About DavidLie

DavidLie · ‎05-08-2023

Hi all, I hope you are doing well. I have a question regarding how to extract observations before and after a dummy. This is what I have. ID Var1 Var2 Dummy 1 20 41 0 1 17 20 0 1 97 68 0 1 93 49 0 1 91 77 1 1 51 37 0 1 88 55 0 1 42 14 0 2 62 40 0 2 93 46 0 2 77 70 0 2 31 32 0 2 53 58 1 2 21 73 0 2 55 94 0 2 73 29 0 2 34 27 0 What I need is to extract observation before, during, and after dummy variable indicating 1 (i.e., the text in red). So, the "want" dataset will be as below: A B C Dummy 1 93 49 0 1 91 77 1 1 51 37 0 2 31 32 0 2 53 58 1 2 21 73 0 Thanks! Best, David

DavidLie · ‎05-18-2022

Hi all, I have a sample of 40 observations. The plan is to: Take the first 20 observations (i.e., obs 1 to 20). Run a regression Keep the result Take the next 20 observation (i.e., obs 2 to 21). Repeat until you reach the maximum (i.e., obs 21 to obs 40). Any help will be greatly appreciated. If possible, I would like to keep the line as little as possible as I have quite a lot of observations. Thanks in advance. Best, David data have; input x1 x2 y; datalines; 69 0.901225752 0.535917754 26 0.979065064 0.328516725 21 0.462043623 0.928984209 70 0.372254307 0.020944067 26 0.70178162 0.015753384 22 0.755669857 0.287674489 45 0.621848244 0.876177263 23 0.049950103 0.524321342 75 0.323187042 0.458245799 62 0.988737694 0.528055761 59 0.047655873 0.637754194 59 0.499943648 0.997049298 25 0.597043632 0.556921095 92 0.679854964 0.433165676 29 0.686543133 0.720057785 35 0.861474371 0.344762962 79 0.591574823 0.876250534 53 0.741976868 0.430488835 71 0.146723447 0.605425714 75 0.435811738 0.861299126 96 0.785859466 0.717045755 99 0.520055579 0.784497337 58 0.394083913 0.712998746 61 0.875958722 0.667760878 15 0.561292166 0.836592031 56 0.652887463 0.236309836 9 0.344428535 0.224147253 6 0.785126736 0.435528686 72 0.847421203 0.160322663 78 0.663642034 0.466674263 83 0.333921138 0.029331531 77 0.486751999 0.706800698 92 0.801502963 0.788823137 9 0.578615463 0.347239912 41 0.053458445 0.094070384 68 0.251134914 0.103399917 2 0.49184594 0.102494486 97 0.120083405 0.055981267 78 0.5423958 0.181672902 17 0.834739212 0.142969285 ; run;

DavidLie · ‎05-17-2021

Thanks 🙂 It works.

DavidLie · ‎05-17-2021

Hi all, I have a question about using an output result for IF statement. For example, I have a following data about size of a product. My plan is to: Use PROC Univariate to obtain the quartiles. Categorise the data into three, based on results from Step 1. Group 1 if it's below Q1 (25th percentile) Group 2 if it's within Q1 and Q3 Group 3 if it's above Q3 Repeat for different products As I have 32 products, I would like to know if it can be done in a loop or something. Thanks in advance. Best, David Have Size 0.5 0.5 1 1 1 2 1 1 1 2 1 1 1 1 1 Want Size Group 0.5 1 0.5 1 1 2 1 2 1 2 2 3 1 2 1 2 1 2 2 3 1 2 1 2 1 2 1 2 1 2

DavidLie · ‎01-12-2021

Hi SAS Communities, I have two datasets here: (1) Have1: Showing all the date ranges. Example: ID Date_From Date_To 1 21 Feb 2000 14 Mar 2000 1 23 Jun 2000 17 Jul 2000 1 18 Oct 2000 8 Nov 2000 .... ... ... 2 29 Sept 2000 01 Jan 2001 ... ... ... (2) Have2: Listings of all dates. Example: Date Price 01 Jan 2000 x 02 Jan 2000 x 03 Jan 2000 x .... ... 31 Dec 2020 x I would like to have a dataset that have the following: Date Price ID1 ID2 01 Jan 2000 x 0 0 02 Jan 2000 x 0 0 03 Jan 2000 x 0 0 .... ... ... ... 21 Feb 2000 x 1 0 22 Feb 2000 x 1 0 ... ... ... ... 14 Mar 2000 x 1 0 15 Mar 2000 x 0 0 16 Mar 2000 x 0 0 ... ... ... ... 31 Dec 2020 x 0 0 In short, the dataset above has the binary code such that the date that falls within the range will be 1, otherwise 0. Best, David

DavidLie · ‎09-26-2020

Hi SAS Community, I have a dataset (extension .txt) that look something like this: SR Number|External System Reference No|Source|Product Category|Commercial Offer|Product Type|VAS| ... (76 variables in total) 1-6530390723||Phone|Internet|Streamyx|Streamyx Basic / Soho|| ... 1-6530396195||Phone|Internet|Streamyx|Streamyx Basic / Soho|| ... From above, you can see that the delimiter is "|" and when there is a missing data, it will just show as "||". In the above example, the variable "External System Reference No" and "VAS" are missing for both first and second observation. I'm currently use the following SAS Syntax to import the data: proc import datafile="&input\Raw Data\TMIDRRPT_MONTHLY_&date.-2010.txt" out=data.&date.2010 dbms=dlm replace; delimiter='|'; getnames=yes; run; Problems with above syntax: - Some variables are not imported properly (at times, I notice some data were incorrectly placed to other variables). - SAS often mixed up with the dates - initial format supposed to be DDMMYYYY and SAS automatically transformed this to MMDDYYYY. For example, 1st of February was transformed by SAS to 2nd of January. If anyone can suggest better way of importing this data, that would be awesome. Thanks in advance and stay safe. Best, David

DavidLie · ‎07-30-2020

Hi alexal, Thank you for replying. I'm unsure - just following some tutorials. How do we check the FQDN? Are there any guidelines that I can follow? Your help is greatly appreciated. David

DavidLie · ‎07-30-2020

Hi SAS Studio Expert, This is the first time that I'm using (and accessing) the SAS Studio. I guess the first part is to create a CAS connection and I'm having trouble with that. The error message that I'm getting is: ERROR: The host name 'sas1' could not be found. ERROR: Unable to connect to Cloud Analytic Services sas1 on port 5570. Verify connection parameters and retry. When I hover around the community, I notice that I need to connect something to somewhere. If you can teach me some of the steps, that would be awesome. Thanks. Best, David 1 OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK; 72 73 /*****************************************************************************/ 74 /* Set the options necessary for creating a connection to a CAS server. */ 75 /* Once the options are set, the cas command connects the default session */ 76 /* to the specified CAS server and CAS port, for example the default value */ 77 /* is 5570. */ 78 /*****************************************************************************/ 79 80 options cashost="sas1" casport=5570; 81 cas; ERROR: The host name 'sas1' could not be found. ERROR: Unable to connect to Cloud Analytic Services sas1 on port 5570. Verify connection parameters and retry. 82 83 OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK; 95

DavidLie · ‎06-30-2020

Hi SAS Experts, I just have a question on specifying series for do loops. Instead of the usual %do n=1 %to..., I would like to specify a series such that it will activate a certain set of numbers (in this case 1, 7,8,10...). But it does not work. Any ways out? 🙂 Thanks. Best, David %let n_MSA=48; %macro combineMSA(MSA); %do n=1,7,8,10,11,17,19,23,27,28,29,35,36,38,40,44,46; data data.diction_MSA&n.; set data.diction; if MSA ne &n. then delete; run; %end; %mend; %combineMSA;

DavidLie · ‎09-10-2019

Thanks all for helping me 🙂 Greatly appreciated.

DavidLie · ‎09-10-2019

Hi Paige, Thank you for your email. In this case, I want to create exact copies of my current observation by ITEM and WEEK. For example, in the WEEK 1166 and ITEM 23, there are 3 stores (namely Store 100, Store 200 and Store 250). I want to create exact entries of these 3 stores to capture the interactions. For example: Store 100 and Store 100; Store 100 and Store 200; Store 100 and Store 250: Store 200 and Store 100; ... Store 250 and Store 250. As a result, I have to inflate my dataset of having the same observations from 3 to 9. WEEK ITEM STORE STORE1 PRICE 1166 23 100 100 1.50 1166 23 200 100 2.50 1166 23 250 100 2.50 1166 23 100 200 1.50 1166 23 200 200 2.50 1166 23 250 200 2.50 1166 23 100 250 1.50 1166 23 200 250 2.50 1166 23 250 250 2.50 Hope I make myself clearer now. Best, David

DavidLie · ‎09-10-2019

Hi Draycut, Thank you for your message. Yes, this is close to something that I want. But: 1. When I tried it in my SAS, item 25 is somehow replaced by item 23. 2. I need to have an entry of STORE1 as well. I wonder if that can be doable? Thanks in advance. Best, David

DavidLie · ‎09-10-2019

Hi SAS Community, I would like to ask how to create multiple copy of observations from a single observation. At the moment, I have the following: WEEK ITEM STORE PRICE 1166 23 100 1.50 1166 23 200 2.50 1166 23 250 2.50 1166 25 110 3.25 1166 25 120 4.50 I want to have the following: WEEK ITEM STORE STORE1 PRICE 1166 23 100 100 1.50 1166 23 200 100 2.50 1166 23 250 100 2.50 1166 23 100 200 1.50 1166 23 200 200 2.50 1166 23 250 200 2.50 1166 23 100 250 1.50 1166 23 200 250 2.50 1166 23 250 250 2.50 … … … … … 1166 25 110 110 3.25 1166 25 120 110 4.50 1166 25 110 120 3.25 1166 25 120 120 4.50 This analysis is in terms of WEEK and ITEM. In the first case, there are 3 observations in WEEK 1166 and ITEM 23. Hence, I want to copy the exact observation by store. Let me know if this makes sense. Best, David

DavidLie · ‎09-09-2018

Hi all, I am currently working on a project that requires me to do some classification, so I thought of PROC HPSPLIT. Particularly, I am interested to look at the subtree that it produced. However, as I am working on 5 different variables and there is one nominal variable (account) that has about 100 levels, it seems that the subtree outcome was only shown for the first three decisions. Is there a way that the PROC HPSPLIT can return me with a complete decision tree? proc hpsplit data=data.trial1 seed=123; class ATT_Type account att_war_d; model ln_eq_sales=ln_eq_price ATT_Type account att_war_d ln_cost ln_btu; run; Your guidance will be much appreciated. Thank you in advance and have a good day. Best, David

DavidLie · ‎04-22-2017

Hi SAS Experts, I have been given a dataset and the dates were incorrectly imported (but I don't have the raw file). So, at the moment, the dataset has the following entries: 01 JAN 2010 01 FEB 2010 (which supposed to be 02 JAN 2010) 01 MAR 2010 (which supposed to be 03 JAN 2010) 01 APR 2010 . . 01 DEC 2010 13 JAN 2010 14 JAN 2010 15 JAN 2010 In short, the first 12 dates are incorrect as the dates and months are swapped. However, from date 13 onwards, it is correct and reads well. So, does anyone have a solution to combat this problem? Best, David

Online Status	Offline
Date Last Visited	‎05-08-2023 12:44 PM

Extracting Observations before, during and after a dummy

SAS Regression Loop in Set of 20 Observations

Re: Using output for IF Statement

Using output for IF Statement

Merge Several Date Ranges

Import Data with Delimiter "|"

Re: Error Create CAS Connection

Error Create CAS Connection

Specifying Series in Macro Do Loop

Re: Creating Multiple Observations from an Observation

Re: Creating Multiple Observations from an Observation

Re: Creating Multiple Observations from an Observation

Splitting string variable into Multiple Column

Extracting Observations before, during and after a dummy

SAS Regression Loop in Set of 20 Observations

Re: Using output for IF Statement

Using output for IF Statement

Merge Several Date Ranges

Import Data with Delimiter "|"

Re: Error Create CAS Connection

Error Create CAS Connection

Specifying Series in Macro Do Loop

Re: Creating Multiple Observations from an Observation

Re: Creating Multiple Observations from an Observation

Re: Creating Multiple Observations from an Observation

Creating Multiple Observations from an Observation

PROC HPSPLIT Decision Tree - Showing Full Decision Tree

Incorrect Date in the Dataset (Reversing Date and Months)