From 86e7dec46ddbef2b33ebc325a0369316d2c25e35 Mon Sep 17 00:00:00 2001 From: John-Marc Chandonia Date: Tue, 30 Jun 2026 16:17:45 -0700 Subject: [PATCH] add fold08 agent evaluation bundle --- .../fold-08-holdout-10/AGENT_ACTION_LOG.md | 24 ++ .../fold-08-holdout-10/AGENT_INSTRUCTIONS.md | 10 + evaluations/fold-08-holdout-10/EVALUATION.md | 52 +++ evaluations/fold-08-holdout-10/MANIFEST.json | 35 ++ .../agent_outputs/curator_bundle.json | 67 ++++ .../agent_outputs/harmonize_heldout.py | 81 +++++ .../agent_outputs/heldout_harmonized.csv | 310 ++++++++++++++++++ .../agent_outputs/mapping.json | 104 ++++++ .../agent_outputs/mapping_notes.md | 11 + .../evaluation_metrics.json | 60 ++++ 10 files changed, 754 insertions(+) create mode 100644 evaluations/fold-08-holdout-10/AGENT_ACTION_LOG.md create mode 100644 evaluations/fold-08-holdout-10/AGENT_INSTRUCTIONS.md create mode 100644 evaluations/fold-08-holdout-10/EVALUATION.md create mode 100644 evaluations/fold-08-holdout-10/MANIFEST.json create mode 100644 evaluations/fold-08-holdout-10/agent_outputs/curator_bundle.json create mode 100644 evaluations/fold-08-holdout-10/agent_outputs/harmonize_heldout.py create mode 100644 evaluations/fold-08-holdout-10/agent_outputs/heldout_harmonized.csv create mode 100644 evaluations/fold-08-holdout-10/agent_outputs/mapping.json create mode 100644 evaluations/fold-08-holdout-10/agent_outputs/mapping_notes.md create mode 100644 evaluations/fold-08-holdout-10/evaluation_metrics.json diff --git a/evaluations/fold-08-holdout-10/AGENT_ACTION_LOG.md b/evaluations/fold-08-holdout-10/AGENT_ACTION_LOG.md new file mode 100644 index 0000000..7a34c91 --- /dev/null +++ b/evaluations/fold-08-holdout-10/AGENT_ACTION_LOG.md @@ -0,0 +1,24 @@ +2026-06-30T16:01:26-07:00 | action=command+write | subject=/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10/AGENT_ACTION_LOG.md and agent_outputs | reason=initialize mandatory trace log and output directory before any further work +2026-06-30T16:01:41-07:00 | action=command+file_read | subject=.runs/fold-08-holdout-10/AGENT_INSTRUCTIONS.md | reason=read fold-local benchmark instructions +2026-06-30T16:01:41-07:00 | action=file_read | subject=.runs/fold-08-holdout-10/MANIFEST.json | reason=read fold-local manifest for held-out dataset and allowed files +2026-06-30T16:01:41-07:00 | action=file_read | subject=.runs/fold-08-holdout-10/skills/essdive_sm_curator/SKILL.md | reason=read required fold-local curator skill +2026-06-30T16:01:41-07:00 | action=file_read | subject=.runs/fold-08-holdout-10/skills/essdive_sm_harmonizer/SKILL.md | reason=read required fold-local harmonizer skill +2026-06-30T16:01:52-07:00 | action=command+directory_listing | subject=.runs/fold-08-holdout-10 sandbox top-level files | reason=identify fold-local allowed exemplars and metadata paths +2026-06-30T16:01:52-07:00 | action=directory_listing | subject=/h/jmc/ess-dive_wfsfa_soil_datasets/ess-dive-01092fc392bc46d-20240819T143818677 | reason=inspect raw held-out package files allowed by benchmark +2026-06-30T16:02:02-07:00 | action=command+directory_listing | subject=.runs/fold-08-holdout-10/data | reason=locate fold-local exemplar mapping and expert code directories +2026-06-30T16:02:54-07:00 | action=command+file_read | subject=fold-local mapping JSON and held-out Soil_water_content_Fig4e.csv | reason=inspect exemplar mapping summaries and raw held-out columns/sample rows +2026-06-30T16:03:14-07:00 | action=command+external_metadata_lookup | subject=ESS-DIVE API package metadata for ess-dive-01092fc392bc46d-20240819T143818677 | reason=retrieve DOI and package-level metadata per fold-local curator skill +2026-06-30T16:03:31-07:00 | action=command+external_metadata_lookup | subject=ESS-DIVE API package metadata for ess-dive-01092fc392bc46d-20240819T143818677 | reason=retry metadata lookup after sandbox DNS failure to retrieve DOI +2026-06-30T16:03:55-07:00 | action=command+file_read | subject=fold-local mapping entries 5, 15, 23, 25, 26 and exemplar code dataset_05/15/23/25/26.py | reason=inspect structurally related VWC examples for mapping and code conventions +2026-06-30T16:04:11-07:00 | action=command+file_read | subject=fold-local expert_code/harmonize_sm/common.py | reason=inspect schema helper behavior and column order convention +2026-06-30T16:04:25-07:00 | action=command+directory_listing | subject=/h/jmc/ess-dive_wfsfa_soil_datasets/ess-dive_b924ba040ecefee_20250707T154402200 | reason=locate raw reference location metadata named in fold-local exemplar mapping index 0 +2026-06-30T16:04:38-07:00 | action=command+file_read+search | subject=raw reference location registry and held-out Soil_water_content_Fig4e.csv | reason=find PLM site coordinates and quantify held-out sampling interval +2026-06-30T16:06:17-07:00 | action=command+write | subject=.runs/fold-08-holdout-10/agent_outputs/{curator_bundle.json,mapping.json,mapping_notes.md,harmonize_heldout.py} | reason=write benchmark held-out curation, mapping, notes, and harmonization script +2026-06-30T16:06:17.958597-07:00 | action=file_write | subject=/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10/agent_outputs/curator_bundle.json | reason=write curator_bundle.json benchmark artifact +2026-06-30T16:06:17.958904-07:00 | action=file_write | subject=/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10/agent_outputs/mapping.json | reason=write mapping.json benchmark artifact +2026-06-30T16:06:17.959075-07:00 | action=file_write | subject=/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10/agent_outputs/mapping_notes.md | reason=write mapping_notes.md benchmark artifact +2026-06-30T16:06:17.959234-07:00 | action=file_write | subject=/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10/agent_outputs/harmonize_heldout.py | reason=write harmonize_heldout.py benchmark artifact +2026-06-30T16:06:27-07:00 | action=command | subject=.runs/fold-08-holdout-10/agent_outputs/harmonize_heldout.py | reason=run held-out harmonization script to generate heldout_harmonized.csv +2026-06-30T16:06:27.949299-07:00 | action=file_read | subject=/h/jmc/ess-dive_wfsfa_soil_datasets/ess-dive-01092fc392bc46d-20240819T143818677/Soil_water_content_Fig4e.csv | reason=read held-out raw soil water content payload +2026-06-30T16:06:27.967549-07:00 | action=file_write | subject=/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10/agent_outputs/heldout_harmonized.csv | reason=write held-out harmonized CSV +2026-06-30T16:06:49-07:00 | action=command+file_read+directory_listing+search | subject=agent_outputs, heldout_harmonized.csv, and AGENT_ACTION_LOG.md | reason=validate artifacts, row count, schema, and scan trace for forbidden path usage diff --git a/evaluations/fold-08-holdout-10/AGENT_INSTRUCTIONS.md b/evaluations/fold-08-holdout-10/AGENT_INSTRUCTIONS.md new file mode 100644 index 0000000..cbe4c29 --- /dev/null +++ b/evaluations/fold-08-holdout-10/AGENT_INSTRUCTIONS.md @@ -0,0 +1,10 @@ +# Run environment — leave-one-cluster-out + +Harmonize the held-out dataset(s) below using ONLY: +- the skills in `skills/`, +- the exemplars in `data/processed/.../sm_data_harmonization_mapping.json` and the code patterns in `data/gold/expert_code/harmonize_sm/` (both have the held-out cluster removed), +- the shared raw inputs under `~/ess-dive_wfsfa_soil_datasets/` and the cached metadata under `data/external/ess-dive_meta/`. + +Do NOT look up the held-out dataset's existing harmonized output, expert code, or mapping entry from any other location. The held-out datasets are: + +- `ess-dive-01092fc392bc46d-20240819T143818677` diff --git a/evaluations/fold-08-holdout-10/EVALUATION.md b/evaluations/fold-08-holdout-10/EVALUATION.md new file mode 100644 index 0000000..b6de8ad --- /dev/null +++ b/evaluations/fold-08-holdout-10/EVALUATION.md @@ -0,0 +1,52 @@ +# fold-08-holdout-10 Agent Evaluation + +## Scope + +This directory records one sandboxed sub-agent attempt for held-out dataset indices `[10]`. + +- Sandbox: `.runs/fold-08-holdout-10` +- Tracked artifact copy: `evaluations/fold-08-holdout-10` +- Successful agent trace: `AGENT_ACTION_LOG.md` + +## Anti-Leakage Audit + +The successful trace was scanned for root gold data, root processed data, other fold sandboxes, held-out expert module names, and explicit `violation` markers. Result: `0` matches. + +## Output Equivalence Against Gold + +| Metric | Agent | Gold | +| --- | ---: | ---: | +| Rows | 309 | 309 | +| Target columns present | 9 / 9 | 9 / 9 | +| Schema exact match | true | n/a | +| Unique keyed rows recovered | 0 | 103 | +| Missing gold keyed rows | 103 | n/a | +| Extra agent keyed rows | 309 | n/a | +| Row precision | 0.000 | n/a | +| Gold recall | 0.000 | n/a | + +Shared-row value matches after key merge: + +| Column | Matched rows | +| --- | ---: | +| `interval_min` | 0/0 | +| `volumetric_water_content_m3_m3` | 0/0 | +| `gravimetric_water_content_gH2O_gs` | 0/0 | +| `water_potential_kPa` | 0/0 | +| `is_timeseries` | 0/0 | + +## JSON Mapping Match + +- Summary: `{"extra_agent_categories": ["gravimetric_water_content"], "field_exact_matches_by_name": {"destination_variable": "8/8", "source_files": "6/8", "source_pattern": "4/8", "transformation": "0/8", "unit_conversion": "6/8"}, "field_level_exact_matches": "24/40", "gold_mapping_categories_present": "8/8", "missing_gold_categories": [], "top_level_exact_matches": "7/7", "top_level_matches": {"archive_repository": true, "data_payload_files": true, "dataset_identifier": true, "doi": true, "index": true, "location_metadata_files": true, "sensor_metadata_files": true}}` + +| Field | Exact matches | +| --- | ---: | +| `destination_variable` | 8/8 | +| `source_pattern` | 4/8 | +| `source_files` | 6/8 | +| `transformation` | 0/8 | +| `unit_conversion` | 6/8 | + +## Overall Assessment + +See `evaluation_metrics.json` for machine-readable details. The run passed the targeted local no-gold path audit. Output equivalence should be interpreted with the key policy recorded in the metrics (`key_includes_dataset_index=False`). diff --git a/evaluations/fold-08-holdout-10/MANIFEST.json b/evaluations/fold-08-holdout-10/MANIFEST.json new file mode 100644 index 0000000..40bb7e8 --- /dev/null +++ b/evaluations/fold-08-holdout-10/MANIFEST.json @@ -0,0 +1,35 @@ +{ + "name": "fold-08-holdout-10", + "holdout_indices": [ + 10 + ], + "holdout_identifiers": [ + "ess-dive-01092fc392bc46d-20240819T143818677" + ], + "exemplar_indices": [ + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 15, + 16, + 17, + 18, + 23, + 24, + 25, + 26, + 27 + ], + "n_exemplars": 27, + "sources": { + "package": "data/gold/expert_code/harmonize_sm", + "mapping": "data/gold/sm_data_harmonization_mapping.json", + "skills": "skills" + } +} \ No newline at end of file diff --git a/evaluations/fold-08-holdout-10/agent_outputs/curator_bundle.json b/evaluations/fold-08-holdout-10/agent_outputs/curator_bundle.json new file mode 100644 index 0000000..71fc442 --- /dev/null +++ b/evaluations/fold-08-holdout-10/agent_outputs/curator_bundle.json @@ -0,0 +1,67 @@ +{ + "package_id": "ess-dive-01092fc392bc46d-20240819T143818677", + "doi": "doi:10.15485/2322567", + "curator_decision": "INCLUDE", + "exclusion_reason": null, + "package_title": "Hydrological control of chemical weathering and rock-carbon fluxes: East River, Colorado", + "data_payload_files": [ + { + "filename": "Soil_water_content_Fig4e.csv", + "columns": [ + "Date", + "PLM1 _vol_water_content", + "PLM2 _vol_water_content", + "PLM3 _vol_water_content" + ], + "row_count_estimate": 104, + "data_row_count_after_units_row": 103, + "file_size_mb": 0.0031, + "column_preview": "Date,PLM1 _vol_water_content,PLM2 _vol_water_content,PLM3 _vol_water_content\\nYYYY-MM-DD,m3/m3,m3/m3,m3/m3\\n2017-05-06,0.387,0.39,0.39", + "classification_reason": "CSV contains date-stamped direct volumetric water content observations in m3/m3 for PLM1, PLM2, and PLM3." + } + ], + "location_metadata_files": [], + "sensor_metadata_files": [], + "readme_content": null, + "location_resolution": { + "source": "varadharajan_lookup", + "qc_flag_recommendation": "g1", + "site_coordinates": [ + { + "site_id": "ER-PLM1", + "latitude": 38.919771, + "longitude": -106.949273 + }, + { + "site_id": "ER-PLM2", + "latitude": 38.920157, + "longitude": -106.948714 + }, + { + "site_id": "ER-PLM3", + "latitude": 38.920784, + "longitude": -106.948367 + } + ], + "note": "Coordinates are not present in the held-out payload; PLM IDs were resolved against the fold-local reference location dataset cited by mapping index 0." + }, + "time_series_inference": { + "is_timeseries": true, + "interval_min": 20160.0, + "reasoning": "Each PLM site has repeated observations from 2017-05-06 to 2021-05-02; sampling is irregular but the median interval is 14 days." + }, + "experimental_context": { + "manipulation_detected": false, + "manipulation_type": null, + "has_control_data": null, + "recommendation": "include_all" + }, + "similar_dataset_reference": { + "index": 25, + "reason": "Similar code pattern: wide-format volumetric water content time series reshaped to long format." + }, + "open_questions": [ + "The CSV does not encode measurement depth; depth_m is populated as missing.", + "The package-level metadata gives watershed bounds, while site-specific PLM coordinates require the Varadharajan location registry lookup and should carry g1 location provenance if location output is generated." + ] +} diff --git a/evaluations/fold-08-holdout-10/agent_outputs/harmonize_heldout.py b/evaluations/fold-08-holdout-10/agent_outputs/harmonize_heldout.py new file mode 100644 index 0000000..8890826 --- /dev/null +++ b/evaluations/fold-08-holdout-10/agent_outputs/harmonize_heldout.py @@ -0,0 +1,81 @@ +from __future__ import annotations + +from datetime import datetime, timezone +from pathlib import Path +import re +import numpy as np +import pandas as pd + +FOLD_DIR = Path('/scratch/jmc/data-harmonization-eval/.runs/fold-08-holdout-10') +LOG_PATH = FOLD_DIR / 'AGENT_ACTION_LOG.md' +RAW_PATH = Path('/h/jmc/ess-dive_wfsfa_soil_datasets/ess-dive-01092fc392bc46d-20240819T143818677/Soil_water_content_Fig4e.csv') +OUT_PATH = FOLD_DIR / 'agent_outputs' / 'heldout_harmonized.csv' + +SCHEMA = [ + 'datetime_UTC', + 'site_id', + 'depth_m', + 'replicate', + 'is_timeseries', + 'interval_min', + 'volumetric_water_content_m3_m3', + 'gravimetric_water_content_gH2O_gs', + 'water_potential_kPa', +] + + +def trace(action: str, subject: str, reason: str) -> None: + ts = datetime.now(timezone.utc).astimezone().isoformat() + with LOG_PATH.open('a', encoding='utf-8') as f: + f.write(f'{ts} | action={action} | subject={subject} | reason={reason}\n') + + +def parse_local_to_utc(series: pd.Series, fmt: str, tz: str) -> pd.Series: + dt = pd.to_datetime(series, format=fmt, errors='coerce') + dt = dt.dt.tz_localize(tz, ambiguous='NaT', nonexistent='shift_forward') + return dt.dt.tz_convert('UTC') + + +def ensure_harmonized_cols(df: pd.DataFrame) -> pd.DataFrame: + for col in SCHEMA: + if col not in df.columns: + df[col] = np.nan + return df[SCHEMA] + + +def harmonize() -> pd.DataFrame: + trace('file_read', str(RAW_PATH), 'read held-out raw soil water content payload') + raw = pd.read_csv(RAW_PATH) + data = raw.iloc[1:].copy() + + value_cols = [c for c in data.columns if re.search(r'vol_water_content', c, flags=re.IGNORECASE)] + long = data.melt( + id_vars=['Date'], + value_vars=value_cols, + var_name='source_variable', + value_name='volumetric_water_content_m3_m3', + ) + + long['datetime_UTC'] = parse_local_to_utc(long['Date'], '%Y-%m-%d', 'America/Denver') + long['site_id'] = 'ER-' + long['source_variable'].str.extract(r'(PLM\d+)')[0] + long['volumetric_water_content_m3_m3'] = pd.to_numeric(long['volumetric_water_content_m3_m3'], errors='coerce') + long['depth_m'] = np.nan + long['replicate'] = 1 + long['is_timeseries'] = True + long['gravimetric_water_content_gH2O_gs'] = np.nan + long['water_potential_kPa'] = np.nan + + long = long.sort_values(['site_id', 'datetime_UTC']).reset_index(drop=True) + long['interval_min'] = long.groupby('site_id')['datetime_UTC'].diff().dt.total_seconds() / 60.0 + + out = ensure_harmonized_cols(long) + out = out[out['datetime_UTC'].notna() & out['site_id'].notna() & out['volumetric_water_content_m3_m3'].notna()].copy() + out['datetime_UTC'] = out['datetime_UTC'].dt.strftime('%Y-%m-%dT%H:%M:%SZ') + return out + + +if __name__ == '__main__': + df = harmonize() + trace('file_write', str(OUT_PATH), 'write held-out harmonized CSV') + df.to_csv(OUT_PATH, index=False) + print(f'wrote {OUT_PATH} rows={len(df)} columns={list(df.columns)}') diff --git a/evaluations/fold-08-holdout-10/agent_outputs/heldout_harmonized.csv b/evaluations/fold-08-holdout-10/agent_outputs/heldout_harmonized.csv new file mode 100644 index 0000000..239421a --- /dev/null +++ b/evaluations/fold-08-holdout-10/agent_outputs/heldout_harmonized.csv @@ -0,0 +1,310 @@ +datetime_UTC,site_id,depth_m,replicate,is_timeseries,interval_min,volumetric_water_content_m3_m3,gravimetric_water_content_gH2O_gs,water_potential_kPa +2017-05-06T06:00:00Z,ER-PLM1,,1,True,,0.387,, +2017-05-15T06:00:00Z,ER-PLM1,,1,True,12960.0,0.391,, +2017-05-29T06:00:00Z,ER-PLM1,,1,True,20160.0,0.383,, +2017-06-12T06:00:00Z,ER-PLM1,,1,True,20160.0,0.328,, +2017-06-26T06:00:00Z,ER-PLM1,,1,True,20160.0,0.06,, +2017-07-10T06:00:00Z,ER-PLM1,,1,True,20160.0,0.056,, +2017-07-17T06:00:00Z,ER-PLM1,,1,True,10080.0,0.056,, +2017-07-31T06:00:00Z,ER-PLM1,,1,True,20160.0,0.056,, +2017-08-17T06:00:00Z,ER-PLM1,,1,True,24480.0,0.056,, +2017-08-31T06:00:00Z,ER-PLM1,,1,True,20160.0,0.056,, +2017-09-17T06:00:00Z,ER-PLM1,,1,True,24480.0,0.309,, +2017-09-29T06:00:00Z,ER-PLM1,,1,True,17280.0,0.233,, +2017-10-01T06:00:00Z,ER-PLM1,,1,True,2880.0,0.223,, +2017-10-15T06:00:00Z,ER-PLM1,,1,True,20160.0,0.237,, +2017-10-29T06:00:00Z,ER-PLM1,,1,True,20160.0,0.25,, +2017-11-12T07:00:00Z,ER-PLM1,,1,True,20220.0,0.334,, +2017-11-26T07:00:00Z,ER-PLM1,,1,True,20160.0,0.341,, +2017-12-12T07:00:00Z,ER-PLM1,,1,True,23040.0,0.104,, +2017-12-26T07:00:00Z,ER-PLM1,,1,True,20160.0,0.106,, +2018-01-09T07:00:00Z,ER-PLM1,,1,True,20160.0,0.105,, +2018-01-23T07:00:00Z,ER-PLM1,,1,True,20160.0,0.105,, +2018-02-04T07:00:00Z,ER-PLM1,,1,True,17280.0,0.103,, +2018-02-18T07:00:00Z,ER-PLM1,,1,True,20160.0,0.107,, +2018-03-01T07:00:00Z,ER-PLM1,,1,True,15840.0,0.105,, +2018-03-15T06:00:00Z,ER-PLM1,,1,True,20100.0,0.107,, +2018-04-01T06:00:00Z,ER-PLM1,,1,True,24480.0,0.127,, +2018-04-15T06:00:00Z,ER-PLM1,,1,True,20160.0,0.253,, +2018-05-01T06:00:00Z,ER-PLM1,,1,True,23040.0,0.363,, +2018-05-06T06:00:00Z,ER-PLM1,,1,True,7200.0,0.369,, +2018-05-15T06:00:00Z,ER-PLM1,,1,True,12960.0,0.372,, +2018-06-01T06:00:00Z,ER-PLM1,,1,True,24480.0,0.339,, +2018-06-15T06:00:00Z,ER-PLM1,,1,True,20160.0,0.154,, +2018-07-01T06:00:00Z,ER-PLM1,,1,True,23040.0,0.067,, +2018-07-15T06:00:00Z,ER-PLM1,,1,True,20160.0,0.057,, +2018-07-29T06:00:00Z,ER-PLM1,,1,True,20160.0,0.057,, +2018-08-18T06:00:00Z,ER-PLM1,,1,True,28800.0,0.056,, +2018-08-23T06:00:00Z,ER-PLM1,,1,True,7200.0,0.056,, +2018-09-06T06:00:00Z,ER-PLM1,,1,True,20160.0,0.056,, +2018-09-11T06:00:00Z,ER-PLM1,,1,True,7200.0,0.056,, +2018-09-27T06:00:00Z,ER-PLM1,,1,True,23040.0,0.056,, +2018-10-02T06:00:00Z,ER-PLM1,,1,True,7200.0,0.056,, +2018-10-06T06:00:00Z,ER-PLM1,,1,True,5760.0,0.056,, +2018-10-15T06:00:00Z,ER-PLM1,,1,True,12960.0,0.056,, +2018-11-01T06:00:00Z,ER-PLM1,,1,True,24480.0,0.11,, +2018-11-15T07:00:00Z,ER-PLM1,,1,True,20220.0,0.214,, +2018-12-01T07:00:00Z,ER-PLM1,,1,True,23040.0,0.071,, +2019-01-01T07:00:00Z,ER-PLM1,,1,True,44640.0,0.069,, +2019-02-01T07:00:00Z,ER-PLM1,,1,True,44640.0,0.061,, +2019-03-01T07:00:00Z,ER-PLM1,,1,True,40320.0,0.077,, +2019-03-19T06:00:00Z,ER-PLM1,,1,True,25860.0,0.149,, +2019-04-01T06:00:00Z,ER-PLM1,,1,True,18720.0,0.267,, +2019-04-15T06:00:00Z,ER-PLM1,,1,True,20160.0,0.372,, +2019-05-06T06:00:00Z,ER-PLM1,,1,True,30240.0,0.376,, +2019-05-10T06:00:00Z,ER-PLM1,,1,True,5760.0,0.383,, +2019-05-24T06:00:00Z,ER-PLM1,,1,True,20160.0,0.314,, +2019-06-03T06:00:00Z,ER-PLM1,,1,True,14400.0,0.279,, +2019-06-18T06:00:00Z,ER-PLM1,,1,True,21600.0,0.241,, +2019-07-01T06:00:00Z,ER-PLM1,,1,True,18720.0,0.162,, +2019-07-09T06:00:00Z,ER-PLM1,,1,True,11520.0,0.133,, +2019-07-16T06:00:00Z,ER-PLM1,,1,True,10080.0,0.102,, +2019-07-30T06:00:00Z,ER-PLM1,,1,True,20160.0,0.084,, +2019-08-15T06:00:00Z,ER-PLM1,,1,True,23040.0,0.061,, +2019-09-05T06:00:00Z,ER-PLM1,,1,True,30240.0,0.056,, +2019-10-02T06:00:00Z,ER-PLM1,,1,True,38880.0,0.056,, +2019-11-03T06:00:00Z,ER-PLM1,,1,True,46080.0,0.056,, +2019-12-04T07:00:00Z,ER-PLM1,,1,True,44700.0,0.056,, +2020-01-06T07:00:00Z,ER-PLM1,,1,True,47520.0,0.056,, +2020-01-23T07:00:00Z,ER-PLM1,,1,True,24480.0,0.056,, +2020-02-10T07:00:00Z,ER-PLM1,,1,True,25920.0,0.056,, +2020-02-17T07:00:00Z,ER-PLM1,,1,True,10080.0,0.056,, +2020-02-28T07:00:00Z,ER-PLM1,,1,True,15840.0,0.056,, +2020-03-07T07:00:00Z,ER-PLM1,,1,True,11520.0,0.056,, +2020-03-15T06:00:00Z,ER-PLM1,,1,True,11460.0,0.056,, +2020-03-23T06:00:00Z,ER-PLM1,,1,True,11520.0,0.069,, +2020-03-30T06:00:00Z,ER-PLM1,,1,True,10080.0,0.102,, +2020-04-04T06:00:00Z,ER-PLM1,,1,True,7200.0,0.198,, +2020-04-06T06:00:00Z,ER-PLM1,,1,True,2880.0,0.241,, +2020-04-08T06:00:00Z,ER-PLM1,,1,True,2880.0,0.383,, +2020-04-17T06:00:00Z,ER-PLM1,,1,True,12960.0,0.383,, +2020-04-23T06:00:00Z,ER-PLM1,,1,True,8640.0,0.383,, +2020-04-29T06:00:00Z,ER-PLM1,,1,True,8640.0,0.383,, +2020-05-14T06:00:00Z,ER-PLM1,,1,True,21600.0,0.381,, +2020-05-28T06:00:00Z,ER-PLM1,,1,True,20160.0,0.351,, +2020-06-10T06:00:00Z,ER-PLM1,,1,True,18720.0,0.275,, +2020-06-24T06:00:00Z,ER-PLM1,,1,True,20160.0,0.118,, +2020-07-08T06:00:00Z,ER-PLM1,,1,True,20160.0,0.061,, +2020-07-22T06:00:00Z,ER-PLM1,,1,True,20160.0,0.057,, +2020-08-03T06:00:00Z,ER-PLM1,,1,True,17280.0,0.057,, +2020-08-26T06:00:00Z,ER-PLM1,,1,True,33120.0,0.057,, +2020-09-12T06:00:00Z,ER-PLM1,,1,True,24480.0,0.068,, +2020-09-29T06:00:00Z,ER-PLM1,,1,True,24480.0,0.065,, +2020-10-15T06:00:00Z,ER-PLM1,,1,True,23040.0,0.057,, +2020-11-03T07:00:00Z,ER-PLM1,,1,True,27420.0,0.06,, +2020-11-10T07:00:00Z,ER-PLM1,,1,True,10080.0,0.061,, +2020-12-08T07:00:00Z,ER-PLM1,,1,True,40320.0,0.056,, +2021-01-06T07:00:00Z,ER-PLM1,,1,True,41760.0,0.058,, +2021-01-28T07:00:00Z,ER-PLM1,,1,True,31680.0,0.057,, +2021-02-19T07:00:00Z,ER-PLM1,,1,True,31680.0,0.06,, +2021-02-26T07:00:00Z,ER-PLM1,,1,True,10080.0,0.06,, +2021-03-05T07:00:00Z,ER-PLM1,,1,True,10080.0,0.059,, +2021-03-24T06:00:00Z,ER-PLM1,,1,True,27300.0,0.061,, +2021-04-12T06:00:00Z,ER-PLM1,,1,True,27360.0,0.174,, +2021-05-02T06:00:00Z,ER-PLM1,,1,True,28800.0,0.257,, +2017-05-06T06:00:00Z,ER-PLM2,,1,True,,0.39,, +2017-05-15T06:00:00Z,ER-PLM2,,1,True,12960.0,0.391,, +2017-05-29T06:00:00Z,ER-PLM2,,1,True,20160.0,0.383,, +2017-06-12T06:00:00Z,ER-PLM2,,1,True,20160.0,0.309,, +2017-06-26T06:00:00Z,ER-PLM2,,1,True,20160.0,0.102,, +2017-07-10T06:00:00Z,ER-PLM2,,1,True,20160.0,0.057,, +2017-07-17T06:00:00Z,ER-PLM2,,1,True,10080.0,0.056,, +2017-07-31T06:00:00Z,ER-PLM2,,1,True,20160.0,0.116,, +2017-08-17T06:00:00Z,ER-PLM2,,1,True,24480.0,0.056,, +2017-08-31T06:00:00Z,ER-PLM2,,1,True,20160.0,0.056,, +2017-09-17T06:00:00Z,ER-PLM2,,1,True,24480.0,0.093,, +2017-09-29T06:00:00Z,ER-PLM2,,1,True,17280.0,0.309,, +2017-10-01T06:00:00Z,ER-PLM2,,1,True,2880.0,0.369,, +2017-10-15T06:00:00Z,ER-PLM2,,1,True,20160.0,0.334,, +2017-10-29T06:00:00Z,ER-PLM2,,1,True,20160.0,0.301,, +2017-11-12T07:00:00Z,ER-PLM2,,1,True,20220.0,0.347,, +2017-11-26T07:00:00Z,ER-PLM2,,1,True,20160.0,0.323,, +2017-12-12T07:00:00Z,ER-PLM2,,1,True,23040.0,0.063,, +2017-12-26T07:00:00Z,ER-PLM2,,1,True,20160.0,0.07,, +2018-01-09T07:00:00Z,ER-PLM2,,1,True,20160.0,0.067,, +2018-01-23T07:00:00Z,ER-PLM2,,1,True,20160.0,0.067,, +2018-02-04T07:00:00Z,ER-PLM2,,1,True,17280.0,0.071,, +2018-02-18T07:00:00Z,ER-PLM2,,1,True,20160.0,0.073,, +2018-03-01T07:00:00Z,ER-PLM2,,1,True,15840.0,0.071,, +2018-03-15T06:00:00Z,ER-PLM2,,1,True,20100.0,0.076,, +2018-04-01T06:00:00Z,ER-PLM2,,1,True,24480.0,0.089,, +2018-04-15T06:00:00Z,ER-PLM2,,1,True,20160.0,0.106,, +2018-05-01T06:00:00Z,ER-PLM2,,1,True,23040.0,0.361,, +2018-05-06T06:00:00Z,ER-PLM2,,1,True,7200.0,0.384,, +2018-05-15T06:00:00Z,ER-PLM2,,1,True,12960.0,0.318,, +2018-06-01T06:00:00Z,ER-PLM2,,1,True,24480.0,0.131,, +2018-06-15T06:00:00Z,ER-PLM2,,1,True,20160.0,0.057,, +2018-07-01T06:00:00Z,ER-PLM2,,1,True,23040.0,0.06,, +2018-07-15T06:00:00Z,ER-PLM2,,1,True,20160.0,0.061,, +2018-07-29T06:00:00Z,ER-PLM2,,1,True,20160.0,0.056,, +2018-08-18T06:00:00Z,ER-PLM2,,1,True,28800.0,0.056,, +2018-08-23T06:00:00Z,ER-PLM2,,1,True,7200.0,0.056,, +2018-09-06T06:00:00Z,ER-PLM2,,1,True,20160.0,0.056,, +2018-09-11T06:00:00Z,ER-PLM2,,1,True,7200.0,0.056,, +2018-09-27T06:00:00Z,ER-PLM2,,1,True,23040.0,0.056,, +2018-10-02T06:00:00Z,ER-PLM2,,1,True,7200.0,0.056,, +2018-10-06T06:00:00Z,ER-PLM2,,1,True,5760.0,0.127,, +2018-10-15T06:00:00Z,ER-PLM2,,1,True,12960.0,0.363,, +2018-11-01T06:00:00Z,ER-PLM2,,1,True,24480.0,0.334,, +2018-11-15T07:00:00Z,ER-PLM2,,1,True,20220.0,0.318,, +2018-12-01T07:00:00Z,ER-PLM2,,1,True,23040.0,0.22,, +2019-01-01T07:00:00Z,ER-PLM2,,1,True,44640.0,0.082,, +2019-02-01T07:00:00Z,ER-PLM2,,1,True,44640.0,0.094,, +2019-03-01T07:00:00Z,ER-PLM2,,1,True,40320.0,0.113,, +2019-03-19T06:00:00Z,ER-PLM2,,1,True,25860.0,0.211,, +2019-04-01T06:00:00Z,ER-PLM2,,1,True,18720.0,0.363,, +2019-04-15T06:00:00Z,ER-PLM2,,1,True,20160.0,0.372,, +2019-05-06T06:00:00Z,ER-PLM2,,1,True,30240.0,0.249,, +2019-05-10T06:00:00Z,ER-PLM2,,1,True,5760.0,0.229,, +2019-05-24T06:00:00Z,ER-PLM2,,1,True,20160.0,0.498,, +2019-06-03T06:00:00Z,ER-PLM2,,1,True,14400.0,0.383,, +2019-06-18T06:00:00Z,ER-PLM2,,1,True,21600.0,0.244,, +2019-07-01T06:00:00Z,ER-PLM2,,1,True,18720.0,0.09,, +2019-07-09T06:00:00Z,ER-PLM2,,1,True,11520.0,0.056,, +2019-07-16T06:00:00Z,ER-PLM2,,1,True,10080.0,0.056,, +2019-07-30T06:00:00Z,ER-PLM2,,1,True,20160.0,0.056,, +2019-08-15T06:00:00Z,ER-PLM2,,1,True,23040.0,0.056,, +2019-09-05T06:00:00Z,ER-PLM2,,1,True,30240.0,0.056,, +2019-10-02T06:00:00Z,ER-PLM2,,1,True,38880.0,0.056,, +2019-11-03T06:00:00Z,ER-PLM2,,1,True,46080.0,0.056,, +2019-12-04T07:00:00Z,ER-PLM2,,1,True,44700.0,0.056,, +2020-01-06T07:00:00Z,ER-PLM2,,1,True,47520.0,0.056,, +2020-01-23T07:00:00Z,ER-PLM2,,1,True,24480.0,0.056,, +2020-02-10T07:00:00Z,ER-PLM2,,1,True,25920.0,0.056,, +2020-02-17T07:00:00Z,ER-PLM2,,1,True,10080.0,0.056,, +2020-02-28T07:00:00Z,ER-PLM2,,1,True,15840.0,0.056,, +2020-03-07T07:00:00Z,ER-PLM2,,1,True,11520.0,0.056,, +2020-03-15T06:00:00Z,ER-PLM2,,1,True,11460.0,0.056,, +2020-03-23T06:00:00Z,ER-PLM2,,1,True,11520.0,0.056,, +2020-03-30T06:00:00Z,ER-PLM2,,1,True,10080.0,0.084,, +2020-04-04T06:00:00Z,ER-PLM2,,1,True,7200.0,0.114,, +2020-04-06T06:00:00Z,ER-PLM2,,1,True,2880.0,0.374,, +2020-04-08T06:00:00Z,ER-PLM2,,1,True,2880.0,0.376,, +2020-04-17T06:00:00Z,ER-PLM2,,1,True,12960.0,0.369,, +2020-04-23T06:00:00Z,ER-PLM2,,1,True,8640.0,0.375,, +2020-04-29T06:00:00Z,ER-PLM2,,1,True,8640.0,0.379,, +2020-05-14T06:00:00Z,ER-PLM2,,1,True,21600.0,0.383,, +2020-05-28T06:00:00Z,ER-PLM2,,1,True,20160.0,0.372,, +2020-06-10T06:00:00Z,ER-PLM2,,1,True,18720.0,0.294,, +2020-06-24T06:00:00Z,ER-PLM2,,1,True,20160.0,0.103,, +2020-07-08T06:00:00Z,ER-PLM2,,1,True,20160.0,0.057,, +2020-07-22T06:00:00Z,ER-PLM2,,1,True,20160.0,0.056,, +2020-08-03T06:00:00Z,ER-PLM2,,1,True,17280.0,0.057,, +2020-08-26T06:00:00Z,ER-PLM2,,1,True,33120.0,0.058,, +2020-09-12T06:00:00Z,ER-PLM2,,1,True,24480.0,0.056,, +2020-09-29T06:00:00Z,ER-PLM2,,1,True,24480.0,0.09,, +2020-10-15T06:00:00Z,ER-PLM2,,1,True,23040.0,0.057,, +2020-11-03T07:00:00Z,ER-PLM2,,1,True,27420.0,0.069,, +2020-11-10T07:00:00Z,ER-PLM2,,1,True,10080.0,0.07,, +2020-12-08T07:00:00Z,ER-PLM2,,1,True,40320.0,0.062,, +2021-01-06T07:00:00Z,ER-PLM2,,1,True,41760.0,0.063,, +2021-01-28T07:00:00Z,ER-PLM2,,1,True,31680.0,0.063,, +2021-02-19T07:00:00Z,ER-PLM2,,1,True,31680.0,0.06,, +2021-02-26T07:00:00Z,ER-PLM2,,1,True,10080.0,0.064,, +2021-03-05T07:00:00Z,ER-PLM2,,1,True,10080.0,0.063,, +2021-03-24T06:00:00Z,ER-PLM2,,1,True,27300.0,0.064,, +2021-04-12T06:00:00Z,ER-PLM2,,1,True,27360.0,0.214,, +2021-05-02T06:00:00Z,ER-PLM2,,1,True,28800.0,0.235,, +2017-05-06T06:00:00Z,ER-PLM3,,1,True,,0.39,, +2017-05-15T06:00:00Z,ER-PLM3,,1,True,12960.0,0.39,, +2017-05-29T06:00:00Z,ER-PLM3,,1,True,20160.0,0.279,, +2017-06-12T06:00:00Z,ER-PLM3,,1,True,20160.0,0.198,, +2017-06-26T06:00:00Z,ER-PLM3,,1,True,20160.0,0.091,, +2017-07-10T06:00:00Z,ER-PLM3,,1,True,20160.0,0.065,, +2017-07-17T06:00:00Z,ER-PLM3,,1,True,10080.0,0.078,, +2017-07-31T06:00:00Z,ER-PLM3,,1,True,20160.0,0.098,, +2017-08-17T06:00:00Z,ER-PLM3,,1,True,24480.0,0.057,, +2017-08-31T06:00:00Z,ER-PLM3,,1,True,20160.0,0.056,, +2017-09-17T06:00:00Z,ER-PLM3,,1,True,24480.0,0.056,, +2017-09-29T06:00:00Z,ER-PLM3,,1,True,17280.0,0.219,, +2017-10-01T06:00:00Z,ER-PLM3,,1,True,2880.0,0.369,, +2017-10-15T06:00:00Z,ER-PLM3,,1,True,20160.0,0.279,, +2017-10-29T06:00:00Z,ER-PLM3,,1,True,20160.0,0.198,, +2017-11-12T07:00:00Z,ER-PLM3,,1,True,20220.0,0.144,, +2017-11-26T07:00:00Z,ER-PLM3,,1,True,20160.0,0.102,, +2017-12-12T07:00:00Z,ER-PLM3,,1,True,23040.0,0.071,, +2017-12-26T07:00:00Z,ER-PLM3,,1,True,20160.0,0.074,, +2018-01-09T07:00:00Z,ER-PLM3,,1,True,20160.0,0.074,, +2018-01-23T07:00:00Z,ER-PLM3,,1,True,20160.0,0.072,, +2018-02-04T07:00:00Z,ER-PLM3,,1,True,17280.0,0.073,, +2018-02-18T07:00:00Z,ER-PLM3,,1,True,20160.0,0.073,, +2018-03-01T07:00:00Z,ER-PLM3,,1,True,15840.0,0.073,, +2018-03-15T06:00:00Z,ER-PLM3,,1,True,20100.0,0.084,, +2018-04-01T06:00:00Z,ER-PLM3,,1,True,24480.0,0.091,, +2018-04-15T06:00:00Z,ER-PLM3,,1,True,20160.0,0.102,, +2018-05-01T06:00:00Z,ER-PLM3,,1,True,23040.0,0.125,, +2018-05-06T06:00:00Z,ER-PLM3,,1,True,7200.0,0.241,, +2018-05-15T06:00:00Z,ER-PLM3,,1,True,12960.0,0.211,, +2018-06-01T06:00:00Z,ER-PLM3,,1,True,24480.0,0.188,, +2018-06-15T06:00:00Z,ER-PLM3,,1,True,20160.0,0.083,, +2018-07-01T06:00:00Z,ER-PLM3,,1,True,23040.0,0.091,, +2018-07-15T06:00:00Z,ER-PLM3,,1,True,20160.0,0.154,, +2018-07-29T06:00:00Z,ER-PLM3,,1,True,20160.0,0.056,, +2018-08-18T06:00:00Z,ER-PLM3,,1,True,28800.0,0.056,, +2018-08-23T06:00:00Z,ER-PLM3,,1,True,7200.0,0.056,, +2018-09-06T06:00:00Z,ER-PLM3,,1,True,20160.0,0.293,, +2018-09-11T06:00:00Z,ER-PLM3,,1,True,7200.0,0.107,, +2018-09-27T06:00:00Z,ER-PLM3,,1,True,23040.0,0.056,, +2018-10-02T06:00:00Z,ER-PLM3,,1,True,7200.0,0.071,, +2018-10-06T06:00:00Z,ER-PLM3,,1,True,5760.0,0.268,, +2018-10-15T06:00:00Z,ER-PLM3,,1,True,12960.0,0.383,, +2018-11-01T06:00:00Z,ER-PLM3,,1,True,24480.0,0.34,, +2018-11-15T07:00:00Z,ER-PLM3,,1,True,20220.0,0.081,, +2018-12-01T07:00:00Z,ER-PLM3,,1,True,23040.0,0.084,, +2019-01-01T07:00:00Z,ER-PLM3,,1,True,44640.0,0.085,, +2019-02-01T07:00:00Z,ER-PLM3,,1,True,44640.0,0.083,, +2019-03-01T07:00:00Z,ER-PLM3,,1,True,40320.0,0.087,, +2019-03-19T06:00:00Z,ER-PLM3,,1,True,25860.0,0.123,, +2019-04-01T06:00:00Z,ER-PLM3,,1,True,18720.0,0.37,, +2019-04-15T06:00:00Z,ER-PLM3,,1,True,20160.0,0.375,, +2019-05-06T06:00:00Z,ER-PLM3,,1,True,30240.0,0.372,, +2019-05-10T06:00:00Z,ER-PLM3,,1,True,5760.0,0.341,, +2019-05-24T06:00:00Z,ER-PLM3,,1,True,20160.0,0.314,, +2019-06-03T06:00:00Z,ER-PLM3,,1,True,14400.0,0.279,, +2019-06-18T06:00:00Z,ER-PLM3,,1,True,21600.0,0.265,, +2019-07-01T06:00:00Z,ER-PLM3,,1,True,18720.0,0.127,, +2019-07-09T06:00:00Z,ER-PLM3,,1,True,11520.0,0.086,, +2019-07-16T06:00:00Z,ER-PLM3,,1,True,10080.0,0.076,, +2019-07-30T06:00:00Z,ER-PLM3,,1,True,20160.0,0.058,, +2019-08-15T06:00:00Z,ER-PLM3,,1,True,23040.0,0.059,, +2019-09-05T06:00:00Z,ER-PLM3,,1,True,30240.0,0.056,, +2019-10-02T06:00:00Z,ER-PLM3,,1,True,38880.0,0.056,, +2019-11-03T06:00:00Z,ER-PLM3,,1,True,46080.0,0.056,, +2019-12-04T07:00:00Z,ER-PLM3,,1,True,44700.0,0.056,, +2020-01-06T07:00:00Z,ER-PLM3,,1,True,47520.0,0.056,, +2020-01-23T07:00:00Z,ER-PLM3,,1,True,24480.0,0.056,, +2020-02-10T07:00:00Z,ER-PLM3,,1,True,25920.0,0.056,, +2020-02-17T07:00:00Z,ER-PLM3,,1,True,10080.0,0.056,, +2020-02-28T07:00:00Z,ER-PLM3,,1,True,15840.0,0.056,, +2020-03-07T07:00:00Z,ER-PLM3,,1,True,11520.0,0.056,, +2020-03-15T06:00:00Z,ER-PLM3,,1,True,11460.0,0.056,, +2020-03-23T06:00:00Z,ER-PLM3,,1,True,11520.0,0.056,, +2020-03-30T06:00:00Z,ER-PLM3,,1,True,10080.0,0.056,, +2020-04-04T06:00:00Z,ER-PLM3,,1,True,7200.0,0.056,, +2020-04-06T06:00:00Z,ER-PLM3,,1,True,2880.0,0.162,, +2020-04-08T06:00:00Z,ER-PLM3,,1,True,2880.0,0.373,, +2020-04-17T06:00:00Z,ER-PLM3,,1,True,12960.0,0.372,, +2020-04-23T06:00:00Z,ER-PLM3,,1,True,8640.0,0.377,, +2020-04-29T06:00:00Z,ER-PLM3,,1,True,8640.0,0.378,, +2020-05-14T06:00:00Z,ER-PLM3,,1,True,21600.0,0.379,, +2020-05-28T06:00:00Z,ER-PLM3,,1,True,20160.0,0.334,, +2020-06-10T06:00:00Z,ER-PLM3,,1,True,18720.0,0.261,, +2020-06-24T06:00:00Z,ER-PLM3,,1,True,20160.0,0.157,, +2020-07-08T06:00:00Z,ER-PLM3,,1,True,20160.0,0.068,, +2020-07-22T06:00:00Z,ER-PLM3,,1,True,20160.0,0.057,, +2020-08-03T06:00:00Z,ER-PLM3,,1,True,17280.0,0.057,, +2020-08-26T06:00:00Z,ER-PLM3,,1,True,33120.0,0.056,, +2020-09-12T06:00:00Z,ER-PLM3,,1,True,24480.0,0.16,, +2020-09-29T06:00:00Z,ER-PLM3,,1,True,24480.0,0.056,, +2020-10-15T06:00:00Z,ER-PLM3,,1,True,23040.0,0.056,, +2020-11-03T07:00:00Z,ER-PLM3,,1,True,27420.0,0.056,, +2020-11-10T07:00:00Z,ER-PLM3,,1,True,10080.0,0.056,, +2020-12-08T07:00:00Z,ER-PLM3,,1,True,40320.0,-9999.0,, +2021-01-06T07:00:00Z,ER-PLM3,,1,True,41760.0,0.056,, +2021-01-28T07:00:00Z,ER-PLM3,,1,True,31680.0,-9999.0,, +2021-02-19T07:00:00Z,ER-PLM3,,1,True,31680.0,0.056,, +2021-02-26T07:00:00Z,ER-PLM3,,1,True,10080.0,-9999.0,, +2021-03-05T07:00:00Z,ER-PLM3,,1,True,10080.0,0.056,, +2021-03-24T06:00:00Z,ER-PLM3,,1,True,27300.0,-9999.0,, +2021-04-12T06:00:00Z,ER-PLM3,,1,True,27360.0,0.096,, +2021-05-02T06:00:00Z,ER-PLM3,,1,True,28800.0,0.376,, diff --git a/evaluations/fold-08-holdout-10/agent_outputs/mapping.json b/evaluations/fold-08-holdout-10/agent_outputs/mapping.json new file mode 100644 index 0000000..3f84535 --- /dev/null +++ b/evaluations/fold-08-holdout-10/agent_outputs/mapping.json @@ -0,0 +1,104 @@ +{ + "index": 10, + "dataset_identifier": "ess-dive-01092fc392bc46d-20240819T143818677", + "doi": "doi:10.15485/2322567", + "archive_repository": "ESS-DIVE", + "data_payload_files": [ + "Soil_water_content_Fig4e.csv" + ], + "location_metadata_files": null, + "sensor_metadata_files": null, + "harmonization_mappings": { + "datetime": { + "pattern_1": { + "source_pattern": "Date", + "source_files": [ + "Soil_water_content_Fig4e.csv" + ], + "destination_variable": "datetime_UTC", + "transformation": "Skip the first units row, parse date strings with format '%Y-%m-%d' in America/Denver local time, and convert to UTC.", + "unit_conversion": null + } + }, + "depth": { + "pattern_1": { + "source_pattern": null, + "source_files": null, + "destination_variable": "depth_m", + "transformation": "Depth is not encoded in the source file. Populate with NA.", + "unit_conversion": null + } + }, + "latitude": { + "pattern_1": { + "source_pattern": "Location_ID in Varadharajan et al. location registry", + "source_files": [ + "data/East_Taylor_Watershed_Community_Observatory_Sites___Point_Locations__Surface_v3_2_20250327.csv" + ], + "destination_variable": "latitude", + "transformation": "Look up ER-PLM1, ER-PLM2, and ER-PLM3 after prefixing source PLM column IDs with 'ER-'.", + "unit_conversion": null + } + }, + "longitude": { + "pattern_1": { + "source_pattern": "Location_ID in Varadharajan et al. location registry", + "source_files": [ + "data/East_Taylor_Watershed_Community_Observatory_Sites___Point_Locations__Surface_v3_2_20250327.csv" + ], + "destination_variable": "longitude", + "transformation": "Look up ER-PLM1, ER-PLM2, and ER-PLM3 after prefixing source PLM column IDs with 'ER-'.", + "unit_conversion": null + } + }, + "replicate": { + "pattern_1": { + "source_pattern": null, + "source_files": null, + "destination_variable": "replicate", + "transformation": "No replicate column is provided; assign replicate 1 for each PLM site series.", + "unit_conversion": null + } + }, + "site_id": { + "pattern_1": { + "source_pattern": "PLM1 _vol_water_content, PLM2 _vol_water_content, PLM3 _vol_water_content", + "source_files": [ + "Soil_water_content_Fig4e.csv" + ], + "destination_variable": "site_id", + "transformation": "Melt wide PLM columns to long format and convert PLM1/PLM2/PLM3 to ER-PLM1/ER-PLM2/ER-PLM3.", + "unit_conversion": null + } + }, + "soil_water_potential": { + "pattern_1": { + "source_pattern": null, + "source_files": null, + "destination_variable": "water_potential_kPa", + "transformation": "Soil water potential is not reported. Populate with NA.", + "unit_conversion": null + } + }, + "gravimetric_water_content": { + "pattern_1": { + "source_pattern": null, + "source_files": null, + "destination_variable": "gravimetric_water_content_gH2O_gs", + "transformation": "Gravimetric water content is not reported. Populate with NA.", + "unit_conversion": null + } + }, + "volumetric_water_content": { + "pattern_1": { + "source_pattern": "PLM[1-3] _vol_water_content", + "source_files": [ + "Soil_water_content_Fig4e.csv" + ], + "destination_variable": "volumetric_water_content_m3_m3", + "transformation": "Melt the three PLM volumetric water content columns from wide to long format and coerce values to numeric.", + "unit_conversion": "None; the source units row reports m3/m3." + } + } + } +} diff --git a/evaluations/fold-08-holdout-10/agent_outputs/mapping_notes.md b/evaluations/fold-08-holdout-10/agent_outputs/mapping_notes.md new file mode 100644 index 0000000..a7ed812 --- /dev/null +++ b/evaluations/fold-08-holdout-10/agent_outputs/mapping_notes.md @@ -0,0 +1,11 @@ +# Held-out Dataset 10 Mapping Notes + +Decision: INCLUDE. + +The package metadata identifies the dataset as `doi:10.15485/2322567` and the held-out raw cache contains one relevant soil-moisture payload, `Soil_water_content_Fig4e.csv`. The first data row is a units row (`YYYY-MM-DD`, `m3/m3`, `m3/m3`, `m3/m3`), so harmonization skips that row before parsing dates and measurements. + +The source is wide by site. Columns `PLM1 _vol_water_content`, `PLM2 _vol_water_content`, and `PLM3 _vol_water_content` are melted to long format and normalized to site IDs `ER-PLM1`, `ER-PLM2`, and `ER-PLM3` to match WFSFA location identifiers. Values are already volumetric water content in `m3/m3`, so no unit conversion is applied. + +Depth is not present in the source file or the package metadata for this figure-level table, so `depth_m` is `NaN`. The repeated dated observations make this a time series, but the intervals are irregular; the output stores per-site elapsed minutes since the previous observation, leaving the first interval for each site missing. + +Location coordinates are not written to `heldout_harmonized.csv` because the target held-out CSV schema has only the nine soil-moisture columns. For curation provenance, PLM coordinates were resolvable from the raw Varadharajan location registry referenced by fold-local mapping index 0, which would imply `g1` if a location output were required. diff --git a/evaluations/fold-08-holdout-10/evaluation_metrics.json b/evaluations/fold-08-holdout-10/evaluation_metrics.json new file mode 100644 index 0000000..bd3e213 --- /dev/null +++ b/evaluations/fold-08-holdout-10/evaluation_metrics.json @@ -0,0 +1,60 @@ +{ + "fold": "fold-08-holdout-10", + "dataset_indices": [ + 10 + ], + "trace_forbidden_path_scan_matches": 0, + "agent_output": { + "rows": 309, + "target_columns_present": 9, + "schema_equal": true, + "extra_columns": [] + }, + "gold_output": { + "rows": 309, + "columns": 9 + }, + "output_equivalence": { + "key_includes_dataset_index": false, + "unique_agent_keys": 309, + "unique_gold_keys": 103, + "key_intersection": 0, + "agent_extra_keys": 309, + "agent_missing_gold_keys": 103, + "common_rows": 0, + "shared_row_value_matches": { + "interval_min": "0/0", + "volumetric_water_content_m3_m3": "0/0", + "gravimetric_water_content_gH2O_gs": "0/0", + "water_potential_kPa": "0/0", + "is_timeseries": "0/0" + }, + "row_precision": 0.0, + "gold_recall": 0.0 + }, + "json_mapping_equivalence": { + "top_level_exact_matches": "7/7", + "top_level_matches": { + "index": true, + "dataset_identifier": true, + "doi": true, + "archive_repository": true, + "data_payload_files": true, + "location_metadata_files": true, + "sensor_metadata_files": true + }, + "gold_mapping_categories_present": "8/8", + "extra_agent_categories": [ + "gravimetric_water_content" + ], + "missing_gold_categories": [], + "field_level_exact_matches": "24/40", + "field_exact_matches_by_name": { + "destination_variable": "8/8", + "source_pattern": "4/8", + "source_files": "6/8", + "transformation": "0/8", + "unit_conversion": "6/8" + } + } +}