I am a MATLAB guy. I love MATLAB. I started with Fortan during my first degree at my Bachelor level. I came across with MATLAB only in year 2010 as a part of my Msc studies. Since then I been using it continuously for various tasks. Just recently, I started using Python and I LOVE IT. The biggest reason being that Python is open-source and there are lots of Python libraries that can be used. But there are times; I have to shuffle data between MATLAB and python, because for some tasks I prefer MATLAB as I am accustom to it. So if you are in the same boat, then here I show you simple way to transfer data between MATLAB and Python. One has to use scipy.io module in Scipy for that purpose. If you have some old data or got some data online that are saved as MATLAB’s .mat file format, you can simply import it as:
import numpy as np
import scipy.io as sio
mydata = sio.loadmat('mydata.mat')
Now your mydata contains a dictinary with keys corresponding to the varible names saved in the original mydata.mat Saving a python variable to .mat file is also straight forward
# write one variable
x = np.arange(1,10,1)
# file name of the file
fname ='export_from_python.mat'
sio.savemat(fname, {'x':x})
When you read export_from_python.mat, you will get 'x' varialbe into MATLAB. If you want to write more than two variable:
# write two variables
x = np.arange(1,10,1)
y = np.ones((5,5))
fname ='export_from_python_1.mat'
sio.savemat(fname, {'x':x, 'y':y})
I do lot of work with classification of remote sensing images using many different types of machine learning algorithms. Proprietary software like ENVI and ERDAS are not flexible enough for me, as these software donot allow an efficient way to tune hyper-parameters that are algorithm specific. I dont like training models with defualt parameters. I do my model traning and classification in python. Here is the typical workflow.
import numpy as np
import scipy.io as sio
mydata = sio.loadmat('mydata.mat')
Now your mydata contains a dictinary with keys corresponding to the varible names saved in the original mydata.mat Saving a python variable to .mat file is also straight forward
# write one variable
x = np.arange(1,10,1)
# file name of the file
fname ='export_from_python.mat'
sio.savemat(fname, {'x':x})
When you read export_from_python.mat, you will get 'x' varialbe into MATLAB. If you want to write more than two variable:
# write two variables
x = np.arange(1,10,1)
y = np.ones((5,5))
fname ='export_from_python_1.mat'
sio.savemat(fname, {'x':x, 'y':y})
I do lot of work with classification of remote sensing images using many different types of machine learning algorithms. Proprietary software like ENVI and ERDAS are not flexible enough for me, as these software donot allow an efficient way to tune hyper-parameters that are algorithm specific. I dont like training models with defualt parameters. I do my model traning and classification in python. Here is the typical workflow.
- Import image and training data in python using GDAL
- Train machine learning model in python using Sci-kit Learn
- For accuracy assessment, i do it within python but for accuracy assessment visualization, i export targets and outputs vectors from Python to MATLAB
- Use 'plotconfusion' function from Neural Network toolbox for a visualization of confusion matrix. Here is the confusion Matrix information that i got from MATLAB. Its nice, isnt it ?
 |
| Confusion matrix |
