You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: docs/index.md
+69-43
Original file line number
Diff line number
Diff line change
@@ -57,57 +57,75 @@ For more information, please see [an introduction to stemflow](https://chenyangk
57
57
-----
58
58
59
59
## Model and data :slot_machine:
60
-
60
+
<!--
61
61
| Main functionality of `stemflow` | Supported data types | Supported tasks | Supported base models |
62
62
| -- | -- | -- | -- |
63
-
|:white_check_mark: Spatiotemporal modeling & prediction<br> |:white_check_mark:All spatial indexing (CRS)<br> |:white_check_mark: Binary classification task<br> |:white_check_mark: sklearn style `BaseEstimator` classes ([you can make your own base model](https://scikit-learn.org/stable/developers/develop.html)), for example [here](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)<br> |
| :white_check_mark: Spatiotemporal modeling & prediction<br> | :white_check_mark: User-defined 2D spatial indexing (CRS)<br> | :white_check_mark: Binary classification task<br> | :white_check_mark: sklearn style `BaseEstimator` classes ([you can make your own base model](https://scikit-learn.org/stable/developers/develop.html)), for example [here](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)<br> |
| | :white_check_mark: Both continuous and categorical features (prefer one-hot encoding)<br> | | |
67
67
| | :white_check_mark: Both static (e.g., yearly mean temperature) and dynamic features (e.g., daily temperature) | | |
68
68
| For details see [AdaSTEM Demo](https://chenyangkang.github.io/stemflow/Examples/01.AdaSTEM_demo.html) | For details and tips see [Tips for data types](https://chenyangkang.github.io/stemflow/Tips/Tips_for_data_types.html) | For details and tips see [Tips for different tasks](https://chenyangkang.github.io/stemflow/Tips/Tips_for_different_tasks.html) | For details see [Base model choices](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)|
69
+
-->
70
+
71
+
| Main functionality of `stemflow`| Supported indexing | Supported tasks |
| For details see [AdaSTEM Demo](https://chenyangkang.github.io/stemflow/Examples/01.AdaSTEM_demo.html)| For details and tips see [Tips for data types](https://chenyangkang.github.io/stemflow/Tips/Tips_for_data_types.html)| For details and tips see [Tips for different tasks](https://chenyangkang.github.io/stemflow/Tips/Tips_for_different_tasks.html)|
| :white_check_mark: Hurdle task (two step regression – classify then regress the non-zero part)<br>
104
+
| For details and tips see [Tips for different tasks](https://chenyangkang.github.io/stemflow/Tips/Tips_for_different_tasks.html) -->
105
+
106
+
107
+
| Supported data types | Supported base models |
108
+
| -- | -- |
109
+
|:white_check_mark: Both continuous and categorical features (prefer one-hot encoding)<br> |:white_check_mark: sklearn style `BaseEstimator` classes ([you can make your own base model](https://scikit-learn.org/stable/developers/develop.html)), for example [here](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)<br> |
110
+
|:white_check_mark: Both static (e.g., yearly mean temperature) and dynamic features (e.g., daily temperature)<br> |:white_check_mark: sklearn style Maxent model. [Example here](https://chenyangkang.github.io/stemflow/Examples/03.Binding_with_Maxent.html). |
111
+
| For details and tips see [Tips for data types](https://chenyangkang.github.io/stemflow/Tips/Tips_for_data_types.html)| For details see [Base model choices](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)|
112
+
113
+
<!-- column 4 -->
114
+
<!-- | Supported data types
115
+
| --
116
+
| :white_check_mark: Both continuous and categorical features (prefer one-hot encoding)<br>
117
+
| :white_check_mark: Both static (e.g., yearly mean temperature) and dynamic features (e.g., daily temperature)<br>
118
+
| For details and tips see [Tips for data types](https://chenyangkang.github.io/stemflow/Tips/Tips_for_data_types.html) -->
119
+
120
+
121
+
<!-- column 5 -->
122
+
<!-- | Supported base models
123
+
| --
124
+
| :white_check_mark: sklearn style `BaseEstimator` classes ([you can make your own base model](https://scikit-learn.org/stable/developers/develop.html)), for example [here](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)<br>
For details see [AdaSTEM Demo](https://chenyangkang.github.io/stemflow/Examples/01.AdaSTEM_demo.html)
80
-
81
-
---
82
-
83
-
### Supported data types
84
-
85
-
:white_check_mark: All spatial indexing (CRS)<br>
86
-
:white_check_mark: All temporal indexing<br>
87
-
:white_check_mark: Spatial-only modeling<br>
88
-
:white_check_mark: Both continuous and categorical features (prefer one-hot encoding)<br>
89
-
:white_check_mark: Both static (e.g., yearly mean temperature) and dynamic features (e.g., daily temperature)
90
-
91
-
For details and tips see [Tips for data types](https://chenyangkang.github.io/stemflow/Tips/Tips_for_data_types.html)
92
-
93
-
--- -->
94
-
95
-
<!-- ### Supported tasks
96
128
97
-
:white_check_mark: Binary classification task<br>
98
-
:white_check_mark: Regression task<br>
99
-
:white_check_mark: Hurdle task (two step regression – classify then regress the non-zero part)<br>
100
-
101
-
For details and tips see [Tips for different tasks](https://chenyangkang.github.io/stemflow/Tips/Tips_for_different_tasks.html)
102
-
103
-
---
104
-
105
-
### Supported base models
106
-
107
-
:white_check_mark: sklearn style `BaseEstimator` classes ([you can make your own base model](https://scikit-learn.org/stable/developers/develop.html)), for example [here](https://chenyangkang.github.io/stemflow/Examples/06.Base_model_choices.html)<br>
Here, each color shows an ensemble generated during model fitting. In each of the 10 ensembles, regions (in terms of space and time) with more training samples were gridded into finer resolution, while the sparse one remained coarse. Prediction results were aggregated across the ensembles (that is, in this example, data were modeled 10 times).
177
195
196
+
If you use `SphereAdaSTEM` module, the gridding plot is a `plotly` generated interactive object by default:
0 commit comments