Machine learning in trading: theory, models, practice and algo-trading - page 885
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
In the program "Deductor Studio" visually everything is cool to see, the tree, the rules - I do not see this in R yet, and in MT5 there will be none (i.e. you can do everything, but how much you have to pay for it...). So, it turns out that I should use the algib library for including of random forests in MT5?
Here I found a piece of code of algorithmC4.5 http://datascientist.one/algorithm-c4-5/ in R, is it very difficult to implement in MT5?
I wrote above the easiest way to do it
You can even do it if you want. I don't know what these chunks are, I have no time to be distracted by small things)
Just have a few man-hours beforehand
2. R Dataset is an r file. It means that on the Data tab the initial data were loaded as RData File - this is the workspace in terms of R. In this workspace two data frames were prepared: one for training and testing the model, and the other as this very R Dataset.
The easiest way for you to do this is to load a ready-made Excel file, download the log, exit to R, and split the data frame you get there into two.
You can do it in another way.
Open R itself and there load the excel file - this is one line. Then we split the data frame into two.
But the second file of the trained model MUST be run.
Honestly - I don't understand. I divided 1 data file into 2 in excel, I trained the first file, now I need to test the model on the second file. To do this, this second file needs to be loaded somehow, I can't do it on the Data tab because the first file already has space there, on theEvaluate tabI can only load a CSV type file, which I can't load due to an error:
"
You have requested that a CSV file be used as your testing dataset, but you have not identified which file.
Please use the Spreadsheet button to select the CSV file you wish to use as your testset before you Execute.
Rattle 5.1.0
"
And I don't know what the fuck I should do with this error.
Or I'm initially dividing the wrong file, I should not cut the excel somehow, but cut the pure R file? What does "split frame" mean?
And, how am I supposed to save the results of model training on the first file and then check them on the second file?
I must be completely dumb...
Honestly - I don't understand. I have divided 1 file with data into 2 in excel, the first file has trained, now I need to test the model on the second file. For this purpose this second file should be somehow loaded, on the tab Data it is impossible to do it as there the place is already occupied by the first file, on the tabEvaluate I can load only file of type CSV which I cannot load because of the error:
...
And fuck knows what I should do with this error.
...
Or I'm initially splitting the wrong file, I should not cut Excel somehow, but cut purely R file? What does "split frame" mean?
And, how should I save the results of model training on the first file and then check them on the second file?
I must be really dumb...
I don't want to learn how to program in R, I need to be able to check predictors and convert rule set to MT5. Anyway, if it's one line, why not just write it to you? Well, for now I've coped with it by improvised means.
In short, you want the aborigines to do everything for you?
In short, are you suggesting that the natives do everything for you?
What do you mean "everything"?
I communicate with people friendly, willing to share knowledge on mastered programs, and on NS, I do not ask to give out any secrets or anything.
I myself share information about my predictors.
In general, what exactly do not suit you? Do I have a personal grudge?
Honestly - I don't understand. I have divided 1 file with data into 2 in Excel, the first file has trained, now I need to test the model on the second file. To do this, this second file should somehow load, on the tab Data it is impossible to do, as there is already a place occupied by the first file, on the tabEvaluate I can load only a file like CSV, which I can not load because of the error:
"
You have requested that a CSV file be used as your testing dataset, but you have not identified which file.
Please use the Spreadsheet button to select the CSV file you wish to use as your testset before you Execute.
Rattle 5.1.0
"
My English is not good, so I use a translator:
"
You requested that the CSV file be used as your test set, but you did not specify which file.
Please use the table button to select the CSV file you want to use as the test set before executing.
Rattle 5.1.0.
"
Well, yes I want the CSV file to be used as the test dataset, but what the fuck does it say that I haven't identified which file if it's selected, which you can see in the screenshot? And where is it the button "Table" (Spreadsheet)?
Honestly - I do not understand.
And, how should I save the results of model training on the first file, and then check them on the second file?
Read carefully! You have clearly written:
But running the trained model on the second file is MUST.
And you have made something up.
Not "model training results on the first file", but "trained model".
So you train a model on the first file and then you feed the data from the second file into the trained model.
Are you a programmer or not? Programmers usually understand every word and comma. Because forgotten or unnecessary .,;:(){}[] will take a lot of time when debugging programs. As a result, you have to be very attentive to details.
If you don't understand it at once, read the code two or three times.
What do you mean "Everything"?
I communicate with people friendly, willing to share knowledge on the programs I've mastered, and on NS, I'm not asking to give away any secrets.
I myself share information about my predictors.
In general, what exactly do not suit you? Do you have a personal dislike?
But to ask about every elementary sneeze, it is, excuse me, already indecent.
Read carefully! You were written very clearly:
And you made something up.
Not "the results of training models on the first file", but "trained model".
That is, you teach the model in the first file and then in the trained model you feed the data from the second file.
Are you a programmer or not? Programmers usually understand every word and comma. Because forgotten or unnecessary .,;:(){}[] will take a lot of time when debugging programs. As a result, you have to be very attentive to details.
If you didn't understand it at once, read the code 2 or 3 times.
Yes, that's how I understood it. Of course, the trained model to check on the new data. I write that I split the files, but when I try to load a new file, I get an error.
Here SanSanych writes:"The easiest way for you is to download a ready-made Excel file, download the log, go to R and split the data frame obtained there into two. "Let me download the log, go to R, but I don't know how to split the frame. And even if I split it, then what to do with the log, where to insert it?
Or"I opened R and loaded the excel file with it, it's one line. Then we divide the data frame into two."Again, I can't divide it in R, so I divided it in excel. What do I do next?
But asking about every elementary sneeze is, I'm sorry, already indecent.
Yes, I think it is better to ask than to sit dumb. And in general, I would understand your claim, if you actively responded to my questions, but no ....
Yes I think it's better to ask than to sit dumb. And in general, I would understand your complaint if you were actively answering my questions, but no ....
Can't you just flip through the book and use it as a reference book? Therefore I do not answer your questions.)