[{"filename":"cat_g_field_data_plots.csv","size_kb":155.7,"label":"Cat-G \u2014 Field Data (per-plot, all features)","description":"400 plots \u00d7 41 numeric features harmonized from the Cat-G database (soil chemistry, plant cover diversity, biomass, plant height, grasshopper counts, landscape areas). Standalone \u2014 ready for ML. REGRESSION target e.g. PC_SHOOTMASS (aboveground biomass). CLASSIFICATION target e.g. RANCH or SLOPE_POS. Shares the PLOT key so it can later be merged with omics layers.","group":"Cat-G Field Data","group_order":1,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","ecology","regression","classification","standalone"]},{"filename":"catg_example_01_forage_biomass.csv","size_kb":132.3,"label":"Cat-G Field \u2014 1. Forage Biomass","description":"393 plots \u00d7 39 cols. Predict aboveground shoot biomass (PC_SHOOTMASS, g/m\u00b2) from soil chemistry, vegetation cover, canopy height, and monthly moisture. Key ranch question: how much forage is available per plot?","group":"Cat-G Field Data","group_order":2,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","agronomy","forage","regression","standalone"]},{"filename":"catg_example_01b_forage_biomass_new_plots.csv","size_kb":16.8,"label":"Cat-G Field \u2014 1b. Forage Biomass \u2014 New Plots (prediction input)","description":"60 new plots \u00d7 38 cols. Same schema as example 1 \u2014 use it to score a model trained on example 1 via the Predictions page. Upload the saved .pkl model + this dataset; select PC_SHOOTMASS as the ground-truth column to see evaluation metrics.","group":"Cat-G Field Data","group_order":2,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","agronomy","forage","prediction-input","standalone"]},{"filename":"catg_example_02_grazing_carrying_capacity.csv","size_kb":4.0,"label":"Cat-G Field \u2014 2. Grazing Carrying Capacity","description":"12 pastures \u00d7 23 cols. Predict predicted pasture biomass, cow-weeks (CW_NUMBER), and stocking rate (SR_NUMBER) from plot-aggregated vegetation and soil indicators. Key ranch question: how many cattle can this pasture support?","group":"Cat-G Field Data","group_order":3,"role":"complete","merge_with":[],"join_key":"PASTURE","tags":["field-data","agronomy","grazing","stocking-rate","regression","standalone"]},{"filename":"catg_example_03_soil_nitrogen_availability.csv","size_kb":67.9,"label":"Cat-G Field \u2014 3. Soil Nitrogen Availability","description":"350 plots \u00d7 26 cols. Predict plant-available ammonium-N (ENV_SOILNH4) and nitrate-N (ENV_SOILNO3, mg/kg) from soil OC, texture, pH, moisture, and CO\u2082 respiration. Key ranch question: where is nitrogen limiting and do I need to fertilize?","group":"Cat-G Field Data","group_order":4,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","soil","nitrogen","fertility","regression","standalone"]},{"filename":"catg_example_04_vegetation_diversity.csv","size_kb":102.3,"label":"Cat-G Field \u2014 4. Vegetation Diversity","description":"396 plots \u00d7 34 cols. Predict mid-season Shannon diversity index (COVER_SHANNON_JUL) from soil chemistry, biomass, and landscape context. Key ranch question: is my pasture floristically healthy or degrading?","group":"Cat-G Field Data","group_order":5,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","ecology","biodiversity","regression","standalone"]},{"filename":"catg_example_05_grasshopper_pest_pressure.csv","size_kb":71.7,"label":"Cat-G Field \u2014 5. Grasshopper Pest Pressure","description":"220 plots \u00d7 37 cols. Predict grasshopper count (GH_COUNT) from vegetation cover, air temperature, soil conditions, and landscape composition. Key ranch question: which plots have the highest pest pressure?","group":"Cat-G Field Data","group_order":6,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","pest","grasshopper","regression","standalone"]},{"filename":"catg_example_06_soil_carbon_credits.csv","size_kb":104.3,"label":"Cat-G Field \u2014 6. Soil Carbon / Carbon Credits","description":"379 plots \u00d7 38 cols. Predict soil organic carbon % (ENV_SOILOC) using biomass, litter, soil respiration (CO\u2082 mg/g), microbial necromass C, and vegetation cover. Key ranch question: which areas store the most carbon and qualify for carbon credits?","group":"Cat-G Field Data","group_order":7,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","soil","carbon","climate","regression","standalone"]},{"filename":"catg_example_07_microbial_soil_biology.csv","size_kb":23.6,"label":"Cat-G Field \u2014 7. Microbial Soil Biology","description":"96 plots \u00d7 27 cols. Predict bacterial, fungal, and total microbial necromass carbon (mg/g soil) from soil chemistry, CO\u2082 respiration, and plant biomass. Key ranch question: how biologically active is my soil?","group":"Cat-G Field Data","group_order":8,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","soil","microbiology","necromass","regression","standalone"]},{"filename":"catg_example_08_woody_encroachment.csv","size_kb":123.9,"label":"Cat-G Field \u2014 8. Woody Encroachment","description":"393 plots \u00d7 38 cols. Predict woody/shrub biomass (PC_WOODMASS, g/m\u00b2) from soil chemistry, vegetation cover, landscape forest fraction, and moisture. Key ranch question: where is shrub encroachment worst and where to prioritise control?","group":"Cat-G Field Data","group_order":9,"role":"complete","merge_with":[],"join_key":"PLOT","tags":["field-data","agronomy","woody-encroachment","regression","standalone"]},{"filename":"example_classification.csv","size_kb":8.4,"label":"Synthetic \u2014 Classification","description":"120 samples, 3 balanced classes with 2 informative features. Recommended method: Model Comparison or Random Forest (classification auto-detected).","group":"Method Examples (synthetic)","group_order":1,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","classification"]},{"filename":"example_posthoc.csv","size_kb":2.3,"label":"Synthetic \u2014 ANOVA + Post-hoc","description":"4 groups x 25 rows; the \"high\" group is strongly shifted so Tukey/Dunn pairwise tests flag it. Recommended method: ANOVA or Kruskal-Wallis.","group":"Method Examples (synthetic)","group_order":2,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","posthoc","anova"]},{"filename":"example_posthoc_two_groups.csv","size_kb":1.1,"label":"Synthetic \u2014 Two-Group Comparison","description":"The \"low\" and \"high\" groups from the post-hoc example (2 groups x 25 rows, strongly separated). Recommended method: t-Test or Mann-Whitney U.","group":"Method Examples (synthetic)","group_order":2,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","two-group","t-test","mann-whitney"]},{"filename":"example_lmm.csv","size_kb":3.9,"label":"Synthetic \u2014 Mixed-Effects (LMM)","description":"40 subjects x 3 repeats under control/treated; subject-level random intercepts. Recommended method: Mixed-Effects Model.","group":"Method Examples (synthetic)","group_order":3,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","mixed_effects"]},{"filename":"example_glm_counts.csv","size_kb":2.4,"label":"Synthetic \u2014 Count GLM","description":"100 Poisson counts driven by a continuous predictor. Recommended method: GLM for Count Data (poisson or negative binomial).","group":"Method Examples (synthetic)","group_order":4,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","glm_counts"]},{"filename":"example_repeated_measures.csv","size_kb":2.1,"label":"Synthetic \u2014 Repeated Measures","description":"30 subjects x wide t1/t2/t3 columns; treated group has a steeper slope. Recommended method: Repeated-Measures ANOVA.","group":"Method Examples (synthetic)","group_order":5,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","repeated_measures"]},{"filename":"example_ordination.csv","size_kb":14.3,"label":"Synthetic \u2014 Ordination","description":"80 samples x 8 features built on two latent gradients. Recommended method: Ordination (PCA/PCoA/NMDS).","group":"Method Examples (synthetic)","group_order":6,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","ordination"]},{"filename":"example_clustering.csv","size_kb":8.9,"label":"Synthetic \u2014 Clustering","description":"75 samples x 6 features forming 3 well-separated blobs. Recommended method: Clustering (kmeans k=3).","group":"Method Examples (synthetic)","group_order":7,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","clustering"]},{"filename":"example_community_matrix.csv","size_kb":8.4,"label":"Synthetic \u2014 Community Matrix","description":"60 plots x 30 species, meadow vs forest communities plus a planted indicator species. Recommended methods: Alpha/Beta Diversity, Indicator Species.","group":"Method Examples (synthetic)","group_order":8,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","ecology"]},{"filename":"example_spatial.csv","size_kb":2.6,"label":"Synthetic \u2014 Spatial Grid","description":"10x10 grid; value follows a strong latitudinal gradient. Recommended method: Morans I (Spatial Autocorrelation).","group":"Method Examples (synthetic)","group_order":9,"role":"complete","merge_with":[],"join_key":"","tags":["synthetic","spatial"]},{"filename":"demo_simple.csv","size_kb":2.2,"label":"demo_simple.csv","description":"","group":"Other","group_order":99,"role":"complete","merge_with":[],"join_key":"","tags":[]},{"filename":"example_gwas.csv","size_kb":1.1,"label":"example_gwas.csv","description":"","group":"Other","group_order":99,"role":"complete","merge_with":[],"join_key":"","tags":[]},{"filename":"example_gwas_protein.csv","size_kb":5.9,"label":"example_gwas_protein.csv","description":"","group":"Other","group_order":99,"role":"complete","merge_with":[],"join_key":"","tags":[]},{"filename":"example_metabolomics.csv","size_kb":4.4,"label":"example_metabolomics.csv","description":"","group":"Other","group_order":99,"role":"complete","merge_with":[],"join_key":"","tags":[]},{"filename":"example_proteomics.csv","size_kb":4.4,"label":"example_proteomics.csv","description":"","group":"Other","group_order":99,"role":"complete","merge_with":[],"join_key":"","tags":[]},{"filename":"cat_g_metabolomics_subset.csv","size_kb":115.5,"label":"Cat-G \u2014 Metabolomics (complete, self-contained)","description":"149 samples \u00d7 60 metabolites + full metadata. Standalone \u2014 ready for ML without merging.","group":"Standalone Examples","group_order":1,"role":"complete","merge_with":[],"join_key":"","tags":["metabolomics","standalone"]},{"filename":"cat_g_proteomics_omics_only.csv","size_kb":48.1,"label":"Cat-G \u2014 Proteomics (omics only)","description":"150 samples \u00d7 60 seed storage proteins (top-60 by CV). Psat/UniProt IDs, keyed by SampleID.","group":"Standalone Examples","group_order":2,"role":"complete","merge_with":[],"join_key":"SampleID","tags":["proteomics","omics-only","standalone"]},{"filename":"cat_g_gwas_real_data.csv","size_kb":95.5,"label":"Cat-G \u2014 GWAS + Phenotype Metadata","description":"314 field samples \u00b7 protein, amylose & starch content \u00b7 accession & country metadata. Includes SNP genotype columns for GWAS workflows.","group":"Standalone Examples","group_order":5,"role":"complete","merge_with":[],"join_key":"Sample_ID","tags":["gwas","phenotype","metadata"]}]