Introduction to Data Visualization

Explore bar charts through general theory and a car-brand dataset. Practice building and styling bar charts using a two-column dataset of car brands and ad counts to visualize information clearly.

Learn to create a bar chart in Python by loading data with Pandas, plotting car listings by brand with Matplotlib, and applying Seaborn styling for a polished visualization.

Explore why pie charts are discouraged and how bar charts yield clearer comparisons for data totals 100 percent, using a two-column, four-row dataset on used car fuel types.

Explain the pie chart showing cars by fuel type with clear labels and layout for non-technical audiences. Highlight diesel ~47%, petrol ~36%, gas ~16%, and other fuels ~4%.

Learn when to use pie charts, avoid common misuses like non-summing data and 3d pie charts, limit categories, and consider line charts for timelines.

Learn how area charts, including stacked and 100 percent stacked area charts, reveal trends across variables over time. Analyze a car engine type dataset (diesel, petrol, gas, other) from 1982–2016.

Use area charts to spot trends over time across fuel types, highlighting petrol and diesel dominance, the rise of gas cars, and data gaps in 2008–2009 and 2016.

Use stacked area charts to compare volume across categories when you have three or more variables with numeric axes, and keep categories few while starting the y axis at zero.

Explore line charts for time series data by analyzing daily stock market returns from the S&P 500 and FTSE 100 across 2000 to 2010, with about 2,500 trading days.

Explore how line charts reveal return volatility across time frames, highlighting the 2008 Great Recession and housing market crisis and showing synchronized moves in the U.S. and U.K. markets.

Use line charts for time series data and multiple variables, avoiding spaghetti charts by limiting categories; show trends by not always starting the y-axis at zero.

Learn how histograms reveal the distribution of a numeric variable by binning values into intervals with bar height showing frequency, using a California real estate price dataset.

Explore how a histogram reveals the price distribution of California real estate, highlighting a right-skewed pattern, a peak between 230k–275k, and mid-range dominance across 267 properties.

Learn how to choose the number of bins in a histogram by balancing pattern visibility with detail, using data-driven guidelines and practical examples from real estate prices and interval-size histograms.

Design and interpret histograms with equal-width bins, avoid misleading axis cuts, and transform qualitative data like Likert scales into numeric data for plotting.

Explore how a 2d scatterplot reveals the relationship between two numerical features, highlighting correlation and outliers, and its use in exploratory data analysis with price and area.

Learn to interpret scatter plots by examining the positive relationship between property size (area) and price, spotting outliers, and assessing data integrity across the full dataset.

Learn how over plotting harms readability and how transparency improves it. Observe an inverse relationship between humidity and temperature from a 300-point sample, noting no direct causation.

Explore scatter plots and regression analysis to quantify relationships between variables, using a regression line to illustrate linear fits and the relation between advertising budget and sales across markets.

Explore how the regression line in a scatterplot links advertising budget to sales, showing how slope, intercept, and R-squared quantify the relationship and model strength.

Examine how to identify data relationships by comparing linear regression plots with exponential growth in a bacterial growth curve using scatter plots and regression lines.

Explore combination charts that fuse bar and line charts with dual y axes, showing participants and Python usage percentages, including cumulative frequency up to 100% from 2012–2019 survey data.

Interpret a bar and line combination chart showing yearly participants and Python usage, while noting data nuances and the dos and don'ts of chart design.

Master combination charts by ensuring compatibility when stacking, using data from the same source, labeling clearly, and choosing dual y-axes only when necessary.