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

Start calculating demand control features.

labels
junos 2022-02-23 19:08:10 +01:00
parent 9a74e74d08
commit 30ac8b1cd5
3 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
config.yaml
View File

@ -634,5 +634,6 @@ PARAMS_FOR_ANALYSIS:
results-survey358134_final.csv, # Belgium 1 results-survey358134_final.csv, # Belgium 1
results-survey413767_final.csv # Belgium 2 results-survey413767_final.csv # Belgium 2
] ]
QUESTION_LIST: survey637813+question_text.csv
FEATURES: [age, gender, startlanguage] FEATURES: [age, gender, startlanguage]
CATEGORICAL_FEATURES: [gender] CATEGORICAL_FEATURES: [gender]

3
rules/models.smk
View File

@ -20,7 +20,8 @@ rule baseline_features:
"data/raw/{pid}/participant_baseline_raw.csv" "data/raw/{pid}/participant_baseline_raw.csv"
params: params:
pid="{pid}", pid="{pid}",
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"]
output: output:
"data/processed/features/{pid}/baseline_features.csv" "data/processed/features/{pid}/baseline_features.csv"
script: script:

15
src/data/baseline_features.py
View File

@ -3,6 +3,13 @@ import pandas as pd
pid = snakemake.params["pid"] pid = snakemake.params["pid"]
requested_features = snakemake.params["features"] requested_features = snakemake.params["features"]
baseline_features = pd.DataFrame(columns=requested_features) baseline_features = pd.DataFrame(columns=requested_features)
question_filename = snakemake.params["question_filename"]
dict_JCQ_demand_control_reverse = {
"demand_0": " [Od mene se ne zahteva,",
"demand_1": " [Imam dovolj časa, da končam",
"demand_2": " [Pri svojem delu se ne srečujem s konfliktnimi"
}
participant_info = pd.read_csv(snakemake.input[0], parse_dates=["date_of_birth"]) participant_info = pd.read_csv(snakemake.input[0], parse_dates=["date_of_birth"])
if not participant_info.empty: if not participant_info.empty:
@ -17,6 +24,14 @@ if not participant_info.empty:
baseline_features.loc[0, "startlanguage"] = participant_info.loc[ baseline_features.loc[0, "startlanguage"] = participant_info.loc[
0, "startlanguage" 0, "startlanguage"
] ]
if "demand" in requested_features:
limesurvey_questions = pd.read_csv(question_filename, header=None).T
limesurvey_questions[["code", "text"]] = limesurvey_questions[0].str.split(r"\.\s", expand=True, n=1)
demand_reverse_lime_rows = limesurvey_questions["text"].str.startswith(dict_JCQ_demand_control_reverse["demand_0"]) | \
limesurvey_questions["text"].str.startswith(dict_JCQ_demand_control_reverse["demand_1"]) | \
limesurvey_questions["text"].str.startswith(dict_JCQ_demand_control_reverse["demand_2"])
demand_reverse_lime = limesurvey_questions[demand_reverse_lime_rows]
demand_reverse_lime.loc[:, "qid"] = demand_reverse_lime["code"].str.extract(r"\[(\d+)\]")
baseline_features.to_csv( baseline_features.to_csv(
snakemake.output[0], index=False, encoding="utf-8", snakemake.output[0], index=False, encoding="utf-8",