Man pages for robertzk/syberiaMungebits
Common mungebits used with Syberia projects.

date_parser_fnParse numeric date distances into numerics.
datetime_fnA simpler, faster mungebit that takes Postgresql CreatedAt...
discretizerDiscretizer
discretizer_fnDiscretizer function
drop_percent_missingDrop columns with over a certain percent missing.
drop_percent_missing_fnDrop columns with over a certain percent missing.
drop_single_value_variables_fnDrop variables with only one unique value
drop_variables_fnDrop variables in a dataframe.
imputer_fnImpute a column by mean Only meant to be used as a mungebit
iris_discretizedA discretized version of the iris data set, used for internal...
new_variableCreates a new variable in the dataframe.
numeric_to_factornumeric to factor helper function
ordererOrder a dataframe by a column
remove_outliers_fnremove outliers based upon a z_score threshold z_score=> (x -...
renamerRename columns in a dataframe
replace_variableReplaces a variable in the dataframe.
restore_categorical_variables_fnRestores categorical variables, allowing you to predict.
select_rowsSelect rows in a dataframe.
select_variablesSelect variables in a dataframe.
sure_independence_screenSure independence screening function
syberiaMungebitssyberiaMungebits
truncator_fnConstrain a numeric column to the range [min,max] of the...
trunc.digi.e trunc.dig(5.732 , digits = 1) => 5.7
value_replacer_fnReplace arbitrary values in your data
robertzk/syberiaMungebits documentation built on July 30, 2019, 3:37 p.m.