Skip to content

Update estimate_infections_workflow vignette #1391

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
github-actions wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update estimate_infections_workflow vignette #1391

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified vignettes/estimate_infections_workflow-results-1.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
67 changes: 33 additions & 34 deletions vignettes/estimate_infections_workflow.Rmd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,12 +76,7 @@ As these will affect any results, it is worth spending some time investigating w

_EpiNow2_ works with different delays that apply to different parts of the infection and observation process.
They are defined using a common interface that involves functions that are named after the probability distributions, i.e. `LogNormal()`, `Gamma()`, etc.
For help with this function, see its manual page


``` r
?EpiNow2::Distributions
```
For help with this function, see its manual page (`?EpiNow2::Distributions`) or the [delays vignette](delays.html) for background on how EpiNow2 handles delay distributions.

In all cases, the distributions given can be *fixed* (i.e. have no uncertainty) or *variable* (i.e. have associated uncertainty).
For example, to define a fixed gamma distribution with mean 3, standard deviation (sd) 1 and maximum value 10, you would write
Expand Down Expand Up @@ -293,6 +288,10 @@ def <- estimate_infections(
rt = rt_opts(prior = rt_prior),
forecast = forecast_opts(horizon = 7)
)
#> Warning: There were 2 divergent transitions after warmup. See
#> https://mc-stan.org/misc/warnings.html#divergent-transitions-after-warmup
#> to find out why this is a problem and how to eliminate them.
#> Warning: Examine the pairs() plot to diagnose sampling problems
```

Alternatively, for production environments, we recommend using the `epinow()` function. It uses `estimate_infections()` internally and provides functionality for logging and saving results and plots in dedicated directories in the user's file system.
Expand Down Expand Up @@ -339,17 +338,17 @@ forecast_obj
#> Key: <date>
#> sample_id predicted observed forecast_date date horizon
#> <int> <num> <num> <Date> <Date> <num>
#> 1: 1 2223 2256 2020-04-21 2020-04-21 0
#> 2: 2 2568 2256 2020-04-21 2020-04-21 0
#> 3: 3 3309 2256 2020-04-21 2020-04-21 0
#> 4: 4 3337 2256 2020-04-21 2020-04-21 0
#> 5: 5 2710 2256 2020-04-21 2020-04-21 0
#> 1: 1 2155 2256 2020-04-21 2020-04-21 0
#> 2: 2 2242 2256 2020-04-21 2020-04-21 0
#> 3: 3 2833 2256 2020-04-21 2020-04-21 0
#> 4: 4 2679 2256 2020-04-21 2020-04-21 0
#> 5: 5 1786 2256 2020-04-21 2020-04-21 0
#> ---
#> 15996: 1996 2966 1739 2020-04-21 2020-04-28 7
#> 15997: 1997 1784 1739 2020-04-21 2020-04-28 7
#> 15998: 1998 1612 1739 2020-04-21 2020-04-28 7
#> 15999: 1999 2145 1739 2020-04-21 2020-04-28 7
#> 16000: 2000 1457 1739 2020-04-21 2020-04-28 7
#> 15996: 1996 3163 1739 2020-04-21 2020-04-28 7
#> 15997: 1997 2021 1739 2020-04-21 2020-04-28 7
#> 15998: 1998 3562 1739 2020-04-21 2020-04-28 7
#> 15999: 1999 1146 1739 2020-04-21 2020-04-28 7
#> 16000: 2000 2553 1739 2020-04-21 2020-04-28 7
score(forecast_obj)
#> Warning: Predictions appear to be integer-valued.
#> ! The log score uses kernel density estimation, which may not be appropriate
Expand All @@ -358,22 +357,22 @@ score(forecast_obj)
#> distributions.
#> forecast_date date horizon bias dss crps overprediction
#> <Date> <Date> <num> <num> <num> <num> <num>
#> 1: 2020-04-21 2020-04-21 0 0.5170 13.11080 214.9536 89.984
#> 2: 2020-04-21 2020-04-22 1 -0.6505 13.31003 305.8814 0.000
#> 3: 2020-04-21 2020-04-23 2 -0.8755 15.26973 657.2073 0.000
#> 4: 2020-04-21 2020-04-24 3 0.2560 13.38751 190.0780 28.593
#> 5: 2020-04-21 2020-04-25 4 -0.5490 13.53322 317.1630 0.000
#> 6: 2020-04-21 2020-04-26 5 0.3910 13.79891 254.7470 70.291
#> 7: 2020-04-21 2020-04-27 6 0.1640 13.68110 204.2124 12.438
#> 8: 2020-04-21 2020-04-28 7 0.4320 13.76404 252.2392 78.715
#> underprediction dispersion log_score mad ae_median se_mean
#> <num> <num> <num> <num> <num> <num>
#> 1: 0.000 124.9696 7.355158 527.8056 355.0 151293.38
#> 2: 190.593 115.2884 7.756721 475.1733 528.5 220416.63
#> 3: 529.589 127.6183 8.763339 539.6664 990.0 850682.48
#> 4: 0.000 161.4850 7.476291 688.6677 211.0 87562.73
#> 5: 166.370 150.7930 7.945295 643.4484 543.0 203621.15
#> 6: 0.000 184.4560 7.620958 768.7281 354.5 224057.86
#> 7: 0.000 191.7744 7.573535 795.4149 146.5 89926.22
#> 8: 0.000 173.5242 7.522562 733.8870 363.5 246446.22
#> 1: 2020-04-21 2020-04-21 0 0.5180 13.00240 206.9490 90.493
#> 2: 2020-04-21 2020-04-22 1 -0.7125 13.32726 306.9011 0.000
#> 3: 2020-04-21 2020-04-23 2 -0.8630 15.28418 655.3489 0.000
#> 4: 2020-04-21 2020-04-24 3 0.2795 13.41517 200.1155 34.763
#> 5: 2020-04-21 2020-04-25 4 -0.5360 13.49324 315.8515 0.000
#> 6: 2020-04-21 2020-04-26 5 0.4450 13.87591 284.8807 101.178
#> 7: 2020-04-21 2020-04-27 6 0.2085 13.67033 214.0379 21.604
#> 8: 2020-04-21 2020-04-28 7 0.4620 13.84288 275.3218 101.619
#> underprediction dispersion log_score mad ae_median se_mean
#> <num> <num> <num> <num> <num> <num>
#> 1: 0.000 116.4560 7.322814 498.1536 331.0 137832.9
#> 2: 199.369 107.5321 7.723186 456.6408 513.5 225721.4
#> 3: 526.699 128.6499 8.783905 533.7360 997.0 846521.4
#> 4: 0.000 165.3525 7.518136 681.2547 255.0 103217.3
#> 5: 161.075 154.7765 7.945730 632.3289 550.5 204575.7
#> 6: 0.000 183.7027 7.671799 791.7084 451.0 292471.7
#> 7: 0.000 192.4339 7.623054 820.6191 203.5 107934.9
#> 8: 0.000 173.7028 7.584995 739.8174 424.0 295036.4
```