Machine Learning with R

DATA SCIENCE:

1. INTRODUCTION TO DATA SCEINCE

• NEED OF DATA SCEINCE
• Who is data scientist
• Who can be data scientist
• Technologies used in data science
• Work flow of data science

2. INTRODUCTION TO MACHINE LEARINING

• What is machine learning
• Types of learning
• Supervised learning
• Un-super vised learning
• Machine learning algorithms
  • KNN
• Naïve Bayes
• Decision trees
• Classification rules
• Regression
• Linear regression
• Logistic regression
• K-means clustering
• Association rules
• Neural networks
• Svm’s

3. MACHINE LEARNING LANGUAGE

• R
• Python
• Mahout
• Spark Mlib
• Amazon machine learning
• Lisp
• Java etc.

4. INTRODUCTION TO R

• History of s/s-plus
• Development with R
• Installing R and R-studio
• C ram
• Setting up R environment
• Installing & loading of R packages
• Basic data types in R
• Structures in R
• Vector
• List
• Matrix
• Data frame
• array
• R as calculator
• Performing calculations on different structure

5. SUB SETTING THE DATA

• Extracting required data from R objects
• Subset
• Using DPLYR and TIDYR package

6. LOADING DATA INTO R OBJECTS

• Data extraction from URL
• Data extraction from CSY
• Data extraction from clipboard

7. VIEWING / THE DATA USING R EXPLORING

• Statistical observation
• Mean
• Mode
• Median
• Quantile
• Box plots/histograms /plot for observing of data

8. GRAPHICS WITH R

• Managing graphics
• High level plotting commands
• Plot() function
• Plotting multiple curves on the same graph
• Pie charts
• Histograms
• Box plot
• Scatter plots
• QQ(Quantile-quantile)plots
• Use copy /paste to copy
• 3-dimensional plots
• Use a legend()function
• Low-level plotting commands

9. ANOVA

• Anova(analysis of variance)
• Data files
• Inputting data
• One –way anova
• Two –way anova
• Graphical summary of anova
• Extracting means and statistics
• Table commands
• More complex anova models

10. LAZY LEARNING –CLASSIFICATION USING NEAREST NEIGHBORS

• Understanding classification using nearest neighbours
• The KNN algorithm
• Calculating distance
• Choosing an appropriate k
• Preparing data for use with KNN
• Why is the KNN algorithm lazy?
• Diagnosing cancer with the KNN algorithm
• Collecting data
• Exploring and preparing the data
• Transformation-normalizing numeric the data
• Data preparing –creating training and test datasets
• Training a model on the data
• Evaluating model performance
• Improving model performance
• Transformation –z-score standardization
• Testing alternative values of k

11. PROBABILISTIC LEARNING – CLASSIFICATION USING NAÏVE BAYES

• Understanding naïve Bayes
• Basic concepts of Bayesian methods
• Probability
• Joint probability
• Conditional probability with Bayes’ theorem
• The naïve Bayes algorithm
• The naïve Bayes classification
• The Laplace estimator
• Using numeric features with naïve Bayes
• Filtering mobile phone spam with the naïve Bayes algorithm
• Collecting data
• Exploring and preparing the data
• Data preparation –processing text data for analysis
• Data preparation –creating training and test datasets
• Visualizing text data-word clouds
• Data preparation-creating indicator features for frequent words
• Training a model on the data
• Evaluating model performance
• Improving model performance

12. DIVIDE AND CONQUER –CLASSIFICATION USING DECISION TREES AND RULES

• Understanding decision trees
• Divide conquer
• The C5.0decision tree algorithm
• Choosing the best split
• Pruning the decision tree
• Identifying risky bank loans using C5.0 decision trees
• Collect data
• Exploring and preparing the data
• Data preparation-creating random training and test datasets
• Training a model on the data
• Evaluating model performance
• Improving model performance
• Boosting the accuracy of decision trees
• Making some mistakes more costly than others
• Understanding classification rules
• Separate and conquer
• The one rule algorithm
• The RIPPER algorithm
• Rules from decision trees
• Identifying poisonous mushrooms with rule learners
• Collecting data
• Exploring and preparing data
• Training a model on the data
• Evaluating model performance
• Improving model performance

13. FORECASTING NUMARIC DATA – REGRESSION METHODS

• Understanding regression
• Simple linear regression
• Ordinary least squares estimation
• Correlations
• Multiple linear regression
• Predicting medical expenses using linear regression
• Collecting data
• Exploring and preparing data
• Exploring relationships among features- the correlation matrix
• Visualizing relationships among features –the scatterplot matrix
• Training a model on the data
• Evaluating model performance
• Improving model performance
• Model specification –adding non-linear relationships
• Transformation –converting a numeric variable to a binary indicator
• Model specification –adding interaction effects
• Putting it all together-an improved regression model
• Understanding regression trees and model trees
• Adding regression to trees
• Estimating the quality of wines with regression trees and model trees
• Collecting data
• Exploring and preparing the data
• Training a model on the data
• Visualizing decision trees
• Evaluating model performance
• Measuring performance with mean absolute error
• Improving model performance

14. FINDING PATTERNS- MARKET BASKET ANALYSIS USING ASSOCIATION RULES

• Understanding association rules
• The Apriori algorithm for association rule learning
• Measuring rule interest –support and confidence
• Building a set of rules with the Apriori
• Identifying frequently purchased groceries with association rules
• Collecting data
• Exploring and preparing the data
• Data preparation – creating a sparse matrix for transaction data
• Visualizing item support –item frequency plots
• Visualizing transaction data-plotting the sparse matrix
• Training a model on the data
• Evaluating model performance
• Improving model performance
• Sorting the set of association rules
• Taking subsets of association rules
• Saving association rules to a file or data frame

15. FINDING GROUPS OF DATA- CLUSTERING WITH K-MEANS

• Understanding clustering
• Clustering as a machine learning task
• The K-means algorithm for clustering
• Using distance to assign and update cluster
• Choosing the appropriate number of cluster
• Finding teen market segments using K-means clustering
• Collecting data
• Exploring and preparing the data
• Data preparation –dummy coding missing values
• Data preparing –imputing missing values
• Training a model on the data
• Evaluating model performance
• Improving model performance

16. EVALUATING MODEL PERFORMANCE

• Measuring performance for classification
• Working with classification prediction data in R
• A closer look at confusion matrices
• Using confusion matrices to measure performance
• Beyond accuracy – other measure of performance
• The kappa statistic
• Sensitivity and specificity
• Precision and recall
• The F- measure
• Visualizing performance TRADEOFFS
• ROC curves
• Estimating future performance
• The holdout method
• Cross-validation
• Bootstrap sampling

17. IMPROVING MODEL PERFORMANCE

• Tuning stock models for better performance
• Using caret for automated parameter tuning
• Creating a simple tuned model
• Customizing the tuning process
• Improving model performance with meta – learning
• Understanding ensembles
• Bagging
• Boosting
• Random forests
• Training random forests
• Evaluating random forest performance