mirror of
https://github.com/K-Dense-AI/claude-scientific-skills.git
synced 2026-03-28 07:33:45 +08:00
c7c5bc21ff
- Add NOAA GISTEMP global temperature anomaly dataset (36 months, 2022-2024) - Run TimesFM 1.0 PyTorch forecast for 2025 (12-month horizon) - Generate fan chart visualization with 80%/90% confidence intervals - Create comprehensive markdown report with findings and API notes API Discovery: - TimesFM 2.5 PyTorch checkpoint has file format issue (model.safetensors vs expected torch_model.ckpt) - Working API uses TimesFmHparams + TimesFmCheckpoint + TimesFm() constructor - Documented API in GitHub README differs from actual pip package Includes: - temperature_anomaly.csv (input data) - forecast_output.csv (point forecast + quantiles) - forecast_output.json (machine-readable output) - forecast_visualization.png (LFS-tracked) - run_forecast.py (reusable script) - visualize_forecast.py (chart generation) - run_example.sh (one-click runner) - README.md (full report with findings)
591 B
591 B
| 1 | date | anomaly_c |
|---|---|---|
| 2 | 2022-01-01 | 0.89 |
| 3 | 2022-02-01 | 0.89 |
| 4 | 2022-03-01 | 1.02 |
| 5 | 2022-04-01 | 0.88 |
| 6 | 2022-05-01 | 0.85 |
| 7 | 2022-06-01 | 0.88 |
| 8 | 2022-07-01 | 0.88 |
| 9 | 2022-08-01 | 0.90 |
| 10 | 2022-09-01 | 0.88 |
| 11 | 2022-10-01 | 0.95 |
| 12 | 2022-11-01 | 0.77 |
| 13 | 2022-12-01 | 0.78 |
| 14 | 2023-01-01 | 0.87 |
| 15 | 2023-02-01 | 0.98 |
| 16 | 2023-03-01 | 1.21 |
| 17 | 2023-04-01 | 1.00 |
| 18 | 2023-05-01 | 0.94 |
| 19 | 2023-06-01 | 1.08 |
| 20 | 2023-07-01 | 1.18 |
| 21 | 2023-08-01 | 1.24 |
| 22 | 2023-09-01 | 1.47 |
| 23 | 2023-10-01 | 1.32 |
| 24 | 2023-11-01 | 1.18 |
| 25 | 2023-12-01 | 1.16 |
| 26 | 2024-01-01 | 1.22 |
| 27 | 2024-02-01 | 1.35 |
| 28 | 2024-03-01 | 1.34 |
| 29 | 2024-04-01 | 1.26 |
| 30 | 2024-05-01 | 1.15 |
| 31 | 2024-06-01 | 1.20 |
| 32 | 2024-07-01 | 1.24 |
| 33 | 2024-08-01 | 1.30 |
| 34 | 2024-09-01 | 1.28 |
| 35 | 2024-10-01 | 1.27 |
| 36 | 2024-11-01 | 1.22 |
| 37 | 2024-12-01 | 1.20 |