Description
|
This is a synthetic dataset generated for the space project.
The dataset was generated using the following configuration:
{"spaceenv": {"base_name": "${hydra:runtime.choices.spaceenv}", "covariates": [{"poverty": ["cs_poverty", "cs_ed_below_highschool"]}, {"race": ["cs_hispanic", "cs_black", "cs_white", "cs_native", "cs_asian", "cs_other"]}, "cs_population_density", "cdc_mean_bmi", {"smoking": ["cdc_pct_cusmoker", "cdc_pct_sdsmoker", "cdc_pct_fmsmoker", "cdc_pct_nvsmoker", "cdc_pct_nnsmoker"]}, {"temperature": ["gmet_mean_tmmn", "gmet_mean_summer_tmmn", "gmet_mean_winter_tmmn", "gmet_mean_tmmx", "gmet_mean_summer_tmmx", "gmet_mean_winter_tmmx"]}, {"relative_humidity": ["gmet_mean_rmn", "gmet_mean_summer_rmn", "gmet_mean_winter_rmn", "gmet_mean_rmx", "gmet_mean_summer_rmx", "gmet_mean_winter_rmx"]}, {"specific_humidity": ["gmet_mean_sph", "gmet_mean_summer_sph", "gmet_mean_winter_sph"]}, {"region": ["bin_NORTHEAST", "bin_SOUTH", "bin_WEST"]}], "outcome": "cdc_mortality_pct", "treament": "???", "index_col": "0", "treatment_max_bins": "100", "scaling": {"outcome": "null", "treatment": "null", "covariates": "null"}, "transforms": {"outcome": "null", "treatment": "null", "covariates": "null"}, "fill_missing_covariate_values": "true", "bsplines": "false", "bsplines_degree": "3", "bsplines_df": "5", "binary_treatment_iteractions": "true", "seed": "42", "autogluon": {"fit": {"presets": "good_quality", "time_limit": "900"}, "leave_out_fit": {"presets": "good_quality", "time_limit": "900"}, "feat_importance": {"time_limit": "900"}}, "spatial_tuning": {"init_frac": "0.03", "levels": "1", "buffer": "1"}, "treatment_quantile_valid_range": ["0.025", "0.975"], "outcome_quantile_valid_range": ["0.01", "0.99"], "ensemble_models": ["FASTAI", "CAT", "NN_TORCH", "XGB"], "collection": "air_pollution_mortality_us", "treatment": "qd_mean_pm25"}, "num_plot_samples": "50", "debug_subsample": "null"}
|