Timeseries forecasting with LSTM for weather prediction example contribution

[PrabhanshuAttri]

I see that 'Timeseries forecasting with LSTM for weather prediction' example if required by the repository

My team in MLH Fellowship is working on this. Here is the link to the Jupiter notebook: https://github.com/MLH-Fellowship/keras-io/blob/example/timeseries/examples/timeseries/ipynb/timeseries_weather_forecasting.ipynb

I just want to confirm that no one else is not working on this.

Also, as per our understanding, the requirements include a single LSTM layer and nice visualizations. We are still figuring out timeseries_dataset_from_array import due to dependency issues.

[fchollet]

timeseries_dataset_from_array requires tf-nightly or TF 2.3 / higher

Please make a PR to the call for contributions doc to notify others that you're working on this example

[PrabhanshuAttri]

Thanks @fchollet

This week we were able to figure out the imports with tf-nightly. We are doing the cleanup and squashing commits. The latest notebook can be found here

Created a new PR to the call for contributions for work in progress #117

[nskplta]

timeseries_dataset_from_array requires tf-nightly or TF 2.3 / higher : ACTUALLY NOT.

In Google Colab, Tensorflow version 2.6.0, and tf-nightly installed:

ImportError: cannot import name 'timeseries_dataset_from_array' from 'keras.preprocessing' (/usr/local/lib/python3.7/dist-packages/keras/preprocessing/init.py)

[sachinprasadhs]

Hi @PrabhanshuAttri , I see your tutorial Timeseries forecasting for weather prediction is already published here https://keras.io/examples/timeseries/timeseries_weather_forecasting/.

Could you please spare some time to close this issue. Thanks!

[PrabhanshuAttri]

Thanks for reminder @sachinprasadhs
Closing the issue.