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

Discard useless parameters and related code of example

pull/98/head
Meng Li 2020-08-17 10:48:15 -04:00
parent 123b78d438
commit 00385dc54d
2 changed files with 2 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
rules/models.smk
View File

@ -17,9 +17,7 @@ rule targets:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["TARGET_TABLE"] + "_raw.csv" participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["TARGET_TABLE"] + "_raw.csv"
params: params:
pid = "{pid}", pid = "{pid}",
summarised = "{summarised}", summarised = "{summarised}"
targets_ratio_threshold = config["PARAMS_FOR_ANALYSIS"]["TARGETS_RATIO_THRESHOLD"],
targets_value_threshold = config["PARAMS_FOR_ANALYSIS"]["TARGETS_VALUE_THRESHOLD"]
output: output:
"data/processed/{pid}/targets_{summarised}.csv" "data/processed/{pid}/targets_{summarised}.csv"
script: script:

11
src/models/targets.py
View File

@ -3,19 +3,10 @@ import numpy as np
pid = snakemake.params["pid"] pid = snakemake.params["pid"]
summarised = snakemake.params["summarised"] summarised = snakemake.params["summarised"]
targets_ratio_threshold = snakemake.params["targets_ratio_threshold"]
targets_value_threshold = snakemake.params["targets_value_threshold"]
participant_info = pd.read_csv(snakemake.input["participant_info"]) participant_info = pd.read_csv(snakemake.input["participant_info"])
if summarised == "summarised": if summarised == "summarised":
targets = pd.DataFrame(columns=["pid", "target"]) raise ValueError("Do not support summarised features for example dataset.")
if not participant_info.empty:
cesds = participant_info.loc[0, ["preop_cesd_total", "inpatient_cesd_total", "postop_cesd_total", "3month_cesd_total"]]
# targets: 1 => 50% (ceiling) or more of available CESD scores were 16 or higher; 0 => otherwise
num_threshold = int((cesds.count() + 1) * targets_ratio_threshold)
target = 1 if cesds.apply(lambda x : 1 if x >= targets_value_threshold else 0).sum() >= num_threshold else 0
targets.loc[0, :] = [pid, target]
elif summarised == "notsummarised": elif summarised == "notsummarised":
targets = participant_info[["local_date", "target"]] targets = participant_info[["local_date", "target"]]