Merge pull request #267 from winedarksea/dev

1.0.0

Author: winedarksea

MANIFEST.in

@@ -1,2 +1,8 @@
 include autots/datasets/data/*.zip
-include README.md LICENSE
+include README.md LICENSE
+include extended_tutorial.md
+include production_example.py
+include docs/metric_weighting_guide.md
+include docs/catlin_m6_paper.tex
+include autots/mcp/mosaic_profile_template.json
+include autots/mcp/README.md

README.md

@@ -112,7 +112,7 @@ Also take a look at the [production_example.py](https://github.com/winedarksea/A
 * Use the `subset` parameter when there are many similar series, `subset=100` will often generalize well for tens of thousands of similar series.
 	* if using `subset`, passing `weights` for series will weight subset selection towards higher priority series.
 	* if limited by RAM, it can be distributed by running multiple instances of AutoTS on different batches of data, having first imported a template pretrained as a starting point for all.
-* Set `model_interrupt=True` which passes over the current model when a `KeyboardInterrupt` ie `crtl+c` is pressed (although if the interrupt falls between generations it will stop the entire training).
+* Set `model_interrupt=True` to skip only the current model when you hit `Ctrl+C`. Tap `Ctrl+C` a second time within 1.5 seconds to end the entire run, or pass something like `model_interrupt={"mode": "skip", "double_press_window": 1.2}` to tighten/loosen the window.
 * Use the `result_file` method of `.fit()` which will save progress after each generation - helpful to save progress if a long training is being done. Use `import_results` to recover.
 * While Transformations are pretty fast, setting `transformer_max_depth` to a lower number (say, 2) will increase speed. Also utilize `transformer_list` == 'fast' or 'superfast'.
 * Check out [this example](https://github.com/winedarksea/AutoTS/discussions/76) of using AutoTS with pandas UDF.
@@ -125,6 +125,19 @@ Also take a look at the [production_example.py](https://github.com/winedarksea/A
 * Set `runtime_weighting` in `metric_weighting` to a higher value. This will guide the search towards faster models, although it may come at the expense of accuracy. 
 * Memory shortage is the most common cause of random process/kernel crashes. Try testing a data subset and using a different model list if issues occur. Please also report crashes if found to be linked to a specific set of model parameters (not AutoTS parameters but the underlying forecasting model params). Also crashes vary significantly by setup such as underlying linpack/blas so seeing crash differences between environments can be expected. 
 
+## MCP Server
+See the README.md in ./autots/mcp
+```json
+{
+  "mcpServers": {
+    "autots": {
+      "command": "autots-mcp"
+    }
+  }
+}
+```
+mcp-name: io.github.winedarksea/AutoTS
+
 ## How to Contribute:
 * Give feedback on where you find the documentation confusing
 * Use AutoTS and...
@@ -167,4 +180,13 @@ flowchart TD
     R --> B[Import Best Models Template]
 ```
 
+## Citation
+If you wish to cite AutoTS in an academic work, the following paper may be used.
+
+Colin Catlin,
+Adaptive forecasting in dynamic markets: An evaluation of AutoTS within the M6 competition,
+International Journal of Forecasting,
+Volume 41, Issue 4, 2025, Pages 1485-1493, ISSN 0169-2070,
+https://doi.org/10.1016/j.ijforecast.2025.08.004.
+
 *Also known as Project CATS (Catlin's Automated Time Series) hence the logo.*

TODO.md

@@ -11,14 +11,32 @@
 * Series will largely be consistent in period, or at least up-sampled to regular intervals
 * The most recent data will generally be the most important
 * Forecasts are desired for the future immediately following the most recent data.
-* trimmed_mean to AverageValueNaive
 
-# 0.6.21 🇺🇦 🇺🇦 🇺🇦
-* Prophet and Cassandra bug fixes
+# 1.0.0 🇺🇦 🇺🇦 🇺🇦
+* added ReconciliationTransformer
+* updated cointegration code, replaced Cointegration with CointegrationTransformer
+* added mocks for dependency fallbacks
+* added variational autoencoder anomaly detection method
+* some fixes for breaking changes in dependencies
+* adjustment to how custom_metric is scaled so it can work with negatives
+* improvements to the calendars, Hindu calendar should be working now
+* changes to HistoricValues which hopefully makes it more reliable
+* added pMLP and MambaSSM models (painfully slow)
+* deleted old models ComponentAnalysis, TFPRegression, TensorflowSTS, Greykite, NeuralProphet, UnivariateRegression
+* improvements to model_interrupt
+* synthetic data generation and feature extractor new, very much in beta
+* updated weather data to CDO v2 (requires API key)
+* added NASA solar data to load_live_daily
+* new methods to LevelShiftTransformer
+* created the seasonal_linear interpolation which is quite promisiing for seasonal data
+* added apply_adjustments
+* added G726Filter and G711Scaler
+* created an MCP server for AutoTS (tool naming and pattern still in beta)
+* many bug fixes, tweaks, reorganizations, and added unittests
 
 ### Unstable Upstream Pacakges (those that are frequently broken by maintainers)
 * Pytorch-Forecasting
-* Neural Prophet
+* NeuralForecast
 * GluonTS
 
 ### New Model Checklist:

autots/__init__.py

@@ -15,6 +15,8 @@
     load_linear,
     load_artificial,
     load_sine,
+    SyntheticDailyGenerator,
+    generate_synthetic_daily_data,
 )
 
 from autots.evaluator.auto_ts import AutoTS
@@ -25,9 +27,10 @@
 from autots.evaluator.auto_model import model_forecast, ModelPrediction
 from autots.evaluator.anomaly_detector import AnomalyDetector, HolidayDetector
 from autots.models.cassandra import Cassandra
+from autots.tools.impute import FillNA
 
 
-__version__ = '0.6.21'
+__version__ = '1.0.0'
 
 TransformTS = GeneralTransformer
 
@@ -56,4 +59,7 @@
     'Cassandra',
     'infer_frequency',
     'ModelPrediction',
+    'SyntheticDailyGenerator',
+    'generate_synthetic_daily_data',
+    'FillNA',
 ]

autots/datasets/__init__.py

@@ -15,6 +15,10 @@
     load_sine,
     load_artificial,
 )
+from autots.datasets.synthetic import (
+    SyntheticDailyGenerator,
+    generate_synthetic_daily_data,
+)
 
 __all__ = [
     'load_daily',
@@ -28,4 +32,6 @@
     'load_linear',
     'load_sine',
     'load_artificial',
+    'SyntheticDailyGenerator',
+    'generate_synthetic_daily_data',
 ]