Set up demographic data download.

Snakefile

@@ -5,6 +5,7 @@ include: "rules/common.smk"
 include: "rules/renv.smk"
 include: "rules/preprocessing.smk"
 include: "rules/features.smk"
+include: "rules/models.smk"
 include: "rules/reports.smk"
 
 import itertools

config.yaml

@@ -622,3 +622,17 @@ ALL_CLEANING_OVERALL:
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R
+
+########################################################################################################################
+#                                              Analysis Workflow Example                                               #
+########################################################################################################################
+
+PARAMS_FOR_ANALYSIS:
+  DEMOGRAPHIC:
+    FOLDER: E:/STRAWbaseline
+    CONTAINER: [results-survey637813_final.csv,  # Slovenia
+                results-survey358134_final.csv,  # Belgium 1
+                results-survey413767_final.csv  # Belgium 2
+    ]
+    FEATURES: [age, gender]
+    CATEGORICAL_FEATURES: [gender]

rules/models.smk

@@ -0,0 +1,9 @@
+rule download_demographic_data:
+    input:
+        participant_file = "data/external/participant_files/{pid}.yaml",
+        data = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["FOLDER"] + "/" + config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["CONTAINER"]
+    output:
+        "data/raw/{pid}/participant_baseline_raw.csv"
+    script:
+        "../src/data/download_demographic_data.py"
+