explore: Simplifies Exploratory Data Analysis

Description

Interactive data exploration with one line of code, automated reporting or use an easy to remember set of tidy functions for low code exploratory data analysis.

Author(s)

Maintainer: Roland Krasser roland.krasser@gmail.com

See Also

Useful links:

• https://rolkra.github.io/explore/

• https://github.com/rolkra/explore

• Report bugs at https://github.com/rolkra/explore/issues

A/B testing

Description

A/B testing

Usage

abtest(data, expr, n, target, sign_level = 0.05, color = "grey")

Arguments

Value

Plot that shows if difference is significant

Examples

## Using chi2-test or t-test depending on target type
data <- create_data_buy(obs = 100)
abtest(data, female_ind == 1, target = buy)  # chi2 test
abtest(data, city_ind == 1, target = age)    # t test

## If small number of observations, Fisher's Exact test
## is used for a binary target (if <= 5 observations in a subgroup)
data <- create_data_buy(obs = 25, seed = 1)
abtest(data, female_ind == 1, target = buy)  # Fisher's Exact test

A/B testing interactive

Description

Launches a shiny app to A/B test

Usage

abtest_shiny(
  size_a = 100,
  size_b = 100,
  success_a = 10,
  success_b = 20,
  success_unit = "percent",
  sign_level = 0.05
)

Arguments

Examples

# Only run examples in interactive R sessions
if (interactive())  {
   abtest_shiny()
}

A/B testing comparing two mean

Description

A/B testing comparing two mean

Usage

abtest_targetnum(data, expr, target, sign_level = 0.05, color = "grey")

Arguments

Value

Plot that shows if difference is significant

Examples

data <- create_data_buy(obs = 100)
abtest(data, city_ind == 1, target = age)

A/B testing comparing percent per group

Description

A/B testing comparing percent per group

Usage

abtest_targetpct(
  data,
  expr,
  n,
  target,
  sign_level = 0.05,
  group_label,
  ab_label = FALSE,
  color = "grey"
)

Arguments

Value

Plot that shows if difference is significant

Examples

data <- create_data_buy(obs = 100)
abtest(data, female_ind == 1, target = buy)
abtest(data, age >= 40, target = buy)

Add a variable id at first column in dataset

Description

Add a variable id at first column in dataset

Usage

add_var_id(data, name = "id", overwrite = FALSE)

Arguments

Value

Data set containing new id variable

Examples

library(magrittr)
iris %>% add_var_id() %>% head()
iris %>% add_var_id(name = "iris_nr") %>% head()

Add a random 0/1 variable to dataset

Description

Add a random 0/1 variable to dataset

Usage

add_var_random_01(
  data,
  name = "random_01",
  prob = c(0.5, 0.5),
  overwrite = TRUE,
  seed
)

Arguments

Value

Dataset containing new random variable

Examples

library(magrittr)
iris %>% add_var_random_01() %>% head()
iris %>% add_var_random_01(name = "my_var") %>% head()

Add a random categorical variable to dataset

Description

Add a random categorical variable to dataset

Usage

add_var_random_cat(
  data,
  name = "random_cat",
  cat = LETTERS[1:6],
  prob,
  overwrite = TRUE,
  seed
)

Arguments

Value

Dataset containing new random variable

Examples

library(magrittr)
iris %>% add_var_random_cat() %>% head()
iris %>% add_var_random_cat(name = "my_cat") %>% head()
iris %>% add_var_random_cat(cat = c("Version A", "Version B")) %>% head()
iris %>% add_var_random_cat(cat = c(1,2,3,4,5)) %>% head()

Add a random double variable to dataset

Description

Add a random double variable to dataset

Usage

add_var_random_dbl(
  data,
  name = "random_dbl",
  min_val = 0,
  max_val = 100,
  overwrite = TRUE,
  seed
)

Arguments

Value

Dataset containing new random variable

Examples

library(magrittr)
iris %>% add_var_random_dbl() %>% head()
iris %>% add_var_random_dbl(name = "random_var") %>% head()
iris %>% add_var_random_dbl(min_val = 1, max_val = 10) %>% head()

Add a random integer variable to dataset

Description

Add a random integer variable to dataset

Usage

add_var_random_int(
  data,
  name = "random_int",
  min_val = 1,
  max_val = 10,
  overwrite = TRUE,
  seed
)

Arguments

Value

Dataset containing new random variable

Examples

library(magrittr)
iris %>% add_var_random_int() %>% head()
iris %>% add_var_random_int(name = "random_var") %>% head()
iris %>% add_var_random_int(min_val = 1, max_val = 10) %>% head()

Add a random moon variable to dataset

Description

Add a random moon variable to dataset

Usage

add_var_random_moon(data, name = "random_moon", overwrite = TRUE, seed)

Arguments

Value

Dataset containing new random variable

Examples

library(magrittr)
iris %>% add_var_random_moon() %>% head()

Add a random starsign variable to dataset

Description

Add a random starsign variable to dataset

Usage

add_var_random_starsign(
  data,
  name = "random_starsign",
  lang = "en",
  overwrite = TRUE,
  seed
)

Arguments

Value

Dataset containing new random variable

Examples

library(magrittr)
iris %>% add_var_random_starsign() %>% head()
iris %>% add_var_random_starsign(lang = "de") %>% head()

Balance target variable

Description

Balances the target variable in your dataset using downsampling. Target must be 0/1, FALSE/TRUE ore no/yes

Usage

balance_target(data, target, min_prop = 0.1, seed)

Arguments

Value

Data

Examples

iris$is_versicolor <- ifelse(iris$Species == "versicolor", 1, 0)
balanced <- balance_target(iris, target = is_versicolor, min_prop = 0.5)
describe(balanced, is_versicolor)

Check vector for low variance

Description

Check vector for low variance

Usage

check_vec_low_variance(values, max_prop = 0.99)

Arguments

Value

TRUE/FALSE (low variance)

Examples

## Not run: 
values <- c(1, rep(0 ,1000))
check_vec_low_variance(values, max_prop = 0.9)

## End(Not run)

Clean variable

Description

Clean variable (replace NA values, set min_val and max_val)

Usage

clean_var(
  data,
  var,
  na = NA,
  min_val = NA,
  max_val = NA,
  max_cat = NA,
  rescale01 = FALSE,
  simplify_text = FALSE,
  name = NA
)

Arguments

Value

Dataset

Examples

library(magrittr)
iris %>% clean_var(Sepal.Width, max_val = 3.5, name = "sepal_width") %>% head()
iris %>% clean_var(Sepal.Width, rescale01 = TRUE) %>% head()

Adds percentage to dplyr::count()

Description

Adds variables total and pct (percentage) to dplyr::count()

Usage

count_pct(data, ...)

Arguments

Value

Dataset

Examples

count_pct(iris, Species)

Create data of A/B testing

Description

Data that can be used for unit-testing or teaching

Usage

create_data_abtest(
  n_a = 100,
  n_b = 100,
  success_a = 10,
  success_b = 5,
  success_unit = "count",
  count = TRUE
)

Arguments

Value

A dataset as tibble

Examples

library(dplyr)
create_data_abtest() %>% abtest()
create_data_abtest(
  n_a = 100,
  n_b = 100,
  success_a = 20,
  success_b = 30,
  success_unit = "count"
) %>% abtest()

Create data app

Description

Artificial data that can be used for unit-testing or teaching

Usage

create_data_app(obs = 1000, add_id = FALSE, seed = 123)

Arguments

Value

A dataset as tibble

Examples

create_data_app()

Create data buy

Description

Artificial data that can be used for unit-testing or teaching

Usage

create_data_buy(
  obs = 1000,
  target_name = "buy",
  factorise_target = FALSE,
  target1_prob = 0.5,
  add_extreme = TRUE,
  flip_gender = FALSE,
  add_id = FALSE,
  seed = 123
)

Arguments

Details

Variables in dataset:

• id = Identifier

• period = Year & Month (YYYYMM)

• city_ind = Indicating if customer is residing in a city (1 = yes, 0 = no)

• female_ind = Gender of customer is female (1 = yes, 0 = no)

• fixedvoice_ind = Customer has a fixed voice product (1 = yes, 0 = no)

• fixeddata_ind = Customer has a fixed data product (1 = yes, 0 = no)

• fixedtv_ind = Customer has a fixed TV product (1 = yes, 0 = no)

• mobilevoice_ind = Customer has a mobile voice product (1 = yes, 0 = no)

• mobiledata_prd = Customer has a mobile data product (NO/MOBILE STICK/BUSINESS)

• bbi_speed_ind = Customer has a Broadband Internet (BBI) with extra speed

• bbi_usg_gb = Broadband Internet (BBI) usage in Gigabyte (GB) last month

• hh_single = Expected to be a Single Household (1 = yes, 0 = no)

Target in dataset:

• buy (may be renamed) = Did customer buy a new product in next month? (1 = yes, 0 = no)

Value

A dataset as tibble

Examples

create_data_buy()

Create data churn

Description

Artificial data that can be used for unit-testing or teaching

Usage

create_data_churn(
  obs = 1000,
  target_name = "churn",
  factorise_target = FALSE,
  target1_prob = 0.4,
  add_id = FALSE,
  seed = 123
)

Arguments

Value

A dataset as tibble

Examples

create_data_churn()

Create an empty dataset

Description

Create an empty dataset

Usage

create_data_empty(obs = 1000, add_id = FALSE)

Arguments

Value

Dataset as tibble

Examples

create_data_empty(obs = 100)
create_data_empty(obs = 100, add_id = TRUE)

Create data esoteric

Description

Random data that can be used for unit-testing or teaching

Usage

create_data_esoteric(obs = 1000, add_id = FALSE, seed = 123)

Arguments

Details

Variables in dataset:

• id = Identifier

• starsign = random starsign

• chinese = random chinese zodiac

• moon = random moon phase

• blood = random blood type

• fingers_crossed = random fingers crossed (1 = yes, 0 = no)

• success = random success (1 = yes, 0 = no)

Value

A dataset as tibble

Examples

create_data_esoteric(obs = 100)

Create data newsletter

Description

Artificial data that can be used for unit-testing or teaching (fairness & AI bias)

Usage

create_data_newsletter(obs = 1000, add_id = FALSE, seed = 123)

Arguments

Value

A dataset as tibble

Examples

create_data_newsletter()

Create data person

Description

Artificial data that can be used for unit-testing or teaching

Usage

create_data_person(obs = 1000, add_id = FALSE, seed = 123)

Arguments

Value

A dataset as tibble

Examples

create_data_person()

Create data random

Description

Random data that can be used for unit-testing or teaching

Usage

create_data_random(
  obs = 1000,
  vars = 10,
  target_name = "target_ind",
  factorise_target = FALSE,
  target1_prob = 0.5,
  add_id = TRUE,
  seed = 123
)

Arguments

Details

Variables in dataset:

• id = Identifier

• var_X = variable containing values between 0 and 100

Target in dataset:

• target_ind (may be renamed) = random values (1 = yes, 0 = no)

Value

A dataset as tibble

Examples

create_data_random(obs = 100, vars = 5)

Create data unfair

Description

Artificial data that can be used for unit-testing or teaching (fairness & AI bias)

Usage

create_data_unfair(
  obs = 1000,
  target_name = "target_ind",
  factorise_target = FALSE,
  target1_prob = 0.25,
  add_id = FALSE,
  seed = 123
)

Arguments

Value

A dataset as tibble

Examples

create_data_unfair()

Generate a notebook

Description

Generate an RMarkdown Notebook template for a report. You must provide a output-directory (parameter output_dir). The default file-name is "notebook-explore.Rmd" (may overwrite existing file with same name)

Usage

create_notebook_explore(output_file = "notebook-explore.Rmd", output_dir)

Arguments

Examples

create_notebook_explore(output_file = "explore.Rmd", output_dir = tempdir())

Cut a variable

Description

Cut a variable

Usage

cut_vec_num_avg(values, bins = 8)

Arguments

Value

Data frame

Create a data dictionary Markdown file

Description

Create a data dictionary Markdown file

Usage

data_dict_md(
  data,
  title = "",
  description = NA,
  output_file = "data_dict.md",
  output_dir
)

Arguments

Value

Create Markdown file

Examples

# Data dictionary of a dataframe
data_dict_md(iris,
             title = "iris flower data set",
             output_dir = tempdir())

# Data dictionary of a dataframe with additional description of variables
description <- data.frame(
                 variable = c("Species"),
                 description = c("Species of Iris flower"))
data_dict_md(iris,
             title = "iris flower data set",
             description = description,
             output_dir = tempdir())

decrypt text

Description

decrypt text

Usage

decrypt(text, codeletters = c(toupper(letters), letters, 0:9), shift = 18)

Arguments

Value

Decrypted text

Examples

decrypt("zw336 E693v")

Describe a dataset or variable

Description

Describe a dataset or variable (depending on input parameters)

Usage

describe(data, var, n, target, out = "text", ...)

Arguments

Value

Description as table, text or list

Examples

# Load package
library(magrittr)

# Describe a dataset
iris %>% describe()

# Describe a variable
iris %>% describe(Species)
iris %>% describe(Sepal.Length)

Describe all variables of a dataset

Description

Describe all variables of a dataset

Usage

describe_all(data, out = "large")

Arguments

Value

Dataset (tibble)

Examples

describe_all(iris)

Describe categorical variable

Description

Describe categorical variable

Usage

describe_cat(data, var, n, max_cat = 10, out = "text", margin = 0)

Arguments

Value

Description as text or list

Examples

describe_cat(iris, Species)

Describe numerical variable

Description

Describe numerical variable

Usage

describe_num(data, var, n, out = "text", margin = 0)

Arguments

Value

Description as text or list

Examples

describe_num(iris, Sepal.Length)

Describe table

Description

Describe table (e.g. number of rows and columns of dataset)

Usage

describe_tbl(data, n, target, out = "text")

Arguments

Value

Description as text or list

Examples

describe_tbl(iris)

iris[1,1] <- NA
describe_tbl(iris)

Drop all observations where expression is true

Description

Drop all observations where expression is true

Usage

drop_obs_if(data, expr)

Arguments

Value

Data frame

Examples

drop_obs_if(iris, Species == "setosa")
drop_obs_if(iris, Sepal.Length < 5 | Sepal.Length >7)

Drop all observations with NA-values

Description

Drop all observations with NA-values

Usage

drop_obs_with_na(data)

Arguments

Value

Data frame

Examples

data <- data.frame(a = 1:10, b = rep("A",10))
data[1,1] <- NA
drop_obs_with_na(data)

Drop variables by name

Description

Drop variables by name

Usage

drop_var_by_names(data, var_names)

Arguments

Value

Data frame

Examples

drop_var_by_names(iris, "Species")
drop_var_by_names(iris, c("Sepal.Length", "Sepal.Width"))

Drop all variables with low variance

Description

Drop all variables with low variance

Usage

drop_var_low_variance(data, max_prop = 0.99)

Arguments

Value

Data frame

Examples

data <- data.frame(a = 1:100, b = c(0, rep(1, 99)))
drop_var_low_variance(data, max_prop = 0.9)

Drop all variables with no variance

Description

Drop all variables with no variance

Usage

drop_var_no_variance(data)

Arguments

Value

Data frame

Examples

data <- data.frame(a = 1:10, b = rep(1,10))
drop_var_no_variance(data)

Drop all not numeric variables

Description

Drop all not numeric variables

Usage

drop_var_not_numeric(data)

Arguments

Value

Data frame

Examples

data <- data.frame(a = 1:10, b = rep("A",10))
drop_var_not_numeric(data)

Drop all variables with NA-values

Description

Drop all variables with NA-values

Usage

drop_var_with_na(data)

Arguments

Value

Data frame

Examples

data <- data.frame(a = 1:10, b = rep(NA,10))
drop_var_with_na(data)

encrypt text

Description

encrypt text

Usage

encrypt(text, codeletters = c(toupper(letters), letters, 0:9), shift = 18)

Arguments

Value

Encrypted text

Examples

encrypt("hello world")

Explain a target using Random Forest.

Description

Explain a target using Random Forest.

Usage

explain_forest(data, target, ntree = 50, out = "plot", ...)

Arguments

Value

Plot of importance (if out = "plot")

Examples

data <- create_data_buy()
explain_forest(data, target = buy)

Explain a binary target using a logistic regression (glm). Model chosen by AIC in a Stepwise Algorithm (MASS::stepAIC()).

Description

Explain a binary target using a logistic regression (glm). Model chosen by AIC in a Stepwise Algorithm (MASS::stepAIC()).

Usage

explain_logreg(data, target, out = "tibble", ...)

Arguments

Value

Dataset with results (term, estimate, std.error, z.value, p.value)

Examples

data <- iris
data$is_versicolor <- ifelse(iris$Species == "versicolor", 1, 0)
data$Species <- NULL
explain_logreg(data, target = is_versicolor)

Explain a target using a simple decision tree (classification or regression)

Description

Explain a target using a simple decision tree (classification or regression)

Usage

explain_tree(
  data,
  target,
  n,
  max_cat = 10,
  max_target_cat = 5,
  maxdepth = 3,
  minsplit = 20,
  cp = 0,
  weights = NA,
  size = 0.7,
  out = "plot",
  ...
)

Arguments

Value

Plot or additional the model (if out = "model")

Examples

data <- iris
data$is_versicolor <- ifelse(iris$Species == "versicolor", 1, 0)
data$Species <- NULL
explain_tree(data, target = is_versicolor)

Explain a binary target using xgboost

Description

Based on the hyperparameters defined in the setup parameter, XGBoost hyperparameter-tuning is carried out using cross-validation. The best model is chosen and returned. As default, the function returns the feature-importance plot. To get the all outputs, use parameter out = "all"

Usage

explain_xgboost(
  data,
  target,
  log = TRUE,
  nthread = 1,
  setup = list(cv_nfold = 2, max_nrounds = 1000, early_stopping_rounds = 50, grid_xgboost
    = list(eta = c(0.3, 0.1, 0.01), max_depth = c(3, 5), gamma = 0, colsample_bytree =
    0.8, subsample = 0.8, min_child_weight = 1, scale_pos_weight = 1)),
  out = "plot"
)

Arguments

Value

Plot of importance (if out = "plot")

Examples

data <- use_data_iris()
data$is_versicolor <- ifelse(data$Species == "versicolor", 1, 0)
data$Species <- NULL
explain_xgboost(data, target = is_versicolor, log = FALSE)

Explore a dataset or variable

Description

Explore a dataset or variable

Usage

explore(
  data,
  var,
  var2,
  n,
  target,
  targetpct,
  split,
  min_val = NA,
  max_val = NA,
  auto_scale = TRUE,
  na = NA,
  ...
)

Arguments

Value

Plot object

Examples

## Launch Shiny app (in interactive R sessions)
if (interactive())  {
   explore(iris)
}

## Explore grafically

# Load library
library(magrittr)

# Explore a variable
iris %>% explore(Species)
iris %>% explore(Sepal.Length)
iris %>% explore(Sepal.Length, min_val = 4, max_val = 7)

# Explore a variable with a target
iris$is_virginica <- ifelse(iris$Species == "virginica", 1, 0)
iris %>% explore(Species, target = is_virginica)
iris %>% explore(Sepal.Length, target = is_virginica)

# Explore correlation between two variables
iris %>% explore(Species, Petal.Length)
iris %>% explore(Sepal.Length, Petal.Length)

# Explore correlation between two variables and split by target
iris %>% explore(Sepal.Length, Petal.Length, target = is_virginica)

Explore all variables

Description

Explore all variables of a dataset (create plots)

Usage

explore_all(
  data,
  n,
  target,
  ncol = 2,
  targetpct,
  color = c("#ADD8E6", "#7BB8DA"),
  split = TRUE
)

Arguments

Value

Plot

Examples

explore_all(iris)

iris$is_virginica <- ifelse(iris$Species == "virginica", 1, 0)
explore_all(iris, target = is_virginica)

Explore categorical variable using bar charts

Description

Create a barplot to explore a categorical variable. If a target is selected, the barplot is created for all levels of the target.

Usage

explore_bar(
  data,
  var,
  target,
  flip = NA,
  title = "",
  numeric = NA,
  max_cat = 30,
  max_target_cat = 5,
  color = c("#ADD8E6", "#7BB8DA"),
  legend_position = "right",
  label,
  label_size = 2.7,
  ...
)

Arguments

Value

Plot object (bar chart)

Explore data without aggregation (label + value)

Description

Label and Value are in the data. Create a bar plot where the heights of the bars represent the values for each label.

Usage

explore_col(
  data,
  var_label,
  var_value,
  title = NA,
  subtitle = "",
  numeric = FALSE,
  max_cat = 30,
  na = 0,
  flip = NA,
  color = "#ADD8E6"
)

Arguments

Value

Plot object

Examples

library(magrittr)
data <- data.frame(label = LETTERS[1:5], value = c(1.5,2,1.2,3,2.6))
data %>% explore_col(label, value)

Explore the correlation between two variables

Description

Explore the correlation between two variables

Usage

explore_cor(
  data,
  x,
  y,
  target,
  bins = 8,
  min_val = NA,
  max_val = NA,
  auto_scale = TRUE,
  title = NA,
  color = c("#ADD8E6", "#7BB8DA"),
  ...
)

Arguments

Value

Plot

Examples

explore_cor(iris, x = Sepal.Length, y = Sepal.Width)

Explore count data (categories + frequency)

Description

Create a plot to explore count data (categories + freuency) Variable named 'n' is auto detected as Frequency

Usage

explore_count(
  data,
  cat,
  n,
  target,
  pct = FALSE,
  split = TRUE,
  title = NA,
  numeric = FALSE,
  max_cat = 30,
  max_target_cat = 5,
  color = c("#ADD8E6", "#7BB8DA"),
  flip = NA
)

Arguments

Value

Plot object

Examples

library(dplyr)
iris %>%
  count(Species) %>%
  explore_count(Species)

Explore density of variable

Description

Create a density plot to explore numerical variable

Usage

explore_density(
  data,
  var,
  target,
  title = "",
  min_val = NA,
  max_val = NA,
  color = c("#ADD8E6", "#7BB8DA"),
  auto_scale = TRUE,
  max_target_cat = 5,
  ...
)

Arguments

Value

Plot object (density plot)

Examples

explore_density(iris, Sepal.Length)
iris$is_virginica <- ifelse(iris$Species == "virginica", 1, 0)
explore_density(iris, Sepal.Length, target = is_virginica)

Explore dataset interactive

Description

Launches a shiny app to explore a dataset

Usage

explore_shiny(data, target, color = c("#ADD8E6", "#7BB8DA"))

Arguments

Examples

# Only run examples in interactive R sessions
if (interactive())  {
   explore_shiny(iris)
}

Explore variable + binary target (values 0/1)

Description

Create a plot to explore relation between a variable and a binary target as target percent. The target variable is choosen automatically if possible (name starts with 'target')

Usage

explore_targetpct(
  data,
  var,
  target = NULL,
  title = NA,
  min_val = NA,
  max_val = NA,
  auto_scale = TRUE,
  na = NA,
  flip = NA,
  ...
)

Arguments

Value

Plot object

Examples

iris$target01 <- ifelse(iris$Species == "versicolor",1,0)
explore_targetpct(iris)

Explore table

Description

Explore a table. Plots variable types, variables with no variance and variables with NA

Usage

explore_tbl(data, n)

Arguments

Examples

explore_tbl(iris)

Format number as character string (auto)

Description

Formats a number depending on the value as number with space, scientific or big number as k (1 000), M (1 000 000) or B (1 000 000 000)

Usage

format_num_auto(number = 0, digits = 1)

Arguments

Value

Formatted number as text

Examples

format_num_kMB(5500, digits = 2)

Format number as character string (kMB)

Description

Formats a big number as k (1 000), M (1 000 000) or B (1 000 000 000)

Usage

format_num_kMB(number = 0, digits = 1)

Arguments

Value

Formatted number as text

Examples

format_num_kMB(5500, digits = 2)

Format number as character string (space as big.mark)

Description

Formats a big number using space as big.mark (1000 = 1 000)

Usage

format_num_space(number = 0, digits = 1)

Arguments

Value

Formatted number as text

Examples

format_num_space(5500, digits = 2)

Format target

Description

Formats a target as a 0/1 variable. If target is numeric, 1 = above average.

Usage

format_target(target)

Arguments

Value

Formated target

Examples

iris$is_virginica <- ifelse(iris$Species == "virginica", "yes", "no")
iris$target <- format_target(iris$is_virginica)
table(iris$target)

Format type description

Description

Format type description of variable to 3 letters (int|dbl|lgl|chr|dat)

Usage

format_type(type)

Arguments

Value

Formatted type description (int|dbl|lgl|chr|dat)

Examples

format_type(typeof(iris$Species))

Get predefined colors

Description

Get predefined colors

Usage

get_color(name, fill = FALSE, fill_color = "#DDDDDD", fill_n = 10)

Arguments

Value

Vector of color-codes

Examples

get_color("mario")

get_color("mario")
show_color(get_color("mario"))
show_color(get_color("mario", fill = TRUE, fill_n = 10))

col <- get_color("mario")
explore(iris, Sepal.Length, target = Species,
  color = col)
explore(iris, Sepal.Length, target = Species,
  color = c(col["peach"], col["bowser"], col["donkeykong"]))

Get number of rows for a grid plot

Description

This function is deprecated, please use total_fig_height() instead.

Usage

get_nrow(varnames, exclude = 0, ncol = 2)

Arguments

Value

Number of rows

Examples

## Not run: 
get_nrow(names(iris), ncol = 2)

## End(Not run)

Return type of variable

Description

Return value of typeof, except if variable contains hide, then return "other"

Usage

get_type(var)

Arguments

Value

Value of typeof or "other"

Examples

get_type(iris$Species)

Put variables into "buckets" to create a set of plots instead one large plot

Description

Put variables into "buckets" to create a set of plots instead one large plot

Usage

get_var_buckets(data, bucket_size = 100, var_name_target = NA, var_name_n = NA)

Arguments

Value

Buckets as a list

Examples

get_var_buckets(iris)
get_var_buckets(iris, bucket_size = 2)
get_var_buckets(iris, bucket_size = 2, var_name_target = "Species")

Return if variable is categorical or numerical

Description

Guess if variable is categorical or numerical based on name, type and values of variable

Usage

guess_cat_num(var, descr)

Arguments

Value

"cat" (categorical), "num" (numerical) or "oth" (other)

Examples

guess_cat_num(iris$Species)

Make a explore-plot interactive

Description

Make a explore-plot interactive

Usage

interact(obj, lower_title = TRUE, hide_geom_text = TRUE)

Arguments

Value

Plot object

Examples

library(dplyr)
if (interactive())  {
   iris %>% explore(Sepal.Length, target = Species) %>% interact()
}

Log conditional

Description

Log conditional

Usage

log_info_if(log = TRUE, text = "log")

Arguments

Value

prints log on screen (if log == TRUE).

Mix colors

Description

Mix colors

Usage

mix_color(color1, color2 = NA, n = 5)

Arguments

Value

Vector of color-codes

Examples

mix_color("blue", n = 10)
mix_color("gold", "red", n = 4)

Plots a legend that can be used for explore_all with a binary target

Description

Plots a legend that can be used for explore_all with a binary target

Usage

plot_legend_targetpct(border = TRUE)

Arguments

Value

Base plot

Examples

plot_legend_targetpct(border = TRUE)

Plot a text

Description

Plots a text (base plot) and let you choose text-size and color

Usage

plot_text(text = "hello world", size = 1.2, color = "black", ggplot = FALSE)

Arguments

Value

Plot

Examples

plot_text("hello", size = 2, color = "red")

Plot a variable info

Description

Creates a ggplot with the variable-name as title and a text

Usage

plot_var_info(data, var, info = "")

Arguments

Value

Plot (ggplot)

Predict target using a trained model.

Description

Predict target using a trained model.

Usage

predict_target(data, model, name = "prediction")

Arguments

Value

data containing predicted probabilities for target values

Examples

data_train <- create_data_buy(seed = 1)
data_test <- create_data_buy(seed = 2)
model <- explain_tree(data_train, target = buy, out = "model")
data <- predict_target(data = data_test, model = model)
describe(data)

Replace NA

Description

Replace NA values of a variable in a dataframe

Usage

replace_na_with(data, var_name, with)

Arguments

Value

Updated dataframe

Examples

data <- data.frame(nr = c(1,2,3,NA,NA))
replace_na_with(data, "nr", 0)

Generate a report of all variables

Description

Generate a report of all variables If target is defined, the relation to the target is reported

Usage

report(data, n, target, targetpct, split, color, output_file, output_dir)

Arguments

Examples

if (rmarkdown::pandoc_available("1.12.3")) {
 report(iris, output_dir = tempdir())
 }

Rescales a numeric variable into values between 0 and 1

Description

Rescales a numeric variable into values between 0 and 1

Usage

rescale01(x)

Arguments

Value

vector with values between 0 and 1

Examples

rescale01(0:10)

Show color vector as ggplot

Description

Show color vector as ggplot

Usage

show_color(color)

Arguments

Value

ggplot

Examples

show_color("gold")
show_color(c("blue", "red", "green"))

Simplifies a text string

Description

A text string is converted into a simplified version by trimming, converting to upper case, replacing german Umlaute, dropping special characters like comma and semicolon and replacing multiple spaces with one space.

Usage

simplify_text(text)

Arguments

Value

text string

Examples

simplify_text(" Hello  World !, ")

Explore categorical variable + target

Description

Create a plot to explore relation between categorical variable and a binary target

Usage

target_explore_cat(
  data,
  var,
  target = "target_ind",
  min_val = NA,
  max_val = NA,
  flip = TRUE,
  num2char = TRUE,
  title = NA,
  auto_scale = TRUE,
  na = NA,
  max_cat = 25,
  color = c("#ECEFF1", "#CFD8DC", "#B0BEC5", "#90A4AE"),
  legend_position = "bottom"
)

Arguments

Value

Plot object

Explore Nuberical variable + target

Description

Create a plot to explore relation between numerical variable and a binary target

Usage

target_explore_num(
  data,
  var,
  target = "target_ind",
  min_val = NA,
  max_val = NA,
  bins = 10,
  flip = TRUE,
  title = NA,
  auto_scale = TRUE,
  na = NA,
  color = c("#ECEFF1", "#CFD8DC", "#B0BEC5", "#90A4AE"),
  legend_position = "bottom"
)

Arguments

Value

Plot object

Get fig.height for RMarkdown-junk using explore_all()

Description

Get fig.height for RMarkdown-junk using explore_all()

Usage

total_fig_height(
  data,
  var_name_n,
  var_name_target,
  nvar = NA,
  ncol = 2,
  size = 3
)

Arguments

Value

Number of rows

Examples

total_fig_height(iris)
total_fig_height(iris, var_name_target = "Species")
total_fig_height(nvar = 5)

Use the beer data set

Description

This data set is an incomplete collection of popular beers in Austria, Germany and Switzerland. Data are collected from various websites in 2023. Some of the collected data may be incorrect.

Usage

use_data_beer()

Value

Dataset as tibble

Examples

use_data_beer()

Use the diamonds data set

Description

This data set comes with the ggplot2 package. It contains the prices and other attributes of almost 54,000 diamonds.

Usage

use_data_diamonds()

Value

Dataset

See Also

ggplot2::diamonds

Examples

use_data_diamonds()

Use the iris flower data set

Description

This data set comes with base R. The data set gives the measurements in centimeters of the variables sepal length and width and petal length and width, respectively, for 50 flowers from each of 3 species of iris. The species are Iris setosa, versicolor, and virginica.

Usage

use_data_iris()

Value

Dataset as tibble

Examples

use_data_iris()

Use the mpg data set

Description

This data set comes with the ggplot2 package. It contains a subset of the fuel economy data that the EPA makes available on https://fueleconomy.gov/. It contains only models which had a new release every year between 1999 and 2008 - this was used as a proxy for the popularity of the car.

Usage

use_data_mpg()

Value

Dataset

See Also

ggplot2::mpg

Examples

use_data_mpg()

Use the mtcars data set

Description

This data set comes with base R. The data was extracted from the 1974 Motor Trend US magazine, and comprises fuel consumption and 10 aspects of automobile design and performance for 32 automobiles (1973–74 models).

Usage

use_data_mtcars()

Value

Dataset

Examples

use_data_mtcars()

Use the penguins data set

Description

This data set comes with the palmerpenguins package. It contains measurements for penguin species, island in Palmer Archipelago, size (flipper length, body mass, bill dimensions), and sex.

Usage

use_data_penguins(short_names = FALSE)

Arguments

Value

Dataset

See Also

palmerpenguins::penguins

Examples

use_data_penguins()
use_data_penguins(short_names = TRUE)

Use the starwars data set

Description

This data set comes with the dplyr package. It contains data of 87 star war characters

Usage

use_data_starwars()

Value

Dataset

See Also

dplyr::starwars

Examples

use_data_starwars()

Use the titanic data set

Description

This data set comes with base R. Survival of passengers on the Titanic.

Usage

use_data_titanic(count = FALSE)

Arguments

Value

Dataset

Examples

use_data_titanic(count = TRUE)
use_data_titanic(count = FALSE)

Use the wordle data set

Description

This data set contains the result of a real wordle challange (in german language) between tow players. Wordle is a game where a player guesses a five-letter word in six tries. The variable "try" reflects the success of player A and B. Other variables like "noun", "aeiou", "unique", "common" and "rare" reflect the properties of the word.

Usage

use_data_wordle()

Value

Dataset

Examples

use_data_wordle()

Weight target variable

Description

Create weights for the target variable in your dataset so that are equal weights for target = 0 and target = 1. Target must be 0/1, FALSE/TRUE ore no/yes

Usage

weight_target(data, target)

Arguments

Value

Weights for each observation (as a vector)

Examples

iris$is_versicolor <- ifelse(iris$Species == "versicolor", 1, 0)
weights <- weight_target(iris, target = is_versicolor)
versicolor <- iris$is_versicolor
table(versicolor, weights)

Calculate with periods (format yyyymm)

Description

Calculate with periods (format yyyymm)

Usage

yyyymm_calc(yyyymm, add_month = 0, add_year = 0, diff_to = NA)

Arguments

Value

Vector of periods (format yyyymm) or number of months

Examples

yyyymm_calc(202412, add_month = 1)
yyyymm_calc(c(202411,202412,202501), add_month = -1, add_year = 1)
yyyymm_calc(202410, diff_to = 202501)
yyyymm_calc(c(202411,202412,202501,202502), diff_to = 202501)