def fit(self, y, n_jobs=1, permutations=999):
"""
Arguments
---------
y : numpy.ndarray
array containing binary (0/1) data
Returns
-------
the fitted estimator.
Notes
-----
Technical details and derivations found in :cite:`AnselinLi2019`.
Examples
--------
>>> import libpysal
>>> w = libpysal.weights.lat2W(4, 4)
>>> y = np.ones(16)
>>> y[0:8] = 0
>>> LJC_uni = Local_Join_Count(connectivity=w).fit(y)
>>> LJC_uni.LJC
>>> LJC_uni.p_sim
Guerry data replicating GeoDa tutorial
>>> import libpysal
>>> import geopandas as gpd
>>> guerry = libpysal.examples.load_example('Guerry')
>>> guerry_ds = gpd.read_file(guerry.get_path('Guerry.shp'))
>>> guerry_ds['SELECTED'] = 0
>>> guerry_ds.loc[(guerry_ds['Donatns'] > 10997), 'SELECTED'] = 1
>>> w = libpysal.weights.Queen.from_dataframe(guerry_ds)
>>> LJC_uni = Local_Join_Count(connectivity=w).fit(guerry_ds['SELECTED'])
>>> LJC_uni.LJC
>>> LJC_uni.p_sim
"""
# Need to ensure that the np.array() are of
# dtype='float' for numba
y = np.array(y, dtype='float')
w = self.connectivity
# Fill the diagonal with 0s
w = weights.util.fill_diagonal(w, val=0)
w.transform = 'b'
keep_simulations = self.keep_simulations
n_jobs = self.n_jobs
seed = self.seed
self.y = y
self.n = len(y)
self.w = w
self.LJC = self._statistic(y, w)
if permutations:
self.p_sim, self.rjoins = _crand_plus(z=self.y,
w=self.w,
observed=self.LJC,
permutations=permutations,
keep=keep_simulations,
n_jobs=n_jobs,
stat_func=_ljc_uni)
# Set p-values for those with LJC of 0 to NaN
self.p_sim[self.LJC == 0] = 'NaN'
return self
def fit(self, variables, n_jobs=1, permutations=999):
"""
Arguments
---------
variables : numpy.ndarray
array(s) containing binary (0/1) data
Returns
-------
the fitted estimator.
Notes
-----
Technical details and derivations can be found in :cite:`AnselinLi2019`.
Examples
--------
>>> import libpysal
>>> w = libpysal.weights.lat2W(4, 4)
>>> x = np.ones(16)
>>> x[0:8] = 0
>>> z = [0,1,0,1,1,1,1,1,0,0,1,1,0,0,1,1]
>>> y = [0,1,1,1,1,1,1,1,0,0,0,1,0,0,1,1]
>>> LJC_MV = Local_Join_Counts_MV(connectivity=w).fit([x, y, z])
>>> LJC_MV.LJC
>>> LJC_MV.p_sim
Guerry data extending GeoDa tutorial
>>> import libpysal
>>> import geopandas as gpd
>>> guerry = libpysal.examples.load_example('Guerry')
>>> guerry_ds = gpd.read_file(guerry.get_path('Guerry.shp'))
>>> guerry_ds['infq5'] = 0
>>> guerry_ds['donq5'] = 0
>>> guerry_ds['suic5'] = 0
>>> guerry_ds.loc[(guerry_ds['Infants'] > 23574), 'infq5'] = 1
>>> guerry_ds.loc[(guerry_ds['Donatns'] > 10973), 'donq5'] = 1
>>> guerry_ds.loc[(guerry_ds['Suicids'] > 55564), 'suic5'] = 1
>>> w = libpysal.weights.Queen.from_dataframe(guerry_ds)
>>> LJC_MV = Local_Join_Counts_MV(connectivity=w).fit([guerry_ds['infq5'], guerry_ds['donq5'], guerry_ds['suic5']])
>>> LJC_MV.LJC
>>> LJC_MV.p_sim
"""
w = self.connectivity
# Fill the diagonal with 0s
w = weights.util.fill_diagonal(w, val=0)
w.transform = 'b'
self.n = len(variables[0])
self.w = w
self.variables = np.array(variables, dtype='float')
keep_simulations = self.keep_simulations
n_jobs = self.n_jobs
seed = self.seed
# Need to ensure that the product is an
# np.array() of dtype='float' for numba
self.ext = np.array(np.prod(np.vstack(variables), axis=0),
dtype='float')
self.LJC = self._statistic(variables, w)
if permutations:
self.p_sim, self.rjoins = _crand_plus(
z=self.ext,
w=self.w,
observed=self.LJC,
permutations=permutations,
keep=True,
n_jobs=n_jobs,
stat_func=_ljc_mv
)
# Set p-values for those with LJC of 0 to NaN
self.p_sim[self.LJC == 0] = 'NaN'
return self
class Local_Join_Count_BV(BaseEstimator):
"""Univariate Local Join Count Statistic"""
def __init__(self,
connectivity=None,
permutations=999,
n_jobs=1,
keep_simulations=True,
seed=None):
"""
Initialize a Local_Join_Count_BV estimator
Arguments
---------
connectivity : scipy.sparse matrix object
the connectivity structure describing
the relationships between observed units.
Need not be row-standardized.
permutations : int
number of random permutations for calculation of pseudo
p_values
n_jobs : int
Number of cores to be used in the conditional randomisation. If -1,
all available cores are used.
keep_simulations : Boolean
(default=True)
If True, the entire matrix of replications under the null
is stored in memory and accessible; otherwise, replications
are not saved
seed : None/int
Seed to ensure reproducibility of conditional randomizations.
Must be set here, and not outside of the function, since numba
does not correctly interpret external seeds
nor numpy.random.RandomState instances.
"""
self.connectivity = connectivity
self.permutations = permutations
self.n_jobs = n_jobs
self.keep_simulations = keep_simulations
self.seed = seed
def fit(self, x, y, case="CLC"):
"""
Arguments
---------
x : numpy.ndarray
array containing binary (0/1) data
y : numpy.ndarray
array containing binary (0/1) data
case : str
"BJC" for bivariate local join count,
"CLC" for co-location local join count.
Details in :cite:`AnselinLi2019`.
Returns
-------
the fitted estimator.
Notes
-----
Technical details and derivations can be found in :cite:`AnselinLi2019`.
Examples
--------
>>> import libpysal
>>> w = libpysal.weights.lat2W(4, 4)
>>> x = np.ones(16)
>>> x[0:8] = 0
>>> y = [0,1,0,1,1,1,1,1,0,0,1,1,0,0,1,1]
>>> LJC_BV_C1 = Local_Join_Count_BV(connectivity=w).fit(x, y, case="BJC")
>>> LJC_BV_C2 = Local_Join_Count_BV(connectivity=w).fit(x, y, case="CLC")
>>> LJC_BV_C1.LJC
>>> LJC_BV_C1.p_sim
>>> LJC_BV_C2.LJC
>>> LJC_BV_C2.p_sim
Commpop data replicating GeoDa tutorial (Case 1)
>>> import libpysal
>>> import geopandas as gpd
>>> commpop = gpd.read_file("https://github.com/jeffcsauer/GSOC2020/raw/master/validation/data/commpop.gpkg")
>>> w = libpysal.weights.Queen.from_dataframe(commpop)
>>> LJC_BV_Case1 = Local_Join_Count_BV(connectivity=w).fit(commpop['popneg'], commpop['popplus'], case='BJC')
>>> LJC_BV_Case1.LJC
>>> LJC_BV_Case1.p_sim
Guerry data replicating GeoDa tutorial (Case 2)
>>> import libpysal
>>> import geopandas as gpd
>>> guerry = libpysal.examples.load_example('Guerry')
>>> guerry_ds = gpd.read_file(guerry.get_path('Guerry.shp'))
>>> guerry_ds['infq5'] = 0
>>> guerry_ds['donq5'] = 0
>>> guerry_ds.loc[(guerry_ds['Infants'] > 23574), 'infq5'] = 1
>>> guerry_ds.loc[(guerry_ds['Donatns'] > 10973), 'donq5'] = 1
>>> w = libpysal.weights.Queen.from_dataframe(guerry_ds)
>>> LJC_BV_Case2 = Local_Join_Count_BV(connectivity=w).fit(guerry_ds['infq5'], guerry_ds['donq5'], case='CLC')
>>> LJC_BV_Case2.LJC
>>> LJC_BV_Case2.p_sim
"""
# Need to ensure that the np.array() are of
# dtype='float' for numba
x = np.array(x, dtype='float')
y = np.array(y, dtype='float')
w = self.connectivity
# Fill the diagonal with 0s
w = weights.util.fill_diagonal(w, val=0)
w.transform = 'b'
self.x = x
self.y = y
self.n = len(x)
self.w = w
self.case = case
keep_simulations = self.keep_simulations
n_jobs = self.n_jobs
seed = self.seed
permutations = self.permutations
self.LJC = self._statistic(x, y, w, case=case)
if permutations:
if case == "BJC":
self.p_sim, self.rjoins = _crand_plus(
z=np.column_stack((x, y)),
w=self.w,
observed=self.LJC,
permutations=permutations,
keep=True,
n_jobs=n_jobs,
stat_func=_ljc_bv_case1)
# Set p-values for those with LJC of 0 to NaN
self.p_sim[self.LJC == 0] = 'NaN'
elif case == "CLC":
self.p_sim, self.rjoins = _crand_plus(
z=np.column_stack((x, y)),
w=self.w,
observed=self.LJC,
permutations=permutations,
keep=True,
n_jobs=n_jobs,
stat_func=_ljc_bv_case2)
# Set p-values for those with LJC of 0 to NaN
self.p_sim[self.LJC == 0] = 'NaN'
else:
raise NotImplementedError(f'The requested LJC method ({case}) \
is not currently supported!')
del (self.n, self.keep_simulations, self.n_jobs, self.permutations,
self.seed, self.w, self.x, self.y, self.connectivity, self.rjoins)
return self
def fit(self, x):
"""
Arguments
---------
x : numpy.ndarray
array containing continuous data
Returns
-------
the fitted estimator.
Notes
-----
Technical details and derivations can be found in :cite:`Anselin1995`.
Examples
--------
Guerry data replication GeoDa tutorial
>>> import libpysal as lp
>>> import geopandas as gpd
>>> guerry = lp.examples.load_example('Guerry')
>>> guerry_ds = gpd.read_file(guerry.get_path('Guerry.shp'))
>>> w = libpysal.weights.Queen.from_dataframe(guerry_ds)
>>> y = guerry_ds['Donatns']
>>> lG = Local_Geary(connectivity=w).fit(y)
>>> lG.localG[0:5]
>>> lG.p_sim[0:5]
"""
x = np.asarray(x).flatten()
w = self.connectivity
w.transform = "r"
permutations = self.permutations
sig = self.sig
keep_simulations = self.keep_simulations
n_jobs = self.n_jobs
seed = self.seed
self.localG = self._statistic(x, w)
if permutations:
self.p_sim, self.rlocalG = _crand_plus(
z=(x - np.mean(x)) / np.std(x),
w=w,
observed=self.localG,
permutations=permutations,
keep=keep_simulations,
n_jobs=n_jobs,
stat_func=_local_geary,
)
if self.labels:
Eij_mean = np.mean(self.localG)
x_mean = np.mean(x)
# Create empty vector to fill
self.labs = np.empty(len(x)) * np.nan
# Outliers
self.labs[(self.localG < Eij_mean) & (x > x_mean) & (self.p_sim <= sig)] = 1
# Clusters
self.labs[(self.localG < Eij_mean) & (x < x_mean) & (self.p_sim <= sig)] = 2
# Other
self.labs[(self.localG > Eij_mean) & (self.p_sim <= sig)] = 3
# Non-significant
self.labs[self.p_sim > sig] = 4
return self
self.w = w
self.case = case
keep_simulations = self.keep_simulations
n_jobs = self.n_jobs
seed = self.seed
self.LJC = self._statistic(x, z, w, case=case)
if permutations:
if case == "BJC":
self.p_sim, self.rjoins = _crand_plus(
z=np.column_stack((x, z)),
w=self.w,
observed=self.LJC,
permutations=permutations,
keep=True,
n_jobs=n_jobs,
stat_func=_ljc_bv_case1,
)
# Set p-values for those with LJC of 0 to NaN
self.p_sim[self.LJC == 0] = "NaN"
elif case == "CLC":
self.p_sim, self.rjoins = _crand_plus(
z=np.column_stack((x, z)),
w=self.w,
observed=self.LJC,
permutations=permutations,
keep=True,
n_jobs=n_jobs,
stat_func=_ljc_bv_case2,