Add age, gender, and language as features.

Move calculation of age from merge_baseline_data.py to baseline_features.py.

config.yaml

@@ -634,5 +634,5 @@ PARAMS_FOR_ANALYSIS:
                 results-survey358134_final.csv,  # Belgium 1
                 results-survey413767_final.csv  # Belgium 2
     ]
-    FEATURES: [age, gender]
+    FEATURES: [age, gender, startlanguage]
     CATEGORICAL_FEATURES: [gender]

src/data/baseline_features.py

@@ -4,3 +4,20 @@ pid = snakemake.params["pid"]
 requested_features = snakemake.params["features"]
 baseline_features = pd.DataFrame(columns=requested_features)
 
+participant_info = pd.read_csv(snakemake.input[0], parse_dates=["date_of_birth"])
+if not participant_info.empty:
+    if "age" in requested_features:
+        now = pd.Timestamp("now")
+        baseline_features.loc[0, "age"] = (
+            now - participant_info.loc[0, "date_of_birth"]
+        ).dt.days / 365.25245
+    if "gender" in requested_features:
+        baseline_features.loc[0, "gender"] = participant_info.loc[0, "gender"]
+    if "startlanguage" in requested_features:
+        baseline_features.loc[0, "startlanguage"] = participant_info.loc[
+            0, "startlanguage"
+        ]
+
+baseline_features.to_csv(
+    snakemake.output[0], index=False, encoding="utf-8",
+)

src/data/merge_baseline_data.py

@@ -24,10 +24,6 @@ baseline = (
 )
 
 baseline.rename(columns=VARIABLES_TO_TRANSLATE, copy=False, inplace=True)
-now = pd.Timestamp("now")
-baseline = baseline.assign(
-    age=lambda x: (now - x.date_of_birth).dt.days / 365.25245,
-)
 
 baseline.to_csv(snakemake.output[0],
                 index=False,