Incorporate DB query for usernames into snakemake workflow.

config.yaml

@@ -7,16 +7,16 @@ PIDS: [nokia_0000003]
 
 # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
 CREATE_PARTICIPANT_FILES:
-  USERNAMES_CSV: "data/external/example_usernames.csv"
-  CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
+  USERNAMES_CSV: "data/external/main_study_usernames.csv"
+  CSV_FILE_PATH: "data/external/main_study_participants.csv" # see docs for required format
   PHONE_SECTION:
     ADD: True
     IGNORED_DEVICE_IDS: []
   FITBIT_SECTION:
-    ADD: True
+    ADD: False
     IGNORED_DEVICE_IDS: []
   EMPATICA_SECTION:
-    ADD: True
+    ADD: False
     IGNORED_DEVICE_IDS: []
 
 # See https://www.rapids.science/latest/setup/configuration/#time-segments

environment.yml

@@ -1,4 +1,4 @@
-name: rapids202108
+name: rapids
 channels:
   - conda-forge
   - defaults
@@ -13,8 +13,8 @@ dependencies:
   - blas=1.0
   - brotlipy=0.7.0
   - bzip2=1.0.8
-  - ca-certificates=2021.7.5
-  - certifi=2021.5.30
+  - ca-certificates
+  - certifi
   - cffi=1.14.4
   - chardet=3.0.4
   - click=7.1.2
@@ -56,20 +56,23 @@ dependencies:
   - numpy=1.19.2
   - numpy-base=1.19.2
   - openblas=0.3.4
-  - openssl=1.1.1k
+  - openssl
   - pandas=1.1.5
   - pbr=5.5.1
   - pip=20.3.3
   - plotly=4.14.1
   - poyo=0.5.0
   - psutil=5.7.2
+  - psycopg2
   - py-xgboost=0.90
   - pycparser=2.20
   - pyerfa=1.7.1.1
   - pyopenssl=20.0.1
+  - pyprojroot
   - pysocks=1.7.1
   - python=3.7.9
   - python-dateutil=2.8.1
+  - python-dotenv
   - python_abi=3.7
   - pytz=2020.4
   - pyyaml=5.3.1
@@ -82,6 +85,7 @@ dependencies:
   - six=1.15.0
   - smmap=3.0.4
   - smmap2=3.0.1
+  - sqlalchemy
   - sqlite=3.33.0
   - threadpoolctl=2.1.0
   - tk=8.6.10

rules/preprocessing.smk

@@ -4,6 +4,15 @@ rule create_example_participant_files:
     shell:
         "echo 'PHONE:\n  DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524]\n  PLATFORMS: [android]\n  LABEL: test-01\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\nFITBIT:\n  DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524]\n  LABEL: test-01\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\n' >> ./data/external/participant_files/example01.yaml && echo 'PHONE:\n  DEVICE_IDS: [13dbc8a3-dae3-4834-823a-4bc96a7d459d]\n  PLATFORMS: [ios]\n  LABEL: test-02\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\nFITBIT:\n  DEVICE_IDS: [13dbc8a3-dae3-4834-823a-4bc96a7d459d]\n  LABEL: test-02\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\n' >> ./data/external/participant_files/example02.yaml"
 
+rule query_device_empatica_ids:
+    params:
+        baseline_folder = "/mnt/e/STRAWbaseline/"
+    output:
+        usernames_file = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"],
+        timezone_file = "data/external/timezone.csv"
+    script:
+        "../../participants/prepare_usernames_file.py"
+
 rule prepare_participants_csv:
     input:
         username_list = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"]