Rename baseline features AGAIN.

Correct other mistakes.

Snakefile

@@ -415,7 +415,7 @@ for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys():
 
 # Baseline features
 if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]:
-    files_to_compute.extend("data/raw/baseline_merged.csv")
+    files_to_compute.extend(expand("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"]))
@@ -423,7 +423,9 @@ if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]:
 # Targets (labels)
 if config["PARAMS_FOR_ANALYSIS"]["TARGET"]["COMPUTE"]:
     files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/input.csv", pid=config["PIDS"]))
-    files_to_compute.extend("data/processed/models/population_model/input.csv")
+    files_to_compute.extend(expand("data/processed/models/population_model/input.csv"))
+
+#files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv", pid=config["PIDS"], cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"]))
 
 rule all:
     input:

rules/models.smk

@@ -54,7 +54,7 @@ rule model_individual_baselines:
         "data/processed/models/individual_model/{pid}/input.csv"
     params:
         cv_method = "{cv_method}",
-        colnames_demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["FEATURES"],
+        colnames_demographic_features = config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["FEATURES"],
     output:
         "data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv"
     log:

src/data/baseline_features.py

@@ -60,15 +60,15 @@ if not participant_info.empty:
             0, "startlanguage"
         ]
     if (
-        ("demand" in requested_features)
-        or ("control" in requested_features)
-        or ("demand_control_ratio" in requested_features)
+        ("limesurvey_demand" in requested_features)
+        or ("limesurvey_control" in requested_features)
+        or ("limesurvey_demand_control_ratio" in requested_features)
     ):
         participant_info_t = participant_info.T
         rows_baseline = participant_info_t.index
 
-        if ("demand" in requested_features) or (
-            "demand_control_ratio" in requested_features
+        if ("limesurvey_demand" in requested_features) or (
+            "limesurvey_demand_control_ratio" in requested_features
         ):
             # Find questions about demand, but disregard time (duration of filling in questionnaire)
             rows_demand = rows_baseline.str.startswith(
@@ -96,12 +96,12 @@ if not participant_info.empty:
             )
             baseline_interim = pd.concat([baseline_interim, limesurvey_demand], axis=0, ignore_index=True)
             if "demand" in requested_features:
-                baseline_features.loc[0, "demand"] = limesurvey_demand[
+                baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
                     "score"
                 ].sum()
 
-        if ("control" in requested_features) or (
-            "demand_control_ratio" in requested_features
+        if ("limesurvey_control" in requested_features) or (
+            "limesurvey_demand_control_ratio" in requested_features
         ):
             # Find questions about control, but disregard time (duration of filling in questionnaire)
             rows_control = rows_baseline.str.startswith(
@@ -130,12 +130,12 @@ if not participant_info.empty:
 
             baseline_interim = pd.concat([baseline_interim, limesurvey_control], axis=0, ignore_index=True)
 
-            if "control" in requested_features:
-                baseline_features.loc[0, "control"] = limesurvey_control[
+            if "limesurvey_control" in requested_features:
+                baseline_features.loc[0, "limesurvey_control"] = limesurvey_control[
                     "score"
                 ].sum()
 
-        if "demand_control_ratio" in requested_features:
+        if "limesurvey_demand_control_ratio" in requested_features:
             limesurvey_demand_control_ratio = (
                 limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
             )
@@ -167,10 +167,10 @@ if not participant_info.empty:
                 limesurvey_quartile = np.nan
 
             baseline_features.loc[
-                0, "demand_control_ratio"
+                0, "limesurvey_demand_control_ratio"
             ] = limesurvey_demand_control_ratio
             baseline_features.loc[
-                0, "demand_control_ratio_quartile"
+                0, "limesurvey_demand_control_ratio_quartile"
             ] = limesurvey_quartile
 
 if not baseline_interim.empty: