data

data/datasets/pmlb_small/README.md

@@ -0,0 +1,9 @@
+# Benchmark data sets
+
+This directory contains over 150 data sets for benchmarking supervised machine learning algorithms.
+
+Each subdirectory corresponds to a separate data set, and will have a README file providing some basic information about the data set.
+
+# High-level summary of data sets
+
+[in progress]

data/datasets/pmlb_small/allbp/README.md

@@ -0,0 +1,80 @@
+# allbp
+
+## Summary Stats
+
+#instances: 3772
+
+#features: 29
+
+  #binary_features: 21
+
+  #integer_features: 8
+
+  #float_features: 0
+
+Endpoint type: integer
+
+#Classes: 3
+
+Imbalance metric: 0.8755228428707819
+
+## Feature Types
+
+ age:discrete
+
+sex:discrete
+
+on thyroxine:binary
+
+query on thyroxine:binary
+
+on antithyroid medication:binary
+
+sick:binary
+
+pregnant:binary
+
+thyroid surgery:binary
+
+I131 treatment:binary
+
+query hypothyroid:binary
+
+query hyperthyroid:binary
+
+lithium:binary
+
+goitre:binary
+
+tumor:binary
+
+hypopituitary:binary
+
+psych:binary
+
+TSH measured:binary
+
+TSH:discrete
+
+T3 measured:binary
+
+T3:discrete
+
+TT4 measured:binary
+
+TT4:discrete
+
+T4U measured:binary
+
+T4U:discrete
+
+FTI measured:binary
+
+FTI:discrete
+
+TBG measured:binary
+
+TBG:binary
+
+referral source:discrete
+

data/datasets/pmlb_small/allhyper/README.md

@@ -0,0 +1,80 @@
+# allhyper
+
+## Summary Stats
+
+#instances: 3771
+
+#features: 29
+
+  #binary_features: 21
+
+  #integer_features: 8
+
+  #float_features: 0
+
+Endpoint type: integer
+
+#Classes: 4
+
+Imbalance metric: 0.9301422508626843
+
+## Feature Types
+
+ age:discrete
+
+sex:discrete
+
+on thyroxine:binary
+
+query on thyroxine:binary
+
+on antithyroid medication:binary
+
+sick:binary
+
+pregnant:binary
+
+thyroid surgery:binary
+
+I131 treatment:binary
+
+query hypothyroid:binary
+
+query hyperthyroid:binary
+
+lithium:binary
+
+goitre:binary
+
+tumor:binary
+
+hypopituitary:binary
+
+psych:binary
+
+TSH measured:binary
+
+TSH:discrete
+
+T3 measured:binary
+
+T3:discrete
+
+TT4 measured:binary
+
+TT4:discrete
+
+T4U measured:binary
+
+T4U:discrete
+
+FTI measured:binary
+
+FTI:discrete
+
+TBG measured:binary
+
+TBG:binary
+
+referral source:discrete
+