Write questionnaire data to data/interim.

Snakefile

@@ -406,6 +406,7 @@ for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys():
 # Baseline features
 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"]))
 
 rule all:

config.yaml

@@ -635,5 +635,5 @@ PARAMS_FOR_ANALYSIS:
                 results-survey413767_final.csv  # Belgium 2
     ]
     QUESTION_LIST: survey637813+question_text.csv
-    FEATURES: [age, gender, startlanguage]
+    FEATURES: [age, gender, startlanguage, demand, control, demand_control_ratio]
     CATEGORICAL_FEATURES: [gender]

rules/models.smk

@@ -23,6 +23,7 @@ rule baseline_features:
         features=config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["FEATURES"],
         question_filename=config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["FOLDER"] + "/" + config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["QUESTION_LIST"]
     output:
-        "data/processed/features/{pid}/baseline_features.csv"
+        interim="data/interim/{pid}/baseline_questionnaires.csv",
+        features="data/processed/features/{pid}/baseline_features.csv"
     script:
         "../src/data/baseline_features.py"

src/data/baseline_features.py

@@ -3,6 +3,7 @@ import pandas as pd
 
 pid = snakemake.params["pid"]
 requested_features = snakemake.params["features"]
+baseline_interim = pd.DataFrame(columns=["qid", "question", "score_original", "score"])
 baseline_features = pd.DataFrame(columns=requested_features)
 question_filename = snakemake.params["question_filename"]
 
@@ -93,7 +94,7 @@ if not participant_info.empty:
                 + LIMESURVEY_JCQ_MIN
                 - limesurvey_demand.loc[rows_demand_reverse, "score_original"]
             )
-            # TODO Write to data/interim
+            pd.concat([baseline_interim, limesurvey_demand], axis=0, ignore_index=True)
             if "demand" in requested_features:
                 baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
                     "score"
@@ -126,7 +127,7 @@ if not participant_info.empty:
                 + LIMESURVEY_JCQ_MIN
                 - limesurvey_control.loc[rows_control_reverse, "score_original"]
             )
-            # TODO Write to data/interim
+            pd.concat([baseline_interim, limesurvey_control], axis=0, ignore_index=True)
             if "control" in requested_features:
                 baseline_features.loc[0, "limesurvey_control"] = limesurvey_control[
                     "score"
@@ -170,6 +171,7 @@ if not participant_info.empty:
                 0, "limesurvey_demand_control_ratio_quartile"
             ] = limesurvey_quartile
 
-baseline_features.to_csv(
+if not baseline_interim.empty:
-    snakemake.output[0], index=False, encoding="utf-8",
+    baseline_interim.to_csv(snakemake.output["interim"], index=False, encoding="utf-8")
-)
+
+baseline_features.to_csv(snakemake.output["features"], index=False, encoding="utf-8")