current_path <- getwd()\(~\)
\(~\)
\(~\)
library('tidyverse')## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.0.6 v dplyr 1.0.4
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.0## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(NHANES)
source(file.path(current_path,'SankeyNetwork_Helpers.R'))NHANES_DATA_12 <- NHANES %>%
filter(!is.na(Depressed)) %>%
mutate_if(is.factor,
fct_explicit_na)
factor_vars <- NHANES_DATA_12 %>%
select_if(is.factor) %>%
colnames()
factor_vars## [1] "SurveyYr" "Gender" "AgeDecade" "Race1"
## [5] "Race3" "Education" "MaritalStatus" "HHIncome"
## [9] "HomeOwn" "Work" "BMICatUnder20yrs" "BMI_WHO"
## [13] "Diabetes" "HealthGen" "LittleInterest" "Depressed"
## [17] "SleepTrouble" "PhysActive" "TVHrsDay" "CompHrsDay"
## [21] "Alcohol12PlusYr" "SmokeNow" "Smoke100" "Smoke100n"
## [25] "Marijuana" "RegularMarij" "HardDrugs" "SexEver"
## [29] "SameSex" "SexOrientation" "PregnantNow"factor_features <- factor_vars[!factor_vars %in% c('Depressed')]
factor_features## [1] "SurveyYr" "Gender" "AgeDecade" "Race1"
## [5] "Race3" "Education" "MaritalStatus" "HHIncome"
## [9] "HomeOwn" "Work" "BMICatUnder20yrs" "BMI_WHO"
## [13] "Diabetes" "HealthGen" "LittleInterest" "SleepTrouble"
## [17] "PhysActive" "TVHrsDay" "CompHrsDay" "Alcohol12PlusYr"
## [21] "SmokeNow" "Smoke100" "Smoke100n" "Marijuana"
## [25] "RegularMarij" "HardDrugs" "SexEver" "SameSex"
## [29] "SexOrientation" "PregnantNow"\(~\)
\(~\)
make_sankey_graph_from_features(data = NHANES_DATA_12,
id = 'ID',
target = 'Depressed',
features = c('Gender','HardDrugs'))## Note: Using an external vector in selections is ambiguous.
## i Use `all_of(target)` instead of `target` to silence this message.
## i See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.
## This message is displayed once per session.## New names:
## * `` -> ...1
## * `` -> ...2## `summarise()` has grouped output by 'Gender'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'HardDrugs'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'Gender'. You can override using the `.groups` argument.## Links is a tbl_df. Converting to a plain data frame.Use at your own risk for more than 5 !
make_sankey_graph_from_features(data = NHANES_DATA_12,
id = 'ID',
target = 'Depressed',
features = sample(factor_features, 5))## New names:
## * `` -> ...1
## * `` -> ...2## `summarise()` has grouped output by 'AgeDecade'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'HealthGen'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'HomeOwn'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'CompHrsDay'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'Smoke100n'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'AgeDecade'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'AgeDecade'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'AgeDecade'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'AgeDecade'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'HealthGen'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'HealthGen'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'HealthGen'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'HomeOwn'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'HomeOwn'. You can override using the `.groups` argument.## `summarise()` has grouped output by 'CompHrsDay'. You can override using the `.groups` argument.## Links is a tbl_df. Converting to a plain data frame.\(~\)
\(~\)
\(~\)
\(~\)
current_path <- getwd()
library('tidyverse')
library(NHANES)
source(file.path(current_path,'SankeyNetwork_Helpers.R'))
NHANES_DATA_12 <- NHANES %>%
filter(!is.na(Depressed)) %>%
mutate_if(is.factor,
fct_explicit_na)
factor_vars <- NHANES_DATA_12 %>%
select_if(is.factor) %>%
colnames()
factor_vars
factor_features <- factor_vars[!factor_vars %in% c('Depressed')]
factor_features
make_sankey_graph_from_features(data = NHANES_DATA_12,
id = 'ID',
target = 'Depressed',
features = c('Gender','HardDrugs'))
make_sankey_graph_from_features(data = NHANES_DATA_12,
id = 'ID',
target = 'Depressed',
features = sample(factor_features, 5))