Commit Graph

1458 Commits (imputation_and_cleaning)

Author SHA1 Message Date
Sam 10e896ca1d
Add data stream for AWARE Micro server (#173)
* Add data stream for AWARE Micro server

* Fix one documentation typo and one ommission
2022-01-27 10:47:50 -05:00
junos afa3b8546f Mutate data in an R script.
The Python script did not read the timestamp correctly for some reason. All timestamps were 0.
2022-01-26 16:34:19 +01:00
junos 1efb8e3112 Clean features across participants.
Explore the best linear regression feature.
2022-01-19 13:41:09 +01:00
Sam e5dbbfce44
Avoid NA problem in barnett location evaluation (#172)
* Avoid occasional issue where does_not_span evaluates to NA, which breaks the if()

* Restored original warning
2022-01-18 10:16:37 -05:00
Sam 8ae26fb845
Fixes issue where 'duration' in the 'ios_calls' dataframe is seen as a character type. (#171) 2022-01-18 10:15:53 -05:00
junos b17a7eff1a Deal with inexplicable snakemake failure. 2022-01-07 18:11:38 +01:00
junos 2fb068cb8b Do not calculate accelerometer features.
Add data cleaning.
2022-01-07 12:20:51 +01:00
junos e1499a5ae2 Account for missing device_ids. 2021-12-15 20:41:28 +01:00
junos b29f902915 Look into ESM table for device_id. 2021-12-15 20:18:12 +01:00
junos c03ee788f6 Add missing dependencies for caret and corrr. 2021-12-15 19:26:16 +01:00
junos 5a9252e46e Merge remote-tracking branch 'origin/master' 2021-12-15 18:32:36 +01:00
junos e5cc02501f Set the timezone.csv path in config.
Take into account that TZCODES_FILE can be created with a rule.
2021-12-15 18:09:30 +01:00
junos 352598f3da Use absolute path to avoid RuleException. 2021-12-15 17:27:13 +01:00
junos 15653b6e70 Add forgotten line for hashed app names in config. 2021-12-15 17:26:54 +01:00
junos a66a7d0cc3 Keep track of warning messages.
These are not runtime errors, but might still indicate a problem.
2021-12-15 16:19:29 +01:00
junos 70cada8bb8 Consider a subset of columns when dropping. 2021-12-15 16:14:33 +01:00
junos d2ed73dccf Debug ValueError for index.
See exploration/debug_heatmap.py for illustration.
2021-12-15 16:03:04 +01:00
junos 6f451e05ac Bring back application_name.
This column still needs to be in the data, so add it in app_add_name.py.
Later, join categories by package hash.
2021-12-15 12:58:27 +01:00
junos 4485c4c95e Delete columns we don't have.
Rename light table.
Correct timesegments.
2021-12-08 20:02:47 +01:00
junos 633384c6a9 Use all available sensors for PHONE_YIELD. 2021-12-08 19:04:19 +01:00
junos 8e2222f307 Bring back deleted lines which are required. 2021-12-08 18:59:10 +01:00
junos 712ff74898 Set table names and calculate all relevant features. 2021-12-08 18:37:34 +01:00
junos 1f54195437 Configure timezone file to be created automatically. 2021-12-08 18:21:29 +01:00
junos 2b52f686b3 Define daily segments. 2021-12-08 18:20:22 +01:00
junos 22513415e9 Do not ask for specific patch numbers of libraries! 2021-12-03 14:38:25 +01:00
junos 0b8a493ff2 Incorporate mulitple timezones into RAPIDS. 2021-12-01 18:20:27 +01:00
junos f0d29d0d1a Incorporate DB query for usernames into snakemake workflow. 2021-12-01 18:14:27 +01:00
junos 37b3460b76 Use Empatica wristband numbers as provided in CSV. 2021-12-01 17:20:57 +01:00
junos 22f9e0722d Start preparing the true usernames CSV file. 2021-12-01 11:29:22 +01:00
junos 0be4cd5a8f Remove unnecessary library. 2021-11-30 17:08:07 +01:00
junos b99a3c19ed Update dbplyr to the latest version.
distinct changed its behaviour from 2.0.0 to 2.1.0.
2021-11-29 18:34:26 +01:00
junos 04ad2d0b81 Source specific container script.
It is probably not worth the effort of making this general.
2021-11-29 18:19:47 +01:00
junos da5ff0f36e Correct small errors in settings. 2021-11-29 18:04:06 +01:00
junos 35d9779026 Prepare the tibble in requested format.
Write it to a CSV file.
2021-11-29 17:54:16 +01:00
junos 32025cbd8c Start with a tibble from CSV. 2021-11-29 17:51:07 +01:00
junos 181e4f0118 Add parameters to yaml file.
And use these in the prepare_participants_file function.
2021-11-29 16:57:50 +01:00
junos 39bd244511 [WIP] Prepare yaml files.
These will be used to create participants files.
2021-11-24 19:11:19 +01:00
junos ab84109d55 Prepare a function to compile participants data.
It combines functions from container.R
2021-11-24 19:07:56 +01:00
junos f9863ec622 Fix small mistakes. 2021-11-24 19:01:30 +01:00
junos c1f56c61e8 Add a function to pull start and end datetimes. 2021-11-24 18:33:06 +01:00
junos 3acf6ece14 Add a function to pull device IDs. 2021-11-24 18:23:53 +01:00
junos 8b2717122d Add a function to get participants' IDs. 2021-11-24 18:05:17 +01:00
Meng Li 9338f77ae6 Update docs for Git Flow section & RAPIDS paper info 2021-11-19 13:57:10 -05:00
Meng Li 5bad3eb8b5
Data cleaning (#166)
* Refactor data cleaning module: move it from example workflow to main directory

* Replace NAs with 0 in selected event-based features

* Add one step to drop highly correlated features

Co-authored-by: Weiyu <weiyuhuang7@gmail.com>
2021-11-19 10:34:36 -05:00
Meng Li 296960f425 Fix the bug of location doryab features when a participant is moving during the whole time segment 2021-11-18 18:42:19 -05:00
Meng Li 3d34036eae
Add firststeptime and laststeptime features to FITBIT_STEPS_INTRADAY RAPIDS provider (#168)
* Add firststeptime and laststeptime features to FITBIT_STEPS_INTRADAY RAPIDS provider

* Update test config files
2021-11-18 18:35:27 -05:00
junos ed193d2290 Revert "Correct the name of a field."
This reverts commit b335561a55.

It was actually correct.
2021-11-17 19:16:35 +01:00
junos 24b11ea101 Force Unix style end of line. 2021-11-17 19:12:40 +01:00
junos 4829b155d5 Make config changes for minimal workflow. 2021-11-17 18:53:44 +01:00
junos b335561a55 Correct the name of a field. 2021-11-17 18:50:06 +01:00