06-29-2020
Prajna_450
Fluorite | Level 6
Member since
12-05-2016
- 43 Posts
- 0 Likes Given
- 0 Solutions
- 1 Likes Received
-
Latest posts by Prajna_450
Subject Views Posted 1549 05-23-2018 05:27 AM 1623 05-22-2018 09:33 AM 1570 03-09-2018 12:03 AM 1655 02-22-2018 08:00 AM 1710 02-22-2018 07:39 AM 1589 02-22-2018 07:34 AM 1664 02-21-2018 02:44 AM 1524 02-16-2018 07:34 AM 1489 02-13-2018 08:52 AM 1818 02-12-2018 09:00 AM -
Activity Feed for Prajna_450
- Posted Re: SAS Eminer Stat Explore Node on SAS Data Science. 05-23-2018 05:27 AM
- Posted SAS Eminer Stat Explore Node on SAS Data Science. 05-22-2018 09:33 AM
- Posted Allowing multiple box plots on sas eminer on SAS Data Science. 03-09-2018 12:03 AM
- Posted SAS Eminer - Chi square test on SAS Data Science. 02-22-2018 08:00 AM
- Posted Sas eminer - execution of chi square test on catagorical variable on SAS Data Science. 02-22-2018 07:39 AM
- Posted Re: SAS Eminer - export results of anynode on SAS Data Science. 02-22-2018 07:34 AM
- Posted SAS Eminer - export results of anynode on SAS Data Science. 02-21-2018 02:44 AM
- Posted EDA help on sas eminer on SAS Data Science. 02-16-2018 07:34 AM
- Posted SAS Eminer - Meta data creation on SAS Data Science. 02-13-2018 08:52 AM
- Posted SAS Eminer - Correlation matrix and VIF on SAS Data Science. 02-12-2018 09:00 AM
- Posted Re: Result window works, request for two more solution on SAS Data Science. 01-31-2018 05:17 AM
- Posted Result window layout in sas eminer for variable selection node on SAS Data Science. 01-30-2018 02:42 AM
- Posted Re: sas eminer - help on a method for increasing sampling on SAS Data Science. 01-30-2018 01:56 AM
- Posted sas eminer - help on a method for increasing sampling on SAS Data Science. 01-29-2018 12:15 AM
- Posted Re: Tip: How to create data sources from imported files and share them across multiple projects on SAS Communities Library. 11-08-2017 02:47 AM
- Posted sas Eminer - variable cluster node on SAS Data Science. 11-08-2017 02:12 AM
- Posted pva7nk datat set on SAS Data Science. 07-31-2017 08:21 AM
- Posted Sentimental Analysis on SAS Data Science. 07-07-2017 01:00 AM
- Posted Re: Sentimental Analysis on SAS Data Science. 07-05-2017 08:36 AM
- Posted Re: Sentimental Analysis on SAS Data Science. 07-05-2017 08:34 AM
05-23-2018
05:27 AM
Hi Mike, Decision tree split search is also based on maximum logworth. Then, why do I see different order in Variable Worth (in Segment profile node) vs Variable importance (in decision tree node)? Could you please explain this difference? Thank you, Prajna
... View more
03-26-2018
03:19 PM
Hello Prajna-
In Enterprise Miner, you can use a SAS Code node to run PROC UNIVARIATE to get the plots. Here is a tip from our Communities page.
Tip: Saving ODS Graphics in a SAS Code Node
https://communities.sas.com/t5/SAS-Communities-Library/Tip-Saving-ODS-Graphics-in-a-SAS-Code-Node/ta-p/221195
Below, I modified the code from that tip for you in a way that you can use to create a normal probability plot.
- Connect a SAS Code node after the Regression node (or after the Metadata node).
- Select the Code Editor property.
- Enter this code:
%let name = npplot;
%let type= PDF;
%let description = my normal probability plot;
%em_register(key=&name, type=FILE, extension=&type);
ods &type file="&&em_user_&name";
/* put code here that you use to generate ODS graphics */
ods graphics on;
ods graphics;
proc univariate data=&EM_IMPORT_DATA plot normal;
var r_:;
run;
ods graphics off;
/* end of code for ODS graphics */
ods &type close;
%em_report(key=&name, block=MODEL, viewtype=FILEVIEWER, autodisplay=Y, description=&description);
- Close the Code Editor window.
- Run the node. View the results. A PDF is created with the PROC UNIVARIATE results.
Here is documentation about PROC UNIVARIATE in case you want to make any customizations.
Base SAS(R) 9.4 Procedures Guide: Statistical Procedures, Second Edition
http://support.sas.com/documentation/cdl/en/procstat/66703/HTML/default/viewer.htm#procstat_univariate_syntax01.htm
Have a good week!
... View more
02-22-2018
03:31 PM
Hello Prajna_450:
Please see the response regarding your other Chi-square post.
Have a great day.
... View more
02-22-2018
03:29 PM
Hello Prajna_450:
The Variable Selection node enables you to evaluate the importance of input variables in predicting or classifying the target variable. The node uses either an R-square or a Chi-square selection (tree based) criterion. The R-square criterion removes variables that have large percentages of missing values, and remove class variables that are based on the number of unique values. The variables that are not related to the target are set to a status of rejected.
Also, the StatExplore node generates Chi-square statistics for your variables.
Have a great day.
... View more
02-22-2018
07:34 AM
Hi, I agree to your solution, but I to send to my client I need to send it via excel. While I am try to export the alignment looks in appropriate. Is there any other way ? Please help ! Thank you, Prajna
... View more
02-16-2018
08:18 AM
Hello Prajna_450 -
If EDA is an acronym for 'exploratory data analysis', then consider using the Graph Explore Node in Enterprise Miner. Here is an excerpt from within Enterprise Miner under Help -> Contents -> Node Reference -> Explore -> Graph Explore Node:
Overview of the Graph Explore Node
The Graph Explore node is on the Explore tab of the Enterprise Miner tools bar. The Graph Explore node is an advanced visualization tool that enables you to explore large volumes of data graphically to uncover patterns and trends and to reveal extreme values in the database. This node is a partial replacement for SAS Insight and Distribution Explorer nodes from Enterprise Miner 4.3. The node creates a runtime sample of the input data source. You use the Graph Explore node to interactively explore and analyze your data using graphs. Your exploratory graphs are persisted when the Graph Explore Results window is closed. When you re-open the Graph Explore Results window the persisted graphs are recreated ...
Have a great day!
... View more
02-13-2018
10:45 AM
1 Like
Hello Prajna_450 -
Here is an excerpt from the Predictive Modeling chapter (in Enterprise Miner select Help -> Contents -> Analytics -> Predictive Modeling) with some comments to help you make decisions about what measurement levels to select for the variables in your analysis.
Have a great day.
Class Variable In data mining, pattern recognition, knowledge discovery, neural networks, and so on, a class variable means a categorical target variable, and classification means assigning cases to categories of a target variable. In traditional SAS procedures, class variable means simply categorical variable, either an input or a target.
Measurement The process of assigning numbers to things such that the properties of the numbers reflect some attribute of the things.
Measurement Level One of several ways in which properties of numbers can reflect attributes of things. The most common measurement levels are nominal, ordinal, interval, log-interval, ratio, and absolute. For details, see the Measurement Theory FAQ at ftp://ftp.sas.com/pub/neural/measurement.html.
Nominal Variable A numeric or character categorical variable in which the categories are unordered, and the category values convey no additional information beyond category membership.
Ordinal Variable A numeric or character categorical variable in which the categories are ordered, but the category values convey no additional information beyond membership and order. In particular, the number of levels between two categories is not informative, and for numeric variables, the difference between category values is not informative. The results of an analysis that includes ordinal variables will typically be unchanged if you replace all the values of an ordinal variable by different numeric or character values as long as the order is maintained, although some algorithms might use the numeric values for initialization. SAS Enterprise Miner provides no explicit support for continuous ordinal variables, although some procedures in other SAS products do so, such as TRANSREG and PRINQUAL.
Interval Variable A numeric variable for which differences of values are informative.
Ratio Variable A numeric variable for which ratios of values are informative. In SAS Enterprise Miner, ratio and higher-level variables are not generally distinguished from interval variables, since the analytical methods are the same. However, ratio measurements are required for some computations in model assessment, such as profit and ROI measures.
Binary Variable A variable that takes only two distinct values. A binary variable can be legitimately treated as nominal, ordinal, interval, or sometimes ratio.
... View more
02-12-2018
01:50 PM
Hello Prajna_450:
In data mining, the number of inputs is often large, The usual correlation/covariance matrix is on the order of the square of the number of inputs, so it can quickly become so large that interpreting it can become tedious. However, if you do want to see it, then one method is to use the Principal Components node with the Print Eigenvalue Source property changed from No to Yes.
A more manageable approach might be to use the StatExplore node to compute standard univariate statistics, to compute standard bivariate statistics by class target and class segment, and to compute correlation statistics for interval variables by interval targets.
Variance Inflation Factor (VIF) is displayed for interval targets by the HP Regression node.
Thank you for your interest!
... View more
01-31-2018
05:17 AM
hi, Thanks a lot! I tried the same parameters on a new diagram and it worked well !!. There are two more Queries I am looking for solution 1. I will need help on a over sampling method, can u share your experience of using the node ? 2. What is the advantage of using segment profile over variable selection (variable Importance) Thank you, Prajna
... View more
01-30-2018
01:56 AM
Hi, Firstly thanks for the reply, but my question is how do I increase the number of observations or records for those predictors whose frequency is low. Help me in finding a method to handle the situation. Thank you Prajna
... View more
11-08-2017
04:04 PM
The Variable Clustering node produces the correlations by default when you run the node.
After the node completes, view the results.
In the Results window, select View -> Model -> Variable Correlation. A heat map is displayed.
To view the values of the heat map, click the Table icon, and a Table Variable Correlation window is displayed.
From that window, you can select File -> Save As if you want to create a SAS data set that contains the correlations.
The covariances are not output.
... View more
08-03-2017
03:26 PM
Here's a link to the column descriptions which I find useful when interpreting the results of my analysis
http://support.sas.com/documentation/cdl/en/emgsj/67981/HTML/default/viewer.htm#p0gbbwhw4eszv5n1rko3o6x34b3g.htm
... View more
07-28-2017
03:32 PM
Please create a track with Technical Support by filling out the form at the following URL:
http://support.sas.com/ctx/supportform/createForm
And we will be better able to help you with this question.
Thanks.
... View more
07-04-2017
02:28 AM
Hi, To obtain text sentiment scores will I need to download sas sentiment Analysis studio ? if yes, is there a trail version too for the same ? thank you, Prajna
... View more