Rename merge metrics for models and add filter valid sensed days
Co-authored-by: Meng Li <AnnieLM1996@gmail.com>pull/95/head
parent
63310b7b90
commit
3d4c26754e
|
@ -107,6 +107,3 @@ reports/
|
||||||
*.Rproj
|
*.Rproj
|
||||||
.RData
|
.RData
|
||||||
.Rhistory
|
.Rhistory
|
||||||
|
|
||||||
# analysis part
|
|
||||||
models/*
|
|
|
@ -57,11 +57,11 @@ rule all:
|
||||||
pid = config["PIDS"],
|
pid = config["PIDS"],
|
||||||
day_segment = config["STEP"]["DAY_SEGMENTS"]),
|
day_segment = config["STEP"]["DAY_SEGMENTS"]),
|
||||||
# Models
|
# Models
|
||||||
expand("models/input/merged_single_participant/{pid}/{source}_{day_segment}.csv",
|
expand("data/processed/{pid}/metrics_for_individual_model/{source}_{day_segment}.csv",
|
||||||
pid = config["PIDS"],
|
pid = config["PIDS"],
|
||||||
source = config["METRICS_FOR_ANALYSIS"]["SOURCES"],
|
source = config["METRICS_FOR_ANALYSIS"]["SOURCES"],
|
||||||
day_segment = config["METRICS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
|
day_segment = config["METRICS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
|
||||||
expand("models/input/merged_all_participants/{source}_{day_segment}.csv",
|
expand("data/processed/metrics_for_population_model/{source}_{day_segment}.csv",
|
||||||
source = config["METRICS_FOR_ANALYSIS"]["SOURCES"],
|
source = config["METRICS_FOR_ANALYSIS"]["SOURCES"],
|
||||||
day_segment = config["METRICS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
|
day_segment = config["METRICS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
|
||||||
# Reports
|
# Reports
|
||||||
|
|
|
@ -130,3 +130,4 @@ METRICS_FOR_ANALYSIS:
|
||||||
PHONE_METRICS: [accelerometer, applications_foreground, battery, call_incoming, call_missed, call_outgoing, google_activity_recognition, light, location_barnett, screen, sms_received, sms_sent]
|
PHONE_METRICS: [accelerometer, applications_foreground, battery, call_incoming, call_missed, call_outgoing, google_activity_recognition, light, location_barnett, screen, sms_received, sms_sent]
|
||||||
FITBIT_METRICS: [fitbit_heartrate, fitbit_step]
|
FITBIT_METRICS: [fitbit_heartrate, fitbit_step]
|
||||||
PHONE_FITBIT_METRICS: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
|
PHONE_FITBIT_METRICS: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
|
||||||
|
DROP_VALID_SENSED_DAYS: True
|
|
@ -4,18 +4,22 @@ def input_merge_metrics_of_single_participant(wildcards):
|
||||||
else:
|
else:
|
||||||
return expand("data/processed/{pid}/{metrics}_{day_segment}.csv", pid=wildcards.pid, metrics=config["METRICS_FOR_ANALYSIS"][wildcards.source.upper()], day_segment=wildcards.day_segment)
|
return expand("data/processed/{pid}/{metrics}_{day_segment}.csv", pid=wildcards.pid, metrics=config["METRICS_FOR_ANALYSIS"][wildcards.source.upper()], day_segment=wildcards.day_segment)
|
||||||
|
|
||||||
rule merge_metrics_of_single_participant:
|
rule merge_metrics_for_individual_model:
|
||||||
input:
|
input:
|
||||||
metric_files = input_merge_metrics_of_single_participant
|
metric_files = input_merge_metrics_of_single_participant,
|
||||||
|
phone_valid_sensed_days = "data/interim/{pid}/phone_valid_sensed_days.csv"
|
||||||
|
params:
|
||||||
|
drop_valid_sensed_days = config["METRICS_FOR_ANALYSIS"]["DROP_VALID_SENSED_DAYS"],
|
||||||
|
source = "{source}"
|
||||||
output:
|
output:
|
||||||
"models/input/merged_single_participant/{pid}/{source}_{day_segment}.csv"
|
"data/processed/{pid}/metrics_for_individual_model/{source}_{day_segment}.csv"
|
||||||
script:
|
script:
|
||||||
"../src/models/merge_metrics_of_single_participant.R"
|
"../src/models/merge_metrics_for_individual_model.R"
|
||||||
|
|
||||||
rule merge_metrics_of_all_participants:
|
rule merge_metrics_for_population_model:
|
||||||
input:
|
input:
|
||||||
metric_files = expand("models/input/merged_single_participant/{pid}/{{source}}_{{day_segment}}.csv", pid=config["PIDS"])
|
metric_files = expand("data/processed/{pid}/metrics_for_individual_model/{{source}}_{{day_segment}}.csv", pid=config["PIDS"])
|
||||||
output:
|
output:
|
||||||
"models/input/merged_all_participants/{source}_{day_segment}.csv"
|
"data/processed/metrics_for_population_model/{source}_{day_segment}.csv"
|
||||||
script:
|
script:
|
||||||
"../src/models/merge_metrics_of_all_participants.R"
|
"../src/models/merge_metrics_for_population_model.R"
|
|
@ -0,0 +1,20 @@
|
||||||
|
source("packrat/init.R")
|
||||||
|
|
||||||
|
library(tidyr)
|
||||||
|
library(purrr)
|
||||||
|
library(dplyr)
|
||||||
|
|
||||||
|
metric_files <- snakemake@input[["metric_files"]]
|
||||||
|
phone_valid_sensed_days <- read.csv(snakemake@input[["phone_valid_sensed_days"]])
|
||||||
|
drop_valid_sensed_days <- snakemake@params[["drop_valid_sensed_days"]]
|
||||||
|
source <- snakemake@params[["source"]]
|
||||||
|
|
||||||
|
metrics_for_individual_model <- metric_files %>%
|
||||||
|
map(read.csv, stringsAsFactors = F, colClasses = c(local_date = "character")) %>%
|
||||||
|
reduce(full_join, by="local_date")
|
||||||
|
|
||||||
|
if(drop_valid_sensed_days && source == "phone_metrics"){
|
||||||
|
metrics_for_individual_model <- merge(metrics_for_individual_model, phone_valid_sensed_days, by="local_date") %>% select(-valid_hours)
|
||||||
|
}
|
||||||
|
|
||||||
|
write.csv(metrics_for_individual_model, snakemake@output[[1]], row.names = FALSE)
|
|
@ -1,13 +0,0 @@
|
||||||
source("packrat/init.R")
|
|
||||||
|
|
||||||
library(tidyr)
|
|
||||||
library(purrr)
|
|
||||||
library(dplyr)
|
|
||||||
|
|
||||||
metric_files <- snakemake@input[["metric_files"]]
|
|
||||||
|
|
||||||
metrics_of_single_participant <- metric_files %>%
|
|
||||||
map(read.csv, stringsAsFactors = F, colClasses = c(local_date = "character")) %>%
|
|
||||||
reduce(full_join, by="local_date")
|
|
||||||
|
|
||||||
write.csv(metrics_of_single_participant, snakemake@output[[1]], row.names = FALSE)
|
|
Loading…
Reference in New Issue