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

Delete mystudy.snakefile and add all rules to models.snakefile

pull/95/head
Meng Li 2020-07-29 15:25:26 -04:00
parent 8d71329e0e
commit 21c3251066
3 changed files with 36 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Snakefile
View File

@ -4,7 +4,6 @@ include: "rules/preprocessing.snakefile"
include: "rules/features.snakefile"
include: "rules/models.snakefile"
include: "rules/reports.snakefile"
include: "rules/mystudy.snakefile" # You can add snakfiles with rules tailored to your project
import itertools

36
rules/models.snakefile
View File

@ -1,5 +1,41 @@
ruleorder: nan_cells_ratio_of_cleaned_features > merge_features_and_targets
rule days_to_analyse:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
params:
days_before_surgery = "{days_before_surgery}",
days_in_hospital = "{days_in_hospital}",
days_after_discharge= "{days_after_discharge}"
output:
"data/interim/{pid}/days_to_analyse_{days_before_surgery}_{days_in_hospital}_{days_after_discharge}.csv"
script:
"../src/models/select_days_to_analyse.py"
rule targets:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
params:
pid = "{pid}",
summarised = "{summarised}",
targets_ratio_threshold = config["PARAMS_FOR_ANALYSIS"]["TARGETS_RATIO_THRESHOLD"],
targets_value_threshold = config["PARAMS_FOR_ANALYSIS"]["TARGETS_VALUE_THRESHOLD"]
output:
"data/processed/{pid}/targets_{summarised}.csv"
script:
"../src/models/targets.py"
rule demographic_features:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
params:
pid = "{pid}",
features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC_FEATURES"]
output:
"data/processed/{pid}/demographic_features.csv"
script:
"../src/features/demographic_features.py"
def input_merge_features_of_single_participant(wildcards):
if wildcards.source == "phone_fitbit_features":
return expand("data/processed/{pid}/{features}_{day_segment}.csv", pid=wildcards.pid, features=config["PARAMS_FOR_ANALYSIS"]["PHONE_FEATURES"] + config["PARAMS_FOR_ANALYSIS"]["FITBIT_FEATURES"], day_segment=wildcards.day_segment)

35
rules/mystudy.snakefile
View File

@ -1,35 +0,0 @@
rule days_to_analyse:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
params:
days_before_surgery = "{days_before_surgery}",
days_in_hospital = "{days_in_hospital}",
days_after_discharge= "{days_after_discharge}"
output:
"data/interim/{pid}/days_to_analyse_{days_before_surgery}_{days_in_hospital}_{days_after_discharge}.csv"
script:
"../src/models/select_days_to_analyse.py"
rule targets:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
params:
pid = "{pid}",
summarised = "{summarised}",
targets_ratio_threshold = config["PARAMS_FOR_ANALYSIS"]["TARGETS_RATIO_THRESHOLD"],
targets_value_threshold = config["PARAMS_FOR_ANALYSIS"]["TARGETS_VALUE_THRESHOLD"]
output:
"data/processed/{pid}/targets_{summarised}.csv"
script:
"../src/models/targets.py"
rule demographic_features:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
params:
pid = "{pid}",
features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC_FEATURES"]
output:
"data/processed/{pid}/demographic_features.csv"
script:
"../src/features/demographic_features.py"