Index
A
- action
- impact, estimating / Estimating the impact of an action
- aggregation / Defining a table with the data
- algorithm accuracy
- measuring / Measuring the accuracy of an algorithm
- apply function / Understanding the basic R objects
- Area Under Curve (AUC) / Predicting the output
- Artificial Neural Networks (ANN)
- about / Perceptron
- average accuracy
- defining / Defining the average accuracy
- computation, visualizing / Visualizing the average accuracy computation
- average linkage / Clustering the clients
B
- binarization / Modifying the features
- business decisions
- data-driven approach / A data-driven approach in business decisions
- origin / Business decisions come from knowledge and expertise
- digital era / The digital era provides more data and expertise
- technology / Technology connects data and businesses
- creating, with unsupervised learning / Making business decisions with unsupervised learning
- business problems
- hidden information, need for / Business problems require hidden information
- future events estimating, need for / Business problems require estimating future events
C
- categoric attribute / Exploring the data using a decision tree
- clients
- clustering / Clustering the clients
- clustering
- clients / Clustering the clients
- clustering techniques / Identifying patterns with unsupervised learning
- clusters
- exploring / Exploring the clusters
- hierarchy, identifying / Identifying a cluster's hierarchy
- complete linkage / Clustering the clients
- contact
- options / Exploring and transforming features
- curve dimensions
- true positive rate / Predicting the output
- false positive rate / Predicting the output
- cvKnn arguments / Defining the average accuracy
D
- data
- containing, hidden information / Data contains hidden information
- reshaping / Reshaping the data
- gathering, to learn from / Gathering the data to learn from
- exploring, interactively / Exploring data interactively
- table, defining with / Defining a table with the data
- visualizing, through histogram / Visualizing the data through a histogram
- exploring, machine learning used / Exploring the data using machine learning models
- exploring, decision tree used / Exploring the data using a decision tree
- overview / Data overview
- data-driven approach
- in business decisions / A data-driven approach in business decisions
- data features
- selecting, to include in model / Selecting the data features to include in the model
- data table syntax / Defining a table with the data
- decision tree
- used, for exploring data / Exploring the data using a decision tree
- decision tree learning, supervised learning
- about / Decision tree learning
- default attribute / Exploring and transforming features
- dendrogram / Hierarchical clustering
- dfFlag object / Building the feature data
- dfGains method / Ranking the features using a filter or a dimensionality reduction
- dimensionality reduction
- used, for ranking features / Ranking the features using a filter or a dimensionality reduction
- discretization / Modifying the features
- dlply function
- .data / Some useful R packages
- .variables / Some useful R packages
- .fun / Some useful R packages
- about / Some useful R packages
- dtLong object / Exploring the data using a decision tree
- dummy / Modifying the features
E
F
- false positive rate (fpr) / Predicting the output
- feature
- impact, visualizing / Visualizing the impact of a feature
- exploring / Exploring and transforming features
- transforming / Exploring and transforming features
- categoric data type / Exploring and transforming features
- numeric data type / Exploring and transforming features
- features
- combined, impact visualizing / Visualizing the impact of two features combined
- data, building / Building the feature data
- visualizing / Exploring and visualizing the features
- exploring / Exploring and visualizing the features
- modifying / Modifying the features
- transforming / Modifying the features
- ranking, filter used / Ranking the features using a filter or a dimensionality reduction
- ranking, dimensionality reduction used / Ranking the features using a filter or a dimensionality reduction
- and parameters, tuning together / Tuning features and parameters together
- features, transforming
- discretization / Modifying the features
- binarization / Modifying the features
- dummy / Modifying the features
- filter
- used, for ranking features / Ranking the features using a filter or a dimensionality reduction
- freqValues method / Exploring and visualizing the features
- future events
- estimating / Business problems require estimating future events
- future outcomes
- predicting, supervised learning used / Predicting future outcomes using supervised learning
- prediciting, supervised learning used / Predicting future outcomes using supervised learning
G
- Generalized Linear Models (GLM)
- about / Predicting the output
- groups
- identifying, k-means used / Identifying the groups using k-means
H
- hidden patterns
- identifying / Identifying hidden patterns
- business problems, need by / Business problems require hidden information
- data, reshaping / Reshaping the data
- with unsupervised learning, identifying / Identifying patterns with unsupervised learning
- hierarchical clustering, unsupervised learning
- about / Hierarchical clustering
- histogram
- used, for visualizing data / Visualizing the data through a histogram
- homogeneous group of items
- identifying / Identifying a homogeneous group of items
- groups identifying, k-means used / Identifying the groups using k-means
- clusters, exploring / Exploring the clusters
- clusters hierarchy, identifying / Identifying a cluster's hierarchy
- k-nearest-neighbour algorithm, applying / Applying the k-nearest neighbor algorithm
- k-nearest-neighbour algorithm, optimizing / Optimizing the k-nearest neighbor algorithm
- housing attribute / Exploring and transforming features
I
- indexTrain / Validating a model
- information gain ratio / Ranking the features using a filter or a dimensionality reduction
K
- k-means
- used, for identifying groups / Identifying the groups using k-means
- K-means, unsupervised learning
- about / k-means
- k-nearest-neighbour algorithm
- applying / Applying the k-nearest neighbor algorithm
- k-nearest neighbors algorithm, supervised learning
- k-nearest neighbour algorithm
- optimizing / Optimizing the k-nearest neighbor algorithm
- Key Performance Indicators (KPIs) / Reshaping the data
- kknn package / Applying the k-nearest neighbor algorithm
- K Nearest Neighbors (KNN) / Predicting future outcomes using supervised learning
L
- lapply function / Understanding the basic R objects
- linear regression
- about / Linear regression
- linkage
- about / Hierarchical clustering
- single linkage / Hierarchical clustering
- complete linkage / Hierarchical clustering
- average linkage / Hierarchical clustering
- loan attribute / Exploring and transforming features
- logistic regression
- about / Predicting the output
M
- machine learning
- about / Technology connects data and businesses
- interactive approach / An interactive approach to machine learning
- expectations / Expectations of machine learning software
- solution, building / Building a machine learning solution
- machine learning model
- building / Building a machine learning model
- validating / Validating a machine learning model
- algorithm accuracy, measuring / Measuring the accuracy of an algorithm
- average accuracy, defining / Defining the average accuracy
- average accuracy computation, visualizing / Visualizing the average accuracy computation
- applying, to business problem / Overview of the problem
- machine learning models
- used, for exploring data / Exploring the data using machine learning models
- machine learning techniques
- about / Overview
- supervised learning / Supervised learning
- unsupervised learning / Unsupervised learning
- mar vector / Exploring and transforming features
- matrixFeatures data table / Identifying the groups using k-means
- mfcol vector / Exploring and transforming features
- Minkowski distance / Applying the k-nearest neighbor algorithm
- model
- using, to predict new outcomes / Using the model to predict new outcomes
- validating / Validating a model
- data features, selecting / Selecting the data features to include in the model
- modelKm function / Identifying the groups using k-means
- multicollinearity / Ranking the features using a filter or a dimensionality reduction
N
- newer outcomes
- predicting / Predicting newer outcomes
- numeric attribute / Exploring the data using a decision tree
O
- objects, R
- operation / Defining a table with the data
- outcomes
- predicting, model used / Using the model to predict new outcomes
- output
- exploring / Exploring the output
- predicting / Predicting the output
P
- packages, R
- about / Some useful R packages
- parameters
- tuning / Tuning the parameters
- and features, tuning together / Tuning features and parameters together
- patterns
- identifying, with unsupervised learning / Identifying patterns with unsupervised learning
- Pearson correlation coefficient filter / Ranking the features using a filter or a dimensionality reduction
- perceptron
- about / Perceptron
- pie function / Applying the k-nearest neighbor algorithm
- Point of sale (POS) data / Data contains hidden information
- Principal component analysis (PCA) / Ranking the features using a filter or a dimensionality reduction
- Principal Components Analysis (PCA)
- about / PCA
R
- R
- about / Why R
- and RStudio / R and RStudio
- objects / Understanding the basic R objects
- standards / What are the R standards?
- packages / Some useful R packages
- random forest
- about / Predicting the output
- random forest algorithm / Predicting newer outcomes
- Receiver Operating Characteristic (ROC) / Predicting the output
- return method / The basic tools of R
- R function, arguments
- RStudio
- and R / R and RStudio
- R tools
- basics / The basic tools of R
- R tutorial
- about / The R tutorial
- R tools, basics / The basic tools of R
- objects / Understanding the basic R objects
- standards / What are the R standards?
- packages / Some useful R packages
S
- sapply function / Understanding the basic R objects
- single linkage / Clustering the clients
- standards, R
- about / What are the R standards?
- supervised learning
- used, for predicting future outcomes / Predicting future outcomes using supervised learning
- about / Overview, Supervised learning
- k-nearest neighbors algorithm / The k-nearest neighbors algorithm
- decision tree learning / Decision tree learning
T
- table
- defining, with data / Defining a table with the data
- test set / Validating a model
- tools, R
- basics / The basic tools of R
- about / The basic tools of R
- training set / Validating a model
- true positive rate (tpr) / Predicting the output
U
- unsupervised learning
- used, for identifying patterns / Identifying patterns with unsupervised learning
- used, for making business decisions / Making business decisions with unsupervised learning
- about / Overview, Unsupervised learning
- K-means / k-means
- hierarchical clustering / Hierarchical clustering
- Principal Components Analysis (PCA) / PCA
W
- weighted KNN / Optimizing the k-nearest neighbor algorithm