I have two questions, [1] How do you turn off scientific notation from results, and [2] Is the decision tree tab running the same analysis as a classification and regression tree (CART) analysis?
@Tererrance- Did you get your questions resolved? Its my first day on the forum- regarding Q[1] How do you turn off scientific notation from results, Did you check output settings?
i.e click on the 3 vertical dots at top right of menu bar, select settings (extreme left below menus). This should take you to output settings. The first line refers to the issue:
Numbers in scientific notation for very small or very large numbers (eg. 0.00001234, 1.234e-5, -0.00001234, -1.234e-5)
The problem is we are calling the rpart.plot function with the default digits =2. See excerpt from the function documentation below
When digits is positive, the following details apply:
Numbers from 0.001 to 9999 are printed without an exponent (and the number of digits is actually only a suggestion, see format for details). Numbers out that range are printed with an “engineering” exponent (a multiple of 3).
As a temporary work around execute the function below, I will also post a link to the video
Ok, so the problem is only with the data in the charts and not in the table, please confirm, also the chart uses the function below, the default is digits =2
If negative, use the standard format function (with the absolute value of digits).
When digits is positive, the following details apply:
Numbers from 0.001 to 9999 are printed without an exponent (and the number of digits is actually only a suggestion, see format for details). Numbers out that range are printed with an “engineering” exponent (a multiple of 3).
Can you send me an anonymized dataset with the saved output file, this will allow me to test and find the best option to use?
There are 2 ways, zip up the data file and the bmd ( the bmd has the dialog with the parameters so I can reproduce the problem), you can send the zipped file to support@blueskystatistics.com if you cannot upload it here
To turn off scientific notation, click triple Dot on the top right menu bar, then click settings, click the output sub headings and uncheck the 1st checkbox
Decision trees uses the rpart function in the rpart package, you can get help by clicking the ? icon on the top right of the Decision Tree dialog or typing in help(rpart) in the BlueSky Statistics code editor, it is basically a classification and regression tree model
@Tererrance- Did you get your questions resolved? Its my first day on the forum- regarding Q[1] How do you turn off scientific notation from results, Did you check output settings?
i.e click on the 3 vertical dots at top right of menu bar, select settings (extreme left below menus). This should take you to output settings. The first line refers to the issue:
Numbers in scientific notation for very small or very large numbers (eg. 0.00001234, 1.234e-5, -0.00001234, -1.234e-5)
Best wishes
Nkem
The problem is we are calling the rpart.plot function with the default digits =2. See excerpt from the function documentation below
When digits is positive, the following details apply:
Numbers from 0.001 to 9999 are printed without an exponent (and the number of digits is actually only a suggestion, see format for details). Numbers out that range are printed with an “engineering” exponent (a multiple of 3).
As a temporary work around execute the function below, I will also post a link to the video
at https://youtu.be/JqT9Y6fjDMo
that will help you paste the syntax and execute the function below
rpart.plot( treeTest, type = 5, main="Decision Tree Diagram", roundint = FALSE, digits =-getOption("digits"))
Ok, so the problem is only with the data in the charts and not in the table, please confirm, also the chart uses the function below, the default is digits =2
rpart.plot(x = stop("no 'x' arg"), type = 2, extra = "auto", under = FALSE, fallen.leaves = TRUE, digits = 2, varlen = 0, faclen = 0, roundint = TRUE, cex = NULL, tweak = 1, clip.facs = FALSE, clip.right.labs = TRUE, snip = FALSE, box.palette = "auto", shadow.col = 0, ...)
See the help for digits below
The number of significant digits in displayed numbers. Default 2.
If 0, use getOption("digits").
If negative, use the standard format function (with the absolute value of digits).
When digits is positive, the following details apply:
Numbers from 0.001 to 9999 are printed without an exponent (and the number of digits is actually only a suggestion, see format for details). Numbers out that range are printed with an “engineering” exponent (a multiple of 3).
Can you send me an anonymized dataset with the saved output file, this will allow me to test and find the best option to use?
No luck, it is still printing results in scientific notation
To turn off scientific notation, click triple Dot on the top right menu bar, then click settings, click the output sub headings and uncheck the 1st checkbox
Decision trees uses the rpart function in the rpart package, you can get help by clicking the ? icon on the top right of the Decision Tree dialog or typing in help(rpart) in the BlueSky Statistics code editor, it is basically a classification and regression tree model