Comments (6)
I've looked at the error but it's a bit difficult to say exactly what it is without some additional data.
I cannot comment on the first part to get the X. It seems like a complicated process, but that is data preparation. In the end, if you are going to use SlidingWindow
you need to prepare a pandas df with the required columns, in the format that you want, and without 'nan' values.
The important things I'd need to know are:
- Could you please use
check_data(X1, y1, splits1)
and print out the output? - I'd also need you to create a batch and print out the following:
xb, yb = first(dls.train)
print(xb, yb)
print(xb.shape, yb.shape)
from tsai.
from tsai.
Great, thanks.
timesteps cannot be 1 as that means you don't have any sequences, just scalars. In your case, timesteps are determined by your window_len hyperparameter in SlidingWindow. You need to set that to the appropriate number depending on your task.
from tsai.
from tsai.
It’s an extreme case indeed. And you want be able to use any of the tsai models as they require time series/ sequences.
If you are trying to predict a value from another value you can use any of the sklearn models.
I have no idea what type of problem you are trying to tackle, but it makes sense to use different window lengths to really understand how much history is required to generate a good forecast. I don’t think there are good rules of thumb to define the window length, although you want yo capture seasonality if present. It depends on the task.
But what you can do to check that your data is well prepared is to set the window length to 30 for example, and then try to train a model.
from tsai.
from tsai.
Related Issues (20)
- Transfer Learning in PatchTST using Fine Tuning and Linear Probing - Notebook Tutorial
- It has not been possible to download the required files - get_classification_data func HOT 2
- Using pre train weight in TSRegressor API
- The label data corresponds to the number of time points, not the number of samples. HOT 2
- Unable to Navigate to self._cell Source Code in RNN Using PyCharm
- Request for Detailed Architecture and Forward Process of xresnet1d50 in XResNet1d.py for Diagramming and Corresponding Paper
- AttributeError: Exception occured in `ShowGraph` when calling event `after_fit`: 'bool' object has no attribute 'all'
- AttributeError: 'TST' object has no attribute 'backbone'
- Bug with `prepare_forecasting_data` in v0.3.7 HOT 1
- Variable `sequence_length` ts for MiniRocket Pytorch
- get_long_term_forecasting_data fails HOT 2
- Does PartchTST work for categorical variables?
- Using MVP callback for pre-training a TSTabFusionTransformer multilabel classification model
- Q: Can i use TST for regression problem?
- How to use the data I've prepared for training HOT 3
- Training LSTM for time series data
- PatchTST tutorial missing data HOT 2
- Support for anomaly detection / segmentation
- PatchTST pretrain
- TSiT Non-trainable parameters
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tsai.