{"date":"June 27, 2022","items":[{"description":"Provides scores for how each input relates to the target.","viz_type":"barchart-horizontal","mapsTo":"feature_importance true","fields":[{"source":"data","group":"ml","name":"clabel","dataTypes":["text","number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Feature Importance","ml_type":"explore","id":"feature_importance"},{"description":"Displays the Schema of the dataset.","viz_type":"","mapsTo":"get_schema true","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":1,"label":"Get Schema","ml_type":"explore","id":"get_schema"},{"description":"Groups data based on a pre-defined number of groups.","viz_type":"kmeanscluster","mapsTo":"cluster kmeans","fields":[{"source":"custom","group":"ml","name":"nc","dataTypes":"number","mapsTo":"nc","description":"Total number of clusters to group the data into.","optional":false,"id":"nc","label":"Number of Clusters"},{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":1,"label":"K-Means","ml_type":"learn","id":"kmeans"},{"description":"Groups data by shifting data to the mode of a region of a pre-defined size.","viz_type":"kmeanscluster","mapsTo":"cluster meanshift","fields":[{"source":"custom","group":"ml","name":"bandwidth","dataTypes":["number"],"mapsTo":"bandwidth","description":"Size of the regions to group data into.","optional":false,"id":"bandwidth","label":"Bandwidth"},{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":1,"label":"Mean Shift","ml_type":"learn","id":"meanshift"},{"description":"Uses a decision tree to build a model whose target is categorical.","viz_type":"tree","mapsTo":"classify dtree","fields":[{"description":"The method used to measure the quality of the splits in a tree.","mapsTo":"criterion","optional":false,"id":"criterion","group":"ml","name":"criterion","value":"gini","label":"Criterion","source":"custom","dataTypes":["list"],"options":[{"id":"gini","label":"Gini Impurity"},{"id":"entropy","label":"Entropy"}]},{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["text"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Decision Tree Classifier","reqDataTypes":["text"],"ml_type":"learn","id":"dtree"},{"description":"Uses a random forest to build a model whose target is categorical.","viz_type":"","mapsTo":"classify rfc","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["text"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Random Forest Classifier","reqDataTypes":["text"],"ml_type":"learn","id":"rfc"},{"description":"Uses Gaussian Naive Bayes to build a model whose target is categorical.","viz_type":"","mapsTo":"classify gnb","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["text"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Gaussian Naive Bayes","reqDataTypes":["text"],"ml_type":"learn","id":"gnb"},{"description":"Uses Logistic Regression to build a model whose target is categorical.","viz_type":"","mapsTo":"classify logistic","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["text"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Logistic Regression","reqDataTypes":["text"],"ml_type":"learn","id":"logistic"},{"description":"Uses Linear Regression to build a model whose target is numeric.","viz_type":"3dscatter","mapsTo":"regression linear","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Linear Regression","reqDataTypes":["number"],"ml_type":"learn","id":"linear"},{"description":"A type of Linear Regression. Lasso is often used when there are a large number of features since it automatically does feature selection.","viz_type":"3dscatter","mapsTo":"regression lasso","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Lasso Regression","reqDataTypes":["number"],"ml_type":"learn","id":"lasso"},{"description":"A type of Linear Regression. Ridge reduces the model complexity by sending coefficients to 0.","viz_type":"3dscatter","mapsTo":"regression ridge","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Ridge Regression","reqDataTypes":["number"],"ml_type":"learn","id":"ridge"},{"description":"Uses Support Vectors to build a model whose target is numeric.","viz_type":"3dscatter","mapsTo":"regression svr","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Support Vector Regression","reqDataTypes":["number"],"ml_type":"learn","id":"svr"},{"description":"Uses a Random Forest to build a model whose target is numeric.","viz_type":"3dscatter","mapsTo":"regression rfr","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Random Forest Regression","reqDataTypes":["number"],"ml_type":"learn","id":"rfr"},{"description":"Uses a Decision Tree to build a model whose target is numeric.","viz_type":"tree","mapsTo":"regression dtreereg","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Decision Tree Regression","reqDataTypes":["number"],"ml_type":"learn","id":"dtreereg"},{"description":"Uses a Gaussian Process to build a model whose target is numeric.","viz_type":"3dscatter","mapsTo":"regression gpr","fields":[{"multiple":true,"description":"A subset of columns that will be used to train the model.","mapsTo":"independents","optional":true,"id":"independents","group":"ml","name":"independents","value":null,"label":"Input Features","source":"data","dataTypes":["text","number"]},{"description":"Normalizes each numerical column.","mapsTo":"normalize","optional":true,"id":"normalize","group":"ml","name":"normalize","value":"none","label":"Normalize","source":"custom","dataTypes":["list"],"options":[{"id":"none","label":"Do not normalize"},{"id":"standard","label":"Standard Scaler"},{"id":"minmax","label":"MinMax Scaler"}]},{"source":"data","group":"ml","name":"clabel","dataTypes":["number"],"mapsTo":"clabel","description":"The name of the target column.","optional":false,"id":"clabel","label":"Target Column"},{"source":"custom","group":"ml","name":"grid_response","dataTypes":["boolean"],"mapsTo":"grid_response","description":"Used to visualize a regression line or surface.","optional":true,"id":"grid_response","value":false,"label":"Regression Line/Surface"},{"source":"custom","group":"ml","name":"autoclean","dataTypes":["boolean"],"mapsTo":"autoclean","description":"Clean a dataset using preset rules.","optional":true,"id":"autoclean","value":false,"label":"Auto Clean"}],"minDataCols":2,"label":"Gaussian Process Regression","reqDataTypes":["number"],"ml_type":"learn","id":"gpr"}],"version":"DEV_TEST"}