search

unit8co / darts

A python library for user-friendly forecasting and anomaly detection on time series.
https://unit8co.github.io/darts/
Apache License 2.0
7.89k stars 854 forks source link

handling dataframe with multiple entries for same days but different corresponding column(say store) #484

Closed kumar-roheit closed 2 years ago

kumar-roheit commented 2 years ago

I have a time series data (using the one found at [https://www.kaggle.com/c/demand-forecasting-kernels-only/data] ). I am following the tutorial at https://github.com/unit8co/darts/blob/master/examples/02-multi-time-series-and-covariates.ipynb while trying to create a series (similar to line number 3 of the example) I am getting the below error.

ERROR | darts.timeseries | ValueError: The time index of the provided DataArray is missing the freq attribute, and the frequency cannot be inferred.

The codes I have done till this stage is imported the training data from the kernel and trying to create a timeseries to be fed into NBEATSModel. Note: df_darts is my train.csv from the Kaggle kernel

series = TimeSeries.from_dataframe(df_darts, 'date', 'sales') series.plot()

May I ask what am I doing wrong and how can I feed the data ? Thankyou for taking the time to read this.

kumar-roheit commented 2 years ago

My apologies I was looking at the incorrect example.