nixtla icon indicating copy to clipboard operation
nixtla copied to clipboard

[FIX] Colab-flag

Open elephaint opened this issue 9 months ago • 5 comments

  • Adds Colab flags to all notebooks
  • Adds Colab badge to capabilities notebooks

elephaint avatar May 08 '24 15:05 elephaint

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.935 199.132 2571.33 10604.2
total_time 4.1452 3.7495 0.0084 0.005

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.22 4110.79 5928.17 18859.2
total_time 2.6003 2.6576 0.0061 0.0049

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 2.125 3.2458 0.0078 0.0067

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 3.4025 2.0701 0.0075 0.007

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 5.3645 3.8609 0.0075 0.007

Plot:

github-actions[bot] avatar May 08 '24 15:05 github-actions[bot]

thank you so much @elephaint, it seems it involved a lot of effort. i'm very sorry about asking a change to his pr, but would you be open to implementing the following logic? i think it can improve readability and might be easier to maintain:

  • define IN_COLAB = 'google.colab' in sys.modules in nixtla/utils so we can import it instead of defining each time.
  • import all the required deps for colab in one cell:
#| hide
if not IN_COLAB:
    from nixtla.utils import colab_badge
    rom dotenv import load_dotenv

@AzulGarza in Colab nixtla is not installed, so we can't import IN_COLAB when it's part of nixtla. Unless the first line in Colab is %pip install nixtla', but then we can't make that install conditional on being in Colab. I can include %pip install nixtla`as first line everywhere? Let me know what you think.

I refactored based on your second comment, good point!

elephaint avatar May 09 '24 06:05 elephaint

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 3.1936 4.3738 0.0084 0.0045

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 3.7778 3.3405 0.005 0.0043

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 4.7668 3.1739 0.0072 0.0063

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 4.3474 4.2618 0.0067 0.0066

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 5.8297 3.7943 0.007 0.0066

Plot:

github-actions[bot] avatar May 09 '24 07:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 22.3491 7.1195 0.0082 0.0045

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 8.9854 13.1764 0.0054 0.0044

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 13.794 15.2337 0.0075 0.0067

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835121 422332 656723 3.17316e+06
total_time 13.924 16.3337 0.0071 0.0065

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 21.4664 24.5086 0.0069 0.0064

Plot:

github-actions[bot] avatar May 09 '24 07:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 31.292 29.183 0.0083 0.0045

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 33.5923 38.7194 0.0054 0.0046

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 46.7641 35.2284 0.0074 0.0064

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 76.2885 42.9577 0.0072 0.0065

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 34.1787 37.6032 0.0071 0.0066

Plot:

github-actions[bot] avatar May 10 '24 08:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 1.9095 2.3632 0.0079 0.0044

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 3.0912 3.1779 0.0052 0.0045

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 2.2364 2.3899 0.0076 0.0064

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 3.9291 3.9888 0.0069 0.0064

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 4.1406 4.102 0.0071 0.0066

Plot:

github-actions[bot] avatar May 10 '24 09:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 3.5778 3.025 0.0083 0.0044

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 2.7831 2.3123 0.0055 0.0046

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 3.6664 2.0793 0.0075 0.0077

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 3.1448 5.2197 0.007 0.0064

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 4.0553 4.5764 0.007 0.0063

Plot:

github-actions[bot] avatar May 10 '24 10:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 4.3805 2.9556 0.0093 0.0045

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 2.9246 4.1057 0.0052 0.0046

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 4.8346 4.5169 0.0076 0.0066

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 4.1531 4.1328 0.007 0.0065

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 5.0645 2.8309 0.007 0.0065

Plot:

github-actions[bot] avatar May 10 '24 10:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 2.2521 1.8874 0.008 0.0045

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 3.3003 3.8466 0.0055 0.0047

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 3.3213 4.2079 0.0072 0.0077

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 4.0322 3.6455 0.007 0.0065

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 4.7531 3.905 0.0073 0.0067

Plot:

github-actions[bot] avatar May 10 '24 10:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 4.3843 2.8333 0.008 0.0043

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 2.9206 3.0044 0.0051 0.0043

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 1.9822 4.3807 0.0071 0.0061

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 4.0309 3.1283 0.0069 0.0062

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 4.2844 4.5795 0.007 0.0065

Plot:

github-actions[bot] avatar May 10 '24 10:05 github-actions[bot]

Experiment Results

Experiment 1: air-passengers

Description:

variable experiment
h 12
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 12.6793 11.0623 47.8333 76
mape 0.027 0.0232 0.0999 0.1425
mse 213.936 199.132 2571.33 10604.2
total_time 2.1644 3.2636 0.008 0.0044

Plot:

Experiment 2: air-passengers

Description:

variable experiment
h 24
season_length 12
freq MS
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 58.1031 58.4587 71.25 115.25
mape 0.1257 0.1267 0.1552 0.2358
mse 4040.21 4110.79 5928.17 18859.2
total_time 3.1592 4.7292 0.0051 0.0042

Plot:

Experiment 3: electricity-multiple-series

Description:

variable experiment
h 24
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 178.293 196.363 269.23 1331.02
mape 0.0234 0.0234 0.0304 0.1692
mse 121588 123119 213677 4.68961e+06
total_time 3.3469 2.3723 0.0074 0.0063

Plot:

Experiment 4: electricity-multiple-series

Description:

variable experiment
h 168
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 465.532 353.528 398.956 1119.26
mape 0.062 0.0454 0.0512 0.1583
mse 835120 422332 656723 3.17316e+06
total_time 3.4133 4.829 0.0077 0.0099

Plot:

Experiment 5: electricity-multiple-series

Description:

variable experiment
h 336
season_length 24
freq H
level None
n_windows 1

Results:

metric timegpt-1 timegpt-1-long-horizon SeasonalNaive Naive
mae 558.649 361.033 602.926 1340.95
mape 0.0697 0.046 0.0787 0.17
mse 1.22721e+06 441118 1.61572e+06 6.04619e+06
total_time 4.4506 5.1124 0.0068 0.0061

Plot:

github-actions[bot] avatar May 13 '24 07:05 github-actions[bot]