How to create a training data from excel sheet to matlab?

close all; clear all; clc;

%load data & display data1= xlsread('DSN OFFSET.xlsx','R0'); disp(data1);

%filter data(divide training sets and test sets) X = data1(2,:); Y = data1(3,:);

%train = training data

What do i do next?

Answer 1

[Shashika Munasingha]

There is a solution for this. I encountered similar problem and struggled for a while as there was no proper answer found in MatLab community. This is little bit lengthy and may not be the optimum solution, but hopefully this will solve some of your issues.

In my excel/csv, I have feature vector of length 7 and one output.

Here I used MatLab Deep Network Designer Toolbox (quite new toolbox) to generate the layer architecture and designed a nn setting input layer of dimension [7,1,1]. Design your network as you wish, but pay attention to the size of the inputs and outputs from each layer. They must be tallied with the data vectors in your excel/csv.

Import the NN model to MatLab workspace or you can create NN from scratch using code.

%% your layer architecture variable
net_layers

What I am going to highlight here is arranging our data such that it could be fed into our model.

%% importing data from csv file and separating them into target and input arrays %%
[~,~,data] = xlsread('temperature_feature_vector.csv');
data_mat  = cell2mat(data);
target_array = categorical(data_mat(:,8));
input_array  =  data_mat(:,1:7);

%% reshaping input data such that it matches our model 2D ---> 4D
%% there are  53 input vectors in this example
x = reshape(input_array',[7,1,1,53]);

Now you have shaped your data accordingly. You are ready to train your network !!!

%define options for your network. you can change accordingly
options = trainingOptions('sgdm', ...
    'ExecutionEnvironment','auto', ...
    'InitialLearnRate',0.000003, ...
    'LearnRateSchedule','piecewise', ...
    'MaxEpochs',10, ...
    'MiniBatchSize',1, ...
    'SequenceLength','longest', ...
    'Shuffle','never', ...
    'Verbose',0, ...
    'Plots','training-progress');

net = trainNetwork(x,target_array,net_layers,options);

With this method you can easily use deep nn models to train your data

Trick is in reshaping your data and defining of layer architecture accordingly.

[NICOLE MIN]

i got this error:

Caused by:

Error using

nnet.internal.cnn.MiniBatchDatastoreDispatcher

An error occurred while trying to determine whether

"readData" is a function name.

[Shashika Munasingha]

What is your MatLab version?

[NICOLE MIN]

I’m using 2018b and 2019a version on 2 different computer

[NICOLE MIN]

>> data_mat = cell2mat(data);

>> target_array = categorical(data_mat(:,8));

>> input_array = data_mat(:,1:24);

>> x = reshape(input_array',[24,1,1,2049]);

>> layers = [

imageInputLayer([22 1 1]) % 22X1X1 refers to number of features per sample

convolution2dLayer(3,16,'Padding','same')

reluLayer

fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer

fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer

fullyConnectedLayer(2) % 2 refers to number of neurons in next output layer (number of output classes)

softmaxLayer

classificationLayer];

>> options = trainingOptions('sgdm', ...

'ExecutionEnvironment','auto', ...

'InitialLearnRate',0.000003, ...

'LearnRateSchedule','piecewise', ...

'MaxEpochs',10, ...

'MiniBatchSize',1, ...

'SequenceLength','longest', ...

'Shuffle','never', ...

'Verbose',0, ...

'Plots','training-progress');

>> net = trainNetwork(x,target_array,layers,options);

this is a code ive followed and input and output created. is it wong somewhere? and i have this error.

Error using trainNetwork (line 150)

An error occurred while trying to determine whether "readData" is a

function name.

Caused by:

An error occurred while trying to determine whether "readData" is a

function name.

Can't reload

'/Applications/MATLAB_R2018b.app/bin/maci64/libmwsl_graphical_classes.dylib'

[NICOLE MIN]

my data variable

[NICOLE MIN]

if i just want a 1D cnn, how should i do it?

[Shashika Munasingha]

Hi Nicole,

This seems to be some file corruption error or installation error in MATLAB. I found this solution for the first issue you encountered.

https://www.mathworks.com/matlabcentral/answers/441088-an-error-occurred-while-trying-to-determine-whether-readdata-is-a-function-name

For 1-d cnn this answer looks like a go!

https://www.mathworks.com/matlabcentral/answers/354258-how-do-i-create-a-1d-cnn

[NICOLE MIN]

>> help readData

readData not found

>> doc readData

just to type thesesfew line able to solve my issue, am i right to say that

[NICOLE MIN]

i got this issue, is matlab version incompatible?

[NICOLE MIN]

firstly, ive copy the whole chuck of coding from the dic under read entire dataset, issue arises. secondly, ive tried replacing 'TEMPERATURE' TO 'X' same issue occur too. im not sure what is going on . i appreviacte very much if this issue can find a solution. thanks