directory)
-
 
 .. raw:: html
 
@@ -381,13 +367,6 @@ And a table with legal rights strength by country:
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-    /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/skrub/datasets/_fetching.py:678: UserWarning: Could not find the dataset 'IC.LGL.CRED.XQ' locally. Downloading it from the World Bank; this might take a while... If it is interrupted, some files might be invalid/incomplete: if on the following run, the fetching raises errors, you can try fixing this issue by deleting the directory /home/circleci/skrub_data/world_bank/IC.LGL.CRED.XQ.csv.
-      info = _fetch_world_bank_data(dataset_id, data_directory)
-
 
 .. raw:: html
 
@@ -1732,7 +1711,7 @@ introduced into a grid search:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 25.014 seconds)
+   **Total running time of the script:** (0 minutes 22.339 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 6.666 seconds)
+   **Total running time of the script:** (0 minutes 5.496 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
 
 
-    {'all_entities', 'games', 'movies', 'schools', 'companies', 'albums'}
+    {'movies', 'companies', 'albums', 'games', 'schools', 'all_entities'}
 
 
 
@@ -327,13 +327,6 @@ Let's see what kind of types we can find in it with the function
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-    /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/skrub/datasets/_fetching.py:680: UserWarning: Could not find the dataset 40019788 locally. Downloading it from figshare; this might take a while... If it is interrupted, some files might be invalid/incomplete: if on the following run, the fetching raises errors, you can try fixing this issue by deleting the directory /home/circleci/skrub_data/figshare/figshare_40019788.parquet.
-      info = _fetch_figshare(dataset_id, data_directory)
-
 
 .. raw:: html
 
@@ -460,15 +453,6 @@ and exclude those with type name "companies" or "developer".
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-    /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/skrub/datasets/_fetching.py:680: UserWarning: Could not find the dataset 39266678 locally. Downloading it from figshare; this might take a while... If it is interrupted, some files might be invalid/incomplete: if on the following run, the fetching raises errors, you can try fixing this issue by deleting the directory /home/circleci/skrub_data/figshare/figshare_39266678.parquet.
-      info = _fetch_figshare(dataset_id, data_directory)
-    /home/circleci/project/miniconda/envs/testenv/lib/python3.10/site-packages/skrub/datasets/_fetching.py:680: UserWarning: Could not find the dataset 39254360 locally. Downloading it from figshare; this might take a while... If it is interrupted, some files might be invalid/incomplete: if on the following run, the fetching raises errors, you can try fixing this issue by deleting the directory /home/circleci/skrub_data/figshare/figshare_39254360.parquet.
-      info = _fetch_figshare(dataset_id, data_directory)
-
 
 
 
@@ -873,7 +857,7 @@ It helped significantly improve the prediction score.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (10 minutes 45.188 seconds)
+   **Total running time of the script:** (10 minutes 43.189 seconds)
 
 
 .. _sphx_glr_download_auto_examples_06_ken_embeddings.py: