I can load the .mat file, but as columns have no names, I don't know how to reference them.
The .mat file consists of four columns, with a lot of rows.
import numpy as np
import pandas as pd
from scipy.io import loadmat
from sklearn.preprocessing import PolynomialFeatures
data = loadmat('data.mat')
data.keys()
This results in: data['no names for columns in mat file']
What is wrong with this code?
When I load a test mat I get a display like
In [50]: data=loadmat('test7.mat')
In [51]: print(data)
{'__globals__': [], 'x': array([[ 1., 2., 3.],
[ 4., 5., 6.]]), '__version__': '1.0', '__header__': b'MATLAB 5.0 MAT-file, written by Octave 4.0.0, 2016-09-01 15:43:02 UTC'}
That tells me the mat contains a variable called x, which I can access with:
In [52]: data['x']
Out[52]:
array([[ 1., 2., 3.],
[ 4., 5., 6.]])
We need similar kind of information for file in order to help.
In [53]: list(data.keys()) # list need in Py3
Out[53]: ['__globals__', 'x', '__version__', '__header__']
I'm not quite sure what you mean by columns and names in MATLAB context. Is the item(s) in the file expected to be MATLAB matrices, cells and/or structs?
Column names is a pandas concept, not numpy or MATLAB (that I know of).