r ml library Cheat Sheet (DRAFT) by worlddoit

Additional material about top libraries for Machine Learning in R.

You can read a xml file in R using the "XML" package.

install.packages("XML")

# Also load the other required package.

library("methods")

# Give the input file name to the function.

result <- xmlParse(file = "input.xml")

# Exract the root node form the xml file.

rootnode <- xmlRoot(result)

# Find number of nodes in the root.

rootsize <- xmlSize(rootnode)

dplyr is a grammar of data manipulation, providing a consistent set of verbs that help you solve the most common data manipulation challenges:

mutate()

adds new variables that are functions of existing variables

select()

picks variables based on their names.

filter()

picks cases based on their values.

summarise()

reduces multiple values down to a single summary.

arrange()

changes the ordering of the rows.
These all combine naturally with

group_by()

which allows you to perform any operation “by group”.

Example:

starwars %>%

  group_by(species) %>%

  summarise( n = n(),  mass = mean(mass, na.rm = TRUE)

  ) %>%

  filter( n > 1, mass > 50)

library(xgboost)

# load data

data(agaricus.train, package = 'xgboost')

data(agaricus.test, package = 'xgboost')

train <- agaricus.train

test <- agaricus.test

# fit model

bst <- xgboost(data = train$data, label = train$label, max_depth = 2, eta = 1, nrounds = 2, 

               nthread = 2, objective = "binary:logistic")

# predict

pred <- predict(bst, test$data)

Lots of functionality, you can deal with clustering, regression, classification, and survival analysis.

library(mlr3)

# create learning task

task_penguins = as_task_classif(species ~ ., data = palmerpenguins::penguins)

# load learner and set hyperparameter

learner = lrn("classif.rpart", cp = .01)

# train/test split

split = partition(task_penguins, ratio = 0.67)

# train the model

learner$train(task_penguins, split$train_set)

# predict data

prediction = learner$predict(task_penguins, split$test_set)

# calculate performance

prediction$confusion

measure = msr("classif.acc")

prediction$score(measure)

# 3-fold cross validation

resampling = rsmp("cv", folds = 3L)

# run experiments

rr = resample(task_penguins, learner, resampling)

# access results

rr$score(measure)[, .(task_id, learner_id, iteration, classif.acc)]

rr$aggregate(measure)

It is reproducible, used for report creation, and integrates with various types of code structures like LaTeX, HTML, Markdown, LyX, etc.
This package is an amazing one, you can make a beautiful pdf report and editable pdf forms with the help of latex coding.

kable

xtable

tikzDevice

Plotly's R graphing library makes interactive, publication-quality graphs. Example of how to make line plots, scatter plots, area charts, bar charts, error bars, box plots, histograms, heatmaps, subplots, multiple-axes, and 3D (WebGL based) charts.

library(plotly)

# volcano is a numeric matrix that ships with R

fig <- plot_ly(z = ~volcano) %>% add_surface(

  contours = list(

    z = list( show=TRUE, usecolormap=TRUE,

      highlightcolor="#ff0000", project=list(z=TRUE) ) ) )

fig <- fig %>% layout(

    scene = list( camera= list(

        eye = list(x=1.87, y=0.88, z=-0.64) )))

fig

Dealing with clustering, Fourier Transform, Naive Bayes, SVM, and other types of modeling data analysis then you can’t avoid e1071.
Example:

#Author DataFlair

library("e1071")

data("iris")

head(iris)

x <- iris[,-5]

y <- iris[5]

model_svm <- svm(Species ~ ., data=iris)

summary(svm_model)

pred <- predict(model_svm,x)

confusionMatrix(pred,y$Species)

For data manipulation. Covered in lectures (see previous sections).
Example:

library(tidyverse)

library(lubridate)

library(nycflights13)

Create a new column basis count option

flights %>%

  mutate(long_flight = (air_time >= 6 * 60)) %>%

  View()

Randomly Shuffle the data

flights %>%

  slice_sample(n = 15)

If you are dealing with classification and regression problems then caret is one of the essential packages.

caret

package is the extension of the caret is CaretEnsemble which is used for combining different models.
Example:
Visualization of feature distribution by class

featurePlot(x = GermanCredit[,c("EmploymentDuration", "Age")],

           y = GermanCredit$Class,

            plot = "box")

Pre-processing: imputation of missing data, one-hot encoding, and normalization

set.seed(355)

bagMissing <- preProcess(trainingSet, method = "bagImpute")

trainingSet <- predict(bagMissing, newdata = trainingSet)

dummyModel <- dummyVars(Class ~ ., data = trainingSet)

trainingSetX <- as.data.frame(predict(dummyModel, newdata = trainingSet))

If you are thinking about an interactive and beautiful web interface then Shiny is the solution.

Shiny interfaces are directly written in R and provide a customizable slider widget that has built-in support for animation.
Example:

library(shiny)

# See above for the definitions of ui and server

ui <- ...

server <- ...

shinyApp(ui = ui, server = server)

tidyquant

is considered as a financial package that is used to carry out quantitative financial analysis.
Package tidyquant is also widely used for importing, analyzing, and visualizing data.
Example:

library(tidyquant)

google <- tq_get(x = "GOOG")

tq_get_options()

?tq_get

tq_exchange_options()

nyse <- tq_exchange("NYSE")

tidyr

is a new package that makes it easy to “tidy” your data. tidyr package is an evolution of Reshape2.

The data is considered tidy when each variable represents columns and each row represents an observation.

gather()

makes “wide” data longer

spread()

makes “long” data wider

separate()

splits a single column into multiple columns

unite()

combines multiple columns into a single column
and More...

Example:

wide_DF <- unite_DF %>% spread(Quarter, Revenue)

head(wide_DF, 24)

Takes away all the limitations of ggplot2.

Example for Networks:

ggraph(ig_loc, layout="fr") + 

  geom_edge_link(aes(color = factor(to), width = log(weight)), alpha = 0.5, 

                  start_cap = circle(2, 'mm'), end_cap = circle(2, 'mm')) + 

  scale_edge_width(range = c(0.5, 2.5)) + 

  geom_node_point(color = V(ig_loc)$color, size = 5, alpha = 0.5) +

  geom_node_text(aes(label = name), repel = TRUE) +

  theme_void() + 

  theme(legend.position = "none") 

ggplot2

is one of the most popular visualization package in R.

It is famous for its functionality and high-quality graphs that set it apart from other visualization packages.
Example:

ggplot(chic, aes(x = o3, y = temp))+

  labs(x = "Ozone Level", y = "Temperature (°F)") +

  geom_smooth(

    method = "lm",

    formula = y ~ x + I(x^2) + I(x^3) + I(x^4) + I(x^5),

    color = "black",

    fill = "firebrick") +

  geom_point(color = "gray40", alpha = .3)