NYC

Data Science Academy

12-Week Data Science Bootcamp C urriculum

Week 1
Data Science Toolkit Linux, Git, Bash, and SQL
Data Science with R Data Analytics Part I
Linux system
o Introduce Linux environment
o Learn Linux commands
o IO redirection and Pipe
o Introduce server-side Linux usage
Git
o Introduce modern source code management
o Learn common git operations
o Setup github and personal portfolio page
Other server related topics
o Text editors and IDEs
o ssh: how to communicate with a remote server
o Linux environment variables
SQL
o Introduction to relational database
o Introduction to structured query language
o SQL major commands and examples
Programming foundation in R I
o Syntax
o Data object: Vectors, Matrices, Data Frames, and Lists
o Common functions
o Rstudio environment and package management
o Local data input/output
o Introduction to R data visualization
Programming foundation in R II
o Data sorting and merging
o String manipulation
o Dates and times
o Connecting to an external database

Week 2
Data Science with R Data Analytics Part II
Data manipulation with dplyr
o Tables in R
o Join
o Subset
o Advanced manipulations with dplyr
Data Visualization with "ggplot2"
Updated June 29, 2016

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

o Histogram
o Point graphics
o Columnar graphics
o Line charts
o Pie charts
o Box plots
o Scatter plots
o Visualizing multivariate data
o Matrix-based visualizations
o Maps
Introduction to Shiny
o Shiny introduction
o Design the User-interface
o Control widgets
o Build reactive output
o Use data table in Shiny Apps
o Use R scripts, data and packages
o UI and server for the App
o Make Shiny perform quickly
o Matrix-based visualizations
o Use reactive expressions
o Share and deploy Shiny apps
Lab: Moneyball
Project 1 Due: Exploratory Data Visualization

Week 3
Data Science with Python - Data Analytics Part I

Python Programming Language I

o
Simple Values and Expressions
o
Functions
o
Lists
o
Conditionals
o
Functional programming: map, filter and reduce

Python Programming Language II

o
String operations
o
File input/output and searching
o
Data Structures:

Mutating operations on Lists

Tuples, sets and dictionaries

Python Programming Language III

o
Control flows
Updated June 29, 2016

Errors and exceptions

Object-oriented programming

Web scraping
o
Regular expression
o
HTML, beautiful soup and scrapy
o
NoSQL and MongoDB


Week 4
Data Science with Python Data Analytics Part II

Numpy and Scipy

o
Basic data structure and operations
o
Matrices and linear algebra
o
Stats module
o
Random Sampling

Pandas
o
Series and data frame
o
I/O of pandas data frame
o
Concatenation and merge
o
Arithmetic, drop, apply and describe
o
Selection and filter
o
Missing values
o
Grouping and aggregation
o
Time series
o
Interacting with data base
Matplotlib and Seaborn
o
Basic plots
o
Statistical plots:

Scatter plots

Histogram

Boxplot

Barchart
o
Multiple figures
o
Advanced plots with seaborn
Python lab: linear regression from scratch
Project 2 Due: R Shiny Interactive Applications

Week 5
Data Science with R - Machine Learning Part I

Foundations of Statistics
o
Descriptive Statistics
o
o

Updated June 29, 2016

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

Measures of Centrality

Measures of Variability

Frequency, Proportion & Contingency Tables

Correlation
o
Hypothesis Testing

One Sample t-test

Two Sample t-test

F-test

One-way ANOVA

X2 Test of Independence
o
Introduction to Machine Learning

Supervised Learning

Regression

Classification

Unsupervised Learning

Clustering

Dimension Reduction

Missingness & Imputation

o
Types of Missingness

MCAR

MAR

MNAR
o
Basic Methods of Imputation

Mean Value Imputation

Simple Random Imputation

Regression Prediction
o
K-Nearest Neighbors

Voronoi Tessellations

KNN for Classification

KNN for Regression

Distance Measures

Linear Regression I
o
Simple Linear Regression

From a Mathematical Standpoint

Accuracy of the Coefficient Estimates

Performing Hypothesis Tests

Constructing Confidence Intervals

o
Assumptions & Diagnostics
o
Transformations

Power Transformation

Box-Cox Transformation
Updated June 29, 2016

The Coefficient of Determination R2

Linear Regression II
o
Multiple Linear Regression

From a Mathematical Standpoint

o
Assumptions & Diagnostics
o
Potential Problems
o
Research Questions
o
Variable Selection
o
Factors
o
Interactions
o
Higher-Order Terms
o

Week 6
Data Science with R - Machine Learning Part II

Lab: Building Bridges

Generalized Linear Models

o
Logistic Regression

The Curse of Dimensionality

o
Ridge Regression
o
Lasso Regression
o
Cross-Validation
o
Bias/Variance Tradeoff
o
Density
o
Principal Component Analysis

The Curse of Dimensionality

o
Density
o
Principal Components Analysis

Guest Lecture: Dataiku Part I

Project 3 Due: Python Web Scraping

Week 7
Data Science with R - Machine Learning Part III

Classification
o
Feature Selection
o
Support Vector Machines
o
Decision Trees
o
Pruning/Purity/Entropy/GINI
o
Random Forests
o
Bagging
o
Boosting

Cluster Analysis
Updated June 29, 2016

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

o
o
o

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

K-Means Clustering
Agglomerative Clustering
Hierarchical Clustering
Neural Networks

Week 8
Data Science with R - Machine Learning Part IV
Introduction to Natural Language Processing

Case Study: Spam Detection

Association Rules
o
Market Basket Analysis

Nave Bayes Analysis

Introduction to Natural Language Processing

o
Creating corpus: stemming and lemmatization
o
POS tag and chunking
o
Text classification

Time Series Analysis

o
Smoothing
o
Seasonal Decomposition
o
ARIMA

Guest Lecture: Dataiku Part II

Week 9
Data Science with Python - Machine Learning
Machine Learning Recap / Linear Regression
o
Introduction to scikit learn
o
Simple linear regression
o
Multiple linear regression
o
Stats module
Classification part I
o
Logistic regression
o
Discriminant analysis
o
Nave Bayes
Model Selection
o
Cross-validation
o
Bootstrap
o
Feature selection
o
Regularization
o
Grid search
Classification part II
Updated June 29, 2016

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

o
Support vector machine
o
Decision tree
o
Random forest
Unsupervised learning
o
Principal Components Analysis
o
Kmeans and Hierarchical Clustering
Project 4 Due: Machine Learning Project (It can be a Kaggle competition, a hiring partner
project or a non-profit project from our partners)

Week 10
Big Data
Parallel processing: Introduction to Hadoop and MapReduce
o
HDFS
o
MapReduce

Conceptual framework

Streaming and Python

o
Examples and lab work
MapReduce design pattern
o
Filtering patterns

Simple filtering

Top N
o
Summarization patterns

Numerical summarizations

Inverted Index summarizations

Apache Hive:
o
Databases for Hadoop
o
Hive

Select

Joins
o
Compiling HiveQL to MapReduce
o
Technical aspects of Hive
o
Extending Hive with TRANSFORM
Spark
o
Basics concepts

RDDs, transformations and actions

PairRDDs
o
Examples

Wordcount

Mean and variance

Updated June 29, 2016

NYC Data Science Academy

12-Week Data Science Bootcamp C urriculum

Week 11
Big Data and Algorithms

Spark MLlib
Amazon Web Service
Introduction to Algorithms
o
Analysis of algorithms: big-O notation
Sorting
o
Elementary sorts
o
Merge sorts
o
Quick sorts
Searching
o
Linear search
o
Binary search
o
Hash tables
Machine Learning Theory Defense Practice

Week 12
Capstone Project Presentations and Review

Machine learning theory defense practice

SQL code review
R code review
Python code review
From the beginning of Bootcamp, you will work on hands-on projects. Now your
Capstone Project lets you create your own data product that showcases your interests
and talents. Students are free to use anything covered in class on this project.

Project 5 Due: Capstone Project

Updated June 29, 2016