I'd like to use Excel to generate a randomized lab partner list, without using VB (due to security settings on the PCs).
Parameters are as follows:
Number of students: 10-30, one worksheet per total number desired
Number of partners: Three for first two labs, and two for the other four-five.
Number of lab stations: 10
Repeats: Ideally none, but it is permissible for a student to have a repeat partner from one of the first two labs.
Excel version: 2007
To clarify, each student will have two labs where they share a lab station with up to two other students, giving a maximum lab size of 30 students. After that, they will be strictly limited to two students per station, giving a maximum of 20 students. Each student will have four of these limited labs, with there being a total of five such labs presented, to allow for either odd-numbered classes, or a class size between 21-30.
Each student is simply numbered from 1-30, so a cell could, for instance, state "5, 24" as the two students for that lab station.
True RNG is not important, and in fact, only needs to be performed once to make these matrices.
I think this is a bit tricky without using VBA, but here is one approach that is OK for small groups. I have tried it using a group of just nine so that the screen shot should be readable.
The method is basic Fisher-Yates
A Start with a group of students size n represented by a list of numbers 1 to n.
B Generate a random number r in range 1 to n
C Pick the rth element from the list
D Remove the rth element from the list
E Reduce n by 1
F Repeat from B until n=1.
In Excel:-
Fill A2:A10 and D2:L2 with numbers 1-9
Put the following in B2 and pull down:-
=RANDBETWEEN(1,10-A2)
Put this in C2 and pull down:-
=OFFSET(D2,0,B2-1)
Put this in D3 and pull down and across:-
=IF(D2>=$C2,E2,D2)
The ID's will be in column C so the first three would be in group 1, the next three in group 2 etc.
By the way, your question is a special case of generating non-repeating random numbers - see
Generating unique random numbers without VBA
The array formula described here does it in one step - modified slightly for this problem it would look like
=SMALL(IF(COUNTIF(C$1:C1,ROW(INDIRECT("1:9")))=0,ROW(INDIRECT("1:9"))),RANDBETWEEN(1,(9-ROWS(C$2:C2)+1)))
Related
I am looking for a way to make a specific graph in Excel and I can't find a solution in Excel or on the web.
I have data about an online training with people completing parts of a course at a certain time:
FullName
Course
TIME
Name-A
Part 1
23/03/2022 10:38
Name-A
Part 2
23/03/2022 12:07
Name-A
Part 3
23/03/2022 16:55
Name-B
Part 1
11/03/2022 15:14
Name-B
Part 2
22/03/2022 12:08
Name-B
Part 3
28/03/2022 16:06
Name-B
Part 4
30/03/2022 14:55
Name-B
Part 5
18/04/2022 08:13
Name-C
Part 1
11/04/2022 15:25
Name-C
Part 2
20/04/2022 13:50
I would like to have a specific graph of this data:
On the vertical axis: one row for each user' name: Name-A, Name-B and Name-C.
On the horizontal axis: continuous time (say, in days) From the minimum time in the table (or less) to the maximum (or more)
Series of plots for the data: Each part of the course (from Part 1 to Part 5 here) would be a series of dots of a specific color, placed on the right row (for a learner's name) above the corresponding time on the horizontal axis.
Do you have any idea on how it could be achieved?
All the best, R.S.
Edit: The table does not appear as in the preview so i try to add a screenshot:
Screenshot of the table
So one way to visualise this as mentioned in the comments is to create a separate series for each person and show passing each part of the course as a vertical step:
It's based very loosely on this but I've set each day in the date range as the x-coordinates and used a lookup to transform the data in H2
=RIGHT(XLOOKUP($G2+TIME(23,59,59),FILTER($C$2:$C$11,$A$2:$A$11=H$1),FILTER($B$2:$B$11,$A$2:$A$11=H$1),0,-1))+(COLUMN()-COLUMN($G$1))*10
pulled down and across to give
Explanation
The data for the graph has dates spanning the times in the raw data for its x-coordinates (column G). I generated it manually but could have used Sequence in Excel 365.
There are three columns of y-values, H to J, generating a separate series for each person. The three lines are initially spaced out by 10 units based on the column number. In the formula above, the raw data is filtered by the person's name so the headers in columns H, I or J match the names in column A in the raw data. Xlookup is used with 'next smallest' match so where the date in column G is greater or equal to the date/time in column C it will return the corresponding course from column B. Because column C actually contains date/times, I have added almost 24 hours when matching the date in column G to make sure that a match is found if the day is the same, regardless of time. In a case like Name-A, where three courses are completed in the same day, this will automatically select the last one (Part 3). Then I take the right-hand character of the course name (which is a digit in the sample data) and add it to the relative column number multiplied by 10. If there is no match, Xlookup returns zero so you just get the initial value for each series (10, 20 or 30), otherwise the result will be an increase by one unit each time a course is passed. If you couldn't assume the last character of the course name was a digit, you would need a lookup to assign a number to each course name.
The data is then plotted on a scatter graph with points joined by straight lines. I had to adjust the x-axis manually to make the range correct and the labelling clearer.
This could be done without Excel 365, probably using Aggregate to get the highest row number with a condition on the name and date.
EDIT
I could have achieved the same result much more easily using Countifs to find how many courses had been passed by a certain person by a certain date:
=COUNTIFS($A$2:$A$11,H$1,$C$2:$C$11,"<="&$G2+TIME(23,59,59))+(COLUMN()-COLUMN($G$1))*10
This wouldn't have needed Excel 365. If you needed to give different courses different weightings, you could do this with a sumproduct and a lookup, also fairly straightforward.
Let's say I have this:
A B
1 10 20
2 12 30
3 25 15
4 40 30
How do I find the row which have same value in column B and different value for column A when compared to all the rows above or below ?
I want to find this cell:
A2:B2
Update: NO revision necessary
Following feedback I have tested this equation (below) with 20k rows (link below) - happy to report back results as expected/all still in order. No changes necessary/warranted. This function works just fine/as expected. Beaut!
Explanation:
When testing large samples of data of type 'integer' (say) that range a common order of magnitude/size (i.e. have material probability of re-occurring), the probability of obtaining a unique value for field A (col B, below screenshot) reduces, due to the law of large numbers (variance is what leads to unique values, and this reduces as the sample size increases).
As a consequence, one may encounter results = !Calc# which simply means 'no unique values could be found in col A (or they could but only for when col C was also unique - although the probability of this is remote, it's mainly due to numerous other cells in respective columns containing identical data. Throw a negative 100 in column A (assuming all other values are positive real/integer number plane), and you should see my eqn. below return '-100' and whatever the corresponding 'col-C' data is (assuming that is not unique too, as I have mentioned)...
NOW - back to the solution already! :)
ORIGINAL SOLN:
This will give you back every such combination (besides {12,30} there is also {40,30}):
=FILTER(B2:B5&"-"&C2:C5,(COUNTIFS(B2:B5,"="&$B$2:$B$5)=1)*(COUNTIFS(C2:C5,"="&$C$2:$C$5)>1))
OneDrive excel-linked spreadsheet for your convenience here, taking careful note of restrictions per 1st comment to this proposed soln.
Screenshot
Notes
Assumes you have Office 365 version of Excel
I am working on a model of charging load of electric vehicle. I am attaching a link to an excel workbook for your better understanding.
Column B contains random time values
Column G to P represents houses and each house can have 1 car. So the each time values needs to be distributed in one column. Now when a car is plugged in, its load stays constant for 3 cells.
I want excel to randomly distribute these cars e.g. 4 cars to 4 houses and leave others blank.
what i can think of is, to assign each time a random house then use IF formula with AND function to match random times with time series and second condition to match random houses with columns 1-10.
the problem i am facing is, the formula gives a value error and only works in the rows with has random generated time in front of them screenshot. I know there is a very small thing that i am missing. please help me find it
Regards
workbook
=IF(ISNA(MATCH(G$5,$C$6:$C$9,FALSE)),"",IF(AND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE))>=$F6,INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE))<=$F6+TIME(0,30,0)),11,""))
The two elements in the AND find the house number in column C and return the corresponding time in column B.
The first element compares the time in F to that time. The second element compares the time + 30 minutes to F (three cells). If it's between those two times, it gets an 11.
The ISNA makes sure that the house in question is on the list. You could also use an IFERROR, but I prefer the precision of ISNA.
Update
If you want the values to wrap around, you need to OR compare to the next day.
=IF(ISNA(MATCH(G$5,$C$6:$C$9,FALSE)),"",IF(OR(AND(ROUND($F6,5)>=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE)),5),ROUND($F6,5)<=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE))+TIME(0,30,0),5)),AND(ROUND($F6+1,5)>=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE)),5),ROUND($F6+1,5)<=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE))+TIME(0,30,0),5))),11,""))
That formula structure looks like
=If(isna(),"",if(or(and(today,today),and(tomorrow,tomorrow)),11,"")
This formulas already getting too big. If you triple it for your three voltages, it will be huge. You should consider writing a UDF in VBA. It won't be as quick to calculate, but will probably be more maintainable.
If you want to stick with a formula, you could put the wattage in row 4 above the house number. Then in another table, list the wattages and minutes to charge. So in, say, B12:C14 you have
3.7 120
11 30
22 15
Now where you have 11 in your formula, you'd have G$4 and the two placed you have TIME(0,30,0), you'd have TIME(0,INDEX($C$12:$C$14,MATCH(G$4,$B$12:$B$14,FALSE)),0). I re-arranged some stuff to make it more 'readable' (but it's still pretty tough) and here's the final formula
=IF(ISNA(MATCH(G$5,$C$6:$C$9,FALSE)),"",IF(OR(AND(ROUND($F6,5)>=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE)),5),ROUND($F6,5)<=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE))+TIME(0,INDEX($C$12:$C$14,MATCH(G$4,$B$12:$B$14,FALSE)),0),5)),AND(ROUND($F6+1,5)>=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE)),5),ROUND($F6+1,5)<=ROUND(INDEX($B$6:$B$9,MATCH(G$5,$C$6:$C$9,FALSE))+TIME(0,INDEX($C$12:$C$14,MATCH(G$4,$B$12:$B$14,FALSE)),0),5))),G$4,""))
I am trying to create a spreadsheet that can find the most likely probability that a student scored a specific grade on a test.
Only one student can score a grade and only one grade can have a student.
I have limited information about each student.
There are 5 students (1,2,3,4,5)
and the grades possible are only (100,90,80,70,60)
In the spreadsheet a 1 denotes that the student DIDN'T score that grade.
Does anyone know how to make a simulation that I can find the most likely probability of what student scored what grade?
Link:
https://docs.google.com/spreadsheets/d/1a8uUIRzUKsY3DolTM1A0ISqMd-42WCUCiDsxmUT5TKI/edit?usp=sharing
Based on your response in comments, each student has an equal likelihood of getting each grade. No simulation is necessary.
If you want to simulate it anyway, don't use Excel*. Create a vector of students, and pair it with a shuffled vector of the grades. Lather, rinse, repeat as many times as you want to see that the student-to-grade matching is uniformly distributed.
* - To get an idea of how bad Excel can be for random variate generation, enable the Analysis Toolpak, go to "Data -> Data Analysis" on the ribbon, and select "Random Number Generation". Fill in the tabs that you want 10 variables, number of random numbers 2000, a "Normal" distribution, leave the mean and std dev at 0 and 1, and enter a "Random Seed" value of 123. You will find that the resulting table contains 3 instances of the value "-9.35764". Values that extreme should occur about once per twenty thousand years if you generate a billion a second. Getting three of them is so extreme that it should happen once per 1030 times the current estimated age of the universe. Conclude that a) it's your lucky day, or b) Excel sucks at random numbers, and despite being informed about this as far back as 1998 Microsoft hasn't bothered to fix it.
I'm going to try to explain this the best that I can.
Right now I have a spreadsheet with a list of football players, each of which has an assigned salary and projected point total for the week.
My goal is to use Solver or some other method to determine the best combination of players to maximize the projected point total while staying under a salary cap.
In this example I have 4 separate player lists, like this:
QB: Player A, Player B, Player C...Player N
RB: Player a, Player b, Player c...Player N
WR: Player X, Player Y, Player Z...Player N
TE: Player x, Player y, Player z...Player N
I need the best combination that includes 2 QBs, 2 RBs, 2 WRs, 1 TE, and 2 "Flex", which means any of RB/WR/TE.
I have tried using Solver to maximize the projected point total, but the variable fields in this case would be the Player's Names and it seems like the variable field needs to be a number, not a list of strings.
Any ideas?
My favorite kind of question :)
Here is the model setup:
Top table shows the decision variables: = 1 if player i = A, B, ..., N of list L = QB, .., TE is selected, =0 otherwise.
Entries in column R, (next to the top table) are the sums of each row. These must be constrained with the numbers in column T. Cell R7 is the total sum of players, which should be 9: 2 flexible and 7 as per the individual list requirements.
Middle table shows the salaries (randomly generated between 50,000 and 150,000). The Sum of Salaries formula is =SUMPRODUCT(C11:P14,C3:P6). The idea here is that only the salaries of players that are selected are taken into account. This SUMPRODUCT should be constrained with the budget, which is in cell T14. For my experiment, I put it equal to 80% of the total sum of all salaries.
Objective: Bottom table shows the projected points for each player. The formula in cell R22 is =SUMPRODUCT(C19:P22,C3:P6) (same logic as with salaries above). This is the value to be maximized.
Solver Model shown below:
I suggest selecting Simplex LP and going to Options and setting the Integer Optimality to zero (0).
Result:
Solver manages to find an optimal solution. The problem is really small and it is very quick. Solver works with up to 200 variables and 100 constraints, for large problems you will need the (commercial) extended version:
Of course, you can just order the real player names so that they fit this setting. For example, if you sort the players of each list alphabetically, then (Player A, QB) = first player of team QB, etc.
I hope this helps! Let me know if you would like me to upload the file for you.
Best,
Ioannis
Excel's solver is built on numerical methods. Applying to a domain that consists of discrete values, like strings or football players is probably going to fail. You should consider writing a brute force solver in a "real" programming language, like c#, java, python, ruby, or javascript. If there are performance problems, then optimize from there.
Solver won't work here because it's not a numeric solution you're after.
Make a spreadsheet that has every possible combination of position players (that meet your criteria) on each row. Then make an Excel formula that calculates projected point total based on the players in that row. Sort the spreadsheet by your projected point column.