Coding - Science topic

See this video explaining the Matlab code for plotting the bifurcation diagram, with code available in the description https://www.youtube.com/watch?v=O506G8DtmQk

CFD softwares are based on numerical methods or techniques to predict the fluid behavior for various conditions e.g. LES and RANS turbulence modelling etc. Unlike exact solutions , the numerical methods involve approximations of the governing fluid parameters which cannot be evaluated at once and thus need iterative computational solvers.

During this process several types of errors are introduced while approximating variable property e.g round off errors ( machine precision) , truncation errors depending on the type of numerical scheme used.

However , according to the nature of fluid and it's interaction with surrounding environment , ( in your e.g yplus wall function which is measure of the fluid friction resistance near wall ) the solutions obtained through numerical schemes present a significant source of error which can interpret the fluid behavior in entirely different manner.

Therefore, the solution is often tested by repeating the process using better approximations and schemes with a focus to obtain the exactness of parameter value leading to iterations.

During iteration process , the error can amplify or reduce ( which is indicative of the stability of solution ) depending on boundary conditions used to obtain solution. So, often an error tolerance is introduced as condition in numerical algorithm to make the solution more meaningful and realistic which closely approximates the fluid behavior. In your case wall shear stress is being approximated using wall units in logarithmic boundary layer.

Once that condition is satisfied, the process stops and proceeds further by evaluating the next dependent variable and so on until complete solution is obtained.

Some ideas and associations:

You state “human can only aspire to fluency in so many different languages before mixing up words due to code switching”. I don’t know if this is true at all. On what research is it based? In my own situation, I am fluent in 5 languages and do not mix up words or get confused to which language a word belongs to.

Fluency in language corresponds to numeracy, that has been demonstrated. Children who are read a lot of stories in pre-school, for example, were no better in general subjects compared to other children, but they were better at maths later on. Both implicate logical thinking. Without logical thinking humans cannot string words into a longer narrative either.

People choosing coding or computer sciences may prefer to work individually and not in groups. That is a different dynamic, social vs solo, than proficiency at languages.

Writing research papers and actual programming are indeed two different fields of knowledge, although they can be complementary. Here's an overview of the differences and the gap between what's written in many AI papers and the actual code:

Gap Between Papers and Code:The gap between what's written in many AI papers and the actual code can vary widely. Several factors contribute to this gap:

It's worth noting that efforts are being made to bridge the gap between AI research papers and code. Some conferences and journals encourage authors to publish code alongside their papers, and open-source communities play a crucial role in creating accessible implementations of research.

Overall, while writing papers and programming are distinct skill sets, they are interconnected in the field of AI research, where practical implementations often validate and extend theoretical findings. AI tools, including GPT-3, can assist in generating code or summaries of research papers, further bridging the gap between these two domains.

Anees Abdullah Khadom You mean you want to standardize them in some way to make them comparable? In theory there is nothing wrong with this. What you seem to do is minmax normalisation (x-min(x))/(max(x)-min(x)). This can sometimes be helpfull (sometimes) such as machine learning.

In practice (mostly) this means you lose information and the only thing you could say is X1 > X2 or similair. The results beyond the study are completely meaningless (literally) because 0.6>0.2, but so what? Often the conlcusion is that 0.6 is more important than 0.2, because it is larger. But the only thing that adds meaning to the number is the "context", which is removed. Moreover, if max temparature = 200 and min = -10 then it becomes 1 and 0. But the same accounts for 30 and 5. You remove any measure of meaning degrees celcius. Boiling point, evaporation, freezing etc. are all ignored. Can you imagine the Ideal gas law, being uniteless? Hence, the meaning is in the "unit" or "context" an how it relates beyond a study. Losing two hairs on my head per day day is not so dramatic, but losing two limbs a day, I rather vote the first. Both the numbers were 2, but only the "unit" or "context" differed.

This form of "standardisation" or "normalization" is done because we want a dichotomy it is easy. So the only goals is: IF 1.) X1>X2=T or 2.) X1>X2=F. If 1.) X2 is more imprtant than X1. I too made such mistakes, but when I critizise and basically ban my own results to the "pseudo-sciences" (for mental effect) explaining why, nobody seems to care they want these standardized monsters.

Sorry for the harsh response, but now +100 years later in aquatic ecology/liminology I try to find out what the relation is i.e. a species (repsonse) and pollution (dependent) I cannot find a single regression coefficient and even worse is the absence of any online published data. Then what have we been doing for +100 years? So, now I ask any ecologist what is the "impact" on species number, nobody knows. So on what "meaning" are our environmental laws than based? I would simply avoid such a things althogheter as much as possible and If you do publish the data online.

Best,

JAS Claude.ai LLM (Choice: Copy & Paste)

Claude can't visit links. Responses may contain hallucination.

JA

Here is a definition of how choice-overload bias can impact the asset structuring of economic variables:

Choice-overload bias refers to the phenomenon where having too many choices or options can lead to decision paralysis, confusion, and potentially poorer decisions. This can apply to economic variables like asset structuring in a few key ways:

The overall result is that economic actors like investors, consumers, employees, and policymakers get overwhelmed by too many choices and end up structuring assets, plans, purchases, and policies in a more confused and suboptimal manner. Limiting options and presenting clear defaults is one way to circumvent the choice-overload bias.

Copy

right, ... can you answer the question posed please?

JA

Here is an attempt to directly answer the question of how choice-overload bias impacts asset structuring of economic variables:

The abundance of choices available when structuring assets leads to several key impacts due to choice-overload bias:

In summary, the availability of too much choice distorts the asset structuring process away from optimal economic decisions. Investors fail to rigorously identify optimal asset allocation and instead display inertia, simplistic heuristics, herd behavior, fragmentation, and paralysis.

Querying data from the Materials Project using its API for machine learning typically involves several steps. The Materials Project is a database of materials properties and can be a valuable resource for materials science-related ML projects. Here's a general guide on how to query data for machine learning from the Materials Project API:

1. Sign Up and Obtain an API Key:

· Go to the Materials Project website (https://materialsproject.org/).

· Sign up for an account if you don't already have one.

· Once you're logged in, navigate to your dashboard and find your API key. You will need this key to authenticate your requests to the API.

2. Choose Your Materials and Properties:

· Determine the specific materials and properties you want to use for your machine learning project. The Materials Project provides data on a wide range of materials and their properties, such as crystal structures, electronic properties, thermodynamic properties, and more.

3. Construct API Queries:

· Use the Materials Project API to construct queries that retrieve the data you need. The API provides various endpoints for different types of data.

· You can use the pymatgen library in Python, which is designed for materials science computations and integrates seamlessly with the Materials Project API.

4. Retrieve and Preprocess Data:

· Once you've constructed your queries, retrieve the data from the API. Depending on your specific ML task, you may need to preprocess the data to suit your needs. This could include cleaning, feature engineering, and data transformation.

5. Training and Evaluating Your ML Model:

· Use the retrieved and preprocessed data to train and evaluate your machine-learning model. Depending on your project's goals, you may apply various ML algorithms and techniques.

6. Iterate and Optimize:

· Iterate on your ML model and data selection to improve its performance.

· Consider experimenting with different materials and properties to achieve better results.

7. Citation and Compliance:

· Ensure you follow the Materials Project's terms of use and citation guidelines. Properly attribute the data you use in your research and publications.

8. Deployment (if applicable):

· If your ML model has practical applications, deploy it to your desired platform or integrate it into your materials science workflow.

Remember that the Materials Project API may have rate limits and usage restrictions, so be sure to check their documentation for any updates or limitations before making extensive use of their services.

Also I'm not sure where you are looking, but I suppose I WAS wrong. It's actually the top 1 percent relative to its release and 82 percent overall, and the stats are the same for my profile. I've attached the picture. Leo Lazauskas Leo Lazauskas

You need to optimize your duty cycle parameters appropriately. You can refer to this paper:

Plant identifier apps typically use a combination of computer vision and machine learning techniques to identify plant species. The coding involves creating a database of plant images with associated labels, training a deep learning model using this data to recognize different plant features and patterns, and then implementing algorithms to process input images and compare them with the trained model to make predictions about the species. While there are advanced plant identifier apps available that can identify a wide range of species from a single image, accurately differentiating multiple species within a bouquet of flowers in a single frame may still be challenging due to overlapping plant parts and variations in lighting and angles. However, ongoing advancements in computer vision and machine learning continue to improve the capabilities of these apps.

Gillian Mccarthy ultimately all qualitative research analysis includes inductive and deductive components. What you described would be twofold: (1)begin with a deductive analysis focused on the 5 areas from your framework. Within this process, you would want to keep your mind open to include ideas that do not align with the framework--that is, if an idea keeps coming up in the transcripts but does not fit in one of the 5 areas, then I recommend putting these data in a separate 'category' or code depending on how you are capturing your analyses processes. (2) your second step is to identify the patterns within each of the 5 areas. In this step, you are combining data that are similar in meaning. The goal is to combine the data until you get to between 2 and 5 groups. You would also do this step for any group of data that emerges outside of the framework.

See the documents attached. I hope this helps.

Veronica

This video might be helpful

I think that the key technique is finding Jacobian Matirx of the two dimensional CML .

Louis Nguyen To obtain Non-equilibrium (NE)-SAFT from an existing equilibrium SAFT code, various changes must be made to the code.

To begin, you would need to adjust the equations used in the SAFT model to account for the polymer volume (or polymer density) dependency on temperature and pressure. This would very certainly necessitate some adjustments to the mathematical form of the equations.

Second, you'd need to change the code's input such that temperature and volume-dependent variables may be provided as independent variables rather than temperature and pressure. This would very certainly necessitate changes to the input procedures and input storage.

Finally, the output routines would need to be modified to allow for the computation of thermodynamic parameters important to the NE-SAFT model, such as the equation of state, heat capacity, and internal energy.

It may be feasible to discover a faster workaround, but it is probable that making these changes to the current code would be easier and easier than trying to find a workaround. Changing the code directly ensures that the result is compatible with the NE-SAFT model.

It's also worth noting that these revisions will very certainly necessitate a solid grasp of the mathematical underpinnings of the SAFT model, as well as the alterations required to achieve the NE-SAFT model.

library("illuminaHumanv4.db")

probeID=c("ILMN_1690170", "ILMN_2410826", "ILMN_1675640", "ILMN_1801246", "ILMN_1658247", "ILMN_1740938", "ILMN_1657871", "ILMN_1769520", "ILMN_1778401") data.frame(Gene=unlist(mget(x = probeID,envir = illuminaHumanv4SYMBOL)))

I would suggest that you use the 2 category variable as the DV in a binary logistic regression. Use the remaining variables as predictor variables in your regression. This approach should yield the maximum amount of information in your data. I am attaching some course notes that cover the topic. There many more with examples that you can find with a Google search. Best wishes David Booth

See platEMO:

Mathematically, the answer to the equation is zero; the answer Python spat out is pretty much as close as you can get to the representation of zero with a typical computer.

This is a classic floating point problem: https://en.wikipedia.org/wiki/Floating-point_error_mitigation

You can set the min and max, for example:

setMinAndMax(2, 160);

The waitForUser(""); command will introduce a pause in the script until you click ok. You can also add a message as an argument e.g., waitForUser("manually adjust the brightness and contrast");

Thanks for your suggestion Mansurbek Urol ugli Abdullaev

Actually I started with the CATMAP program, but it was not giving me the results I expected, perhaps it has limitations. So, I decided to prepare my own script with python code.

Dear Mohd,

there is an easy solution: Use st_point_on_surface() instead of st_centroid. It guarantees that the point you create is in the polygon. For a more comprehensive overview take a look here: https://geocompr.robinlovelace.net/geometric-operations.html

Cheers

Philipp

Sajad Abasi Take a look https://www.youtube.com/watch?v=-0poQ0LA0CU

This is the response I got from their support team:

You can highlight text by creating quotations (https://urldefense.com/v3/__https://doc.atlasti.com/ManualMac.v22/Quotations/QuotationsTextCreating.html__;!!PAKc-5URQlI!9cNJGlVs-jOAmniAih5RkQDCckYHj8MVvqYI49uPEtip3NW8JtnsewbdPViiQnjuTsUUZSAfXYLeeJQI1UxIYuq3KA$) in ATLAS.ti 22. You can also edit text(https://doc.atlasti.com/ManualMac.v22/Documents/DocumentsManaging.html?highlight=edit%20text#editing-documents) documents in case you want to add colors, bold formatting, etc.

interested

Hi,

Kindly refer this link:

Best wishes..

I am not sure you have the right question or problem statement in your head. I tend to agree with Prem Baboo. I myself can tell you I am not much of a programmer. It is a tool to me not a career. Python is something being used a lot, but are you going into a programing career or a chemical engineer career? That would not be the same thing. When I think chemical engineering I do not think IT. I think problem solving, working in a team on projects, etc. As a sustainable chemical engineer what would you be doing? That's kind of vague. I think as a chemical engineer you need to be flexible with the changing demands. I myself have been in one company but I know other that have moved around from company to company and role to role. I think you need to figure out more what you want to do or would be happy doing. School will have failed to teach you everything you will need to know. There is no way your college classes could ever do so. You gain knowledge and needed skills over time based on what you are working on.

Generically speaking, be flexible and no one set of IT skills is going to set you up. Each problem, task... will may need a different approach. If I don't know how to do something I would ask someone that does or team with someone that knows a skill I don't have and instead of taking a few months to learning a new still I might be better off teaming with someone that has the skills. Its called teamwork and at a company both of you working together for the betterment of the company as a whole. Does your company put more value on individual accomplishment or team solutions? You don't need to know everything. But having a nice network of contacts and collogues that can help you will take your needs. They in return can utilize your skills and expertise with problems they have as well.

Miriam Corraliza-Gomez

All the best :-)

Update: re-running the calculation with identical parameters helped - it converged as usual, no error appeared this time. It seems that this is some kind of bug which only appears occasionally (at least I have only experienced it once in more than 10 calculations using IVDW = 2).

You can use my algorithm (SSO)

a <- replicate(1000, mean(replicate(1000, BigFunction())))

Code will be almost the same, only you need to change the function and variables as per VUMAT and there is no need for Jacobina calculation in VUMAT, after this change, I think it should work.

Dear Murana Awad ,

You sent ma a notification that you solved the problem.

May I propose a solution?

The solution is as follows:

Assume that you have N files

Then you want to pare them uniquely

Then you can use the following formulation:

The combinations = SUM X1i with i=2 to N + SUM X2i with i= 3 to N+ SUM X3i with i=4 toN + .................+ SUM (N-1)N + SUM Xi with i from 1 to N.

Please tell me whether this solution satisfies your requirement or not.

Best wishes

Found the answers on this link:

Could you read the data into a very simple program, possibly multiplying the numbers to see if you get the error because the file is corrupted a bit. You could also move the lines around before running the program to see where it has the problem. As Liang Chen suggests, it seems like a simple problem with the file.

God bless you all for recommending,reading and citing my research work,i assure you all that i would recommend,read and cite any work on my researchers on researchgate.

There is no one-fit-for-all formula. Visuals and texts are good for theory based subjects. But good old verbal discussions are better for subjects like language teaching and communication classes.

Mostafa Shabani you can share your coding using GitHub.com. You need to get an account there then upload your code publicly

pleasure Mohamed Sherif

Stay Happy Stay Healthy.

Hi Jason, I realize that you asked this question 4 years ago. Did you get an answer somewhere? I have the same problem/question and I also cannot figure it out. I agree that it does seem like a basic function that should exist (somewhere).

Dear Adib Amini

Have a look: https://www.cfd-online.com/Forums/fluent-udf/168994-can-i-change-flow-direction-using-udf.html

Kind Regards

Dear Jorge Rodríguez

Have a look:

1. https://www.cfd-online.com/Forums/fluent-udf/191229-udf-heterogeneous-reaction.html

2. https://www.researchgate.net/post/Heterogeneous_reactions_in_ansys_fluent

3. https://forum.ansys.com/index.php?p=/discussion/30125/heterogenous-reaction-rates-returned-by-fluent-and-cfd-post-are-different

4. https://research.monash.edu/en/publications/influence-of-biomass-blends-on-the-particle-temperature-and-burno

Kind Regards

I concur with Mahmoud

I concur with Arash

I had the same problem but if you close each file after opening

then it will read all files

Dear Slim，

I have an equation, as shown in the picture in the attachment. I want to know its eigenvalues. I did it with spectral methods in MATLAB, but I don't know if I'm right. Can you help me calculate this eigenvalue?

Thank you very much!

Dear K L A V Harnadh

These links might be an asset, have a look:

1. https://www.mathworks.com/matlabcentral/fileexchange/54555-linear-viscoelastic-design-optimization

2. https://www.mathworks.com/matlabcentral/fileexchange/68710-dma2prony_opt

Kind Regards

Adrien Wehrlé I will try using this and then let you know.

Actually NIST Test suite consists of a bundle tests. Hence, you need not write code for all these tests to find the Randomness of the image. The code for all these tests are given in NIST web site. You need to download the code and run using Eclipse or any other IDE. It will be simple and useful. Only thing you should know that the procedure to the run the different tests.

The first data analytic phase of GT begins with the coding of the data. This is undertaken to conceptualize the data by discovering categories into which they fit. The coding process has three phases: open coding, axial coding, and selective coding. In open coding, researchers describe the data by looking at it line-by-line. This strategy of focusing on small units of data, and their interpretation, encourages the development of a theoretical sensitivity to new ideas with regard to the data, and helps prevent the forcing of data into existing categories. Most researchers maintain that when a full array of categories have been identified, one should undertake axial coding – whereby one puts the data back together again in new ways by making connections between the numerous categories. Following that, a selective coding step is implemented in which the researcher looks to systematically identify those categories that relate closely to the core category. The core category lies at the heart of the emerging theory and is central to its integration. https://www.sciencedirect.com/topics/neuroscience/grounded-theory

usually more than one employee is reporting to a supervisor in a department.In that case you may use coding scheme according to number of suervisors and reporting employees.For example S1 for supervisor 1 and E1a, E1b,E1c ect for employees under S1 supervision

Hi

Anaconda 3 and python 3

In your UMAT subroutine, replace include 'aba_param.inc'

with

implicit real*4(a-h,o-z) (for single precision)

or

implicit real*8(a-h,o-z) (for double precision)

Be careful, the above statement indicates that all the variables starting with a-h or o-z will be treated as real variables.

That means, you "just" want to compute nodes' centrality and relate that to some other node-level characteristics? Density is a network-level concept, so I don't know what you want to do with that in this context.

Did you solve this problem?

I am facing same problem .

Hi Julia,

to produce the matrix of the edited img, you could use:

rownames(matrix)<-matrix[,1]

This takes the names of your V1 column and uses them as new row names. Afterwards you can delete the first column with the names

However, it might be a good idea to use a data.frame instead of a matrix.

see

hi Muhammad Abbas Khan That is my post on the Matlab forums, no one has answered it.

Hi Lucy Anderson,

I recently found an implementation of kprototypes in Python.

Besides, here is a useful example of kprototypes.

Hopefully the following publications could help:

^^ To: All 19 million scientists and researchers at R^G platform!

In my view, R is efficient for quick data analysis and visualization. It is also simple to expose results through an interactive web app with the package shiny.

However, I agree with Clément Poiret that Python is almost inevitable when you work in industry thanks to its versatility and the ability to respect processes of continuous integration. I've first learned coding with R at school, few years after I had to use Java and C++. This lead me to review and improve the way I coded with R. After that I've learned Python for OOP and statistical programming, this lead me to improve again my R skills. Now with few years of experience, I often switch between R and Python depending on the task. As I said firstly, I always use R and RStudio for data exploration (I found it powerful to deal with big datasets and parallel processing) and quick reports with Rmarkdown (HTML and TeX). I necessarily use Python when I need robustness for heavy project and OOP (e.g. to improve factorization and inheritance).

Finally, I would say that there ALWAYS be a rigorous way to code in R, but it is not mandatory and the language do authorize bad practice to obtain same results. It is not just about code performance, but also about the syntax of the functions or even simply about the code implementation. For statisticians working in teams who learned only R, I would recommend to use packages with documentation (e.g. roxygen2) and unit tests (e.g. testthat).

I am doing some research about RUMs, but I cannot find CRUSH code. Could you help me with my study by share this code with me? I am very grateful for you，my email is [email protected].

I was able to delete these codes later by dissociating them from groups and other links.

Hi Maryam

Are you sure you have SSH software installed?... If you execute just "SSH" did you get any answer from the system?

It looks you are accessing a Linux box from a Windoze computer. I would advice you to use a very popular software called MobaXterm, which will allow you to connect easily with Linux systems from Windoze, since it has an Xfree server and a SSH client included. Check it out at:

Best of luck. Let me know if it helps.

Paco

Have you tried without giving the option "ind.names" so that they are taken from the row names of your data frame?

You can read this book :

Yes, It can be implemented with python in keras. Although i have not implemented it personally, but I can suggest something which might be useful. You can write a class in python for the GATE that you want to program. You can use normal numpy operations to write the function. Algorithm would look something like this:

Input: prev_output, current_input;

Output: activated_output;

preactivated_output=prev_output+current_input

activated_output=sigmoid(preactivated_output)

You might have to do vector embedding so that the size of the vectors are consistent. You can try this approach and good luck.

Dear;

Please check the attached files

THESE Particle Swarm Optimization and Particle Filter Applied to Object Tracking.pdf

Regards

Let's do it.

@Vanessa T Vaillancourt

Other major qualitative analysis include MaxQDa and RQDA.

There is also WeftQDA which is a free software. You will find it on Google.