def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["manually"],
"manually_param": {
"filter_out_indexes": None,
"filter_out_names": None,
"left_col_indexes": [0, 1, 2],
"left_col_names": ["x3"]
}
}
pipeline = common_tools.make_normal_dsl(config, namespace, selection_param)
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
common_tools.prettify(
pipeline.get_component("hetero_feature_selection_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
binning_param = {
"name": 'hetero_feature_binning_0',
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"bin_names": None,
"category_indexes": None,
"category_names": None,
"adjustment_factor": 0.5,
"local_only": False,
"transform_param": {
"transform_cols": -1,
"transform_names": None,
"transform_type": "bin_num"
}
}
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["manually", "iv_value_thres", "iv_percentile"],
"manually_param": {
"filter_out_indexes": [],
"filter_out_names": []
},
"unique_param": {
"eps": 1e-06
},
"iv_value_param": {
"value_threshold": 0.1
},
"iv_percentile_param": {
"percentile_threshold": 0.9
},
"variance_coe_param": {
"value_threshold": 0.3
},
"outlier_param": {
"percentile": 0.95,
"upper_threshold": 2.0
}
}
pipeline = common_tools.make_single_predict_pipeline(
config, namespace, selection_param, binning_param=binning_param)
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
common_tools.prettify(
pipeline.get_component("hetero_feature_selection_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
pipeline = make_normal_dsl(config, namespace)
pipeline.fit()
common_tools.prettify(
pipeline.get_component("hetero_feature_selection_0").get_summary())
common_tools.prettify(pipeline.get_component("evaluation_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
pipeline = make_normal_dsl(config, namespace)
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
common_tools.prettify(pipeline.get_component("hetero_feature_selection_0").get_summary())
common_tools.prettify(pipeline.get_component("evaluation_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
fast_sbt_param = {
"name": "fast_secureboost_0",
"task_type": "classification",
"learning_rate": 0.1,
"num_trees": 4,
"subsample_feature_rate": 1,
"n_iter_no_change": False,
"work_mode": "layered",
"guest_depth": 2,
"host_depth": 3,
"tol": 0.0001,
"bin_num": 50,
"metrics": ["Recall", "ks", "auc", "roc"],
"objective_param": {
"objective": "cross_entropy"
},
"encrypt_param": {
"method": "iterativeAffine"
},
"predict_param": {
"threshold": 0.5
},
"validation_freqs": 1
}
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["hetero_fast_sbt_filter"],
"sbt_param": {
"metrics": "feature_importance",
"filter_type": "threshold",
"take_high": True,
"threshold": 0.03
}
}
pipeline = common_tools.make_normal_dsl(config,
namespace,
selection_param,
fast_sbt_param=fast_sbt_param)
pipeline.fit(backend=backend, work_mode=work_mode)
common_tools.prettify(
pipeline.get_component("hetero_feature_selection_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
binning_param = {
"name": 'hetero_feature_binning_0',
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"bin_names": None,
"category_indexes": None,
"category_names": None,
"adjustment_factor": 0.5,
"local_only": False,
"transform_param": {
"transform_cols": -1,
"transform_names": None,
"transform_type": "bin_num"
}
}
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["iv_value_thres", "iv_filter"],
"iv_value_param": {
"value_threshold": 1,
"local_only": True
},
"iv_top_k_param": {
"k": 7,
"local_only": False
}
}
pipeline = common_tools.make_normal_dsl(config,
namespace,
selection_param,
binning_param=binning_param)
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
common_tools.prettify(
pipeline.get_component("hetero_feature_selection_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["percentage_value"],
"percentage_value_param": {
"upper_pct": 0.8
}}
pipeline = common_tools.make_normal_dsl(config, namespace, selection_param)
pipeline.fit()
common_tools.prettify(pipeline.get_component("hetero_feature_selection_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
binning_param = {
"name": 'hetero_feature_binning_0',
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"bin_names": None,
"category_indexes": None,
"category_names": None,
"adjustment_factor": 0.5,
"local_only": False,
"transform_param": {
"transform_cols": -1,
"transform_names": None,
"transform_type": "bin_num"
}
}
statistic_param = {
"name": "statistic_0",
"statistics": ["95%", "coefficient_of_variance", "stddev"],
"column_indexes": -1,
"column_names": []
}
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": [
"manually",
"unique_value",
"iv_value_thres",
"coefficient_of_variation_value_thres",
"iv_percentile",
"outlier_cols"
],
"manually_param": {
"filter_out_indexes": [],
"filter_out_names": []
},
"unique_param": {
"eps": 1e-06
},
"iv_value_param": {
"value_threshold": 0.1
},
"iv_percentile_param": {
"percentile_threshold": 0.9
},
"variance_coe_param": {
"value_threshold": 0.3
},
"outlier_param": {
"percentile": 0.95,
"upper_threshold": 2.0
}}
pipeline = common_tools.make_normal_dsl(config, namespace, selection_param,
binning_param=binning_param,
statistic_param=statistic_param)
pipeline.fit()
common_tools.prettify(pipeline.get_component("hetero_feature_selection_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
binning_param = {
"name": 'hetero_feature_binning_0',
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"bin_names": None,
"category_indexes": None,
"category_names": None,
"adjustment_factor": 0.5,
"local_only": False,
"transform_param": {
"transform_cols": -1,
"transform_names": None,
"transform_type": "bin_num"
}
}
statistic_param = {
"name": "statistic_0",
"statistics": ["95%", "coefficient_of_variance", "stddev"],
"column_indexes": -1,
"column_names": []
}
psi_param = {"name": "psi_0", "max_bin_num": 20}
secureboost_param = {
"name": "secureboost_0",
"task_type": "classification",
"learning_rate": 0.1,
"num_trees": 5,
"subsample_feature_rate": 1,
"n_iter_no_change": False,
"tol": 0.0001,
"bin_num": 50,
"objective_param": {
"objective": "cross_entropy"
},
"encrypt_param": {
"method": "paillier"
},
"predict_param": {
"threshold": 0.5
},
"validation_freqs": 1
}
selection_param = {
"name":
"hetero_feature_selection_0",
"select_col_indexes":
-1,
"select_names": [],
"filter_methods":
["iv_filter", "statistic_filter", "psi_filter", "hetero_sbt_filter"],
"iv_param": {
"metrics": ["iv", "iv", "iv"],
"filter_type": ["threshold", "top_k", "top_percentile"],
"take_high": True,
"threshold": [0.03, 15, 0.7],
"host_thresholds": [[0.15], None, None],
"select_federated": True
},
"statistic_param": {
"metrics": ["skewness", "skewness", "kurtosis", "median"],
"filter_type": "threshold",
"take_high": [True, False, True, True],
"threshold": [-10, 10, -1.5, -1.5]
},
"psi_param": {
"metrics": "psi",
"filter_type": "threshold",
"take_high": False,
"threshold": -0.1
},
"sbt_param": {
"metrics": "feature_importance",
"filter_type": "threshold",
"take_high": True,
"threshold": 0.03
}
}
pipeline = common_tools.make_normal_dsl(config,
namespace,
selection_param,
binning_param=binning_param,
statistic_param=statistic_param,
psi_param=psi_param,
sbt_param=secureboost_param)
pipeline.fit(backend=backend, work_mode=work_mode)
common_tools.prettify(
pipeline.get_component("hetero_feature_selection_0").get_summary())
