EpistasisLab · trangdata · Feb 25, 2025 · Sep 3, 2024 · Oct 31, 2024 · Oct 31, 2024
diff --git a/.lfs-assets-id b/.lfs-assets-id
@@ -21,6 +21,7 @@
 0baa7b708956fd05b84d47b18a86f926335db5f42d2cd7e29ca83558c139aff3
 0be6203e167cc5e7b038368dbfe0a7790d5dc423c9d7e42887907c5c03f81c27
 0c342ef5d61bbcf43180a3b71d407b9d994942ce43e8960052201daf88dd095d
+0c848103ae200b9a969cf5eb9836592b7663aa7553e8a129102d7fc387c2f490
 0d05767a4c118752a25c4632aeea3b71ffa1bfe122b6a2401f85d20541be19a4
 0d39f17afc3a1712bd6c460aa941aed7835b3feb142538adfdd31ddc2451d60d
 0d43780ab866e54a2a78d8c86ba231ad0a5d55588450a33ed6fe52bee9638341
@@ -43,6 +44,7 @@
 1ee8cf9693351db7afe68f6fc32942845caae3e1030c688efa6c5d0b24229f46
 1f5cf829d2e58032e5d9067f1e7bf3fe7644cd5fe2825c81ef7fbaa445f496a7
 1f69f25b0168c39018c214ae39f2bb8fe6da97e1df389c2cb88cf9bde2f08ace
+21586d500f0961c0d2c8296644e3ec269e2ecf783f3c39c0fdf1dc6159edee0a
 21d506c397dfeb3edbbbc253b923f59be6edb516689677ebef535296c6c62242
 22053c4cdaaaf6169d90e4ee03f8b994cb682281ab6787bf14c617301db5663b
 22baa768886091d61e13e894610dfea3435dfd201f8300fbebe46cd6cf814c0b
@@ -79,6 +81,7 @@
 32abe7e2579387f0439d1595cb72f1f0fe79f41822ec99d06f0e219a65dda362
 32bdeb725bc79d00349bcc66c41d306f463005cf6ac623cf8c15b5f3f7bbbb83
 32d94576f8622f22279a02099e5269511a8b14fee6a441e880730966763b79c9
+346b2e3bbc0c631bc00b2d001dfc5791fe729cb472795b23d593895252ce6bb8
 34fd665457403f66db49a4d012c59d7c387f99a35597c8f0f0e31d40ada255f8
 35724de77dbb2d325f81905aa01f639cae3f29a3d24ae7b24ec84acbc9e08a8f
 35aefd558529484575b142f122c5e2af2eb337025a9607e3df5ab60a57783e09
@@ -107,6 +110,7 @@
 45b06a3b07f45e5aa49f13f030860b245507ba94185219571ceb314fbdd87c2f
 45b6fb5d5c4bb09f2f21b53b069b3994e4f6fa69a5a932cf01c1ebb335bf8645
 46578097c3f1477b9f4f2eb2dc74421162fa9a14e139b0e3e791e41679e459d9
+469d734ef8b6f79d2e38bc487251940bcaa9349050cb455063209e3371dcd439
 46e26ab2e17e1e92728b1a27ebcad5fc8319b4195414746064da34d95f27280e
 47478e3af60f8a6cc09dcfba8495af699c8187edc279a0e226e4e63b410d64b7
 4757ff95609abb91a98577cf6023c804ba2b0b749a9dfcc48597ac49d4bf72a0
@@ -142,10 +146,13 @@
 56f25ef2fcadcd25cc5ccdc721663194ead75bcd90c4d5c1b806d72ea193948f
 56f5ba3f3ba78f6e522a13e5a97e03ff28cf9fa4107021b22b932f6d4064c145
 56f81f2a4cdd1968cc83d45bfdaa049c90cf7cdf3141b2db9979d31c000e3937
+5704b631ba0afc6bf761196ae757565c6ea8398019094526f16383802b8f6cda
 57b36b18d3ed1b78d6ca647f701fdef974b27979cda7dda2fe91a81eb7e329d6
 588ef519ce346285e4cb9cdd5780abbbac32cab9661625c6e517a9b70c87495d
+5910dd1ee08ef353c08e2c25b629f66d42565eb4c990656e06d1b575fe5880a7
 5940ac21f3c7e93dd1dca45266304d160c45256f0628419f001c8b54e1c98360
 596303e877cb91ec3f96cab8c0eac3205f8c50d2e56debdde6a6b4bcffe57ccd
+59df1d16cb8aa383900dc43a067ca79437912283dd3b32e4834b20185efc586e
 5adc7d62cd741fde41554ad50ba608973a19f87f795787156e7f16855a227a49
 5b1d8788d9512819fd46d1acf1e86e70cb5f4418c8e8bfe299ebd3abf2188217
 5b20048751e68b6dd76a7b66ada790fb90f9dd41bd8c82d448fe439f8d038969
@@ -233,6 +240,7 @@
 840eff365b01eacb770f1e78f97bc889611362bd3bbf835f344a2792973c985a
 849976657dc371578819f225ce81eb9a76bd084ce743b5ff6753e415567c68dd
 854aedabba36d89fb2a79246592f2858d6905e7e75a1031128f67ed0c8a446a6
+85b0d6a23ccc3a1db5e2a94928c32e35dd2388d2cb13328c9a914fc594e7bab1
 86e18c1aa7247f824f7097219d75d29f8dcba3034bc89e1ee92c7778aa31bd9c
 8712952be1bc739d221729dd94705dc67e189981a728ecc9cfe08c8df5d8b125
 87df1bbfb83b8204093ccd84ed18bb3695220c03aa4096f63a84cc5e136dbc0b
@@ -284,17 +292,21 @@
 9def90abb62c1b9872ae2dbed3e425850ae44f98d3664e8b29e2444548e9fec9
 9e1ec477e8af8356c3b731f8815f19b57bb404bd7c1629a2020bc9d90b0c028a
 9e69e5aa34b36b4f528c42711c7fbaf88abcda9f0b7ba4181e4f57525b6d1527
+9f946159fb4fa4d6351952d89148572682de6c062f14b6c0f401b9479ad277de
 a15ad0797f0d445cafcf5afb14f26df0aee2417181a2081ad26b1c10e0aaf79c
 a2b0fbfc6f24cb86e3c612be4d59f5dc48b4e3e73620b480dd9f54dccf4d90da
 a39fc5f054db506e83a4a4ec47eba1f7f9bf9bfdc983174e699312f32f42f1f5
 a3a7bf32a44deebb795cf6faf6fc88936d24fc94157468f352c8972906318984
 a4e3dfadeb34bba861ef56046d2fc99c4d50d8475882d610a0b652d39c510f6b
 a551e2941365201552a3a819f035c64f297467464f7c7c349d00711316ce3c57
 a55638ba902c8afb52d5b006f2ac438c72dfcdd6325efe7488b125f7a9662989
+a568223ad5181bf644ca9e871fd235d0e614895b995155b0cb2dfec53f8f9328
 a5a5d15adf74702c323b62b595cdefcdd157f68ebd86af5e504bc16c9890c2ff
 a5c0e0103dc8caf7a9b18ab4546a046ba2e01425259c639069fa02f0824ae0f2
 a5fff4a8241312d53818c146ca0b132dc760a6848e7b89ec2e3271fc6454e7da
+a70e4196c6288b9132c1fa2515235a18be44b16f6a54fdb04ea043b8027b6ea0
 a71c05581e59bc83a6e500c66ea94ff9e355d5e457f0b094e10a61e7f13fdecc
+a80f850226d7a536fad6f33fdae2d08bee9bf36c3a28c452ed0aaa244c88bf39
 a857a458b0621f46b60f326d5760f7d3d39d6ba1fe87db1a7f1114bdfeb99862
 a8a1931c568c9637e3671aa4919cc6a1a3acfa26358fd3f81ca89e4b01f96a72
 a96ca8012634e20d924624747b939c1b99f7b4ec36a7819c80c962d7a1fafe49
@@ -330,6 +342,7 @@ bd0e747cb0a16d9f68843ccd6fa0b0d382bb21f2c83ccbc222712426ee42274b
 bd9d5214451c3b72e8a5ba4ae75a565d373d90a804659d0a5f4617fad3ac4cfd
 be6942e13096c21f10496a24056b01ff791e24d6172f5b7a09013c3307d38f28
 beedc054b8e7d974a98326db8c834843eb188cffba0f07029a8370b193ce020e
+bef7e5fb62eb611f1d60e8418df7b546c0df0ae28a51b5c3f7501b2128fdbb17
 bf066d8b8431c89d3c8afd58b0bfe56f53e0aaedd8d4ec05c132268115af3f36
 bfc6131af9d009576a82d25e0590955980535eb61c67d1553434da993e79af92
 bfd1b9c6e5f6314f6ddfc285ace11381570ad688c6c857562c3155a4e478530d

diff --git a/datasets/auto_insurance_losses/README.md b/datasets/auto_insurance_losses/README.md
@@ -0,0 +1,6 @@
+# auto_insurance_losses
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/auto_insurance_losses.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/auto_insurance_losses/summary_stats.tsv b/datasets/auto_insurance_losses/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-auto_insurance_losses	164	24	3	7	14	continuous	51	0.00844289113622844	regression
+auto_insurance_losses	164	24	3	6	15	categorical	51.0	0.008442891136228436	regression
diff --git a/datasets/auto_insurance_price/README.md b/datasets/auto_insurance_price/README.md
@@ -0,0 +1,6 @@
+# auto_insurance_price
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/auto_insurance_price.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/auto_insurance_price/summary_stats.tsv b/datasets/auto_insurance_price/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-auto_insurance_price	201	23	4	6	13	continuous	186	0.000343181229792947	regression
+auto_insurance_price	201	23	4	5	14	categorical	186.0	0.0003431812297929476	regression
diff --git a/datasets/auto_insurance_symboling/README.md b/datasets/auto_insurance_symboling/README.md
@@ -0,0 +1,6 @@
+# auto_insurance_symboling
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/auto_insurance_symboling.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/auto_insurance_symboling/summary_stats.tsv b/datasets/auto_insurance_symboling/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-auto_insurance_symboling	205	24	4	6	14	ordinal	6	0.0755788221296847	classification
+auto_insurance_symboling	205	24	4	5	15	categorical	6.0	0.07557882212968471	classification
diff --git a/datasets/breast_cancer_wisconsin_diagnostic/README.md b/datasets/breast_cancer_wisconsin_diagnostic/README.md
@@ -0,0 +1,6 @@
+# breast_cancer_wisconsin_diagnostic
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/breast_cancer_wisconsin_diagnostic.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/breast_cancer_wisconsin_diagnostic/summary_stats.tsv b/datasets/breast_cancer_wisconsin_diagnostic/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-breast_cancer_wisconsin_diagnostic	569	30	0	0	30	binary	2	0.064939878490615	classification
+breast_cancer_wisconsin_diagnostic	569	30	0	0	30	categorical	2.0	0.06493987849061501	classification
diff --git a/datasets/breast_cancer_wisconsin_original/README.md b/datasets/breast_cancer_wisconsin_original/README.md
@@ -0,0 +1,6 @@
+# breast_cancer_wisconsin_original
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/breast_cancer_wisconsin_original.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/breast_cancer_wisconsin_original/summary_stats.tsv b/datasets/breast_cancer_wisconsin_original/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-breast_cancer_wisconsin_original	699	9	0	0	9	binary	2	0.0963751609186227	classification
+breast_cancer_wisconsin_original	699	9	0	9	0	categorical	2.0	0.09637516091862275	classification
diff --git a/datasets/car_evaluation/README.md b/datasets/car_evaluation/README.md
@@ -0,0 +1,6 @@
+# car_evaluation
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/car_evaluation.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/car_evaluation/summary_stats.tsv b/datasets/car_evaluation/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-car_evaluation	1728	6	0	6	0	categorical	4	0.390288315900777	classification
+car_evaluation	1728	6	0	6	0	categorical	4.0	0.39028831590077734	classification
diff --git a/datasets/congressional_voting_records/README.md b/datasets/congressional_voting_records/README.md
@@ -0,0 +1,6 @@
+# congressional_voting_records
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/congressional_voting_records.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/congressional_voting_records/summary_stats.tsv b/datasets/congressional_voting_records/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-congressional_voting_records	435	16	0	16	0	binary	2	0.0517954815695601	classification
+congressional_voting_records	435	16	0	16	0	categorical	2.0	0.05179548156956005	classification
diff --git a/datasets/contraceptive_method/README.md b/datasets/contraceptive_method/README.md
@@ -0,0 +1,6 @@
+# contraceptive_method
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/contraceptive_method.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/contraceptive_method/summary_stats.tsv b/datasets/contraceptive_method/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-contraceptive_method	1473	9	3	4	2	categorical	3	0.030700608232641	classification
+contraceptive_method	1473	9	3	4	2	categorical	3.0	0.03070060823264104	classification
diff --git a/datasets/credit_approval_australia/README.md b/datasets/credit_approval_australia/README.md
@@ -0,0 +1,6 @@
+# credit_approval_australia
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/credit_approval_australia.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/credit_approval_australia/summary_stats.tsv b/datasets/credit_approval_australia/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-credit_approval_australia	690	15	4	5	6	binary	2	0.0121319050619618	classification
+credit_approval_australia	690	15	4	4	7	categorical	2.0	0.012131905061961762	classification
diff --git a/datasets/credit_approval_germany/README.md b/datasets/credit_approval_germany/README.md
@@ -0,0 +1,6 @@
+# credit_approval_germany
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/credit_approval_germany.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/credit_approval_germany/summary_stats.tsv b/datasets/credit_approval_germany/summary_stats.tsv
@@ -1,2 +1,2 @@
 dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
-credit_approval_germany	1000	20	3	14	3	binary	2	0.16	classification
+credit_approval_germany	1000	20	3	14	3	categorical	2.0	0.15999999999999998	classification
diff --git a/datasets/first_principles_absorption/README.md b/datasets/first_principles_absorption/README.md
@@ -0,0 +1,6 @@
+# first_principles_absorption
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/first_principles_absorption.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/first_principles_absorption/first_principles_absorption.tsv.gz b/datasets/first_principles_absorption/first_principles_absorption.tsv.gz
diff --git a/datasets/first_principles_absorption/metadata.yaml b/datasets/first_principles_absorption/metadata.yaml
@@ -0,0 +1,18 @@
+# Created by Guilherme Aldeia (@galdeia)
+dataset: first_principles_absorption
+description: |
+    A real-world dataset containing the absorption of light for a solution containing a specific molecule at different levels of concentration. The original publication has data for 4 different molecules, and here we include data from only one of them (`real_data/absorption/examples/example0.csv`), the one with highest number of samples. 
+source: publication repository https://github.com/erusseil/MvSR-analysis
+publication: Etienne Russeil, Fabricio Olivetti de Franca, Konstantin Malanchev, Bogdan Burlacu, Emille Ishida, Marion Leroux, Clément Michelin, Guillaume Moinard, and Emmanuel Gangler. 2024. Multiview Symbolic Regression. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '24). Association for Computing Machinery, New York, NY, USA, 961-970. https://doi.org/10.1145/3638529.3654087
+task: regression
+keywords:
+  - symbolic regression
+  - physics
+  - first principles
+target:
+  type: continuous
+  description: Absorption, the amount of light absorbed by the solution
+features:
+  - name: Xaxis0
+    type: continuous
+    description: Concentration (mol/L)
diff --git a/datasets/first_principles_absorption/summary_stats.tsv b/datasets/first_principles_absorption/summary_stats.tsv
@@ -0,0 +1,2 @@
+dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
+first_principles_absorption	14	1	0	0	1	continuous	14.0	0.0	regression
diff --git a/datasets/first_principles_bode/README.md b/datasets/first_principles_bode/README.md
@@ -0,0 +1,6 @@
+# first_principles_bode
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/first_principles_bode.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/first_principles_bode/first_principles_bode.tsv.gz b/datasets/first_principles_bode/first_principles_bode.tsv.gz
diff --git a/datasets/first_principles_bode/metadata.yaml b/datasets/first_principles_bode/metadata.yaml
@@ -0,0 +1,25 @@
+# Created by Guilherme Aldeia (@galdeia)
+dataset: first_principles_bode
+description: |
+  The Bode's law is a model for the distance of planets from the sun, given their order in the solar system.
+
+  The governing equation is given by:
+
+  a = 0.4 + 0.3 (2^n)
+
+  Data was taken from bonnet Contemplating Nature 1764, and planets Neptuno and Pluto are skipped.
+
+source: publication repository https://github.com/MilesCranmer/PySR
+publication: Interpretable machine learning for science with PySR and SymbolicRegression, CRANMER, Miles, arXiv preprint arXiv:2305.01582, 2023.
+task: regression
+keywords:
+  - symbolic regression
+  - physics
+  - first principles
+target:
+  type: continuous
+  description: semi-major axis, AU
+features:
+  - name: "n"
+    type: categorical
+    description: planet index
diff --git a/datasets/first_principles_bode/summary_stats.tsv b/datasets/first_principles_bode/summary_stats.tsv
@@ -0,0 +1,2 @@
+dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
+first_principles_bode	8	1	0	1	0	continuous	8.0	0.0	regression
diff --git a/datasets/first_principles_hubble/README.md b/datasets/first_principles_hubble/README.md
@@ -0,0 +1,6 @@
+# first_principles_hubble
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/first_principles_hubble.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/first_principles_hubble/first_principles_hubble.tsv.gz b/datasets/first_principles_hubble/first_principles_hubble.tsv.gz
diff --git a/datasets/first_principles_hubble/metadata.yaml b/datasets/first_principles_hubble/metadata.yaml
@@ -0,0 +1,19 @@
+# Created by Guilherme Aldeia (@galdeia)
+dataset: first_principles_hubble
+description: |
+  The Hubble constant is a measure of the rate of expansion of the universe, measured as v = H_0 D, where v is the velocity of a galaxy, D is its distance from us, and H_0 is the Hubble constant (73.3 (km/s)/Mpc). 
+
+source: publication repository https://github.com/MilesCranmer/PySR
+publication: Interpretable machine learning for science with PySR and SymbolicRegression, CRANMER, Miles, arXiv preprint arXiv:2305.01582, 2023.
+task: regression
+keywords:
+  - symbolic regression
+  - physics
+  - first principles
+target:
+  type: continuous
+  description: velocity, in km/s
+features:
+  - name: D
+    type: continuous
+    description: distance of a galaxy from us (in million parsecs, Mpc)
diff --git a/datasets/first_principles_hubble/summary_stats.tsv b/datasets/first_principles_hubble/summary_stats.tsv
@@ -0,0 +1,2 @@
+dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
+first_principles_hubble	32	1	0	0	1	continuous	32.0	0.0	regression
diff --git a/datasets/first_principles_ideal_gas/README.md b/datasets/first_principles_ideal_gas/README.md
@@ -0,0 +1,6 @@
+# first_principles_ideal_gas
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/first_principles_ideal_gas.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/first_principles_ideal_gas/first_principles_ideal_gas.tsv.gz b/datasets/first_principles_ideal_gas/first_principles_ideal_gas.tsv.gz
diff --git a/datasets/first_principles_ideal_gas/metadata.yaml b/datasets/first_principles_ideal_gas/metadata.yaml
@@ -0,0 +1,27 @@
+# Created by Guilherme Aldeia (@galdeia)
+dataset: first_principles_ideal_gas
+description: |
+  The ideal dass law is a model for the pressure of an ideal gas, given it's temperature and volume.
+
+  Data was generated using the ideal gas law, with a range of parameters using the scripts in the publication repository.
+
+source: publication repository https://github.com/MilesCranmer/PySR
+publication: Interpretable machine learning for science with PySR and SymbolicRegression, CRANMER, Miles, arXiv preprint arXiv:2305.01582, 2023.
+task: regression
+keywords:
+  - symbolic regression
+  - physics
+  - first principles
+target:
+  type: continuous
+  description: pressure
+features:
+  - name: "n"
+    type: continuous
+    description: number density
+  - name: T
+    type: continuous
+    description: temperature
+  - name: V
+    type: continuous
+    description: volume
diff --git a/datasets/first_principles_ideal_gas/summary_stats.tsv b/datasets/first_principles_ideal_gas/summary_stats.tsv
@@ -0,0 +1,2 @@
+dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
+first_principles_ideal_gas	30	3	0	0	3	continuous	30.0	0.0	regression
diff --git a/datasets/first_principles_kepler/README.md b/datasets/first_principles_kepler/README.md
@@ -0,0 +1,6 @@
+# first_principles_kepler
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/first_principles_kepler.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/first_principles_kepler/first_principles_kepler.tsv.gz b/datasets/first_principles_kepler/first_principles_kepler.tsv.gz
diff --git a/datasets/first_principles_kepler/metadata.yaml b/datasets/first_principles_kepler/metadata.yaml
@@ -0,0 +1,23 @@
+# Created by Guilherme Aldeia (@galdeia)
+dataset: first_principles_kepler
+description: |
+  The Keppler dataset is based on the Kepler's third law of planetary motion. The features are the semi-major axis (a) and the period (P) of a planet's orbit, given by the equation:
+
+  P^2 = k a^3
+
+  Each row corresponds to a planet in the following order: Mercury, Venus, Earth, Mars, Jupiter, Saturn, and it is based on the data used by Kepler in 1618.
+
+source: publication repository https://github.com/MilesCranmer/PySR
+publication: Interpretable machine learning for science with PySR and SymbolicRegression, CRANMER, Miles, arXiv preprint arXiv:2305.01582, 2023.
+task: regression
+keywords:
+  - symbolic regression
+  - physics
+  - first principles
+target:
+  type: continuous
+  description: Period in days
+features:
+  - name: a
+    type: continuous
+    description: semi-major axis, AU
diff --git a/datasets/first_principles_kepler/summary_stats.tsv b/datasets/first_principles_kepler/summary_stats.tsv
@@ -0,0 +1,2 @@
+dataset	n_instances	n_features	n_binary_features	n_categorical_features	n_continuous_features	endpoint_type	n_classes	imbalance	task
+first_principles_kepler	6	1	0	0	1	continuous	6.0	0.0	regression
diff --git a/datasets/first_principles_leavitt/README.md b/datasets/first_principles_leavitt/README.md
@@ -0,0 +1,6 @@
+# first_principles_leavitt
+
+[**Pandas Profiling Report**](https://epistasislab.github.io/pmlb/profile/first_principles_leavitt.html)
+
+[Metadata](metadata.yaml) | [Summary Statistics](summary_stats.tsv)
+
diff --git a/datasets/first_principles_leavitt/first_principles_leavitt.tsv.gz b/datasets/first_principles_leavitt/first_principles_leavitt.tsv.gz
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		dataset n_instances n_features n_binary_features n_categorical_features n_continuous_features endpoint_type n_classes imbalance task
		first_principles_absorption 14 1 0 0 1 continuous 14.0 0.0 regression
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		dataset n_instances n_features n_binary_features n_categorical_features n_continuous_features endpoint_type n_classes imbalance task
		first_principles_bode 8 1 0 1 0 continuous 8.0 0.0 regression
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		dataset n_instances n_features n_binary_features n_categorical_features n_continuous_features endpoint_type n_classes imbalance task
		first_principles_hubble 32 1 0 0 1 continuous 32.0 0.0 regression
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		dataset n_instances n_features n_binary_features n_categorical_features n_continuous_features endpoint_type n_classes imbalance task
		first_principles_ideal_gas 30 3 0 0 3 continuous 30.0 0.0 regression
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		dataset n_instances n_features n_binary_features n_categorical_features n_continuous_features endpoint_type n_classes imbalance task
		first_principles_kepler 6 1 0 0 1 continuous 6.0 0.0 regression