TFB

TFB copied to clipboard

new metric: Mean Directional Accuracy; new benchmark: Repeat Last Known Value

1

Hi.. Please, can you add new metric Mean Directional Accuracy? In financial prediction like Exchange rate (Forex), predicting the direction (up/down) is more important than MSE. Because if the investor...

ericleonardo

How to extract the features for machine learning methods?

2

The paper mentions using traditional machine learning methods, such as LR (Logistic Regression) and RF (Random Forest). How did you extract the features for these methods?

isCopyman

What is the reason for not considering using the M5 dataset

1

The paper introduced the M3 and M4 datasets, but did not consider the M5 dataset. What is the reason for this consideration.

isCopyman

How to obtain the FORECAST_META.csv file?

1

Hello，Thank you for your open source work！When I followed the instructions to process my own dataset, and I'm using the git bash terminal in pycharm，I get the following error： So...

LETUSFLYLPF

Verify data correlation

5

Hello, I'd like to check if my data has strong correlations. How can I run this using your code block?

starry-ZRY

Using multiple variables to predict one of the single variables How to handle the data set？

1

In your examples, both multivariable and univariable, what should I do with the data? All I can think of so far is to add a linear layer after calling the...

jahaur1

About the results of Crossformer on PEMS dataset

4

Hi, I tried the script of the model Crossformer on the PEMS dataset, but the results I got are so different (considerable drops) compared with those reported in the paper,...

Luoauoa

Plot model predictions against target

11

Hi again ! From the csv generated following your 'steps_to_get_predict_and_actual_data.md' file, how do you manage to plot the predictions ? Do you have some chunk of codes I could reuse...

ARBrachet

json problem in pycharm

2

If I directly run the last line of code in the.sh file in the pycharm terminal.Such as python ./scripts/run_benchmark.py --config-path "rolling_forecast_config.json" --data-name-list "ETTh1.csv" --strategy-args '{"horizon": 720}' --model-name "time_series_library.DLinear" --model-hyper-params '{"batch_size":...

jahaur1

Statistics of Univariate datasets by domain

1

 Hello! Do you have the statistics of univariate datasets by domain? In the paper and on the website, I can only find them by frequency, but not by domain...

jdalonsos