writing function for logistic regression

Question

[saadleeshehreen]

Hi, My .csv files contain 2021 rows with 25 columns. All of the columns have "0" or "1" on the basis of absence and presence. I want to see the correlation among column CAS_COUNT(24), ACR_COUNT(25) and Antibiotic(8-23). Logistic regression analysis might be the best way to describe the association. I am very new to R programming and almost zero coding background. Any help to write a code for this purpose?

[1] "ASSEMBLY"               "ORGANISM"               "ANTI_I_E"               "ANTI_I_F"              
[5] "ACA1"                   "I.E"                    "I.F"                    "Aminoglycoside"        
[9] "Beta_lactam"            "colistin"               "fosfomycin"             "fusidicacid"           
[13] "glycopeptid"            "macrolide"              "nitroimidazole"         "oxazolidinone"         
[17] "oxazolidinone_phenicol" "phenicol"               "quinolone"              "rifampicin"            
[21] "sulphonamide"           "tetracycline"           "trimethoprim"           "CAS_COUNT"             
[25] "ACR_COUNT"

Example of the first line:

   GCA_000148745.1 Pseudomonas aeruginosa 39016 chromosome whole genome shotgun 0 0 0 0 0 0 0 0 0 0......

[WouterDeCoster]

I am very new to R programming and almost zero coding background. Any help to write a code for this purpose?

Maybe this project isn't the most optimal to be your first R coding project. You could do yourself a favour and spend a few hours/days following R tutorials - your understanding will increase a lot and it will definitely pay off in the long run.

[Jean-Karim Heriche]

I want to see the correlation...

Then compute correlation coefficients.
What is the question you're trying to answer ?
If you take a regression approach, what is the dependent variable ?

Answer 1

[Michael]

There is a tutorial here, https://www.r-bloggers.com/how-to-perform-a-logistic-regression-in-r/ Working through the example "Titanic" dataset might give you an impression on whether your assumption on the method is ok. There are many questions that could be asked about the variables in your data. Unfortunately, I do not understand your data and approach well-enough to tell whether they are sane.