Skip to content
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

Adding summary output #18

Merged
merged 7 commits into from
Jul 3, 2018
Merged

Adding summary output #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
e73a2ac
fork
Ziqi-Li Jun 21, 2018
a9dd093
gwr sum done
Ziqi-Li Jun 21, 2018
9439373
summary for mgwr
Ziqi-Li Jun 21, 2018
22e7d8b
summary
Ziqi-Li Jun 21, 2018
9ec1612
rm pyc
Ziqi-Li Jun 21, 2018
6b2f1b4
aicc for global
Ziqi-Li Jun 22, 2018
3eac546
add adj t and alpha for mgwr
Ziqi-Li Jun 25, 2018
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
27 changes: 23 additions & 4 deletions mgwr/gwr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
from spglm.utils import cache_readonly
from .diagnostics import get_AIC, get_AICc, get_BIC, corr
from .kernels import *
from .summary import *

fk = {'gaussian': fix_gauss, 'bisquare': fix_bisquare, 'exponential': fix_exp}
ak = {'gaussian': adapt_gauss, 'bisquare': adapt_bisquare, 'exponential': adapt_exp}
Expand Down Expand Up @@ -1153,6 +1154,16 @@ def predictions(self):
predictions = np.sum(P*self.params, axis=1).reshape((-1,1))
return predictions

def summary(self):
"""
Print out GWR summary
"""
summary = summaryModel(self) + summaryGLM(self) + summaryGWR(self)
print(summary)
return



class GWRResultsLite(object):
"""
Lightweight GWR that computes the minimum diagnostics needed for bandwidth
Expand Down Expand Up @@ -1780,15 +1791,15 @@ def spatial_variability(self, selector, n_iters=1000, seed=None):
the number of Monte Carlo iterations to include for
the tests of spatial variability.

seed : int
seed : int
optional parameter to select a custom seed to ensure
stochastic results are replicable. Default is none
which automatically sets the seed to 5536

Returns
-------
Returns
-------

p values : list
p values : list
a list of psuedo p-values that correspond to the model
parameter surfaces. Allows us to assess the
probability of obtaining the observed spatial
Expand Down Expand Up @@ -1824,3 +1835,11 @@ def spatial_variability(self, selector, n_iters=1000, seed=None):

p_vals = (np.sum(np.array(SDs) > init_sd, axis=0) / float(n_iters))
return p_vals

def summary(self):
"""
Print out MGWR summary
"""
summary = summaryModel(self) + summaryGLM(self) + summaryMGWR(self)
print(summary)
return
150 changes: 150 additions & 0 deletions mgwr/summary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,150 @@
import numpy as np
from spglm.family import Gaussian, Binomial, Poisson
from spglm.glm import GLM
from .diagnostics import get_AICc

def summaryModel(self):
summary = '=' * 75 + '\n'
summary += "%-54s %20s\n" % ('Model type', self.family.__class__.__name__)
summary += "%-60s %14d\n" % ('Number of observations:', self.n)
summary += "%-60s %14d\n\n" % ('Number of covariates:', self.k)
return summary

def summaryGLM(self):

XNames = ["X"+str(i) for i in range(self.k)]
glm_rslt = GLM(self.model.y,self.model.X,constant=False,family=self.family).fit()

summary = "%s\n" %('Global Regression Results')
summary += '-' * 75 + '\n'

if isinstance(self.family, Gaussian):
summary += "%-62s %12.3f\n" % ('Residual sum of squares:', glm_rslt.deviance)
summary += "%-62s %12.3f\n" % ('Log-likelihood:', glm_rslt.llf)
summary += "%-62s %12.3f\n" % ('AIC:', glm_rslt.aic)
summary += "%-62s %12.3f\n" % ('AICc:', get_AICc(glm_rslt))
summary += "%-62s %12.3f\n" % ('BIC:', glm_rslt.bic)
summary += "%-62s %12.3f\n" % ('R2:', glm_rslt.D2)
summary += "%-62s %12.3f\n\n" % ('Adj. R2:', glm_rslt.adj_D2)
else:
summary += "%-62s %12.3f\n" % ('Deviance:', glm_rslt.deviance)
summary += "%-62s %12.3f\n" % ('Log-likelihood:', glm_rslt.llf)
summary += "%-62s %12.3f\n" % ('AIC:', glm_rslt.aic)
summary += "%-62s %12.3f\n" % ('AICc:', get_AICc(glm_rslt))
summary += "%-62s %12.3f\n" % ('BIC:', glm_rslt.bic)
summary += "%-62s %12.3f\n" % ('Percent deviance explained:', glm_rslt.D2)
summary += "%-62s %12.3f\n\n" % ('Adj. percent deviance explained:', glm_rslt.adj_D2)

summary += "%-31s %10s %10s %10s %10s\n" % ('Variable', 'Est.', 'SE' ,'t(Est/SE)', 'p-value')
summary += "%-31s %10s %10s %10s %10s\n" % ('-'*31, '-'*10 ,'-'*10, '-'*10,'-'*10)
for i in range(self.k):
summary += "%-31s %10.3f %10.3f %10.3f %10.3f\n" % (XNames[i], glm_rslt.params[i], glm_rslt.bse[i], glm_rslt.tvalues[i], glm_rslt.pvalues[i])
summary += "\n"
return summary

def summaryGWR(self):
XNames = ["X"+str(i) for i in range(self.k)]

summary = "%s\n" %('Geographically Weighted Regression (GWR) Results')
summary += '-' * 75 + '\n'

if self.model.fixed:
summary += "%-50s %20s\n" % ('Spatial kernel:', 'Fixed ' + self.model.kernel)
else:
summary += "%-54s %20s\n" % ('Spatial kernel:', 'Adaptive ' + self.model.kernel)

summary += "%-62s %12.3f\n" % ('Bandwidth used:', self.model.bw)

summary += "\n%s\n" % ('Diagnostic information')
summary += '-' * 75 + '\n'

if isinstance(self.family, Gaussian):

summary += "%-62s %12.3f\n" % ('Residual sum of squares:', self.resid_ss)
summary += "%-62s %12.3f\n" % ('Effective number of parameters (trace(S)):', self.tr_S)
summary += "%-62s %12.3f\n" % ('Degree of freedom (n - trace(S)):', self.df_model)
summary += "%-62s %12.3f\n" % ('Sigma estimate:', np.sqrt(self.sigma2))
summary += "%-62s %12.3f\n" % ('Log-likelihood:', self.llf)
summary += "%-62s %12.3f\n" % ('AIC:', self.aic)
summary += "%-62s %12.3f\n" % ('AICc:', self.aicc)
summary += "%-62s %12.3f\n" % ('BIC:', self.bic)
summary += "%-62s %12.3f\n" % ('R2:', self.R2)
else:
summary += "%-62s %12.3f\n" % ('Effective number of parameters (trace(S)):', self.tr_S)
summary += "%-62s %12.3f\n" % ('Degree of freedom (n - trace(S)):', self.df_model)
summary += "%-62s %12.3f\n" % ('Log-likelihood:', self.llf)
summary += "%-62s %12.3f\n" % ('AIC:', self.aic)
summary += "%-62s %12.3f\n" % ('AICc:', self.aicc)
summary += "%-62s %12.3f\n" % ('BIC:', self.bic)
#summary += "%-60s %12.6f\n" % ('Percent deviance explained:', 0)


summary += "%-62s %12.3f\n" % ('Adj. alpha (95%):', self.adj_alpha[1])
summary += "%-62s %12.3f\n" % ('Adj. critical t value (95%):', self.critical_tval(self.adj_alpha[1]))

summary += "\n%s\n" % ('Summary Statistics For GWR Parameter Estimates')
summary += '-' * 75 + '\n'
summary += "%-20s %10s %10s %10s %10s %10s\n" % ('Variable', 'Mean' ,'STD', 'Min' ,'Median', 'Max')
summary += "%-20s %10s %10s %10s %10s %10s\n" % ('-'*20, '-'*10 ,'-'*10, '-'*10 ,'-'*10, '-'*10)
for i in range(self.k):
summary += "%-20s %10.3f %10.3f %10.3f %10.3f %10.3f\n" % (XNames[i], np.mean(self.params[:,i]) ,np.std(self.params[:,i]),np.min(self.params[:,i]) ,np.median(self.params[:,i]), np.max(self.params[:,i]))

summary += '=' * 75 + '\n'

return summary



def summaryMGWR(self):

XNames = ["X"+str(i) for i in range(self.k)]

summary = ''
summary += "%s\n" %('Multi-Scale Geographically Weighted Regression (MGWR) Results')
summary += '-' * 75 + '\n'

if self.model.fixed:
summary += "%-50s %20s\n" % ('Spatial kernel:', 'Fixed ' + self.model.kernel)
else:
summary += "%-54s %20s\n" % ('Spatial kernel:', 'Adaptive ' + self.model.kernel)

summary += "%-54s %20s\n" % ('Criterion for optimal bandwidth:', self.model.selector.criterion)

if self.model.selector.rss_score:
summary += "%-54s %20s\n" % ('Score of Change (SOC) type:', 'RSS')
else:
summary += "%-54s %20s\n" % ('Score of Change (SOC) type:', 'Smoothing f')

summary += "%-54s %20s\n\n" % ('Termination criterion for MGWR:', self.model.selector.tol_multi)

summary += "%s\n" %('MGWR bandwidths')
summary += '-' * 75 + '\n'
summary += "%-15s %14s %10s %16s %16s\n" % ('Variable', 'Bandwidth', 'ENP_j','Adj t-val(95%)','Adj alpha(95%)')
for j in range(self.k):
summary += "%-14s %15.3f %10.3f %16.3f %16.3f\n" % (XNames[j], self.model.bw[j], self.ENP_j[j],self.critical_tval()[j],self.adj_alpha_j[j,1])

summary += "\n%s\n" % ('Diagnostic information')
summary += '-' * 75 + '\n'

summary += "%-62s %12.3f\n" % ('Residual sum of squares:', self.resid_ss)
summary += "%-62s %12.3f\n" % ('Effective number of parameters (trace(S)):', self.tr_S)
summary += "%-62s %12.3f\n" % ('Degree of freedom (n - trace(S)):', self.df_model)

summary += "%-62s %12.3f\n" % ('Sigma estimate:', np.sqrt(self.sigma2))
summary += "%-62s %12.3f\n" % ('Log-likelihood:', self.llf)
summary += "%-62s %12.3f\n" % ('AIC:', self.aic)
summary += "%-62s %12.3f\n" % ('AICc:', self.aicc)
summary += "%-62s %12.3f\n" % ('BIC:', self.bic)

summary += "\n%s\n" % ('Summary Statistics For MGWR Parameter Estimates')
summary += '-' * 75 + '\n'
summary += "%-20s %10s %10s %10s %10s %10s\n" % ('Variable', 'Mean' ,'STD', 'Min' ,'Median', 'Max')
summary += "%-20s %10s %10s %10s %10s %10s\n" % ('-'*20, '-'*10 ,'-'*10, '-'*10 ,'-'*10, '-'*10)
for i in range(self.k):
summary += "%-20s %10.3f %10.3f %10.3f %10.3f %10.3f\n" % (XNames[i], np.mean(self.params[:,i]) ,np.std(self.params[:,i]),np.min(self.params[:,i]) ,np.median(self.params[:,i]), np.max(self.params[:,i]))

summary += '=' * 75 + '\n'
return summary