Scalable time series features computation
Project description
FastTSFeatures
Compute static or temporal time-series features at scale.
Install
pip install fasttsfeatures
How to use
1. Request free trial
Request a free trial sending an email to: fede.garza.ramirez@gmail.com.
2. Required information
To use fasttsfeatures
you need:
- An AWS url provided by
Nixtla
. You'll upload your dataset here. - An user and a password to enter the previous url.
- An API Key to interact with the scalable API.
- An API ID to interact with the scalable API.
3. Upload your dataset
- Access the url provided by
Nixtla
. You'll see a login page like the following. Just enter your user and paswsword.
- Next you'll see the bucket where you can upload your dataset:
- Upload your dataset and copy its S3 URI.
4. Run the process
- Import the library.
from fasttsfeatures.core import TSFeatures
- Instantiate
TSFeatures
introduce yourapi_id
andapi_key
.
tsfeatures = TSFeatures(api_id=os.environ['API_ID'],
api_key=os.environ['API_KEY'])
- Run the process introducing your previous copied S3 uri.
response = tsfeatures.calculate_features_from_s3_uri(s3_uri='s3://tsfeatures-api-public/train.csv',
freq=7)
display_df(response)
status | body | id | message | |
---|---|---|---|---|
0 | 200 | "s3://tsfeatures-api-public/features/features.csv" | 740a410a-d138-41b4-8373-581710f020f8 | Check job status at GET /tsfeatures/jobs/{job_id} |
- Monitor the process with the following code. Once it's done, access to your bucket to download the generated features.
job_id = response['id'].item()
display(tsfeatures.get_status(job_id))
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
status | processing_time_seconds | |
---|---|---|
0 | InProgress | 20 |
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fasttsfeatures-0.0.3.tar.gz
(11.0 kB
view hashes)
Built Distribution
Close
Hashes for fasttsfeatures-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3bc7b29e4c03c563f5c2669a7fefafb29deecd420b487b051935e962fd8177f6 |
|
MD5 | 87daa3d7afd593787900fe4839cd11d6 |
|
BLAKE2b-256 | c3f486c3e0986a9009ba6bf4234b7b35585a341b1a2b3216977112c0dd050a18 |