[WIP] Add a rule to parse targets.

Does nothing for now.

Snakefile

@@ -415,11 +415,15 @@ for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys():
 
 # Baseline features
 if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]:
-    files_to_compute.extend(expand("data/raw/baseline_merged.csv"))
+    files_to_compute.extend("data/raw/baseline_merged.csv")
     files_to_compute.extend(expand("data/raw/{pid}/participant_baseline_raw.csv", pid=config["PIDS"]))
     files_to_compute.extend(expand("data/interim/{pid}/baseline_questionnaires.csv", pid=config["PIDS"]))
     files_to_compute.extend(expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]))
 
+# Targets (labels)
+if config["PARAMS_FOR_ANALYSIS"]["TARGET"]["COMPUTE"]:
+    files_to_compute.extend(expand("data/processed/targets/{pid}/parsed_targets.csv", pid=config["PIDS"]))
+
 rule all:
     input:
         files_to_compute

config.yaml

@@ -649,5 +649,6 @@ PARAMS_FOR_ANALYSIS:
     CATEGORICAL_FEATURES: [gender]
 
   TARGET:
+    COMPUTE: True
     SCALE: [positive_affect, negative_affect]
 

rules/models.smk

@@ -27,3 +27,12 @@ rule baseline_features:
         features="data/processed/features/{pid}/baseline_features.csv"
     script:
         "../src/data/baseline_features.py"
+
+rule parse_targets:
+    input:
+        targets = "data/processed/features/{pid}/phone_esm.csv",
+        time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv"
+    output:
+        "data/processed/targets/{pid}/parsed_targets.csv"
+    script:
+        "../src/models/parse_targets.py"

src/models/parse_targets.py

@@ -0,0 +1,6 @@
+import pandas as pd
+
+
+targets = pd.read_csv(snakemake.input["targets"])
+
+targets.to_csv(snakemake.output[0], index=False)