Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Multi bw changes #57

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
mehak-sachdeva wants to merge 10 commits into from
Closed

Multi bw changes #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4ad7706
adding a univariate example for Poisson MGWR
mehak-sachdeva Jun 18, 2019
09ef414
adding important equations for reference
mehak-sachdeva Jun 18, 2019
3ed2f41
minor error update
mehak-sachdeva Jun 18, 2019
edf4bcf
cleaning
mehak-sachdeva Jun 18, 2019
f3c957b
adding the notebook for Binomial MGWR model
mehak-sachdeva Jun 18, 2019
e44555b
changes to accomodate Poisson and Binomial MGWR
mehak-sachdeva Jun 19, 2019
2c2edc3
changes to accomodate Poisson and Binomial MGWR
mehak-sachdeva Jun 19, 2019
48b9766
Merge remote-tracking branch 'upstream/master' into multi_bw_changes
mehak-sachdeva Jun 22, 2019
ac981d7
fixed merge conflicts
mehak-sachdeva Jun 22, 2019
279f518
fixing MGWR init error
mehak-sachdeva Jun 24, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 26 additions & 18 deletions mgwr/gwr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ class GWR(GLM):
spherical : boolean
True for shperical coordinates (long-lat),
False for projected coordinates (defalut).

hat_matrix : boolean
True to store full n by n hat matrix,
False to not store full hat matrix to minimize memory footprint (defalut).
Expand Down Expand Up @@ -516,10 +516,10 @@ class GWRResults(GLMResults):

R2 : float
R-squared for the entire model (1- RSS/TSS)

adj_R2 : float
adjusted R-squared for the entire model

aic : float
Akaike information criterion

Expand Down Expand Up @@ -575,11 +575,11 @@ class GWRResults(GLMResults):
pDev : float
local percent of deviation accounted for; analogous to
r-squared for GLM's

D2 : float
percent deviance explained for GLM, equivaleng to R2 for
Gaussian.

adj_D2 : float
adjusted percent deviance explained, equivaleng to adjusted
R2 for Gaussian.
Expand Down Expand Up @@ -1438,8 +1438,8 @@ class MGWR(GWR):

"""

def __init__(self, coords, y, X, selector, sigma2_v1=True,
kernel='bisquare', fixed=False, constant=True,
def __init__(self, coords, y, X, selector, family, offset=None,
sigma2_v1=True, kernel='bisquare', fixed=False, constant=True,
spherical=False, hat_matrix=False):
"""
Initialize class
Expand All @@ -1448,17 +1448,18 @@ def __init__(self, coords, y, X, selector, sigma2_v1=True,
self.bws = self.selector.bw[0] #final set of bandwidth
self.bws_history = selector.bw[1] #bws history in backfitting
self.bw_init = self.selector.bw_init #initialization bandiwdth
self.family = Gaussian(
) # manually set since we only support Gassian MGWR for now
GWR.__init__(self, coords, y, X, self.bw_init, family=self.family,
sigma2_v1=sigma2_v1, kernel=kernel, fixed=fixed,
constant=constant, spherical=spherical,
self.family = family
self.offset = offset
# manually set since we only support Gassian MGWR for now
GWR.__init__(self, coords, y, X, self.bw_init, self.family,
self.offset,sigma2_v1=sigma2_v1, kernel=kernel,
fixed=fixed, constant=constant, spherical=spherical,
hat_matrix=hat_matrix)
self.selector = selector
self.sigma2_v1 = sigma2_v1
self.points = None
self.P = None
self.offset = None
self.family = family
self.exog_resid = None
self.exog_scale = None
self_fit_params = None
Expand Down Expand Up @@ -1520,21 +1521,28 @@ def _chunk_compute_R(self, chunk_id=0):
def fit(self, n_chunks=1, pool=None):
"""
Compute MGWR inference by chunk to reduce memory footprint.

Parameters
----------

n_chunks : integer, optional
A number of chunks parameter to reduce memory usage.
A number of chunks parameter to reduce memory usage.
e.g. n_chunks=2 should reduce overall memory usage by 2.
pool : A multiprocessing Pool object to enable parallel fitting; default is None.

Returns
-------
: MGWRResults
"""
params = self.selector.params
predy = np.sum(self.X * params, axis=1).reshape(-1, 1)
if isinstance(self.family,Poisson):
predy = self.offset*(np.exp(np.sum(self.X * params, axis=1).reshape(-1, 1)))

elif isinstance(self.family,Binomial):
predy = 1/(1+np.exp(-1*np.sum(self.X * params, axis=1).reshape(-1, 1)))

else:
predy = np.sum(self.X * params, axis=1).reshape(-1, 1)

try:
from tqdm.autonotebook import tqdm #progress bar
Expand Down Expand Up @@ -1692,7 +1700,7 @@ class MGWRResults(GWRResults):

R2 : float
R-squared for the entire model (1- RSS/TSS)

adj_R2 : float
adjusted R-squared for the entire model

Expand Down
45 changes: 39 additions & 6 deletions mgwr/search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@

import numpy as np
from copy import deepcopy
from spglm.family import Gaussian, Binomial, Poisson


def golden_section(a, c, delta, function, tol, max_iter, int_score=False,
Expand Down Expand Up @@ -164,7 +165,7 @@ def equal_interval(l_bound, u_bound, interval, function, int_score=False,
return opt_val, opt_score, output


def multi_bw(init, y, X, n, k, family, tol, max_iter, rss_score, gwr_func,
def multi_bw(init, y, X, n, k, family, offset, tol, max_iter, rss_score, gwr_func,
bw_func, sel_func, multi_bw_min, multi_bw_max, bws_same_times,
verbose=False):
"""
Expand All @@ -180,7 +181,14 @@ def multi_bw(init, y, X, n, k, family, tol, max_iter, rss_score, gwr_func,
err = optim_model.resid_response.reshape((-1, 1))
param = optim_model.params

XB = np.multiply(param, X)
if isinstance(family, Poisson):
XB = offset*np.exp(np.multiply(param,X))
elif isinstance(family, Binomial):
XXB = 1/(1+np.exp(-1*np.multiply(param,X)))
XB = np.multiply(param, X)
else:
XB = np.multiply(param, X)

if rss_score:
rss = np.sum((err)**2)
iters = 0
Expand All @@ -199,12 +207,23 @@ def tqdm(x, desc=''): #otherwise, just passthrough the range

for iters in tqdm(range(1, max_iter + 1), desc='Backfitting'):
new_XB = np.zeros_like(X)
neww_XB = np.zeros_like(X)

params = np.zeros_like(X)

for j in range(k):
temp_y = XB[:, j].reshape((-1, 1))
temp_y = temp_y + err

if isinstance(family, Binomial):
for i in range(n):
if temp_y[i]>=0:
temp_y[i]=1
else:
temp_y[i]=0

temp_X = X[:, j].reshape((-1, 1))

bw_class = bw_func(temp_y, temp_X)

if np.all(bw_stable_counter == bws_same_times):
Expand All @@ -220,17 +239,31 @@ def tqdm(x, desc=''): #otherwise, just passthrough the range
optim_model = gwr_func(temp_y, temp_X, bw)
err = optim_model.resid_response.reshape((-1, 1))
param = optim_model.params.reshape((-1, ))
new_XB[:, j] = optim_model.predy.reshape(-1)
if isinstance(family, Binomial):
new_XB[:, j] = np.multiply(param.reshape(-1,1),temp_X).reshape(-1)
neww_XB[:, j] = optim_model.predy.reshape(-1)
else:
new_XB[:, j] = optim_model.predy.reshape(-1)
params[:, j] = param
bws[j] = bw

num = np.sum((new_XB - XB)**2) / n
den = np.sum(np.sum(new_XB, axis=1)**2)
if isinstance(family, Binomial):
num = np.sum((neww_XB - XXB)**2) / n
den = np.sum(np.sum(neww_XB, axis=1)**2)
else:
num = np.sum((new_XB - XB)**2) / n
den = np.sum(np.sum(new_XB, axis=1)**2)
score = (num / den)**0.5
XB = new_XB
XXB = neww_XB

if rss_score:
predy = np.sum(np.multiply(params, X), axis=1).reshape((-1, 1))
if isinstance(family, Poisson):
predy = offset*(np.exp(np.sum(X * params, axis=1).reshape(-1, 1)))
elif isinstance(family, Binomial):
predy = 1/(1+np.exp(-1*np.sum(X * params, axis=1).reshape(-1, 1)))
else:
predy = np.sum(np.multiply(params, X), axis=1).reshape((-1, 1))
new_rss = np.sum((y - predy)**2)
score = np.abs((new_rss - rss) / new_rss)
rss = new_rss
Expand Down
8 changes: 4 additions & 4 deletions mgwr/sel_bw.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@ class Sel_BW(object):
>>> pov = np.array(data.by_col('PctPov')).reshape((-1,1))
>>> african_amer = np.array(data.by_col('PctBlack')).reshape((-1,1))
>>> X = np.hstack([rural, pov, african_amer])

Golden section search AICc - adaptive bisquare

>>> bw = Sel_BW(coords, y, X).search(criterion='AICc')
Expand Down Expand Up @@ -213,7 +213,7 @@ def search(self, search_method='golden_section', criterion='AICc',
min value used in bandwidth search
bw_max : float
max value used in bandwidth search
multi_bw_min : list
multi_bw_min : list
min values used for each covariate in mgwr bandwidth search.
Must be either a single value or have one value for
each covariate including the intercept
Expand Down Expand Up @@ -391,9 +391,9 @@ def sel_func(bw_func, bw_min=None, bw_max=None):
bw_min=bw_min, bw_max=bw_max, interval=interval, tol=tol,
max_iter=max_iter, pool=self.pool, verbose=False)

self.bw = multi_bw(self.init_multi, y, X, n, k, family, self.tol_multi,
self.bw = multi_bw(self.init_multi, y, X, n, k, family, offset, self.tol_multi,
self.max_iter_multi, self.rss_score, gwr_func,
bw_func, sel_func, multi_bw_min, multi_bw_max,
bw_func,sel_func, multi_bw_min, multi_bw_max,
bws_same_times, verbose=self.verbose)

def _init_section(self, X_glob, X_loc, coords, constant):
Expand Down
Loading