target_by.data.frame: Target by one variables

In dlookr: Tools for Data Diagnosis, Exploration, Transformation

Target by one variables

Description

In the data analysis, a target_df class is created to identify the relationship between the target variable and the other variable.

Usage

target_by(.data, target, ...)

## S3 method for class 'data.frame'
target_by(.data, target, ...)

Arguments

.data	a data.frame or a tbl_df.
target	target variable.
...	arguments to be passed to methods.

Details

Data analysis proceeds with the purpose of predicting target variables that correspond to the facts of interest, or examining associations and relationships with other variables of interest. Therefore, it is a major challenge for EDA to examine the relationship between the target variable and its corresponding variable. Based on the derived relationships, analysts create scenarios for data analysis.

target_by() inherits the grouped_df class and returns a target_df class containing information about the target variable and the variable.

See vignette("EDA") for an introduction to these concepts.

Value

an object of target_df class. Attributes of target_df class is as follows.

• type_y : the data type of target variable.

See Also

relate.

Examples

# If the target variable is a categorical variable
categ <- target_by(heartfailure, death_event)

# If the variable of interest is a numerical variable
cat_num <- relate(categ, sodium)
cat_num
summary(cat_num)

plot(cat_num)

# If the variable of interest is a categorical variable
cat_cat <- relate(categ, hblood_pressure)
cat_cat
summary(cat_cat)
 
plot(cat_cat)

##---------------------------------------------------
# If the target variable is a numerical variable
num <- target_by(heartfailure, creatinine)

# If the variable of interest is a numerical variable
num_num <- relate(num, sodium)
num_num
summary(num_num)

plot(num_num)

# If the variable of interest is a categorical variable
num_cat <- relate(num, smoking)
num_cat
summary(num_cat)

plot(num_cat)

# Non typographic
plot(num_cat, typographic = FALSE)

dlookr documentation built on July 9, 2023, 6:31 p.m.