hierarchicalforecast
hts
hierarchicalforecast | hts | |
---|---|---|
11 | 3 | |
522 | 107 | |
2.3% | - | |
6.7 | 0.0 | |
17 days ago | over 1 year ago | |
Python | R | |
Apache License 2.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hierarchicalforecast
- [D] When less is more in the hierarchical forecasting case.
-
Time series and cross validation
I also recommend you check Nixtla's libraries, in particular StatsForecast and HierarchicalForecast. They offer a wide selection of forecasting models, and can work with multiple time series. Given that you're working with many products in a warehouse, I think the hierarchical forecast can be very useful, especially for the short time series (the ones that don't seem to have enough time stamps).
- Show HN: Probabilistic hierarchical forecasting with statistical methods
- Sh: Probabilistic hierarchical forecasting with statistical methods
-
Probabilistic and nonnegative methods for hierarchical forecasting in python are now available in Nixtla's HierachicalForecast
Repo: https://github.com/Nixtla/hierarchicalforecast Example: https://nixtla.github.io/hierarchicalforecast/examples/australiandomestictourism-intervals.html
- Probabilistic hierarchical reconciliation for time series
-
[D] Can anyone explain the MinTrace method for reconciliation of Hierarchical Time Series Forecast?
If you use python take a look to the HierarchicalForecast package.
-
[D] Python's library to multivariate time series forecasting: Sktime, modeltime, darts.
Here is the repo for hierarchical methods: https://github.com/nixtla/hierarchicalforecast/
-
Time series forecasting model predicts increasing number for target variable when the actual values are zeroes
You can try HierarchicalForecast package to reconciliate predictions.
-
[D] What are some statistical packages you use in R that aren't available in Python?
[HierarchicalForecast package](https://github.com/Nixtla/hierarchicalforecast) that mirrors [hts](https://cran.r-project.org/web/packages/hts/vignettes/hts.pdf) that is now part of fable. The same with previous comment on efficient implementations of ARIMA and ETS on the [StatsForecast package](https://github.com/Nixtla/statsforecast).
hts
- Time Series Forecasting Compositional Data - no good package exists?
-
[P] Fastest and most accurate version of the Exponential Smoothing (ETS) Algorithm for Python
sadly a lot of statistics research is done with R and is unavailable with Python, hopefully this kind of work will also motivate new libraries for Python. I am particularly interested in hierarchical forecasting. Are there Python alternatives to the hts library?(https://github.com/earowang/hts)
-
Can anyone explain me hierarchical time series forecating?
Additionally, you could use one of the more complex methods from the aforementioned hts package. This will allow you to make forecasts on all levels of the hierarchy, and use the bootstrapped errors to make adjustments to all forecasts in the hierarchy using a constrained least-squares approach, in order to make all forecasts sum-consistent (make the aggregates of the forecasts equal the forecasts of the aggregates). This allows you to model cannibalisation effects between different products, for example. However for this to work, you'd need quite good models, as the bootstrapped errors are taken as the 'wiggle room' for the adjustments, which means that if you have a badly fitting model, the adjustments might be quite large and no longer make sense (eg. be negative for a sales forecast).
What are some alternatives?
statsforecast - Lightning ⚡️ fast forecasting with statistical and econometric models.
atspy - AtsPy: Automated Time Series Models in Python (by @firmai)
telegram.bot - Develop a Telegram Bot with R
dicomtrolley - Retrieve medical images via WADO, MINT, RAD69 and DICOM-QR
rtweet - 🐦 R client for interacting with Twitter's [stream and REST] APIs
recon-cli - Simple command line tool to reconcile datasets
tableone - R package to create "Table 1", description of baseline characteristics with or without propensity score weighting
RobinHood - An R interface for the RobinHood.com no commision investing site
meta - Official Git repository of R package meta
littler - A scripting and command-line front-end for GNU R
future - :rocket: R package: future: Unified Parallel and Distributed Processing in R for Everyone