Visualization_Data with ggplot2_Day 2.pptx

Visualization_Data with ggplot2_Day 2.pptx

• 1.
  Visualizing Data with ggplot2 CREATING THELAYERS RAVI PRAKASH JHA BIOSTATISTICS FACULT Y DEPARTMENT OF COMMUNIT Y MEDICINE DR BSA MEDICAL COLLEGE AND HOSPITAL
• 2.
  Outline Effective data visualization transformsnumbers into a story, revealing patterns and insights that words alone cannot convey.  What is ggplot2  Key Concepts  Basic Structure of a ggplot2 Plot  Important Functions in ggplot2  Aesthetic Mappings  Common Geometric Layers  Faceting or Sub-setting  Themes and Customization  Univariate Graphs  Hands-On Exercise  Key Takeaways for the Next Talk
• 3.
  What is ggplot2? ggplot2is a data visualization package in R that allows the creation of complex multi- layered visualizations using a coherent grammar. Advantages: • Highly customizable • Elegant and intuitive syntax • Wide variety of plot types Why Use ggplot2? • Consistent and powerful framework • Facilitates easy exploratory data analysis (EDA)
• 4.
  Key Concepts Grammar ofGraphics: ggplot2 uses a layered grammar to build plots step by step. Core Components: • Data: The dataset being visualized. • Aesthetic Mappings (aes): Define how variables map to visual properties like position, color, or size. • Geometric Objects (geoms): Visual representations of data, like points, lines, or bars. • Statistical Transformations (stats): Summarize or transform data for plotting (e.g., counts for bar charts). • Faceting: Splits the data into subsets and creates separate plots for each subset. • Themes: Control the appearance of non-data elements.
• 5.
  Basic Structure ofa ggplot2 Plot • Load the data • Convert to dataframe Data Frame • Initialize plot • Mention data ggplot() • Define aesthetic mapping • Map axis to variables aes() • Geometric objects-point, line, bar etc • Add layers, facets, themes, labels with “+” geom_ <layer name>()
• 6.
  Important Functions inggplot2 • ggplot(): Initialize the plot. • aes(): Map variables to aesthetics. • geom_*(): Add geometric layers (e.g., points, lines, bars). • facet_*(): Split data into panels. • scale_*(): Modify scales for colors, sizes, or axes. • theme_*(): Customize non-data elements like background and text. Core Functions :
• 7.
  Aesthetic Mappings •What CanBe Mapped? • Position: X and Y axes • Color, size, shape, and fill •Dynamic Mappings: Map data variables to visual properties for deeper insights.
• 8.
  Common Geometric Layers •Overviewof Common Layers: •geom_point(): Scatterplots •geom_line(): Line graphs •geom_bar(): Bar charts •geom_histogram(): Histograms •geom_boxplot(): Boxplots •Geom_smooth(): Best Fit
• 9.
  Faceting or Sub-setting •Purpose:Break down data by categories into separate plots. •Faceting Functions: •facet_wrap(): Wrap panels in a grid. •facet_grid(): Arrange panels by row and column.
• 10.
  Themes and Customization •AvailableThemes: •theme_gray(): Default theme. •theme_minimal(): Simple and clean. •theme_classic(): Traditional appearance. •Customization Options: •Titles and axis labels •Legend placement and styling •Background colors and grid lines
• 11.
  Univariate Graphs Univariate graphsplot the distribution of data from a single variable. The variable can be categorical (e.g., race, sex, political affiliation) or quantitative (e.g., age, weight, income). Qualitative/ Categorical 1) Bar Chart 2) Pie Chart 3) Tree Map 4) Waffle Chart Quantitative 1) Histogram 2) Kernel Density Plot 3) Dot Chart
• 12.
  Hands-On Exercise in R Studio
• 13.
  Key Takeaways forthe Next Talk What We Have Learnt? • Hands-on session using ggplot2 • Building layered plots with ggplot2. • Customizing themes and aesthetics. • Exploring advanced visualizations (e.g., faceted plots, annotations). Preparation for the Next Talk: • Multivariate Graphs.