I have N samples of training data and M samples of test data, how i combine it together to make it MxN samples.

testdata 40X1 cell

traindat 80X1 cell

train_label 80X1 double

I have N samples of training data and M samples of test data, how i combine it together to make it MxN samples. The rows, here, represent each sample and the columns the different types of features detected from a sample. also i want to add an extra column at LAST of the data (preferably): This column should represent the desired labels for the data.

[Ameer Hamza]

Can you give a simple example of what you are trying to do? For example, give us 3 training samples and 3 test samples and show us how do you want them converted to 3x3=9 samples.

Also describe what data is stored in these cell arrays.

[Balaji M. Sontakke]

I want to give input to classificationLearner in matlab, I refer fishertable = readtable('fisheriris.csv'); where size of fishertable is M X N i.e. 150 X 5, Petal and sepal length and width are predictors, and species is the response.

Just i want to do classification using classificationLearner, my samples are in cell arrays testdata having the size 40 X 3 and traindata having the size 80 X 3 also trainlabel and testlabel are seperately created.

can i create predictors and species like fisheriris.csv with my data(here am attaching mat files of those test and train data).

Answer 1

[Ameer Hamza]

Following code shows how to convert the cell array from your code to the table as generated by fishertable = readtable('fisheriris.csv')

load('db3.mat');

testdata = cell2mat(reduced_testdata')';

testdata_table = array2table(testdata, ...
    'VariableNames', ...
    {'SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth'});

sample_labels = repmat("abcd", 40, 1); % creating random data to fill last column
                                       % you should use your testlabels
testdata_table = addvars(testdata_table, sample_labels, ...
    'NewVariableNames', 'Species');

[Balaji M. Sontakke]

Undefined function or variable 'addvars'.

Error in demo (line 8)

testdata_table = addvars(testdata_table, sample_labels,'NewVariableNames', 'Species');

The above code shows only testdata, what about traindata?

[Ameer Hamza]

Which release of MATLAB are you using? addvars was added to MATLAB R2018b. You can repeat the same with traindata to create a second table. Or do you want to join both tables?

[Balaji M. Sontakke]

MATLAB R2016b

yes i want to join both tables but how?

[Ameer Hamza]

This should work in MATLAB R2016b. The code join two tables (testdata table entries above and traindata entries below). data_tables has dimension of 120x5.

load('db3.mat');
testdata = cell2mat(reduced_testdata')';
testdata_table = array2table(testdata, ...
    'VariableNames', ...
    {'SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth'});
sample_labels = repmat("abcd", 40, 1); % creating random data to fill last column
                                       % you should use your testlabels
testdata_table.Species = sample_labels;

load('db4.mat');
traindata = cell2mat(reduced_traindata')';
traindata_table = array2table(traindata, ...
    'VariableNames', ...
    {'SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth'});
sample_labels = repmat("abcd", 80, 1); % creating random data to fill last column
                                       % you should use your testlabels
traindata_table.Species = sample_labels;

data_tables = [testdata_table; traindata_table];

[Balaji M. Sontakke]

Thank you sir..