{"title":"Row Sampler","nodeType":"Manipulator","id":"*3o-UY2qMENf5piCd","factoryName":"org.knime.base.node.preproc.sample.SamplingNodeFactory","factoryId":"org.knime.base.node.preproc.sample.SamplingNodeFactory","path":["Manipulation","Row","Transform"],"owner":"knime","ownerAccountId":"account:team:b5f0848f-496d-4e6a-b869-fa3532248db7","description":"<p>This node extracts a sample (a bunch of rows) from the input data. The dialog enables you to specify the sample size.</p>\n        ","shortDescription":"Extracts a sample (a bunch of rows) from the input data.","keywords":["Row Sampling","sample","sampling"],"deprecated":false,"streamable":true,"tags":["Manipulation","Row","Transform","Streamable"],"icon":"data:image/png;base64,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","views":[],"inPorts":[{"objectClass":"org.knime.core.node.BufferedDataTable","color":"000000","dataType":"Table","optional":false,"name":"Table to sample from","description":"Table to sample from."}],"outPorts":[{"objectClass":"org.knime.core.node.BufferedDataTable","color":"000000","dataType":"Table","optional":false,"name":"The sampled table","description":"The sampled table."}],"dynInPorts":[],"dynOutPorts":[],"additionalSiteInformation":{"url":"https://update.knime.com/analytics-platform/5.12","trusted":true,"enabledByDefault":true,"name":"KNIME Analytics Platform 5.12 Update Site","version":"5.12.0"},"dialog":[{"sectionName":"Options","fields":[{"name":"Output size type","description":"Defines how the size of the output is specified: as a percentage of total rows (relative) or as an absolute number of rows.","optional":false},{"name":"Relative size","description":"Specifies the percentage of rows from the input table to be included in the output. Must be between 0 and 100 (inclusive).","optional":false},{"name":"Number of rows","description":"Specifies the absolute number of rows to include in the output. If the input table contains fewer rows than specified, all rows are placed in the output.","optional":false},{"name":"Sampling strategy","description":"Determines how rows are selected for the output. Strategies include random, stratified, linear, and first rows (sequential).\n<ul><li><b>Random</b> : Randomly selects rows from the input table. You can optionally specify a random seed for reproducible results.</li><li><b>Stratified</b> : Preserves the distribution of values in the selected group column. You can optionally specify a random seed for reproducible stratified sampling.</li><li><b>Linear</b> : Selects rows evenly spaced across the input table, always including the first and last row. This method is useful for downsampling sorted columns while preserving boundary values.</li><li><b>First rows</b> : Allows you to select the top-most rows of the input table.</li></ul>","optional":false},{"name":"Group column","description":"Specifies the column whose value distribution should be preserved in stratified sampling. Ensures both selected and non-selected rows reflect the same distribution of values.","optional":false},{"name":"Fixed random seed","description":"Optional seed value for random or stratified sampling. Using a seed ensures the same rows are selected each time the node is executed. Without a seed, a different random selection will occur each time.","optional":false},{"name":"If input table is empty","description":"Defines how the node should behave when the input table has no rows. Options include generating empty outputs or failing the execution.","optional":false}]}],"links":[],"kudos":[],"kudosCount":0,"bundleInformation":{"bundleVersion":"5.12.0.v202606261225","bundleName":"KNIME Base Nodes","bundleSymbolicName":"org.knime.base","bundleVendor":"KNIME AG, Zurich, Switzerland","featureSymbolicName":"org.knime.features.base","featureName":"KNIME Base nodes","featureVersion":"5.12.0.v202606261225","featureVendor":"KNIME AG, Zurich, Switzerland","extensionId":"*bjR3r1yWOznPIEXS"},"frequentSuccessors":[{"id":"*0rhLXWO6OS1xMi8T","factoryName":"org.knime.base.node.preproc.append.row.AppendedRowsNodeFactory","probability":0.06363636363636363},{"id":"*DOkyMaii62U05xZ1","factoryName":"org.knime.base.node.preproc.filter.column.DataColumnSpecFilterNodeFactory","probability":0.045454545454545456},{"id":"*5stmXk6zY_ORA4bC","factoryName":"org.knime.base.node.preproc.groupby.GroupByNodeFactory","probability":0.03939393939393939},{"id":"*ZgYyOm1P9VJVBE9e","factoryName":"org.knime.base.node.preproc.joiner.Joiner2NodeFactory","probability":0.03737373737373737},{"id":"*Oy714gpoifm4PiOZ","factoryName":"org.knime.base.node.io.csvwriter.CSVWriterNodeFactory","probability":0.03282828282828283},{"id":"*LKxrCJihG46anH0Q","factoryName":"org.knime.base.node.preproc.filter.rowref.RowFilterRefNodeFactory","probability":0.025252525252525252},{"id":"*jd2U-FYTI8jCbQls","factoryName":"org.knime.base.node.preproc.filter.row.RowFilterNodeFactory","probability":0.019696969696969695},{"id":"*eOn8ibZnxIkY7XhT","factoryName":"org.knime.base.node.preproc.stringmanipulation.StringManipulationNodeFactory","probability":0.01717171717171717},{"id":"*T0AhxSe0Yi42rQK8","factoryName":"org.knime.base.node.preproc.partition.PartitionNodeFactory","probability":0.01717171717171717},{"id":"*QNB4FsAPnEAgOMVh","factoryName":"org.knime.base.node.jsnippet.JavaSnippetNodeFactory","probability":0.016666666666666666}]}