commit files to HF hub

.gitattributes

@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.skops filter=lfs diff=lfs merge=lfs -text
+geographic.png filter=lfs diff=lfs merge=lfs -text
+permutation-importances.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,218 @@
+---
+library_name: sklearn
+tags:
+- sklearn
+- skops
+- tabular-regression
+model_format: skops
+model_file: model.skops
+widget:
+  structuredData:
+    AveBedrms:
+    - 0.9290780141843972
+    - 0.9458483754512635
+    - 1.087360594795539
+    AveOccup:
+    - 3.1134751773049647
+    - 3.0613718411552346
+    - 3.2657992565055762
+    AveRooms:
+    - 6.304964539007092
+    - 6.945848375451264
+    - 3.8884758364312266
+    HouseAge:
+    - 17.0
+    - 15.0
+    - 24.0
+    Latitude:
+    - 34.23
+    - 36.84
+    - 34.04
+    Longitude:
+    - -117.41
+    - -119.77
+    - -118.3
+    MedInc:
+    - 6.1426
+    - 5.3886
+    - 1.7109
+    Population:
+    - 439.0
+    - 848.0
+    - 1757.0
+---
+
+# Model description
+
+Gradient boosting regressor trained on California Housing dataset
+
+The model is a gradient boosting regressor from sklearn. On top of the standard
+features, it contains predictions from a KNN models. These predictions are calculated
+out of fold, then added on top of the existing features. These features are really
+helpful for decision tree-based models, since those cannot easily learn from geospatial
+data.
+
+## Intended uses & limitations
+
+This model is meant for demonstration purposes
+
+## Training Procedure
+
+### Hyperparameters
+
+The model is trained with below hyperparameters.
+
+<details>
+<summary> Click to expand </summary>
+
+| Hyperparameter                                | Value                                                        |
+|-----------------------------------------------|--------------------------------------------------------------|
+| cv                                            |                                                              |
+| estimators                                    | [('knn@5', Pipeline(steps=[('select_cols',<br />                 ColumnTransformer(transformers=[('long_and_lat', 'passthrough',<br />                                                  ['Longitude', 'Latitude'])])),<br />                ('knn', KNeighborsRegressor())]))]                                                              |
+| final_estimator__alpha                        | 0.9                                                          |
+| final_estimator__ccp_alpha                    | 0.0                                                          |
+| final_estimator__criterion                    | friedman_mse                                                 |
+| final_estimator__init                         |                                                              |
+| final_estimator__learning_rate                | 0.1                                                          |
+| final_estimator__loss                         | squared_error                                                |
+| final_estimator__max_depth                    | 3                                                            |
+| final_estimator__max_features                 |                                                              |
+| final_estimator__max_leaf_nodes               |                                                              |
+| final_estimator__min_impurity_decrease        | 0.0                                                          |
+| final_estimator__min_samples_leaf             | 1                                                            |
+| final_estimator__min_samples_split            | 2                                                            |
+| final_estimator__min_weight_fraction_leaf     | 0.0                                                          |
+| final_estimator__n_estimators                 | 500                                                          |
+| final_estimator__n_iter_no_change             |                                                              |
+| final_estimator__random_state                 | 0                                                            |
+| final_estimator__subsample                    | 1.0                                                          |
+| final_estimator__tol                          | 0.0001                                                       |
+| final_estimator__validation_fraction          | 0.1                                                          |
+| final_estimator__verbose                      | 0                                                            |
+| final_estimator__warm_start                   | False                                                        |
+| final_estimator                               | GradientBoostingRegressor(n_estimators=500, random_state=0)  |
+| n_jobs                                        |                                                              |
+| passthrough                                   | True                                                         |
+| verbose                                       | 0                                                            |
+| knn@5                                         | Pipeline(steps=[('select_cols',<br />                 ColumnTransformer(transformers=[('long_and_lat', 'passthrough',<br />                                                  ['Longitude', 'Latitude'])])),<br />                ('knn', KNeighborsRegressor())])                                                              |
+| knn@5__memory                                 |                                                              |
+| knn@5__steps                                  | [('select_cols', ColumnTransformer(transformers=[('long_and_lat', 'passthrough',<br />                                 ['Longitude', 'Latitude'])])), ('knn', KNeighborsRegressor())]                                                              |
+| knn@5__verbose                                | False                                                        |
+| knn@5__select_cols                            | ColumnTransformer(transformers=[('long_and_lat', 'passthrough',<br />                                 ['Longitude', 'Latitude'])])                                                              |
+| knn@5__knn                                    | KNeighborsRegressor()                                        |
+| knn@5__select_cols__n_jobs                    |                                                              |
+| knn@5__select_cols__remainder                 | drop                                                         |
+| knn@5__select_cols__sparse_threshold          | 0.3                                                          |
+| knn@5__select_cols__transformer_weights       |                                                              |
+| knn@5__select_cols__transformers              | [('long_and_lat', 'passthrough', ['Longitude', 'Latitude'])] |
+| knn@5__select_cols__verbose                   | False                                                        |
+| knn@5__select_cols__verbose_feature_names_out | True                                                         |
+| knn@5__select_cols__long_and_lat              | passthrough                                                  |
+| knn@5__knn__algorithm                         | auto                                                         |
+| knn@5__knn__leaf_size                         | 30                                                           |
+| knn@5__knn__metric                            | minkowski                                                    |
+| knn@5__knn__metric_params                     |                                                              |
+| knn@5__knn__n_jobs                            |                                                              |
+| knn@5__knn__n_neighbors                       | 5                                                            |
+| knn@5__knn__p                                 | 2                                                            |
+| knn@5__knn__weights                           | uniform                                                      |
+
+</details>
+
+### Model Plot
+
+The model plot is below.
+
+<style>#sk-container-id-13 {color: black;background-color: white;}#sk-container-id-13 pre{padding: 0;}#sk-container-id-13 div.sk-toggleable {background-color: white;}#sk-container-id-13 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-13 label.sk-toggleable__label-arrow:before {content: "▸";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-13 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-13 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-13 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-13 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-13 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-13 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: "▾";}#sk-container-id-13 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-13 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-13 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-13 div.sk-parallel-item::after {content: "";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-13 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-serial::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-13 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-13 div.sk-item {position: relative;z-index: 1;}#sk-container-id-13 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-13 div.sk-item::before, #sk-container-id-13 div.sk-parallel-item::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-13 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-13 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-13 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-13 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-13 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-13 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-13 div.sk-label-container {text-align: center;}#sk-container-id-13 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-13 div.sk-text-repr-fallback {display: none;}</style><div id="sk-container-id-13" class="sk-top-container" style="overflow: auto;"><div class="sk-text-repr-fallback"><pre>StackingRegressor(estimators=[(&#x27;knn@5&#x27;,Pipeline(steps=[(&#x27;select_cols&#x27;,ColumnTransformer(transformers=[(&#x27;long_and_lat&#x27;,&#x27;passthrough&#x27;,[&#x27;Longitude&#x27;,&#x27;Latitude&#x27;])])),(&#x27;knn&#x27;,KNeighborsRegressor())]))],final_estimator=GradientBoostingRegressor(n_estimators=500,random_state=0),passthrough=True)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class="sk-container" hidden><div class="sk-item sk-dashed-wrapped"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-41" type="checkbox" ><label for="sk-estimator-id-41" class="sk-toggleable__label sk-toggleable__label-arrow">StackingRegressor</label><div class="sk-toggleable__content"><pre>StackingRegressor(estimators=[(&#x27;knn@5&#x27;,Pipeline(steps=[(&#x27;select_cols&#x27;,ColumnTransformer(transformers=[(&#x27;long_and_lat&#x27;,&#x27;passthrough&#x27;,[&#x27;Longitude&#x27;,&#x27;Latitude&#x27;])])),(&#x27;knn&#x27;,KNeighborsRegressor())]))],final_estimator=GradientBoostingRegressor(n_estimators=500,random_state=0),passthrough=True)</pre></div></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-parallel"><div class="sk-parallel-item"><div class="sk-item"><div class="sk-label-container"><div class="sk-label sk-toggleable"><label>knn@5</label></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-serial"><div class="sk-item sk-dashed-wrapped"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-42" type="checkbox" ><label for="sk-estimator-id-42" class="sk-toggleable__label sk-toggleable__label-arrow">select_cols: ColumnTransformer</label><div class="sk-toggleable__content"><pre>ColumnTransformer(transformers=[(&#x27;long_and_lat&#x27;, &#x27;passthrough&#x27;,[&#x27;Longitude&#x27;, &#x27;Latitude&#x27;])])</pre></div></div></div><div class="sk-parallel"><div class="sk-parallel-item"><div class="sk-item"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-43" type="checkbox" ><label for="sk-estimator-id-43" class="sk-toggleable__label sk-toggleable__label-arrow">long_and_lat</label><div class="sk-toggleable__content"><pre>[&#x27;Longitude&#x27;, &#x27;Latitude&#x27;]</pre></div></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-44" type="checkbox" ><label for="sk-estimator-id-44" class="sk-toggleable__label sk-toggleable__label-arrow">passthrough</label><div class="sk-toggleable__content"><pre>passthrough</pre></div></div></div></div></div></div></div></div><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-45" type="checkbox" ><label for="sk-estimator-id-45" class="sk-toggleable__label sk-toggleable__label-arrow">KNeighborsRegressor</label><div class="sk-toggleable__content"><pre>KNeighborsRegressor()</pre></div></div></div></div></div></div></div></div></div></div><div class="sk-item"><div class="sk-parallel"><div class="sk-parallel-item"><div class="sk-item"><div class="sk-label-container"><div class="sk-label sk-toggleable"><label>final_estimator</label></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-46" type="checkbox" ><label for="sk-estimator-id-46" class="sk-toggleable__label sk-toggleable__label-arrow">GradientBoostingRegressor</label><div class="sk-toggleable__content"><pre>GradientBoostingRegressor(n_estimators=500, random_state=0)</pre></div></div></div></div></div></div></div></div></div></div></div></div>
+
+## Evaluation Results
+
+Metrics are calculated on the test set
+
+| Metric                  |        Value |
+|-------------------------|--------------|
+| Root mean squared error | 44273.5      |
+| Mean absolute error     | 30079.9      |
+| R²                      |     0.805954 |
+
+## Dataset description
+
+California Housing dataset
+--------------------------
+
+**Data Set Characteristics:**
+
+    :Number of Instances: 20640
+
+    :Number of Attributes: 8 numeric, predictive attributes and the target
+
+    :Attribute Information:
+        - MedInc        median income in block group
+        - HouseAge      median house age in block group
+        - AveRooms      average number of rooms per household
+        - AveBedrms     average number of bedrooms per household
+        - Population    block group population
+        - AveOccup      average number of household members
+        - Latitude      block group latitude
+        - Longitude     block group longitude
+
+    :Missing Attribute Values: None
+
+This dataset was obtained from the StatLib repository.
+https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html
+
+The target variable is the median house value for California districts,
+expressed in hundreds of thousands of dollars ($100,000).
+
+This dataset was derived from the 1990 U.S. census, using one row per census
+block group. A block group is the smallest geographical unit for which the U.S.
+Census Bureau publishes sample data (a block group typically has a population
+of 600 to 3,000 people).
+
+An household is a group of people residing within a home. Since the average
+number of rooms and bedrooms in this dataset are provided per household, these
+columns may take surpinsingly large values for block groups with few households
+and many empty houses, such as vacation resorts.
+
+It can be downloaded/loaded using the
+:func:`sklearn.datasets.fetch_california_housing` function.
+
+.. topic:: References
+
+    - Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,
+      Statistics and Probability Letters, 33 (1997) 291-297
+
+### Data distribution
+
+<details>
+<summary> Click to expand </summary>
+
+![Data distribution](geographic.png)
+
+</details>
+
+# How to Get Started with the Model
+
+Run the code below to load the model
+
+```python
+import json
+import pandas as pd
+import skops.io as sio
+model = sio.load("model.skops")
+with open("config.json") as f:
+    config = json.load(f)
+model.predict(pd.DataFrame.from_dict(config["sklearn"]["example_input"]))
+```
+
+# Model Card Authors
+
+Benjamin Bossan
+
+# Model Card Contact
+
+[email protected]
+
+# Permutation Importances
+
+![Permutation Importances](permutation-importances.png)

config.json

@@ -0,0 +1,67 @@
+{
+    "sklearn": {
+        "columns": [
+            "MedInc",
+            "HouseAge",
+            "AveRooms",
+            "AveBedrms",
+            "Population",
+            "AveOccup",
+            "Latitude",
+            "Longitude"
+        ],
+        "environment": [
+            "scikit-learn==1.2.0",
+            "pandas==1.5.3",
+            "skops==0.6.dev0"
+        ],
+        "example_input": {
+            "AveBedrms": [
+                0.9290780141843972,
+                0.9458483754512635,
+                1.087360594795539
+            ],
+            "AveOccup": [
+                3.1134751773049647,
+                3.0613718411552346,
+                3.2657992565055762
+            ],
+            "AveRooms": [
+                6.304964539007092,
+                6.945848375451264,
+                3.8884758364312266
+            ],
+            "HouseAge": [
+                17.0,
+                15.0,
+                24.0
+            ],
+            "Latitude": [
+                34.23,
+                36.84,
+                34.04
+            ],
+            "Longitude": [
+                -117.41,
+                -119.77,
+                -118.3
+            ],
+            "MedInc": [
+                6.1426,
+                5.3886,
+                1.7109
+            ],
+            "Population": [
+                439.0,
+                848.0,
+                1757.0
+            ]
+        },
+        "model": {
+            "file": "model.skops"
+        },
+        "model_format": "skops",
+        "task": "tabular-regression",
+        "use_intelex": false
+    }
+}

model.skops

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5baa2695cda0fbcc186e2e8473cb73c13d0ad728d96844479c0b32c15827fa
+size 14674596