From 685ed6a546149ee6fdef37cfd2359ca4b92dddcf Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Fri, 4 Feb 2022 17:37:00 +0100
Subject: [PATCH] Set up demographic data download.

---
 Snakefile                             |  1 +
 config.yaml                           | 14 ++++++++++++++
 rules/models.smk                      |  9 +++++++++
 src/data/download_demographic_data.py |  0
 4 files changed, 24 insertions(+)
 create mode 100644 rules/models.smk
 create mode 100644 src/data/download_demographic_data.py

diff --git a/Snakefile b/Snakefile
index 7dc5ad3a..a42f8b6d 100644
--- a/Snakefile
+++ b/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
diff --git a/config.yaml b/config.yaml
index 2817cba9..169ed5be 100644
--- a/config.yaml
+++ b/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]
diff --git a/rules/models.smk b/rules/models.smk
new file mode 100644
index 00000000..51212c0b
--- /dev/null
+++ b/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"
+
diff --git a/src/data/download_demographic_data.py b/src/data/download_demographic_data.py
new file mode 100644
index 00000000..e69de29b