随机森林回归特征重要性

概述

采用随机森林回归算法计算数据集特征的特征重要性

输入

输出

特征重要性结果数据集

参数说明

样例

inputs = {
    "dataframe": None,  # @input {"label":"dataframe","type":"DataFrame"}
    "pipeline_model": None,  # @input {"label":"pipeline_model","type":"PipelineModel"}
    "random_forest_regressor_model": None
}
params = {
    "inputs": inputs,
    "input_columns_str": "",  # @param {"label": "input_columns_str", "type": "string", "required": "false", "helpTip": ""}
    "label_col": "",  # @param {"label": "label_col", "type": "string", "required": "true", "helpTip": ""}
    "model_input_features_col": "model_features",  # @param {"label": "model_input_features_col", "type": "string", "required": "false", "helpTip": ""}
    "prediction_col": "prediction",  # @param {"label": "prediction_col", "type": "string", "required": "false", "helpTip": ""}
    "max_depth": 5,  # @param {"label": "max_depth", "type": "integer", "required": "false","range":"(0,2147483647]", "helpTip": ""}
    "max_bins": 32,  # @param {"label": "max_bins", "type": "integer", "required": "false","range":"(0,2147483647]", "helpTip": ""}
    "min_instances_per_node": 1,  # @param {"label": "min_instances_per_node", "type": "integer", "required": "false","range":"(0,2147483647]", "helpTip": ""}
    "min_info_gain": 0.0,  # @param {"label": "min_info_gain", "type": "number", "required": "false", "helpTip": ""}
    "impurity": "variance",
    "subsampling_rate": 1.0,  # @param {"label": "subsampling_rate", "type": "number", "required": "false", "helpTip": ""}
    "num_trees": 20,  # @param {"label": "num_trees", "type": "integer", "required": "false","range":"(0,2147483647]", "helpTip": ""}
    "feature_subset_strategy": "auto"  # @param {"label": "feature_subset_strategy", "type": "enum", "options":"auto,all,onethird,sqrt,log2", "required": "false", "helpTip": ""}
}
rf_regression_feature_importance____id___ = MLSRandomForestRegressorFeatureImportance(**params)
rf_regression_feature_importance____id___.run()
# @output {"label":"dataframe","name":"rf_regression_feature_importance____id___.get_outputs()['output_port_1']","type":"DataFrame"}