2023 CORE: Data Science and Machine Learning

Explore the data analyst role as a gateway to data science, delivering data products and real-time dashboards to decision makers using spreadsheets, SQL, and Tableau.

Explore what spreadsheets are—electronic grids of data used for calculations. The course centers on Microsoft Excel as the widely used, feature-rich business calculator, with context on Google Sheets and Numbers.

Explore how Microsoft Excel fits into Office 365, compare browser-based and desktop experiences, and learn to create workbooks, use templates, and collaborate with others.

Explore Microsoft Excel's grid structure, ribbon tools, and 1 million-row limit, then learn to reference across sheets, format cells, and understand Excel files as open XML zip containers.

Explore Excel templates in 365, including premium and standard options, to jumpstart projects, format data, and manage workbooks without starting from scratch.

Protect a workbook by locking it with a password, restricting changes, and applying a digital signature or marking it final, while encrypting sensitive analyses for authorized users.

Learn to share and secure workbooks with link-based access, permissions, expiration, and passwords, then apply fine-grained editing rights via the review tab for what-if analysis and decision-ready collaboration.

Explore how Excel uses operators to perform arithmetic, concatenation, and logical comparisons, and learn the order of operations and parentheses to build powerful formulas.

Explore built-in Excel formulas for data cleaning, rounding, text manipulation, and financial analysis. Learn to use average, min, max, proper, left, right, len, now, and npv with the formula ribbon.

Explore summary statistics, the high-level measures of distributions that drive data exploration and modeling, including mean, median, mode, quantiles, variance, standard deviation, covariance, correlation (r), and r squared.

Learn to compute summary statistics in Excel from scratch and with built-in functions, including mean, variance, standard deviation, covariance, and correlation, while distinguishing population versus sample calculations.

Learn to import a text file into Excel via the data tab and get and transform data, using the California housing prices csv from Kaggle.

Learn how to work with Excel data tables, apply filters, sorts, slicers, and total rows, and compute summary statistics like mean and median for data science analysis.

Explore summary statistics on a data table in Excel, calculating mean, population vs. sample standard deviation, and correlations between income, bedrooms, and housing value, with 3D maps for visualization.

Analyze a California home price data set from 1990, computing summary statistics and correlations among numeric variables, with visualizations and guidance on publishing as web pages or Power BI.

import a cleaned Titanic train CSV into Excel, explore passenger features from age and fare to class and survival, and set up for matching and lookups in intermediate data analysis.

Master lookups and matches in excel by using VLOOKUP and HLOOKUP, and extend with MATCH and INDEX to retrieve values from tables, plus data validation dropdowns for interactive exploration.

Calculate churn rate and customer lifetime value, using margin over churn to estimate each new customer's worth.

Apply Excel's black-box forecasting tools to time series data from Yahoo! Finance, importing five years of monthly Microsoft prices to generate forecasts with confidence intervals.

Learn data visualization foundations by exploring distributions and relationships across single, two, and three variables, composition over time, and comparison using Excel, plus tools like the Juice Analytics chart chooser.

Explore how to visualize Microsoft stock data in Excel using line and candlestick charts, create chart sheets, adjust formats, and compare chart types, noting data layout for meaningful visuals.

Discover how dashboards provide a single, focused view of analysis that delivers quick insights, using Excel to model data, design simple templates, and separate data analysis from visuals.

Explore a Microsoft stock performance dashboard in Excel, highlighting total return, average monthly returns, annual return, and the max monthly return, with visuals and sparc lines.

Explore Power Query to import data from files, databases, and the web, create refreshable queries, and automate data loading into structured tables with optional editor transformations.

Explore how to create and analyze pivot tables in Excel to summarize data, compare Titanic survival by sex and class, and visualize findings with charts.

Learn how modeling represents real-world systems through physical, graphical, and mathematical forms, with a focus on optimization using linear programming to maximize or minimize objectives under constraints.

Explore linear programming through a chocolate milk production example and a daily fantasy sports lineup, demonstrating how to formulate objectives and constraints and solve with Excel's solver.

Explore the Excel Analysis ToolPak to perform ANOVA, regression, descriptive statistics, and exponential smoothing, then build histograms with bin ranges and view cumulative percentages.

learn to enable the developer tab in Excel, write and run VBA macros, and use the macro recorder to automate tasks and create custom functions for data work.

Master the core topics of spreadsheets for data analysis, balancing fast, visual data work in Excel with its limitations, and preview SQL and Tableau as complementary tools.

Learn how databases persist data beyond memory, contrast file systems with relational databases and SQL, and explore local and server deployments, plus NoSQL and big data concepts.

Set up Sublime Text as a sql editor, explore syntax highlighting by file extension, and practice creating sql and Python files to prepare queries to execute against a database.

Explore SQL syntax for data science by learning comments, commands, keywords, identifiers, and literals, and practice crafting select statements that fetch all columns from a table with semicolon termination.

Explore SQLite, a free, open-source, local SQL database engine that is fast, self-contained, and cross-platform, with practical setup on Windows, Mac, and Linux.

Set up sqlite on windows by downloading the tools folder, placing the sqlite3 executable in your sql directory, and using the sqlite command prompt and .help to learn commands.

Create and populate a SQLite database from HR schema using SQL scripts, including tables like employees, dependents, departments, jobs, locations, countries, and regions; load schema, populate data, and run queries.

Master core sql basics to query a single table using select, from, limit, and where. Understand selecting all columns and filtering results with operators.

Explore sql query basics with between and like operators, using inclusive ranges, wildcard patterns, and underscores to match conditions, while applying and, parentheses, and where clauses.

Learn to combine sql conditions with and, or, and not; understand exists with subqueries, and identify null and not null values to filter data and validate tables.

Learn to use order by and distinct in basic SQL queries to sort employees by first name and salary, with ascending or descending order and multi-column sorting.

Explore intermediate SQL aggregate functions such as count, sum, average, min, max, and group by to compute department level salaries; learn aliases and rounding for clean results.

Explore inner joins to combine data from employees and departments and reveal department names. Practice using aliases, join on department_id, and extend to locations for state provinces to enrich analysis.

Learn to use the with clause and subqueries to identify departments by location and filter employees via department IDs, applying in and not in conditions.

Explore how to insert, update, and delete data in a database, using insert into values, update set where, and delete from clauses on the dependence table.

Create views to turn complex queries into virtual tables that return consistent results across sessions. Build, query, and manage the salary report view, including dropping and recreating updates in SQLite.

Discover how business intelligence tools connect data lakes and data warehouses, extract insights visually through ETL and SQL-backed dashboards.

explains why we pick Tableau for business intelligence, noting its popularity, strong community, and Tableau Public portfolio capabilities, with comparisons to Power BI and legacy ERP tools.

Install tableau public by downloading the Windows or Mac app with your email, then explore tableau public’s Discover tab, resources, how-to videos, and publish your work after creating an account.

Explore how to import CO2 emissions data from Kaggle into Tableau, create geospatial maps and time-series visuals, and build interactive dashboards with filters.

Explore Tableau data types by comparing dimensions and measures, including discrete and continuous values; learn to filter nulls, count years per country code, and create bar charts.

Explore basic visualizations in Tableau, including bar charts, line charts, and maps of annual CO2 emissions, by manipulating filters, discrete vs continuous variables, and aggregations across years and regions.

Explore Tableau filters and meta filters that update entire data sources, including continuous vs discrete filters, handling nulls, and customizing dropdown, slider, or checkbox lists for country selections.

Connect Tableau to the WHO data API to pull indicator tables and smoking data. Build map visualizations using spatial dimensions and sex filters to compare male, female, and both sexes.

Learn how to join data from multiple sources in Tableau using relationships and joins, combining GDP and CO2 emissions datasets by country code and year to create integrated insights.

Explore advanced bar chart techniques in Tableau using South America GDP data to compare years, apply filters, and create calculated fields and bullet charts.

Explore how Tableau handles dates, times, and date parts for year, month, and day. Visualize year over year performance, average adjusted close, and heat maps by date parts in Tableau.

Explore tableau visualizations to compare Titanic survival by sex, family size, and title, using the Titanic csv dataset, with bar charts, color mappings, and tree maps.

Explore how to visualize distributions in Tableau using circle charts, average lines, and box plots to analyze Titanic survival by family size, class, and age.

Master Tableau dual axis visualizations by comparing high and low prices by date and overlaying stock price with volume, using date parts to reveal their relationship.

Explore fine-grained formatting in Tableau, including workbook- and sheet-level font, color, and axis formatting, and learn to customize tooltips and integrate cross-sheet visuals.

Learn to build Tableau dashboards and stories by joining GDP and CO2 emissions data, crafting maps and charts, configuring filters and actions, and previewing dashboards across devices.

Explore Tableau's advanced analysis tools that enable statistical analysis without really knowing what's going on in the background, using trend lines and forecasts with monthly aggregation to reveal future trends.

Learn to save and publish to Tableau Public, sign in, share dashboards, and build a Tableau story for your project portfolio.

Discover Tableau desktop pro overview: connect to local files or servers, use sqlite and sql via odbc, choose live or extract data, and export workbooks for sharing.

Explore the generalist data scientist role, blending applied statistics with algorithms to uncover insights and support executive decision making with predictive and prescriptive analytics using R, SQL, and dashboards.

Explore CRAN and install base R to access a powerful open-source statistical programming language with base R, packages, and the RStudio IDE for efficient data analysis.

Explore installing and using RStudio as an integrated development environment for R, from the CRAN site to desktop and open-source server options, and how to write and run .r scripts.

Explore the RStudio environment through a hands-on tour of the console, plots pane, and script editor. Learn to run code, manage objects, install packages like ggplot2, and use keyboard shortcuts.

Use R as a calculator for basic operations (addition, subtraction, multiplication, division, powers), with immediate interpreted output, and learn to write comments with # and to manage simple chained calculations.

Explore how base r stores results as objects, using the assignment arrow and indexing for vectors, and perform arithmetics and matrix operations, while following naming rules and session behavior.

Explore base R built-in functions for rounding, factorials, means, medians, and sampling, learn about function arguments and defaults, and create custom, dice-rolling functions with sourcing.

Discover base R datasets and prepackaged examples, use the data() function to list them, and practice exploring datasets from ggplot and other packages.

Import data with the data function, explore the diamonds dataset, and create histograms and plots using hist and the base graphics in R, while inspecting the environment.

Install R packages from cran or local mirrors, manage dependencies with install.packages, explore the tidyverse, and use c(), library, qplot, ggplot, rnorm, and runif to create and plot data.

Explore atomic vectors in R, including integers, doubles, characters, logical, and other vector types, and learn how to inspect length, perform sums, and understand floating point and type coercion.

Learn to attach and inspect metadata on vectors with the attributes function, focusing on names and dimensions, and add custom attributes with attr to enrich objects.

Learn how to create and manipulate matrix and array objects in R by adjusting dimensions, using matrix for two-dimensional data and array for three-dimensional data.

Examine the class attribute as a foundational property that guides object behavior, showing numeric vectors becoming matrices and how character, logical, and time objects like posix time fit.

Explore how factors transform categorical variables into numeric representations by wrapping a vector in a factor, revealing levels and integers that support regression, classification, and visualization.

Explore how coercion switches a data object's class between numeric, character, and logical, and how warnings show when a value can't be coerced, a key aspect of data cleaning.

learn how lists in R enable heterogeneous storage and nested structures, with indexing via double and single brackets, and handle XML data from the World Bank API.

Data frames are two-dimensional, tabular structures—like Excel tables—for storing heterogeneous data. Access columns with the dollar sign, flatten lists into frames, and use table counts in exploratory data analysis.

Learn how to import data from csv and other formats into R, creating data frames with read.csv, read.table, and read Excel. Save and load to manage in-memory objects.

Update values in data frames by index or condition, add new columns, create calculated columns like age divided by fare, and handle missing values and zeros to clean data.

Master subsetting a data frame with logical operators, selecting frames or columns, changing zero fares, and creating new columns based on conditions, while chaining and or for complex filters.

Identify missing values in data frames using is.na and boolean indexing, then subset or replace them to enable clean data for analysis in R and compute mean on non-NA values.

Explore the which function to locate indices of data matching a condition, such as zero fares in the Titanic data set, enabling targeted subsetting and data inspection.

Explore core flow control in R, including if, else if, for loops, while loops, and repeat loops, with break statements and performance tips to avoid slow looping when possible.

Explore the foundations and evolution of exploratory data analysis, from inference to data-driven storytelling. Learn core techniques—summary statistics and clean, intuitive plots—that help tell a data story.

Explore exploratory data analysis on a Kaggle house price dataset using ggplot visualizations, summary statistics, and regression modeling to guide feature engineering and prediction.

Revisit summary statistics, clarify numeric, continuous, discrete, categorical and ordinal data types, and show robust location measures (median, trimmed mean, weighted mean) for handling outliers and power-law distributions.

Explore robust location estimates in R by comparing mean, median, weighted mean, and trimmed mean, showing how weights and 10% trimming influence outliers.

Explore how spread measures dispersion, compare standard deviation, range, mean and median absolute deviation, and robust estimates like the interquartile range, quantiles, and degrees of freedom; compute these in R.

Explore spread measures in R by comparing standard deviation, mean absolute deviation, and interquartile range, highlighting robustness to outliers and when to trust each metric.

Explore essential exploratory data analysis tools, from box plots and Tukey's quartiles to frequency tables, histograms, density plots, and scatter and correlation visuals, using the tidyverse.

Explore the tidyverse and ggplot2 to manipulate data with dplyr and build layered, readable visualizations using the grammar of graphics.

Explore the tidyverse website for resources, documentation, and package installation guidance, including ggplot2, and bookmark cheat sheets and the data science roadmap repository.

Learn how to map data to aesthetics in ggplot by using mapping in geom_point, control color by sex or set a fixed color, and add layers with the plus operator.

Learn to use ggplot facets, including wrap and grid, to create subplots by survived and passenger class, and facet by two variables; coercing numeric to character or factor.

Learn to stack multiple geoms in ggplot, apply smoothing with standard error, and control global versus local mappings to build more and more story-like data visualizations.

Explore how ggplot handles stat transforms by default, plotting counts or proportions for variables like family size, and learn to switch from count to prop using computed variables.

Explore how to use ggplot position adjustments (identity, dodge, and fill) to tell stories by coercing variables into factors, coloring and stacking survival by family size on the Titanic dataset.

Explore ggplot coordinate systems, from cartesian to polar, and learn flips and tweaks that transform plots like the box plot and bar plot into clear, space-efficient visuals.

Explore the ggplot framework by mastering its seven layer components—data, mappings, aesthetics, statistical transformation, position, and coordinates—enabling flexible visualizations and in-depth exploratory data analysis.

Explore the ggplot gallery book and Our Graph Gallery to reproduce and customize plots—from distributions, correlation plots, and rankings to scatter plots—using code and inspiration for your data science journey.

Learn naming conventions for R objects in ggplot, contrasting snake_case and camelCase, avoid periods, and ensure readable, consistent, explicit names.

Use dplyr filter to create explicit subsets, compose criteria with and/or and in operators, and handle missing values to examine pclass, age, and cabin.

Employ mutate to add new columns by computing values from existing data or external vectors, such as the absolute distance from the column mean, enhancing data frame flexibility.

Master the pipe syntax to chain data operations in the tidyverse, using group_by and summarize to compute counts and averages across subgroups like sex, passenger class, and family size.

Explore string handling in R with stringr, covering quotes, escapes, lengths, substrings, and concatenation, and extract titles from names in the Titanic dataset using grep and regex.

Use stringr to pattern-match strings with regular expressions, view results, and detect matches; build a Titanic title column labeling Mr., Mrs., or other.

Learn to handle dates and times in R using the lubridate package, converting strings to date objects, formatting dates, and visualizing time-based data with ggplot for exploratory data analysis.

Discover how markdown helps data scientists share Kaggle-style exploratory data analysis on the web, using headers, lists, links, images, and code blocks in RStudio and r markdown.

Learn how to extend markdown with R Markdown in RStudio, create notebooks and raw markdown, knit code to HTML, and publish interactive documents, dashboards, and websites.

Explore notebooks in Kaggle as interactive computing environments that mix code and markdown, show outputs, and enable iterative analysis and easy sharing.