About majdi_ka

majdi_ka · ‎02-03-2016

Hi @Kurt_Bremser, Thanks for your answer. I'am aware that the I/O is the main reason of the important execution time. That's why i'am looking for ways that load partially or totally data into memory. I used this program but still have the same execution time (cpu time 1:38 // real time 11:42). data want (keep=max); set have (keep=variable) end=eof; array v{1} variable; max=v{1}; do i=2 to dim(b); if max<max(v{i}) then max=max(v{i}); end; if eof; run; For your suggestion of using compress option, I'm using the data step keep= option, which I think more efficient. best regards, MK

majdi_ka · ‎02-03-2016

Hi, I have a dataset with tens of millions of lines and I wand to calculate the max of a column. calculating this max took more than 10 minutes with proc sql and proc means. Is there a fastest way to do this (Arrays, hash objects, iml) thanks in advance MK

majdi_ka · ‎12-02-2015

Jason, It's exactly about 'informativeness of the missing". I didn't know about this name before. You described the problem very well. Your suggested solution works very well if it's only about a flag (Binary or even nominal variable). However, when the variable is numeric it's more complicated to deal with because -1 or even -9999 is considered as a value of the variable's range and not as an extra independent information. this will effect the estimated parameter of the variable. Not sure it's relevant. I think that the model can distinguish between both populations (those who don't have an email and those who didn't open emails) as long as a variable "flag email" is present in the final model. This is because it takes into account different interactions between variables...But this it remains a hypothesis. I'm not sure if there is a solution that sas stat or SAS Enterprise Miner consider. But it could be a format like this Proc format; value nb_opened_email_fmt . = "No email"; run; Or may be a special missing value. I didn't try anyone of them yet but it can solve the problem. Best Regards, MK

majdi_ka · ‎12-02-2015

@Reeza, Thanks for your answer. In fact, it's about my input variables and not my target variables. It's what @JasonXin talked about!

majdi_ka · ‎12-01-2015

Hi, I built a data set for scoring purpose. And it needed multiple merges between many tables especially left joins. that means I have many missing values for customers who aren't present in the second table of the join. For example, the variable indicating the number of times the customer has opened an email will be missing for those who have not an email. So a missing value is a different information from a 0 which indicates that the customer recieved emails but didn't open them! I replaced missing values with 0, but I think it's not optimal. My question is is there a way to distinguish between missing values and 0, so that it can be taken into account by the model (logistic regression which don't accept missing values) Any advice is appreciated! Thanks, MK

majdi_ka · ‎11-26-2015

Based on your previous post, I edited the code because I have only numeric variables : PROC TABULATE DATA=SASHELP.CLASS ; VAR Height Age; TABLE /* ROW Statement */ Height * Mean={LABEL="Mean"} Height={LABEL=""} * Median={LABEL="Median"} Age * Mean={LABEL="Mean"} Age={LABEL=""} * Median={LABEL="Median"} , /* COLUMN statement */ ALL=' ' ; ; RUN; And I have the result that I want : Height Mean 62.34 Median 62.80 Age Mean 13.32 Median 13.00 What I looked for is the " , ALL=' ' " Thanks a lot @Reeza!

majdi_ka · ‎11-26-2015

it gives a vertical summary table like this : Age Revenue mean median mean median

majdi_ka · ‎11-26-2015

@Reeza, OK, it's a simple code: proc tabulate data=have; var age revenue; tables /*line*/ age revenue, /*column*/ (mean median); run; MK

majdi_ka · ‎11-26-2015

Hi, with proc tabulate I have this output : mean median Age 30 25 Revenue 2700 2600 and what I want to have is this form : Age mean 30 median 25 Revenue mean 2700 median 2600 Is this possible? Thanks

majdi_ka · ‎11-25-2015

Thanks @SteveM_UK it works

majdi_ka · ‎11-25-2015

Hi there, I want to combine two formats : Here is an example of what I want (but it does not work): proc format; value purchase_date_fmt . = "No purchase " other = ddmmyy10. ; run; I performed a left join and want to display "No purchase" instead of the missing values and display the non missing values using ddmmyy10. format. Is there a solution to do this ? Thanks !

majdi_ka · ‎11-17-2015

Thank you @pearsoninst, @DanH_sas and @Jay54 for your help. Very instructive ! I finally used a butterfly plot to compare nominal variables. I used the eval function in GTL to keep values related to a specific filter variable's modality, and then compare them to overall values. Butterfly plot is finally clearer and easier to compare than a pie chart. I created a macro to automate all this so that it can be reusable. Thanks !

majdi_ka · ‎11-10-2015

Thx @pearsoninst and @DanH_sas ! Great idea. However, I didn't find yet how to do this with all the data and a subset in the same graphic. And this is the hardest part. I think it can be done with proc template.

majdi_ka · ‎11-10-2015

Thanks for answering. This is not exactly what I'm looking for. I want to compare the distribution of a subgroup with the overall distribution. Let's take an example. Assuming I have different clusters of customers, I want to see what are the characteristics of each one. This can be done by comparing the distribution of each cluster with the overall distribution. For example, for cluster1, I compare its countries' proportions to all data countiries' proportions. A pie chart grouping both proportions can be visually easier to compare than two side by side pie charts. Hope my example is clear

majdi_ka · ‎11-10-2015

Hi, I want to compare overall data with a subset. I could do this overlaying histograms thanks to these great answers. That was for continuous data. Can the same be done with nominal and ordinal data in a grouped Pie chart or barplot? Thanks

Online Status	Offline
Date Last Visited	‎01-12-2017 01:10 PM

Re: Benefits of SAS server

Re: Converting to a Date

Re: Converting to a Date

Re: Converting to a Date

Re: Converting to a Date

Re: Converting to a Date

Re: what is T-value in logistic regression result ?

what is T-value in logistic regression result ?

Re: Fastest way to calculate the max of a variable in a large dataset

Re: Fastest way to calculate the max of a variable in a large dataset

Re: Benefits of SAS server

Re: Benefits of SAS server

Re: Benefits of SAS server

Re: SAS Enterprise Guide 7.1 - Data Grid - Missing entries on context ...

Re: SAS Date Function

Re: group extreme values in a single bin in a histogram

Re: Converting to a Date

Re: Fastest way to calculate the max of a variable in a large dataset

Re: Fastest way to calculate the max of a variable in a large dataset

Re: Fastest way to calculate the max of a variable in a large dataset

Re: Fastest way to calculate the max of a variable in a large dataset

Fastest way to calculate the max of a variable in a large dataset

Re: missing values VS 0 in a logistic regression

Re: missing values VS 0 in a logistic regression

missing values VS 0 in a logistic regression

Re: horizontal summary table

Re: horizontal summary table

Re: horizontal summary table

horizontal summary table

Re: Combining two formats

Combining two formats

Re: Grouped pie Chart and barplot comparing overall vs subset data

Re: Grouped pie Chart and barplot comparing overall vs subset data

Re: Grouped pie Chart and barplot comparing overall vs subset data

Grouped pie Chart and barplot comparing overall vs subset data