Closed codemzs closed 5 years ago
I'm a big data science n00b. Any chance that a simple tutorial will be provided? I'm aiming for something like this with my data:
But then better :)
@codemzs is there a PR associated with this, or this issue is closed?
@shauheen Yes, PR has been checked-in but you can see it at PR #1727 and sample at #1762
Hello, can you please elaborate how you got p-values and martingale values for the DetectIidChangePoint function? If possible, can you give the algorithm for calculating these values? Thank you
Hi,
why MovingAverageTransform class from Microsoft.Transforms.TimeSeries is not publicly accessible? I want to use it in my app? Whats the strategy behind it?
it does not have an API ready yet.
Do u have any roadmap? When this api will be ready?
hi @codemzs
we have Spike Detector to find the sudden jump, but for any sudden drop, is Change Point Detector meant for this kind of situation?
Thanks.
Whatever happened to the smoothing transforms! They would be incredibly useful.
Time Series in ML.NET
Forecasting
Anomaly Detection
Smoothing transforms
New Features to come
Estimator and PiGSTy APIs for the below components
Example:
Prediction Engine
Currently to achieve stateful prediction engine users have to write the below code and then create checkpoints by saving the model every so often.
Instead we could have a below API that allows the user to save the model at fixed intervals to a disk or a stream while updating the model.
Online Training Currently we have to train the model with the entire train dataset to update the model but instead it would be nice if the model got updated as the data came in. #163
Evaluator
ARIMA model It seems the first thing novice time series users look for in a toolkit when doing a forecasting task is ARMIA model because it is the first thing that comes up in search results for forecasting. While ARMIA model isn’t the most accurate or performant model but it is the most well-known forecasting model. We should consider bringing in a simple implementation of ARIMA in ML.NET. #929
Time Series Featurizer
The more performant models are the one that combine the features from a time series transform with non-time series features and feed in the resulting vector into a black-box regression learning algorithm. For example, one could have two features A and B, where A will contain data points that have temporal relationship between them, example, stock price and B contains non-temporal feature like country or zip code. We could feed A into SSA transform that will extract various components from an individual feature value such as trend, level, seasonality and then repeat this for all the feature values of A and then combine the result vector with feature B that could be feed into a regressor for prediction. The feature extraction step could be SSA or it could be a deep learning model such as LSTM. The regressor could be any regression based learner. #929
... and many more with
time
.