# Scatterplots including Time Series `lessR` introduces the concept of a **data view** visualization function, in which the choice of visualization function directly reflects the structure of the data and the analyst's goal for understanding the data. The function `XY()` visualizes the joint distribution of two continuous variables, or more generally the relationship among multiple variables, along with associated summary statistics. The specific representation is selected with the `type` argument: * Scatterplot of points with `type = "scatter"` (default) * Smoothed scatterplot with `type = "smooth"` * Contour plot (2-dimensional density display) with `type = "contour"` For the standard scatterplot, stratification divides the data into groups via the arguments `by` and `facet`. The `by` argument overlays groups in a single coordinate system for direct comparison, while `facet` produces coordinated small multiples on separate panels. Depending on the combination of variable types supplied to `x` and `y`, `XY()` can also create time series, bubble plots, and Cleveland-style dot or lollipop plots. When running in RStudio, static graphics are drawn in the `Plots` window. When the default `use_plotly=TRUE`, the interactive `plotly` version of the scatterplot (including time series) display is also drawn in the `Viewer` window. A scatterplot displays the joint values of one or more variables as points in an $n$-dimensional coordinate system, in which the coordinates of each point are the values of $n$ variables for a single observation (row of data). With a common syntax, `XY(x, y, ...)` generates a family of related 1- or 2-dimensional relationship plots, possibly enhanced with fitted lines, ellipses, and outlier labeling. Categorical variables should typically be defined as factors, and date variables should be stored as `Date` objects. When `x` is of class `Date`, the display is treated as a time-indexed series. `XY()` therefore serves as the relationship-oriented counterpart to `Chart()` (aggregated values) and `X()` (univariate distributions) within the three-function visualization framework implemented in `lessR`. ```r XY( # ------------------------------------------------------- # Data from which to construct the plot for x- and y-axis x, y=NULL, data=d, filter=NULL, # -------------------------------------------------- # Stratification: Same panel or Trellis (facet) plot [x, or x and y] by=NULL, facet=NULL, n_row=NULL, n_col=NULL, aspect="fill", # ---------------------------------------------------------- # Types of plots type=c("scatter", "smooth", "contour"), # ------------------------------- # Enhancements and customizations # ------------------------------- # -------------------------------------------------------------------- # Analogy of physical Marks on paper that create the points and labels # See ?style for more options with the style() function theme=getOption("theme"), fill=NULL, color=NULL, transparency=getOption("trans_pt_fill"), enhance=FALSE, means=TRUE, size=NULL, size_cut=NULL, shape="circle", line_width=1.5, segments=FALSE, segments_y=FALSE, segments_x=FALSE, # ---------------------- # Sort and jitter points sort=c("0", "-", "+"), jitter_x=NULL, jitter_y=NULL, # ---------------- # Outlier analysis ID="row.name", ID_size=0.60, MD_cut=0, out_cut=0, out_shape="circle", out_size=1, # ------------------------------------------------- # Fit line, confidence interval, confidence ellipse fit=c("off", "loess", "lm", "ls", "null", "exp", "quad", "power", "log"), fit_power=1, fit_se=0.95, fit_color=getOption("fit_color"), fit_lwd=getOption("fit_lwd"), fit_new=NULL, plot_errors=FALSE, ellipse=0, # ----------------------------------------------------------------------- # Time series and forecasting, plot x values sequentially [xDate, y or Y] ts_unit=NULL, ts_ahead=0, ts_method=c("es", "lm"), ts_source=c("fable", "classic"), ts_agg=c("sum", "mean"), ts_NA=NULL, ts_format=NULL, ts_fitted=FALSE, ts_PI=.95, ts_trend=NULL, ts_seasons=NULL, ts_error=NULL, ts_alpha=NULL, ts_beta=NULL, ts_gamma=NULL, ts_new_x=NULL, ts_stack=FALSE, ts_area_fill="transparent", ts_area_split=0, ts_n_x_tics=NULL, # Run chart (indicate with .Index for the name of the x-variable) show_runs=FALSE, center_line=c("off", "mean", "median", "zero"), # ---------------------------------- # Integrated violin/box/scatter plot [x only] vbs_plot="vbs", vbs_ratio=0.9, bw=NULL, bw_iter=10, violin_fill=getOption("violin_fill"), box_fill=getOption("box_fill"), vbs_pt_fill="black", vbs_mean=FALSE, fences=FALSE, n_min_pivot=1, k=1.5, box_adj=FALSE, a=-4, b=3, # ----------- # Bubble plot [xCategorical, or xCategorical and yCategorical] radius=NULL, power=0.5, low_fill=NULL, hi_fill=NULL, # ----------------------------------------------------------- # Large data sets, smoothing, contours and binning [x and y] smooth_points=100, smooth_size=1, smooth_power=0.25, smooth_bins=128, n_bins=1, contour_n=10, contour_nbins=50, contour_points=FALSE, # ------------------------------------------------------ # Bins for frequency polygon or text output of VBS plots bin=FALSE, bin_start=NULL, bin_width=NULL, bin_end=NULL, breaks="Sturges", cumulate=FALSE, # ---------------------- # Axes labels and values # ---------------------- # ----------------------- # Axis labels and spacing xlab=NULL, ylab=NULL, main=NULL, sub=NULL, label_adjust=c(0,0), margin_adjust=c(0,0,0,0), # top, right, bottom, left pad_x=c(0,0), pad_y=c(0,0), # --------------------- # Axis values specified scale_x=NULL, scale_y=NULL, origin_x=NULL, origin_y=NULL, # --------------------- # Axis values formatted rotate_x=getOption("rotate_x"), rotate_y=getOption("rotate_y"), offset=getOption("offset"), axis_fmt=c("K", ",", ".", ""), axis_x_prefix="", axis_y_prefix="", xy_ticks=TRUE, n_axis_x_skip=0, n_axis_y_skip=0, # ------ # legend legend_title=NULL, # ------------- # Miscellaneous # ------------- # ---------------------------------------------------- # Add one or more objects, text, or geometric figures add=NULL, x1=NULL, y1=NULL, x2=NULL, y2=NULL, # --------------------------------------------- # Output: turn off, to PDF file, decimal digits quiet=getOption("quiet"), do_plot=TRUE, use_plotly=getOption("lessR.use_plotly"), pdf_file=NULL, width=6.5, height=6, digits_d=NULL, # ------------------------------------------------------------- # Deprecated, to be removed in future versions n_cat=getOption("n_cat"), value_labels=NULL, # use R factors instead rows=NULL, facet1=NULL, facet2=NULL, smooth=FALSE, stat=c("mean", "sum", "sd", "deviation", "min", "median", "max"), stat_x=c("count", "proportion", "%"), # --------------------------------- # Other eval_df=NULL, fun_call=NULL, ...) ``` ## Arguments - `x`: The **variable** plotted on the `x`-axis. The data values can be continuous or categorical, cross-sectional or a time series. If `x` is sorted with equal intervals separating the values, or is a time series, then by default the points are plotted sequentially and connected with line segments. If named `.Index`, a run chart is generated from the corresponding `y` variable. Can specify multiple `x`-variables or multiple `y`-variables as vectors, but not both. - `y`: The **variable** plotted on the vertical `y`-axis. Can be continuous or categorical. - `data`: Optional data frame that contains one or both of `x` and `y`. Default data frame is `d`. - `filter`: A logical expression or a vector of integers that specify the row numbers to retain, defining a subset of rows of the data frame to analyze. - `by`: A **grouping variable**, a categorical variable that provides separate group profiles of the primary numeric variables `x` and, optionally, `y` on the **same** plot. For two-variable plots, the same grouping applies to the panels of a Trellis graphic if `facet1` is specified. - `facet`: One categorical variable, or a vector of two categorical variables, that activates facet graphics (Trellis plots) via the `lattice` package, providing a separate plot of the primary variable(s) `x` and `y` for each level of the variable or combination of two levels. - `n_row`: Optional specification for the number of rows in the layout of a multi-panel display with Trellis graphics. Specify `n_col` or `n_row`, but not both. - `n_col`: Optional specification for the number of columns in the layout of a multi-panel display with Trellis (facet) graphics. Specify `n_col` or `n_row`, but not both. The default is `1`. - `aspect`: Lattice parameter for the aspect ratio of the Trellis panels (facets), defined as height divided by width. The default value is `"fill"` to have the panels expand to occupy as much space as possible. Set to `1` for square panels. Set to `"xy"` to specify a ratio that “banks” to 45 degrees, that is, with the typical line slope approximately 45 degrees. - `type`: Display type. The default is `"scatter"` for a scatter plot. Set to `"smooth"` for a smoothed density plot for two numeric variables, or `"contour"` for a contour plot summarizing the bivariate density. - `theme`: Color theme for this analysis. Make persistent across analyses with `style`. - `fill`: Fill color for the points or for the area under a line chart. Can also be set via the lessR function `getColors` to select from a variety of color palettes. For points, the default is `pt_fill`; for the area under a line chart, `violin_fill`. For a line chart, set to `"on"` to use the default color. - `color`: Border color of the points or line color for a line plot. Can be a vector to customize the color for each point or a color range such as `"blues"` (see `getColors`). Default is `pt_color` from the lessR `style` function. - `transparency`: Transparency factor of the fill color of each point. Default is `trans_pt_fill` from the lessR `style` function, which is 0.1 for points. Bubbles have a default transparency of 0.3. - `enhance`: For a two-variable scatterplot, if `TRUE`, automatically add the 0.95 data ellipse, labels for outliers beyond a Mahalanobis distance of 6 from the ellipse center, the least squares line for all data, the least squares line for the data excluding outliers, and horizontal and vertical lines representing the means of the two variables. - `means`: If one variable is categorical (factor) and the other is continuous, then if `TRUE` the group means are plotted in the scatterplot by default. Also applies to a 1-D scatterplot. - `size`: When set to a constant, the scaling factor for standard points (not bubbles) or for a line, with default of 1.0 for points and 2.0 for a line. Set to 0 to suppress plotting of points or lines. If `ts_area_fill` is used for a line chart, then the default is 0. When set to a variable, activates a bubble plot, with the size of each bubble further determined by the value of `radius`. Applies to the standard two-variable scatterplot. - `size_cut`: For a bubble plot in which bubble sizes are defined by a `size` variable, controls whether and how many bubble labels are shown. If `1` (or `TRUE`), show the value of the sizing variable for selected bubbles in the center of the bubbles, except when the bubble is too small. If `0` (or `FALSE`), no values are displayed. If a number greater than 1, display labels only for the indicated number of values (e.g., the maximum and minimum when set to `2`). The color of the displayed text is set by `bubble_text` from the `style` function. - `shape`: Plot character(s). The default value is `"circle"`, with both a default exterior color and filled interior, explicitly specified by `"color"` and `"fill"`. Other possible values with fillable interiors are `"circle"`, `"square"`, `"diamond"`, `"triup"` (triangle up), and `"tridown"` (triangle down), all uppercase and lowercase letters, all digits, and most punctuation characters. The integers 0–25 as defined by the base R `points` function also apply. If plotting levels for different groups according to `by`, specify a vector of shapes with one shape per group, or set to `"vary"` to have shapes selected automatically across `by` groups. - `line_width`: Width of the line segments that connect adjacent points, such as in time series plots. Set to 0 to remove line segments. - `segments`: Designed for interaction plots of means: connects each pair of successive points with a line segment. Pass a data frame of means, such as from `pivot`. To turn off connecting line segments for sorted, equal-interval data, set to `FALSE`. Currently, does not apply to Trellis plots. - `segments_y`: For one `x`-variable, draw a line segment from the `y`-axis to each plotted point, such as for a Cleveland dot plot. For two `x`-variables, the line segments connect the two points. - `segments_x`: Draw a line segment from the `x`-axis for each plotted point. - `sort`: Sort the values of `y` by the values of `x`, such as for a Cleveland dot plot (numeric `x` paired with a categorical `y` with unique values). If `x` is a vector of two variables, sort by their difference. - `jitter_x`: Randomly perturb the plotted points of a scatterplot horizontally within the limits of the specified value, or set to `NULL` to rely upon the computed default value. - `jitter_y`: Vertical jitter. Defaults to `0`. Same interpretation as `jitter_x`. - `ID`: Name of a variable that provides the labels for selected plotted points for outlier identification , row names of the data frame by default. To label all points, use the `add` parameter (see below). - `ID_size`: Size of the plotted labels. Modify label text color with the `style` function parameter `ID_color`. - `MD_cut`: Mahalanobis distance cutoff to define an outlier in a two-variable scatterplot. - `out_cut`: Count or proportion of plotted points to label, in order of their distance from the center (means) of the univariate distribution or scatterplot, sorted from most to least extreme. For two-variable plots, distance from the center is based on Mahalanobis distance. - `out_shape`: Shape of outlier points in a two-variable scatterplot or VBS plot. Modify fill color from the current `theme` with `out_fill` and `out2_fill` in `style`. - `out_size`: Size of outlier points in a two-variable scatterplot or VBS plot. - `fit`: Type of best fit line . Default is `"off"`. Options include `"loess"` for a non-linear smooth, `"lm"` for a linear least squares model, `"null"` for the null (intercept-only) model, `"exp"` for exponential growth or decay, `"power"` for a general power model in conjunction with `fit_power`, and `"quad"` for a quadratic (power 2) model. If potential outliers are identified according to `out_cut`, a second (dashed) fit line is displayed based on the data **excluding** those outliers. - `fit_power`: Power that describes the response `y` as a power function of the predictor `x`, required when `fit = "power"`. Optionally, and experimentally, may apply to `fit = "exp"`. - `fit_se`: Confidence level for the error band displayed around the line of best fit. Default is 0.95 when a fit line is specified, but is turned off when `plot_errors = TRUE`. Can be a vector to display multiple confidence bands. Set to 0 to suppress error bands. - `fit_color`: Color of the fit line. - `fit_lwd`: Line width of the fit line. - `fit_new`: When `fit` is set to a fitted curve such as `"lm"` or `"quad"`, predicted values are computed at the `x`-values supplied here. - `plot_errors`: If `TRUE`, plot line segments joining each point to the regression line (`"loess"` or `"lm"`), illustrating the size of the residuals. - `ellipse`: Confidence level of a data ellipse for a scatterplot of one `x`-variable and one `y`-variable according to the contours of the corresponding bivariate normal density. Specify the confidence level(s) as a single number or a vector of values between 0 and 1 to plot one or more ellipses. Ellipses are not available in the interactive `plotly` version. For Trellis graphics, only the maximum level is used, with one ellipse per panel. Modify fill and border colors with the `style` parameters `ellipse_fill` and `ellipse_color`. - `ts_unit`: Time unit for plotting time series data when `x` is of type `Date`. Default is the time unit that describes the regular time intervals as they occur in the data. Aggregate to a coarser time unit as specified, such as a daily series aggregated to `"months"`. Dates are stored as variables of type `Date`, which represent calendar dates without times-of-day. Valid values include `"days"`, `"weeks"`, `"months"`, `"quarters"`, and `"years"`, as well as `"days7"` to model weekly seasonality for daily data. Otherwise the time unit for detecting seasonality is typically `"months"` or `"quarters"`. - `ts_ahead`: Number of `ts_unit` steps ahead of the last time period to forecast. - `ts_method`: Forecasting method. Default is `"es"` for exponential smoothing models. Alternatively, choose `"lm"` for a least squares linear regression model that accounts for seasonality. - `ts_source`: Source of forecasting functions. Default is `"fable"` for access to `ETS()` and `TSLM()` from the `fable` package and related functions from the `fpp3` ecosystem, or `"classic"` for base R forecasting functions. - `ts_agg`: Function used to aggregate over time according to `ts_unit`. Default is `"sum"` with an option for `"mean"`. - `ts_NA`: By default, missing `y` values (`NA`) are not plotted, leaving gaps. Alternatively, specify a value, usually 0, to replace `NA` and plot that value (e.g., 0) at the corresponding date. Forecasting with missing data is not supported. - `ts_format`: Optional format string for `as.Date()` describing the values of the date variable on the `x`-axis, needed if the function cannot infer the date format. For example, the character string `"09/01/2024"` can be described by `"%m/%d/%Y"`. See `details` for more information. - `ts_fitted`: If `TRUE` and `ts_ahead` is used for forecasting, display for each data point the fitted value, level, trend, and seasonal component. - `ts_PI`: Prediction interval level about the forecasted values, with default of `0.95`. - `ts_trend`: Trend parameter. Default value is `NULL`, allowing the procedure to choose the specification that yields the best-fitting model for the data. Values `"A"` and `"M"` indicate additive and multiplicative models, respectively. Specify `"N"` to omit the trend component. See the forecasting documentation for valid combinations of trend, season, and error. - `ts_seasons`: Seasonality parameter. See `ts_trend`. - `ts_error`: Error parameter. See `ts_trend`. - `ts_alpha`: Exponential smoothing level parameter. Sets the value for `HoltWinters()`, and acts as a suggestion for `ETS()` in the `"fable"` framework. - `ts_beta`: Exponential smoothing trend parameter. See `ts_alpha`. - `ts_gamma`: Exponential smoothing seasonal parameter. See `ts_alpha`. - `ts_new_x`: A data frame of predictor variable names and new values for exogenous regressors used for model fitting and forecasting. The number of rows of new data values determines the number of future time periods for which forecasts are generated. Currently applies only to the default `"fable"` linear model for `ts_method = "lm"`. - `ts_stack`: If `TRUE`, multiple time plots are stacked on each other, with `area` set to `TRUE` by default. - `ts_area_fill`: Fill under line segments, if present. If `ts_stack` is `TRUE`, the default is a gradient from the default color range (e.g., `"blues"`). If not specified, and `fill` is set with no plotted points and `ts_area_fill` is not specified, then `fill` generally controls the area under the line segments. - `ts_area_split`: Applies only to a Trellis plot activated with `facet1`. Value of `y` that defines a reference line splitting the filled area under the time series line. Values of `y` below this threshold lie below the reference line; values above lie above the line. - `ts_n_x_tics`: Suggested number of ticks for dates on the `x`-axis, overriding the default of approximately seven ticks. - `show_runs`: If `TRUE`, display the individual runs in the run analysis. Also sets `run` to `TRUE`. Customize the color of the line segments with `segments_color` via `style`. - `center_line`: Plots a dashed line through the middle of a run chart. Default center line is the `"median"`, suitable when values randomly vary about the median. Alternatively, `"mean"` and `"zero"` specify that the center line goes through the mean or zero, respectively. Currently not supported for Trellis plots. - `vbs_plot`: A character string that specifies the components of the integrated Violin–Box–Scatterplot (VBS) of a continuous variable . A `"v"` in the string indicates a violin plot, a `"b"` indicates a box plot with flagged outliers, and a `"s"` indicates a 1-variable scatterplot. Default value is `"vbs"`. The characters can be in any order and in upper- or lower-case. Generalize to Trellis plots with the `facet1` and `facet2` parameters, but currently only for horizontal displays. Modify fill and border colors from the current `theme` with the `style` parameters `violin_fill`, `violin_color`, `box_fill` and `box_color`. - `vbs_ratio`: Height of the violin plot relative to the plot area. Make the violin (and the accompanying box plot) larger or smaller by adjusting either the plot area or this value. - `bw`: Bandwidth for the smoothness of the violin plot. Higher values give smoother plots. Default is to calculate a bandwidth that provides a relatively smooth density estimate. - `bw_iter`: Number of iterations used to adjust the default R bandwidth for further smoothing of the density estimate. When set, the iterations and corresponding results are displayed. - `violin_fill`: Fill color for a violin plot. - `box_fill`: Fill color for a box plot. - `vbs_pt_fill`: Points in a VBS scatterplot are black by default because the background violin is based on the current theme color. To use the `pt_fill` and `pt_color` values specified by `style`, set `vbs_pt_fill = "default"`. Otherwise, set to any desired color. - `vbs_mean`: Show the mean on the box plot with a strip in the color of `out_fill`, which can be changed with the `style` function. - `fences`: If `TRUE`, draw the inner upper and lower fences as dotted line segments. - `n_min_pivot`: For the pivot table underlying a VBS plot over at least a `by` or `facet1` categorical variable, sets the minimum sample size for a group for the corresponding row to be displayed. Default is 1 for all non-empty groups. Set to 0 to view all groups. - `k`: IQR multiplier that determines the distance of the whiskers of the box plot from the box. Default is Tukey's setting of 1.5. - `box_adj`: Adjust the box and whiskers, and thus outlier detection, for skewness using the medcouple statistic as a robust measure of skewness according to Hubert and Vandervieren (2008). - `a, b`: Scaling factors for the adjusted box plot to set the lengths of the whiskers. If explicitly set, `box_adj` is activated. - `radius`: Scaling factor of the bubbles in a bubble plot , which sets the radius of the largest displayed bubble in inches. To activate bubble scaling, set `size` to a third variable, or for categorical variables (factors), the bubble sizes represent frequencies. - `power`: Relative scaling of bubble sizes. The default value of 0.5 scales bubbles so that the area of each bubble is proportional to the corresponding sizing variable. A value of 1 scales bubble radii directly by the sizing variable, increasing the size differences between values. - `low_fill`: For a categorical variable and the resulting bubble plot, or a matrix of such plots, sets the low end of a color gradient for bubble fill. - `hi_fill`: For a categorical variable and the resulting bubble plot, or a matrix of such plots, sets the high end of a color gradient for bubble fill. - `smooth_points`: Number of points superimposed on the density plot in the areas of lowest density to help identify outliers, thereby controlling how dark the smoothed display becomes. - `smooth_size`: Size of points superimposed on the density plot. Default value is 1, resulting in very small points. - `smooth_power`: Exponent of the function that maps the density scale to the color scale. Smaller values than the default of 0.25 yield darker plots. - `smooth_bins`: Number of bins in each direction for the density estimation. - `n_bins`: Number of bins for a single numeric `x`-variable when visualizing the mean or median of a numeric `y`-variable for each bin. Points are plotted as bubbles, with bubble size proportional to the bin sample size, unless `size` is specified as a constant. Default is 1 (no binning). - `contour_n`: Number of contour levels in a contour plot, with default of 10. - `contour_nbins`: Number of bins constructed for each of `x` and `y`, forming the 2D grid from which densities are estimated. - `contour_points`: If `TRUE`, plot the original scatterplot points in a light gray with white borders, representing the data from which the contour curves are estimated. Color is not affected by other color settings, but point size can be changed with `size`. Default size is 0.72. - `bin`: If `values = "count"`, display the frequency distribution for a frequency polygon. - `bin_start`: Optional starting value of the bins for a frequency polygon . - `bin_width`: Optional specified bin width. Also sets `bin = TRUE`. - `bin_end`: Optional value that lies within the last bin, so the actual endpoint of the last bin may be larger than the specified value. - `breaks`: Method for calculating bins, or an explicit specification of the bins, such as via `seq` or other options provided by `hist`. Also sets `bin = TRUE`. - `cumulate`: If `TRUE`, display a cumulative frequency polygon. - `xlab, ylab`: Axis labels for the `x`- and `y`-axes. If not specified, labels default to the corresponding variable labels (if present), otherwise to the variable names. If `xy_ticks` is `FALSE`, no `ylab` is displayed. Customize these and related parameters with options such as `lab_color` in `style`. - `main`: Label for the plot title. If corresponding variable labels exist, the title is set by default from those labels. - `sub`: Subtitle for the graph, below `xlab`. Not yet implemented. - `label_adjust`: Two-element vector (x-axis label, y-axis label) that adjusts the positions of axis labels in approximate inches. Positive values move labels away from the plot edge. Not applicable to Trellis graphics. - `margin_adjust`: Four-element vector (top, right, bottom, left) that adjusts plot margins in approximate inches. Positive values move the corresponding margin away from the plot edge. Can be used with `offset` to move axis values into the expanded margin space. Not applicable to Trellis graphics. - `pad_x`: Proportion of padding added to the left and right sides of the `x`-axis. Values range from 0 to 1 for each of the two elements. If only one element is specified, it is applied to both sides. - `pad_y`: Proportion of padding added to the bottom and top sides of the `y`-axis. Values range from 0 to 1 for each of the two elements. If only one element is specified, it is applied to both sides. - `scale_x`: If specified, a vector of three values that define the numeric `x`-axis: starting value, ending value, and number of intervals. - `scale_y`: If specified, a vector of three values that define the numeric `y`-axis: starting value, ending value, and number of intervals. - `origin_x`: Origin of the `x`-axis. Default is the minimum value of `x`, except for time series plots and when `stat` is set to `"count"` or a related option, in which case the origin defaults to 0. - `origin_y`: Origin of the `y`-axis. Default is the minimum value of `y`, except for time series plots and when `stat` is set to `"count"` or a related option, in which case the origin defaults to 0. - `rotate_x`: Rotation in degrees of the axis value labels on the `x`-axis, usually to accommodate longer labels, typically used with `offset`. If set to 90, labels are perpendicular to the axis and a different placement algorithm is used so that `offset` is not needed. - `rotate_y`: Rotation in degrees of the axis value labels on the `y`-axis, usually to accommodate longer labels, typically used with `offset`. - `offset`: Spacing between axis value labels and the axis. Default is 0.5. Larger values (e.g., 1.0) create additional space for labels, especially when rotated. Can be used with `margin_adjust` to create additional margin space for axis labels and values. - `axis_fmt`: Numeric format of axis labels for both axes. Default rounds thousands to `"K"` (e.g., 100000 becomes 100K). Alternatives include `","` to insert commas in large numbers with a decimal point, `"."` to insert periods, or `""` to turn off formatting. - `axis_x_prefix`: Prefix for axis labels on the `x`-axis, such as `"$"`. - `axis_y_prefix`: Prefix for axis labels on the `y`-axis, such as `"$"`. - `xy_ticks`: Flag indicating whether tick marks and associated value labels on the axes are displayed. To rotate axis values, use `rotate_x`, `rotate_y`, and `offset` (see `style`). - `n_axis_x_skip`: Particularly useful for Trellis or facet plots with many labels on the `x`-axis. Specifies the spacing for skipping labels. A value of 0 includes all labels (default). A value of 1 skips every other label, 2 includes every third label, etc. Also consider `rotate_x`. - `n_axis_y_skip`: Same as `n_axis_x_skip` but applies to the `y`-axis. - `legend_title`: Title of the legend for a multiple-variable `x` or `y` plot. - `add`: Overlay one or more objects , text or geometric figures, on the plot. Possible values include any text (first argument) or `"text"`; `"labels"` to label each point with the row name; and geometric objects `"rect"` (rectangle), `"line"`, `"arrow"`, `"v_line"` (vertical line), and `"h_line"` (horizontal line). The value `"means"` draws vertical and horizontal lines at the respective means. Does not apply to Trellis graphics. Customize with parameters such as `add_fill` and `add_color` via `style`. - `x1`: First x-coordinate for each overlaid object; may be `"mean_x"`. Not used for `"h_line"`. - `y1`: First y-coordinate for each overlaid object; may be `"mean_y"`. Not used for `"v_line"`. - `x2`: Second x-coordinate for each object; may be `"mean_x"`. Used only for `"rect"`, `"line"`, and `"arrow"`. - `y2`: Second y-coordinate for each object; may be `"mean_y"`. Used only for `"rect"`, `"line"`, and `"arrow"`. - `quiet`: If `TRUE`, suppress text output. Can change the system default with `style`. - `do_plot`: If `TRUE` (default), generate the plot. - `use_plotly`: If `TRUE` (default), draw a `plotly` interactive plot in the RStudio `Viewer` window in addition to the static plot in the `Plots` window. Not all options are available in the interactive version, but key options are supported. - `pdf_file`: If specified, direct PDF graphics to the given file name. - `width`: Width of the plot window in inches, default 5 except within RStudio, where the default maintains an approximately square plotting area. - `height`: Height of the plot window in inches, default 4.5 except for 1-D scatterplots and when running in RStudio. - `digits_d`: Number of significant digits for each displayed summary statistic. - `n_cat`: Maximum number of unique, equally spaced integer values of a variable for which it will be analyzed as categorical rather than continuous. Default is 0. Use to treat such variables as informal factors. **Deprecated**. Best to convert integer-coded categoricals to factors explicitly. - `value_labels`: For factors, default labels are the factor levels; for character variables, default labels are the character values. Optionally provide labels for the `x`-axis to override defaults. If the variable is a factor and `value_labels` is `NULL`, then labels are set to the factor levels with spaces replaced by line breaks. If `x` and `y` share the same scale, labels also apply to the `y`-axis. Control label size with `axis_cex` and `axis_x_cex` from the lessR `style` function. - `rows`: **Deprecated**. Old parameter name; use `filter`. - `facet1`: **Deprecated**. Old parameter name; use `facet`. - `facet2`: **Deprecated**. Old parameter name; use a two-element vector in `facet`. - `smooth`: **Deprecated**. Use parameter `type`. - `stat`: Apply a specified aggregation such as `"mean"` to the numerical `y` variable at each level of a categorical `x` variable. The resulting dot plot (Cleveland plot) is analogous to a bar chart but emphasizes position along a common scale. - `stat_x`: If no `y` variable is specified, constructs a frequency polygon for `x` with access to `bin_width`. Either use the default `"count"` for each bin or `"proportion"`, also indicated by `%`. - `eval_df`: Controls whether to check for an existing data frame and specified variables. Default is `TRUE`, unless the `shiny` package is loaded, in which case it is set to `FALSE` so that Shiny can run. Must be set to `FALSE` when using the pipe operator `%\>%`. - `fun_call`: Function call. Used with `knitr` to pass the function call when obtained from the abbreviated helper `sp`. - ``...``: Other parameters for non-Trellis graphics as recognized by base R functions `plot` and `par`, including `cex.main` for the size of the title, `col.main` for the color of the title, and `sub` and `col.sub` for a subtitle and its color. ## Details VARIABLES and TRELLIS PLOTS There is at least one primary variable, `x`, which defines the horizontal `x`-axis. A second primary variable, `y`, defines the vertical `y`-axis. Either `x` or `y` (but not both simultaneously) may be a vector of variables. The simplest usage—single `x` and `y`—produces a single scatterplot on one panel. With `type = "scatter"` this is a standard point plot; alternative values such as `"smooth"` and `"contour"` invoke 2-D kernel density and contour displays, respectively. For numeric primary variables, multiple plots can appear on a single panel in two ways. First, by defining groups with the `by` argument: `by` identifies a categorical grouping variable, and a separate scatterplot layer is drawn for each of its levels. Group levels are distinguished by color and/or shape. By default, colors vary across groups; for two groups, a common pattern is a filled symbol for one group and a point with transparent interior for the other. Second, multiple numeric `x`-variables or multiple `y`-variables can be supplied as a vector, which produces multiple series on the same panel. This is commonly used for time series overlays and multi-series line plots. Trellis graphics (facets), from Deepayan Sarkar's (2009) `lattice` package, may also be used. A variable specified with `facet` is a conditioning variable. A single `facet` variable produces one panel for each of its levels; a length-two vector of facet variables produces one panel for each cross-classified combination of their levels. Within each panel, `x` and `y` are plotted as usual, and an additional grouping variable specified with `by` may be applied to all panels. When `x` has at most 1000 unique values, XY() can provide a brief diagnostic of the maximum number of repeated values for each level of `facet`. Control the panel dimensions and the overall size of the Trellis display with `width` and `height` for the graphics device, `n_row` and `n_col` for the number of panels in each direction, and `aspect` for the panel height-to-width ratio. The plot window is the active graphics device (e.g., the standard R plotting window, RStudio `Plots` pane, or a pdf file when `pdf_file` is specified). CATEGORICAL VARIABLES Conceptually, lessR distinguishes continuous and categorical variables. Categorical variables have relatively few unique values and are often coded as factors. However, categorical variables may also be coded numerically, such as Likert responses from 1 to 5. The structuring arguments `by` and `facet` apply when at least one of `x` or `y` is numeric, but that numeric variable may represent either a truly continuous scale or a discrete Likert-type scale. Scatterplots of Likert-type data can be challenging because the number of possible joint values is small. For two five-point scales there are only 25 possible combinations, so many points overlap at the same coordinates. For such situations, jittering, or dot/mean plots (using `stat`) may provide clearer displays. DATA The default input data frame is `d`. Another data frame can be specified with the `data` argument. Regardless of the name of the data frame, variables can be referenced directly by name—no need to attach the data frame or use `d$name`. Referenced variables may live in the data frame, the global environment, or both. The plotted values can be the raw data themselves, or summaries derived from them. With a single numeric variable, counts or proportions can be plotted on the `y`-axis, optionally after binning `x`. For a categorical `x`-variable paired with a continuous `y`-variable, summary statistics such as means can be plotted at each level of `x`. When `x` is continuous and binning is desired, XY() uses the same binning parameters as `Histogram`, such as `bin_width`, to override defaults. The `stat` parameter controls what is plotted (e.g., `"data"`, `"mean"`, `"median"`). By default, connecting line segments are drawn, yielding a frequency polygon. Turn off line segments by setting `line_width = 0`. The `filter` parameter subsets rows (cases) of the input data frame according to a logical expression or a vector of integers specifying row numbers to retain. Use standard R logical operators as described in `Logic`—for example, `&` (and), `|` (or), and `!` (not)—and relational operators as described in `Comparison` such as `==` (equality), `!=` (not equal), and `>` (greater than). To specify rows directly, create an integer vector using standard R syntax. See `Examples`. VALUE LABELS **Deprecated. Use `factor()` instead.** The `value_labels` option can override the axis tick labels with user-supplied values. This is particularly useful for Likert-style data coded as integers: for example, a data value `0` can be displayed as `"Strongly Disagree"`. These labels apply to integer categorical variables and to factor variables. Any spaces in a label are translated into line breaks to improve readability. In current workflows, the recommended approach is to define factors with the desired labels directly, typically via `factors`, which allows convenient creation of labeled factors for one or more variables in a single statement. VARIABLE LABELS Base R does not natively support variable labels, but lessR stores labels in the data frame alongside the variables, typically created by `Read` or `VariableLabels`. When variable labels exist, XY() uses them by default for axis labels and in text output. Otherwise, the variable names are used. TWO VARIABLE PLOT With two variables specified, XY() behaves as follows. If the values of `x` are unsorted, have unequal intervals, or there is missing data in either variable, a standard scatterplot is produced (for `type = "scatter"`). When `x` is sorted with equal intervals and there are no missing values, the default display connects adjacent points with line segments, yielding a function or time-series style plot. Supplying multiple continuous `x`-variables against a single `y`, or vice versa, produces multiple series on the same graph. The points for the second series reuse the first series' color but with transparent fill; for more series, additional colors from the current theme are used. SCATTERPLOT MATRIX If `x` is a vector of continuous variables and `y` is omitted, XY() generates a scatterplot matrix. The matrix adopts the current color theme. Individual colors (e.g., `fill`, `color`) can be overridden. The lower triangle shows the pairwise scatterplots, and the upper triangle shows the corresponding correlation coefficients. By default a non-linear loess fit line is added to each scatterplot; the `fit` parameter can be used to request a linear least squares line instead, along with `fit_color` to set its color. SIZE VARIABLE Specifying a numeric `size` variable activates a bubble plot in which the area of each bubble is determined by the corresponding value of `size` (modified by `radius` and `power`). To vary shapes explicitly across groups, use `shape` and provide a vector of values (e.g., created with `c`). One shape is used for each level of the grouping variable in `by`. To vary colors, use `fill`; if `fill` is specified without `shape`, colors vary but shapes do not. To vary both, specify both `shape` and `fill` with values for each `by` level. Beyond the named shapes such as `"circle"`, any single character (letters, digits, `"+"`, `"*"`, `"#"`) may be used as a plotting symbol. Within a single specification, either use standard named shapes or single characters, but not both. SCATTERPLOT ELLIPSE For a scatterplot of two numeric variables, the `ellipse` argument requests one or more data ellipses, based on the contours of the corresponding bivariate normal density. For a single `x`- and `y`-variable pair, setting `ellipse` to a numeric value between 0 and 1 (e.g., 0.95) draws the corresponding probability contour. A vector of values produces multiple ellipses. XY() expands the axes as needed so that ellipses extending beyond the range of the data remain fully visible. For Trellis graphics, only the largest ellipse level is used (one ellipse per panel). Ellipse fill and border colors are controlled via `ellipse_fill` and `ellipse_color` in `style`. TIME CHARTS See [https://web.pdx.edu/~gerbing/lessR/examples/Time.html](https://web.pdx.edu/~gerbing/lessR/examples/Time.html) for additional examples and explanation. When `x` is the special variable `.Index`, XY() produces a run chart of `y`. The `y`-values are plotted against their index positions (1, 2, …), and run-chart diagnostics such as center lines and runs analysis can be displayed via the corresponding arguments. If `x` is of type `Date` or an R time-series object, XY() produces a time series plot for each specified variable. Time-series data can be supplied in “long” format (a single column of values plus a date column) or in “wide” format (multiple time-series columns sharing a date index). XY() will attempt to convert character string date values (e.g., `"08/18/1952"`) to `Date` via `as.Date()`, using default date formats when possible. XY() makes a reasonable attempt to decode common date formats, but some formats (e.g., those with month names rather than numbers) may require an explicit format string via `ts_format`. If the default conversion fails or is ambiguous, specify the correct format using examples such as those in the table below. ||| |:--|:--| |Example Date|Format| |---------------------------|-----------------| |`"2022-09-01"`|`"%Y-%m-%d"`| |`"2022/9/1"`|`"%Y/%m/%d"`| |`"2022.09.01"`|`"%Y.%m.%d"`| |`"09/01/2022"`|`"%m/%d/%Y"`| |`"9/1/22"`|`"%m/%d/%y"`| |`"September 1, 2022"`|`"%B %d, %Y"`| |`"Sep 1, 2022"`|`"%b %d, %Y"`| |`"20220901"`|`"%Y%m%d"`| |---------------------------|-----------------| XY() also converts character-string dates such as `"2024 Aug"` and `"2024 Q1"`, interpreting three-letter month abbreviations and quarter codes `Q1`–`Q4`. The `ts_unit` argument optionally aggregates the date variable to a higher time unit using `endpoints()` and `period.apply()` from the `xts` package. For example, daily data can be aggregated and plotted as monthly or quarterly series. The aggregation function is specified with `ts_agg`, default `"sum"`, with `"mean"` as a common alternative. For missing data, if a date is present but the corresponding `y`-value is `NA`, the line is broken at that point (no segment is drawn). If both the date and value are absent (the entire row is missing), the line connects the nearest observed dates, spanning the gap in calendar time but skipping the missing tick label. For example, if "2021-01-07" and "2021-01-09" are present but "2021-01-08" is absent, the plot includes points for the 7th and 9th connected by a line; the 8th does not appear on the axis. Forecasting is activated by setting `ts_ahead` to a positive integer. The trend, seasonal, and error components for exponential smoothing and regression models follow the `fable` conventions and are controlled by `ts_trend`, `ts_seasons`, and `ts_error`. XY() supports four forecasting engines: `ETS()` and `TSLM()` from `fable` via `ts_source = "fable"`, and classic `HoltWinters()` and regression decomposition (`stl()` + `lm()`) via `ts_source = "classic"`. Multiplicative components require positive data. Additive trend is linear, while multiplicative trend corresponds to exponential growth or decay; additive and multiplicative seasonality scale the seasonal pattern differently as the series level changes. Exponential smoothing via `ETS()` (the default when `ts_source = "fable"`) generally provides flexible model specification and often superior predictive performance compared to classic Holt–Winters. For regression with seasonality, `TSLM()` and the `stl()`+`lm()` approach both rely on least squares but handle seasonal structure differently. Setting `ts_fitted = TRUE` provides fitted values and decomposed trend and seasonal components for inspection. 2-D KERNEL DENSITY Set `type = "smooth"` to invoke `smoothScatter` and display a 2-D kernel density estimate for large data sets. The display respects the current theme. The `smooth_points` argument controls how many points from low-density regions are superimposed, `smooth_bins` sets the number of bins in each direction for density estimation, and `smooth_power` controls the transformation from density scale to color scale. Larger `smooth_power` values reduce saturation in low-density regions. These arguments map directly to `nrpoints`, `nbin`, and `transformation` in `smoothScatter`. Grid lines are disabled by default for smooth density plots, but can be re-enabled via the appropriate styling options (e.g., `grid_color` in `style`). Alternatively, set `type = "contour"` to plot contour lines of the estimated bivariate density, with the level resolution controlled by `contour_n` and `contour_nbins`. COLORS A global color theme for `XY()` and other lessR graphics can be set with `style` (e.g., `style(theme = "lightbronze")`). The default theme is `"lightbronze"`. A grayscale theme is available via `"gray"`, and other themes (e.g., `"sienna"`, `"darkred"`) are described in `style`. The `sub_theme = "black"` option yields a black background with partially transparent plotted colors. Individual graphical elements (points, lines, panels, grid lines, etc.) can be customized with additional `style` arguments, such as `panel_fill`. For a subtle warm background, try `panel_fill = "snow"`; very light grays such as `"gray99"` or `"gray97"` provide a neutral tone. For many color options, the value `"off"` is equivalent to `"transparent"`, removing the corresponding fill or borde See `showColors` for a display of all named R colors and their RGB values. ANNOTATIONS The `add` argument and its related coordinates (`x1`, `y1`, `x2`, `y2`) annotate the plot with text and geometric objects. Each object type requires a specific set of coordinates, summarized below. `x`-coordinates may take the special value `"mean_x"` and `y`-coordinates may take `"mean_y"`. |||| |:--|:--|:--| |Value|Object|Required Coordinates| |-----------|-------------------|-----------------------| |`"text"`|text|x1, y1| |`"point"`|point|x1, y1| |`"rect"`|rectangle|x1, y1, x2, y2| |`"line"`|line segment|x1, y1, x2, y2| |`"arrow"`|arrow|x1, y1, x2, y2| |`"v_line"`|vertical line|x1| |`"h_line"`|horizontal line|y1| |`"means"`|horizontal and vertical lines at the means|| |-----------|-------------------|-----------------------| The value of `add` specifies the object type. For a single object, provide one value and its required coordinates. For multiple placements of the same object, supply coordinate vectors. For multiple different objects, supply a vector of `add` values and, for each coordinate argument (`x1`, `y1`, `x2`, `y2`), a vector whose elements correspond to the sequence of objects in `add`. Styling options such as `add_color`, `add_fill`, and transparency may also be given as vectors, allowing different objects to have different colors or other properties. PDF OUTPUT To obtain pdf output, set `pdf_file` to a file name, optionally with `width` and `height` to control device size. The pdf is written to the current working directory, which can be explicitly set with `setwd`. ADDITIONAL OPTIONS Many commonly used graphical parameters from the base function `plot` are passed through by XY(), including: - **cex.main, col.lab, font.sub, etc.**: Settings for main/sub-titles and axis annotation; see `title` and `par`. - **main**: Main title of the graph; see `title`. - **xlim**: Limits of the `x`-axis, expressed as `c(x1, x2)`. Note that `x1 > x2` is allowed and produces a reversed axis. - **ylim**: Limits of the `y`-axis. ONLY VARIABLES ARE REFERENCED A referenced variable in a lessR plotting function such as `XY` must be a variable name (or vector of variable names), not an arbitrary expression. The variable must exist either in the referenced data frame (e.g., the default `d`) or in the user's workspace (global environment). Expressions are not evaluated in place. For example: `> XY(rnorm(50), rnorm(50)) # does NOT work` Instead, create named objects and reference them directly: ``` > X <- rnorm(50) # create vector X in user workspace > Y <- rnorm(50) # create vector Y in user workspace > XY(X, Y) # directly reference X and Y ``` ## Returns The output may be assigned to an `R` object; otherwise it is printed directly to the console. Each component appears only when the corresponding analytic option is activated. For example, outlier identification must be enabled (e.g., via `MD_cut`) for `out_outliers` to be included in the output. To save the results, assign the output to an object, such as `p <- XY(Years, Salary)`. Use `names(p)` to view the available components, and access any one by prefixing with `p$`, for example `p$out_stats`. Output can be viewed interactively at the console or inserted into R~Markdown documents for reproducible reporting. READABLE OUTPUT `out_stats`: Correlational analysis. `out_outliers`: Mahalanobis Distance values for detected outliers. `out_frcst`: Forecasted values. `out_fitted`: Fitted values for the observed data. `out_coefs`: Linear and seasonal coefficients from forecasting models. `out_smooth`: Smoothing parameters from exponential smoothing models. `out_bubble`: Bubble-plot settings, including `radius` and `power`. `out_reg`: Regression statistics produced when `fit` is specified. `out_parm`: Parameter settings for a VBS plot of a continuous variable. `out_pivot`: Pivot table for VBS plots based on any combination of `by` and `facet` variables. `out_by`: Pivot table for VBS plots aggregated by the `by` variable. `out_facet1`: Pivot table for VBS plots aggregated by the first facet variable. `out_facet2`: Pivot table for VBS plots aggregated by the second facet variable. STATISTICS `outliers`: Row numbers corresponding to detected outliers. ## References Brys, G., Hubert, M., & Struyf, A. (2004). A robust measure of skewness. Journal of Computational and Graphical Statistics, 13(4), 996-1017. Murdoch, D, and Chow, E. D. (2013). `ellipse` function from the `ellipse` package. Gerbing, D. W. (2023). R Data Analysis without Programming, 2nd edition, Chapter 10, NY: Routledge. Gerbing, D. W. (2020). R Visualizations: Derive Meaning from Data, Chapter 5, NY: CRC Press. Gerbing, D. W. (2021). Enhancement of the Command-Line Environment for use in the Introductory Statistics Course and Beyond, **Journal of Statistics and Data Science Education**, 29(3), 251-266, https://www.tandfonline.com/doi/abs/10.1080/26939169.2021.1999871. Hyndman, R. J., & Athanasopoulos, G. (2021). **Forecasting: Principles and Practice** (3rd ed.). Melbourne, Australia: OTexts. Retrieved from https://otexts.com/fpp3/ Sarkar, Deepayan (2008) Lattice: Multivariate Data Visualization with R, Springer. http://lmdvr.r-forge.r-project.org/ Sievert, C. (2020). **Interactive Web-Based Data Visualization with R, plotly, and shiny**. Chapman and Hall/CRC. URL: [https://plotly.com/r/](https://plotly.com/r/) ## Author(s) David W. Gerbing (Portland State University; gerbing@pdx.edu ) ## See Also `X`, `Chart`, `style`. ## Examples ```r # read the data d <- rd("Employee", quiet=TRUE) d <- d[.(random(0.6)),] # less computationally intensive dd=d #--------------------------------------------------- # traditional scatterplot with two numeric variables #--------------------------------------------------- # scatterplot with all defaults XY(Years, Salary) # or use Plot in place of XY, the older method XY(Years, Salary, by=Gender, size=2, fit="lm", fill=c(M="olivedrab3", W="gold1"), color=c(M="darkgreen", W="gold4")) # maximum information, minimum input: scatterplot + # means, outliers, ellipse, least-squares lines with and w/o outliers XY(Years, Salary, enhance=TRUE) # extend x and y axes XY(Years, Salary, scale_x=c(-10, 35, 10), scale_y=c(0,200000,10)) XY(Years, Salary, add="Hi", x1=c(12, 16, 18), y1=c(80000, 100000, 60000)) d <- factors(Gender, levels=c("M", "W")) XY(Years, Salary, facet=Gender) d <- dd # just males employed more than 5 years XY(Years, Salary, filter=(Gender=="M" & Years > 5)) # plot 0.95 data ellipse with the points identified that represent # outliers defined by a Mahalanobis Distance larger than 6 # save outliers into R object out d[1, "Salary"] <- 200000 out <- XY(Years, Salary, ellipse=0.95, MD_cut=6) # new shape and point size, no grid or background color # then put style back to default style(panel_fill="powderblue", grid_color="powderblue") XY(Years, Salary, size=2, shape="diamond") style() # translucent data ellipses without points or edges # show the idealized joint distribution for bivariate normality style(ellipse_color="off") XY(Years, Salary, size=0, ellipse=seq(.1,.9,.10)) style() # bubble plot with size determined by the value of Pre # display the value for the bubbles with values of min, median and max XY(Years, Salary, size=Pre, size_cut=3) # variables in a data frame not the default d # plot 0.6 and 0.9 data ellipses with partially transparent points # change color theme to gold with black background style("gold", sub_theme="black") XY(eruptions, waiting, transparency=.5, ellipse=seq(.6,.9), data=faithful) # scatterplot with two x-variables, plotted against Salary # define a new style, then back to default style(window_fill=rgb(247,242,230, maxColorValue=255), panel_fill="off", panel_color="off", pt_fill="black", transparency=0, lab_color="black", axis_text_color="black", axis_y_color="off", grid_x_color="off", grid_y_color="black", grid_lty="dotted", grid_lwd=1) XY(c(Pre, Post), Salary) style() # increase span (smoothing) from default of .7 to 1.25 # span is a loess parameter, which generates a caution that can be # ignored that it is not a graphical parameter -- we know that # display confidence intervals about best-fit line at # 0.95 confidence level XY(Years, Salary, fit="loess", span=1.25) # 2-D kernel density (more useful for larger sample sizes) XY(Years, Salary, type="smooth") #------------------------------------------------------ # scatterplot matrix from a vector of numeric variables #------------------------------------------------------ # with least squares fit line XY(c(Salary, Years, Pre), c(Salary, Years, Pre), fit="lm") #-------------------------------------------------------------- # Trellis graphics and by for groups with two numeric variables #-------------------------------------------------------------- # Trellis plot with condition on 1-variable # optionally re-order default alphabetical R ordering by converting # to a factor with lessR factors (which also does multiple variables) # always save to the full data frame with factors d <- factors(Gender, levels=c("M", "W")) XY(Years, Salary, facet=Gender) d <- Read("Employee", quiet=TRUE) # all three by (categorical) variables XY(Years, Salary, facet=c(Dept, Gender), by=Plan, n_axis_y_skip=1) # vary both shape and color with a least-squares fit line for each group style(color=c("darkgreen", "brown")) XY(Years, Salary, facet=Gender, fit="lm", shape=c("W","M"), size=.8) style("gray") # compare the men and women Salary according to Years worked # with an ellipse for each group XY(Years, Salary, by=Gender, ellipse=.50) # time charts #------------ # run chart, with default fill area XY(.Index, Salary, ts_area_fill="on") # two run charts in same panel # or could do a multivariate time series XY(.Index, c(Pre, Post)) # Trellis graphics run chart with custom line width, no points XY(.Index, Salary, facet=Gender, line_width=3, size=0) # daily time series plot # create the daily time series from R built-in data set airquality oz.ts <- ts(airquality$Ozone, start=c(1973, 121), frequency=365) XY(oz.ts) # multiple time series plotted from dates and stacked # black background with translucent areas, then reset theme to default style(sub_theme="black", color="steelblue2", transparency=.55, window_fill="gray10", grid_color="gray25") date <- seq(as.Date("2013/1/1"), as.Date("2016/1/1"), by="quarter") x1 <- rnorm(13, 100, 15) x2 <- rnorm(13, 100, 15) x3 <- rnorm(13, 100, 15) df <- data.frame(date, x1, x2, x3) rm(date); rm(x1); rm(x2); rm(x3) XY(date, x1:x3, data=df) style() # aggregate monthly data to plot by quarter n.q <- 42 month <- seq(as.Date("2013/1/1"), length=n.q, by="months") x <- rnorm(n.q, 100, 15) XY(month, x, ts_unit="quarters") # trigger a time series with a Date variable specified first # stock prices for three companies by month: Apple, IBM, Intel d <- rd("StockPrice") # only plot Apple XY(Month, Price, filter=(Company=="Apple")) # Trellis plots, one for each company XY(Month, Price, facet=Company, n_col=1) # all three plots on the same panel, three shades of blue XY(Month, Price, by=Company, color="blues") # exponential smoothing forecast for next 12 months, # aggregate monthly data by mean over quarters XY(Month, Price, ts_ahead=12, ts_unit="quarters") #------------------------------------------ # analysis of a single categorical variable #------------------------------------------ d <- rd("Employee") # default 1-D bubble plot # frequency plot, replaces bar chart XY(Dept) # plot of frequencies for each category (level), replaces bar chart XY(Dept, stat_x="count") #---------------------------------------------------- # scatterplot of numeric against categorical variable #---------------------------------------------------- # generate a chart with the plotted mean of each level # rotate x-axis labels and then offset from the axis style(rotate_x=45, offset=1) XY(Dept, Salary) style() #------------------- # Cleveland dot plot #------------------- # standard scatterplot XY(Salary, row_names, segments_y=FALSE) # Cleveland dot plot with two x-variables XY(c(Pre, Post), row_names) #------------ # annotations #------------ # add text at the one location specified by x1 and x2 XY(Years, Salary, add="Hi There", x1=12, y1=80000) # add text at three different specified locations XY(Years, Salary, add="Hi", x1=c(12, 16, 18), y1=c(80000, 100000, 60000)) # add three different text blocks at three different specified locations XY(Years, Salary, add=c("Hi", "Bye", "Wow"), x1=c(12, 16, 18), y1=c(80000, 100000, 60000)) # add an 0.95 data ellipse and horizontal and vertical lines through the # respective means XY(Years, Salary, ellipse=0.95, add=c("v_line", "h_line"), x1="mean_x", y1="mean_y") # can be done also with the following short-hand XY(Years, Salary, ellipse=0.95, add="means") # a rectangle requires two points, four coordinates, and style(add_trans=.8, add_fill="gold", add_color="gold4", add_lwd=0.5) XY(Years, Salary, add="rect", x1=12, y1=80000, x2=16, y2=115000) # the first object, a rectangle, requires all four coordinates # the vertical line at x=2 requires only an x1 coordinate, listed 2nd XY(Years, Salary, add=c("rect", "v_line"), x1=c(10, 2), y1=80000, x2=12, y2=115000) # two different rectangles with different locations, fill colors and translucence style(add_fill=c("gold3", "green"), add_trans=c(.8,.4)) XY(Years, Salary, add=c("rect", "rect"), x1=c(10, 2), y1=c(60000, 45000), x2=c(12, 75000), y2=c(80000, 55000)) #---------------------------------------------------- # analysis of two categorical variables (Likert data) #---------------------------------------------------- d <- Read("Mach4", quiet=TRUE) # Likert data, 0 to 5 XY(m06, m07) #--------------- # function curve #--------------- x <- seq(10,50,by=2) y1 <- sqrt(x) y2 <- x**.33 # x is sorted with equal intervals so run chart by default XY(x, y1) # multiple plots from variable vectors need to have the variables # in a data frame d <- data.frame(x, y1, y2) # if variables are in the user workspace and in a data frame # with the same names, the user workspace versions are used, # which do not work with vectors of variables, so remove rm(x); rm(y1); rm(y2) XY(x, c(y1, y2)) ```

XY function