I have a DataFrame of satellite data points. The points are arranged in an evenly spaced grid that is slightly rotated from North South. I want to transform this data into a matrix that I can feed into a Convolutional Neural Network. I want to eliminate the Lat Lon data but preserve the grid structure. How can I do this?
Gamma0_VV lat lon dist cell
0 0.172325 39.378442 -74.398499 0.003194 0.0
1 0.101932 39.378459 -74.398385 0.012222 0.0
2 0.116957 39.378549 -74.398407 0.017423 0.0
3 0.139411 39.378638 -74.398429 0.025786 0.0
4 0.134255 39.378728 -74.398451 0.035122 0.0
I want something of the form:
Gamma0_VV (zeros for simplicity)
[[0, 0, 0, ... 0, 0],
[0, 0, 0, ... 0, 0],
[0, 0, 0, ... 0, 0]]
