junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Write questionnaire data to data/interim.

labels
junos 2022-03-01 11:39:58 +01:00
parent b5a6317f4b
commit f13a91044d
2 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
rules/models.smk
View File

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

12
src/data/baseline_features.py
View File

@ -3,6 +3,7 @@ import pandas as pd
pid = snakemake.params["pid"] pid = snakemake.params["pid"]
requested_features = snakemake.params["features"] requested_features = snakemake.params["features"]
baseline_interim = pd.DataFrame(columns=["qid", "question", "score_original", "score"])
baseline_features = pd.DataFrame(columns=requested_features) baseline_features = pd.DataFrame(columns=requested_features)
question_filename = snakemake.params["question_filename"] question_filename = snakemake.params["question_filename"]
@ -93,7 +94,7 @@ if not participant_info.empty:
+ LIMESURVEY_JCQ_MIN + LIMESURVEY_JCQ_MIN
- limesurvey_demand.loc[rows_demand_reverse, "score_original"] - 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: if "demand" in requested_features:
baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[ baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
"score" "score"
@ -126,7 +127,7 @@ if not participant_info.empty:
+ LIMESURVEY_JCQ_MIN + LIMESURVEY_JCQ_MIN
- limesurvey_control.loc[rows_control_reverse, "score_original"] - 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: if "control" in requested_features:
baseline_features.loc[0, "limesurvey_control"] = limesurvey_control[ baseline_features.loc[0, "limesurvey_control"] = limesurvey_control[
"score" "score"
@ -170,6 +171,7 @@ if not participant_info.empty:
0, "limesurvey_demand_control_ratio_quartile" 0, "limesurvey_demand_control_ratio_quartile"
] = limesurvey_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")