Namespaces
scicloj.ml.core
Core functions for machine learninig and pipeline execution.
Public variables and functions:
- ->pipeline
- auc
- categorical
- classification-accuracy
- classification-loss
- confusion-map
- confusion-map->ds
- def-ctx
- default-loss-fn
- default-result-dissoc-in-fn
- default-result-dissoc-in-seq
- define-model!
- do-ctx
- ensemble-pipe
- evaluate-pipelines
- explain
- fit
- fit-pipe
- hyperparameters
- lift
- linear
- mae
- model-definition-names
- model-definitions*
- mse
- options->model-def
- pipe-it
- pipeline
- predict
- result-dissoc-in-seq--all
- result-dissoc-in-seq--all-fn
- result-dissoc-in-seq--ctxs
- result-dissoc-in-seq-ctx-fn
- rmse
- sobol-gridsearch
- thaw-model
- train
- transform-pipe
scicloj.ml.dataset
This namespace contains functions which operate on a dataset and mostly return a dataset.
Public variables and functions:
- ->array
- add-column
- add-columns
- add-or-replace-column
- add-or-replace-columns
- aggregate
- aggregate-columns
- anti-join
- append
- array-column->columns
- as-regular-dataset
- asof-join
- bind
- boolean
- by-rank
- categorical
- categorical->number
- categorical->one-hot
- clone
- column
- column-count
- column-filter
- column-names
- column-values->categorical
- columns
- columns->array-column
- complete
- concat
- concat-copying
- convert-types
- create-categorical-map
- cross-join
- crosstab
- dataset
- dataset->categorical-maps
- dataset->categorical-xforms
- dataset->one-hot-maps
- dataset->str
- dataset-name
- dataset?
- datetime
- difference
- drop
- drop-columns
- drop-missing
- drop-rows
- empty-ds?
- expand
- feature
- feature-ecount
- fill-range-replace
- first
- fit-categorical-map
- fit-one-hot
- fold-by
- full-join
- get-entry
- group-by
- grouped?
- groups->map
- groups->seq
- has-column?
- head
- inference-column?
- inference-target-column-names
- inference-target-ds
- inference-target-label-inverse-map
- inference-target-label-map
- info
- inner-join
- intersect
- intersection
- invert-categorical-map
- invert-one-hot-map
- join-columns
- k-fold-datasets
- labels
- last
- left-join
- map-columns
- map-rows
- mark-as-group
- metadata-filter
- missing
- model-type
- no-missing
- num-inference-classes
- numeric
- of-datatype
- order-by
- pivot->longer
- pivot->wider
- prediction
- print-dataset
- probability-distribution
- probability-distributions->label-column
- process-group-data
- rand-nth
- random
- read-nippy
- rename-columns
- reorder-columns
- replace-missing
- reverse-map-categorical-xforms
- right-join
- row-count
- rows
- select
- select-columns
- select-missing
- select-rows
- semi-join
- separate-column
- set-dataset-name
- set-inference-target
- shape
- shuffle
- split
- split->seq
- string
- tail
- target
- train-test-split
- transform-categorical-map
- transform-one-hot
- ungroup
- union
- unique-by
- unmark-group
- unroll
- update-columns
- write!
- write-csv!
- write-nippy!
scicloj.ml.metamorph
This namespace contains functions, which operate on a metamorph context. They all return the context as well.
Public variables and functions:
- ->array
- add-column
- add-columns
- add-or-replace-column
- add-or-replace-columns
- add-or-update-column
- aggregate
- aggregate-columns
- anti-join
- append
- append-columns
- array-column->columns
- as-regular-dataset
- asof-join
- assoc-ds
- assoc-metadata
- bind
- bow->something-sparse
- bow->sparse-array
- bow->SparseArray
- bow->tfidf
- brief
- by-rank
- categorical->number
- categorical->one-hot
- clone
- cluster
- column
- column->dataset
- column-cast
- column-count
- column-labeled-mapseq
- column-map
- column-names
- column-values->categorical
- columns
- columns->array-column
- columns-with-missing-seq
- columnwise-concat
- complete
- concat
- concat-copying
- concat-inplace
- convert-types
- count-vectorize
- cross-join
- crosstab
- data->dataset
- dataset->categorical-xforms
- dataset->data
- dataset->str
- dataset-name
- dataset?
- descriptive-stats
- difference
- drop
- drop-columns
- drop-missing
- drop-rows
- empty-dataset
- empty-ds?
- ensure-array-backed
- expand
- feature-ecount
- fill-range-replace
- filter
- filter-column
- filter-dataset
- first
- fold-by
- full-join
- get-entry
- group-by
- group-by->indexes
- group-by-column
- group-by-column->indexes
- group-by-column-consumer
- grouped?
- groups->map
- groups->seq
- has-column?
- head
- induction
- inference-column?
- inference-target-column-names
- inference-target-ds
- inference-target-label-inverse-map
- inference-target-label-map
- info
- inner-join
- intersect
- join-columns
- labels
- last
- left-join
- map-columns
- map-rows
- mapseq-reader
- mark-as-group
- min-max-scale
- min-n-by-column
- missing
- model
- model-type
- new-column
- new-dataset
- num-inference-classes
- order-by
- order-column-names
- pivot->longer
- pivot->wider
- pmap-ds
- print-all
- print-dataset
- probability-distributions->label-column
- process-group-data
- rand-nth
- random
- read-nippy
- reduce-dimensions
- remove-column
- remove-columns
- remove-rows
- rename-columns
- reorder-columns
- replace-missing
- replace-missing-value
- reverse-rows
- right-join
- row-at
- row-count
- row-map
- row-mapcat
- rows
- rowvec-at
- rowvecs
- sample
- select
- select-by-index
- select-columns
- select-columns-by-index
- select-missing
- select-rows
- semi-join
- separate-column
- set-dataset-name
- set-inference-target
- shape
- shuffle
- sort-by
- sort-by-column
- std-scale
- tail
- take-nth
- transform-one-hot
- ungroup
- union
- unique-by
- unique-by-column
- unmark-group
- unordered-select
- unroll
- unroll-column
- update
- update-column
- update-columns
- update-columnwise
- update-elemwise
- value-reader
- write!
- write-nippy!