I want to multiply two Kernel Density Estimates to get a composite likelihood ... The multiplication operator doesn't exist for sklearn.
I have KDR for data from 3 independent sources and I want multiply KDE from each sources. The below code is from https://scikit-learn.org/stable/auto_examples/neighbors/plot_species_kde.html#sphx-glr-auto-examples-neighbors-plot-species-kde-py and should run easily.
Although I made some small modification to get get two KDEs and then multiply them which fails.
Someone can help. Below code should run without error except the multiplication part.
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_species_distributions
from sklearn.neighbors import KernelDensity
# if basemap is available, we'll use it.
# otherwise, we'll improvise later...
try:
from mpl_toolkits.basemap import Basemap
basemap = True
except ImportError:
basemap = False
def construct_grids(batch):
"""Construct the map grid from the batch object
Parameters
----------
batch : Batch object
The object returned by :func:`fetch_species_distributions`
Returns
-------
(xgrid, ygrid) : 1-D arrays
The grid corresponding to the values in batch.coverages
"""
# x,y coordinates for corner cells
xmin = batch.x_left_lower_corner + batch.grid_size
xmax = xmin + (batch.Nx * batch.grid_size)
ymin = batch.y_left_lower_corner + batch.grid_size
ymax = ymin + (batch.Ny * batch.grid_size)
# x coordinates of the grid cells
xgrid = np.arange(xmin, xmax, batch.grid_size)
# y coordinates of the grid cells
ygrid = np.arange(ymin, ymax, batch.grid_size)
return (xgrid, ygrid)
# Get matrices/arrays of species IDs and locations
data = fetch_species_distributions()
species_names = ['Bradypus Variegatus', 'Microryzomys Minutus']
Xtrain = np.vstack([data['train']['dd lat'], data['train']['dd long']]).T
ytrain = np.array([d.decode('ascii').startswith('micro')
for d in data['train']['species']], dtype='int')
Xtrain *= np.pi / 180. # Convert lat/long to radians
# Set up the data grid for the contour plot
xgrid, ygrid = construct_grids(data)
X, Y = np.meshgrid(xgrid[::5], ygrid[::5][::-1])
land_reference = data.coverages[6][::5, ::5]
land_mask = (land_reference > -9999).ravel()
xy = np.vstack([Y.ravel(), X.ravel()]).T
xy = xy[land_mask]
xy *= np.pi / 180.
# Plot map of South America with distributions of each species
fig = plt.figure()
fig.subplots_adjust(left=0.05, right=0.95, wspace=0.05)
kde0 = KernelDensity(bandwidth=0.04, metric='haversine',
kernel='gaussian', algorithm='ball_tree')
kde0.fit(Xtrain[ytrain == 0])
kde1 = KernelDensity(bandwidth=0.04, metric='haversine',
kernel='gaussian', algorithm='ball_tree')
kde1.fit(Xtrain[ytrain == 1])
kde01=kde0*kde1
plt.subplot(1, 1, 1)
# evaluate only on the land: -9999 indicates ocean
Z = np.full(land_mask.shape[0], -9999, dtype='int')
Z[land_mask] = np.exp(kde01.score_samples(xy))
Z = Z.reshape(X.shape)
# plot contours of the density
levels = np.linspace(0, Z.max(), 25)
plt.contourf(X, Y, Z, levels=levels, cmap=plt.cm.Reds)
plt.show()