The Data Visualization Course: Excel, Tableau, Python, R

Set up your data visualization environments, including Tableau, Python, Jupyter Notebook, and R Studio, with installation guidance; Excel tutorial is skipped as it comes automatically.

Learn how to download and install Tableau public, including providing an email address to download the exe and accepting terms before launching the program.

Learn why Python powers data visualization workflows with open source, cross-platform ease, and a rich ecosystem of packages; discover how Jupyter notebooks connect kernels with browser-based coding for collaborative projects.

Install Anaconda to get Python, Jupyter Notebook, and data science packages; choose Windows, Mac, or Linux, prefer Python 3, 64-bit, and complete the setup.

Navigate the Jupyter dashboard, manage files with checkboxes to duplicate, shut down, rename, move, or delete items, and upload notebooks, create new Python ipynb notebooks in the interactive shell.

Master the Jupyter notebook shell by using code cells, executing with ctrl+enter or shift+enter, and converting between code and markdown cells for efficient, piecewise problem solving.

Explore data visualization libraries, note that Anaconda includes pandas and Matplotlib by default, and learn to install Seaborn via the Anaconda prompt using pip install seaborn.

Install and set up R and the RStudio IDE to begin using the R language for data visualization. Learn to download from CRAN mirrors and complete the installation wizard.

Open RStudio and navigate the console, environment, history, and script pane to run code and manage variables. Learn to set working directory, view plots, manage packages, and access help.

Learn to personalize your RStudio appearance to reduce eye strain by choosing an editor theme—Solarized Dark or cobalt. Adjust font size and font, and preview changes in the editor.

Install and load packages in R using install.packages and library, compare base functions to those in packages, and manage packages in RStudio's packages tab to support visualization with ggplot2.

Explore the general theory of bar charts and practice building a two-column dataset visualization (car brands and ads) using Excel, Tableau, Python, and R.

Create a professional bar chart in Excel by formatting data on a separate sheet, inserting a clustered column chart, adding data labels and axis titles for car listings by brand.

Learn to create a bar chart in Tableau by connecting to a CSV file, exploring dimensions and measures, styling with colors and labels, formatting fonts, and saving to Tableau Public.

Create a Python bar chart of car listings by brand using pandas and matplotlib, enhanced with seaborn styling, labeled axes, a title, and color customization.

Learn to build a bar chart in R with ggplot2, mapping brand to x and listings to y, and tailor appearance with color, title, labels, theme, and rotation.

Interpret bar charts to tell a data story, using Volkswagen's lead and other brand comparisons. Avoid misleading visuals by choosing appropriate axis scales and explain intent when presenting price comparisons.

Explore the general theory of pie charts, why experts like Edward Tufte discourage them, and when to use them in data visualization—illustrated with a used car fuel types dataset.

Create an Excel pie chart from engine fuel type and car count data. Style it with chart design options, add data labels showing percentages, and position a bold legend.

Create a pie chart in Tableau from a CSV data file, display engine fuel type and cars sold, apply percent of total, add labels, and use a colorblind palette.

Create a Python pie chart from a csv dataset using pandas, matplotlib, and seaborn, with labeled percentages, rotation, colorblind-friendly palette, and legend.

Learn to create a pie chart in R with ggplot by converting a stacked bar chart using coord_polar, add percent labels, and apply a colorblind-friendly palette.

Interpret the pie chart showing cars by engine fuel type, with clearly labeled visuals, noting diesel as predominant, petrol next, and others at a small share.

Learn when to use a pie chart, ensuring data sums to 100%, and why 3d pies and donuts mislead; if not suitable, use a line chart.

Explore aria charts, including stacked area charts and 100% stacked area, learn how to display multiple variables over time, and study engine-type car ads from 1982 to 2016.

Create a stacked area chart in Excel from a preformatted data sheet, order categories from largest to smallest, and customize colors with rgb values. Add axis label and a title.

Learn to build a stacked area chart in Tableau from a CSV data source, color by measure names, filter categories, and customize fonts, colors, and axes.

Create a stacked area chart in Python using pandas, matplotlib, and seaborn; load data from CSV, customize colors, add a legend and labels, and visualize engine fuel types by year.

Create a stacked area chart in R using ggplot2, dplyr, and reshape2 by cleaning data, melting engine types, and customizing colors, theme, and axis formatting.

Interpret stacked area charts to reveal fuel-type trends over time, showing petrol and diesel dominance, shifts in fuel popularity, and data gaps such as 2016 and the 2008–2009 stock crisis.

Use area charts to compare category volumes over time with at least three categories and ordered numerical variables, starting at zero. Avoid clutter and note the link to line charts.

Create a line chart in Excel to compare S&P 500 and FTSE returns from 2000 to 2010, then narrow the time frame and adjust axis formatting for readability.

Create a line chart in Tableau by plotting S&P 500 and FTSE returns over time, then adjust granularity, timeframes, and formatting for axes, colors, and labels.

Create a two-line chart of S&P and FTSE returns from 2000 to 2010 in Python using pandas, matplotlib, and seaborn, converting dates to datetime and labeling axes and legend.

Create a line chart in R using ggplot2, reshape2, and plyr; load 2000–2010 data, convert dates, melt S&P and FTSE returns, apply a minimal theme.

Analyze a line chart of the S&P 500 and FTSE 100 returns, highlighting the 2008 housing market crisis and its global spillover, with zoomed views of shorter periods.

Line charts effectively display time series data and multiple variables, while avoiding spaghetti charts by limiting categories; set a baseline that shows the data, not necessarily zero.

Explore histogram basics, including bin intervals, frequency, and distribution, and compare histograms with bar charts using a California real estate price dataset.

Create and format an Excel histogram of California real estate prices from a pre-processed sheet, adjust eight bins, add axis labels, and apply 365 data science blue.

Create a price histogram in Tableau from the real estate data using eight bins, adjust intervals and labels, and apply color, font, and a clear distribution title.

Explore creating a Python histogram of real estate prices using pandas, matplotlib, and seaborn, adjusting bins, range, density, and styling for a clean, interpretable chart.

Create a histogram of price in the real estate data using ggplot in R, customizing bins, color, borders, and axis labels to reveal insights about price distribution.

Analyze a histogram of California real estate prices, with price bins. Highlight the right-skewed pattern, with the 223,000 to 275,000 range as the peak in a 267-property dataset.

Learn how to choose the right number of bins for histograms by balancing detail and pattern, using real estate prices in Excel and interval-size considerations with 6 to 10 bins.

Learn to design and interpret histograms with equal-width bins, avoid misleading axis cuts, and use numerical representations (like Likert scales) for any numeric variable.

Explore how two-dimensional scatter plots display relationships between price and area in a real estate dataset, revealing correlations and outliers and supporting exploratory data analysis, correlograms, and regression checks.

Create a classic scatter plot in Excel from the California real estate dataset, displaying price versus area with customized titles, axis labels, fonts, colors, and adjusted marker size and transparency.

Create a scatter plot in Tableau by converting price and area from sums to dimensions, format the axes and title, and apply color and opacity to show a third variable.

Create a scatter plot in Python using pandas, Matplotlib, and Seaborn to visualize California real estate by area and price, color coded by building type.

Create a scatter plot in R with ggplot2 to show area versus price for California real estate, coloring by building type and adjusting legend and palette.

Explore scatterplots by examining the relationship between property area in feet and price in a California real estate dataset, identify outliers, and note positive collinearity.

Explore how overplotting hides patterns in scatter plots, using transparency or a 300-point sample to reveal relations; remember that humidity and temperature relate inversely and correlation does not imply causation.

Examine scatterplots and linear regression, fitting a regression line to reveal the relationship between advertising budget and sales.

Create a regression line scatter plot in Excel by selecting the data, inserting a scatter chart, and adding a linear trend line with its equation and R squared.

Create a regression scatter plot in Tableau by converting measures to dimensions, adding a linear regression trend line, and formatting axes, colors, and labels for clear data visualization.

Create regression scatter plots in Python with seaborn regplot and lmplot, loading data from CSV with pandas, and format axes and titles to show ad expenditure versus sales (95% CI).

Create a regression scatter plot in R using ggplot2, plotting ad expenditure versus sales, adding a linear model with a 95% confidence interval, and customizing labels and theme.

Explore how regression lines quantify the relation between advertising budget and sales in a scatter plot. Learn how slope, intercept, and r-squared reveal the strength and specifics of the trend.

Explore how regression plots and scatter plots reveal data relationships, from linear fits to exponential or logarithmic patterns, and identify when a regression line misrepresents data like bacterial growth.

Explore combination charts, including bar and line charts with dual y axes, to plot participants and Python usage percentages from the Kdnuggets annual survey (2012–2019) for a Pareto-style analysis.

Create a combo bar and line chart in Excel using a dual axis to display participants and Python user percentages from the Nugget survey, with proper axis labels and formatting.

Create a Tableau combo chart by combining a bar chart of participants over years with a line chart of Python users' percentages on a dual axis.

Create a dual-axis bar and line chart in Python using pandas and matplotlib to show participants and Python user percentages from 2012–2019, with proper axis labeling and percent formatting.

Create a dual y axis bar and line chart in R using ggplot2 to display participants and Python users as a percentage, scaling line by max participants for 2012–2019 data.

Interpret combination charts by examining a bar chart of survey participants and a line chart of Python usage, noting 2014 onward increases, 2019 data collection anomalies, and do's and don'ts.

Assess how to construct effective combination charts by ensuring compatible data sources, choosing appropriate bar or line charts, and clear labeling, avoiding overload and misleading dual axes.