spatial_stats 0.2.2 → 1.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +126 -55
- data/Rakefile +7 -0
- data/ext/spatial_stats/csr_matrix.c +380 -0
- data/ext/spatial_stats/csr_matrix.h +34 -0
- data/ext/spatial_stats/extconf.rb +6 -0
- data/ext/spatial_stats/spatial_stats.c +32 -0
- data/lib/spatial_stats.rb +1 -0
- data/lib/spatial_stats/global/bivariate_moran.rb +60 -22
- data/lib/spatial_stats/global/moran.rb +43 -36
- data/lib/spatial_stats/global/stat.rb +55 -27
- data/lib/spatial_stats/local/bivariate_moran.rb +84 -2
- data/lib/spatial_stats/local/geary.rb +35 -5
- data/lib/spatial_stats/local/getis_ord.rb +45 -17
- data/lib/spatial_stats/local/moran.rb +39 -9
- data/lib/spatial_stats/local/multivariate_geary.rb +45 -22
- data/lib/spatial_stats/local/stat.rb +112 -80
- data/lib/spatial_stats/narray_ext.rb +5 -5
- data/lib/spatial_stats/spatial_stats.so +0 -0
- data/lib/spatial_stats/utils.rb +25 -0
- data/lib/spatial_stats/utils/lag.rb +10 -10
- data/lib/spatial_stats/version.rb +1 -1
- data/lib/spatial_stats/weights/contiguous.rb +20 -10
- data/lib/spatial_stats/weights/distant.rb +38 -20
- data/lib/spatial_stats/weights/weights_matrix.rb +83 -26
- metadata +33 -11
- data/MIT-LICENSE +0 -20
@@ -19,10 +19,28 @@ module SpatialStats
|
|
19
19
|
@scope = scope
|
20
20
|
@x_field = x_field
|
21
21
|
@y_field = y_field
|
22
|
-
@weights = weights
|
22
|
+
@weights = weights.standardize
|
23
23
|
end
|
24
24
|
attr_accessor :scope, :x_field, :y_field, :weights
|
25
25
|
|
26
|
+
##
|
27
|
+
# A new instance of BivariateMoran, from vector and weights.
|
28
|
+
#
|
29
|
+
# @param [Array] x observations of dataset
|
30
|
+
# @param [Array] y observations of dataset
|
31
|
+
# @param [WeightsMatrix] weights to define relationships between observations
|
32
|
+
#
|
33
|
+
# @return [BivariateMoran]
|
34
|
+
def self.from_observations(x, y, weights)
|
35
|
+
n = weights.n
|
36
|
+
raise ArgumentError, 'Data size != weights.n' if x.size != n || y.size != n
|
37
|
+
|
38
|
+
instance = new(nil, nil, nil, weights.standardize)
|
39
|
+
instance.x = x
|
40
|
+
instance.y = y
|
41
|
+
instance
|
42
|
+
end
|
43
|
+
|
26
44
|
##
|
27
45
|
# Computes the local indicator of spatial correlation for
|
28
46
|
# x against lagged y.
|
@@ -62,6 +80,61 @@ module SpatialStats
|
|
62
80
|
mc_bv(permutations, seed)
|
63
81
|
end
|
64
82
|
|
83
|
+
##
|
84
|
+
# Determines what quadrant an observation is in. Based on its value
|
85
|
+
# compared to its neighbors. This does not work for all stats, since
|
86
|
+
# it requires that values be negative.
|
87
|
+
#
|
88
|
+
# In a standardized array of z, high values are values greater than 0
|
89
|
+
# and it's neighbors are determined by the spatial lag and if that is
|
90
|
+
# positive then it's neighbors would be high, low otherwise.
|
91
|
+
#
|
92
|
+
# Quadrants are:
|
93
|
+
# [HH] a high value surrounded by other high values
|
94
|
+
# [LH] a low value surrounded by high values
|
95
|
+
# [LL] a low value surrounded by low values
|
96
|
+
# [HL] a high value surrounded by low values
|
97
|
+
#
|
98
|
+
# @return [Array] of labels
|
99
|
+
def quads
|
100
|
+
# https://github.com/pysal/esda/blob/master/esda/moran.py#L925
|
101
|
+
z_lag = SpatialStats::Utils::Lag.neighbor_average(weights, y)
|
102
|
+
zp = x.map(&:positive?)
|
103
|
+
lp = z_lag.map(&:positive?)
|
104
|
+
|
105
|
+
# hh = zp & lp
|
106
|
+
# lh = zp ^ true & lp
|
107
|
+
# ll = zp ^ true & lp ^ true
|
108
|
+
# hl = zp next to lp ^ true
|
109
|
+
hh = zp.each_with_index.map { |v, idx| v & lp[idx] }
|
110
|
+
lh = zp.each_with_index.map { |v, idx| (v ^ true) & lp[idx] }
|
111
|
+
ll = zp.each_with_index.map { |v, idx| (v ^ true) & (lp[idx] ^ true) }
|
112
|
+
hl = zp.each_with_index.map { |v, idx| v & (lp[idx] ^ true) }
|
113
|
+
|
114
|
+
# now zip lists and map them to proper terms
|
115
|
+
quad_terms = %w[HH LH LL HL]
|
116
|
+
hh.zip(lh, ll, hl).map do |feature|
|
117
|
+
quad_terms[feature.index(true)]
|
118
|
+
end
|
119
|
+
end
|
120
|
+
alias groups quads
|
121
|
+
|
122
|
+
##
|
123
|
+
# Summary of the statistic. Computes +stat+, +mc+, and +groups+ then returns the values
|
124
|
+
# in a hash array.
|
125
|
+
#
|
126
|
+
# @param [Integer] permutations to run. Last digit should be 9 to produce round numbers.
|
127
|
+
# @param [Integer] seed used in random number generator for shuffles.
|
128
|
+
#
|
129
|
+
# @return [Array]
|
130
|
+
def summary(permutations = 99, seed = nil)
|
131
|
+
p_vals = mc(permutations, seed)
|
132
|
+
data = weights.keys.zip(stat, p_vals, groups)
|
133
|
+
data.map do |row|
|
134
|
+
{ key: row[0], stat: row[1], p: row[2], group: row[3] }
|
135
|
+
end
|
136
|
+
end
|
137
|
+
|
65
138
|
def x
|
66
139
|
@x ||= SpatialStats::Queries::Variables.query_field(@scope, @x_field)
|
67
140
|
.standardize
|
@@ -79,8 +152,17 @@ module SpatialStats
|
|
79
152
|
x[idx] * y_lag_i
|
80
153
|
end
|
81
154
|
|
155
|
+
def mc_observation_calc(stat_i_orig, stat_i_new, _permutations)
|
156
|
+
# Since moran can be positive or negative, go by this definition
|
157
|
+
if stat_i_orig.positive?
|
158
|
+
(stat_i_new >= stat_i_orig).count
|
159
|
+
else
|
160
|
+
(stat_i_new <= stat_i_orig).count
|
161
|
+
end
|
162
|
+
end
|
163
|
+
|
82
164
|
def y_lag
|
83
|
-
@y_lag ||= SpatialStats::Utils::Lag.neighbor_sum(
|
165
|
+
@y_lag ||= SpatialStats::Utils::Lag.neighbor_sum(weights, y)
|
84
166
|
end
|
85
167
|
end
|
86
168
|
end
|
@@ -32,6 +32,25 @@ module SpatialStats
|
|
32
32
|
end
|
33
33
|
alias c stat
|
34
34
|
|
35
|
+
##
|
36
|
+
# Computes the groups each observation belongs to.
|
37
|
+
# Potential groups for Geary's C are:
|
38
|
+
# [HH] High-High
|
39
|
+
# [LL] Low-Low
|
40
|
+
# [N] Negative - Group traditionally for HL and LH, but since the difference is squared they are in the same group.
|
41
|
+
#
|
42
|
+
#
|
43
|
+
# @return [Array] groups for each observation
|
44
|
+
def groups
|
45
|
+
quads.map do |quad|
|
46
|
+
if %w[HL LH].include?(quad)
|
47
|
+
'N'
|
48
|
+
else
|
49
|
+
quad
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
35
54
|
##
|
36
55
|
# Values of the +field+ queried from the +scope+
|
37
56
|
#
|
@@ -45,9 +64,11 @@ module SpatialStats
|
|
45
64
|
private
|
46
65
|
|
47
66
|
def stat_i(idx)
|
48
|
-
|
49
|
-
|
50
|
-
|
67
|
+
# TODO: maybe don't even use stat_i
|
68
|
+
# just form all of the modified zs and then
|
69
|
+
# pass it to a loop of mulvec all implemented in c ext
|
70
|
+
zi = z.map { |val| (z[idx] - val)**2 }
|
71
|
+
weights.sparse.dot_row(zi, idx)
|
51
72
|
end
|
52
73
|
|
53
74
|
def mc_i(wi, perms, idx)
|
@@ -55,8 +76,17 @@ module SpatialStats
|
|
55
76
|
(wi * zi).sum(1)
|
56
77
|
end
|
57
78
|
|
58
|
-
def
|
59
|
-
|
79
|
+
def mc_observation_calc(stat_i_orig, stat_i_new, _permutations)
|
80
|
+
# Geary cannot be negative, so we have to use this technique from
|
81
|
+
# GeoDa to determine p values. Note I slightly modified it to be inclusive
|
82
|
+
# on both tails not just the lower tail.
|
83
|
+
# https://github.com/GeoDaCenter/geoda/blob/master/Explore/LocalGearyCoordinator.cpp#L981 mean = stat_i_new.mean
|
84
|
+
mean = stat_i_new.mean
|
85
|
+
if stat_i_orig <= mean
|
86
|
+
(stat_i_new <= stat_i_orig).count
|
87
|
+
else
|
88
|
+
(stat_i_new >= stat_i_orig).count
|
89
|
+
end
|
60
90
|
end
|
61
91
|
end
|
62
92
|
end
|
@@ -14,13 +14,18 @@ module SpatialStats
|
|
14
14
|
# @param [ActiveRecord::Relation] scope
|
15
15
|
# @param [Symbol, String] field to query from scope
|
16
16
|
# @param [WeightsMatrix] weights to define relationship between observations in scope
|
17
|
+
# @param [Boolean] star to preset if star will be true or false. Will be calculated otherwise.
|
17
18
|
#
|
18
19
|
# @return [GetisOrd]
|
19
20
|
def initialize(scope, field, weights, star = nil)
|
20
|
-
|
21
|
+
@scope = scope
|
22
|
+
@field = field
|
23
|
+
@weights = weights
|
21
24
|
@star = star
|
25
|
+
calc_weights
|
22
26
|
end
|
23
27
|
attr_accessor :star
|
28
|
+
attr_writer :x
|
24
29
|
|
25
30
|
##
|
26
31
|
# Computes the G or G* statistic for every observation in x.
|
@@ -33,6 +38,25 @@ module SpatialStats
|
|
33
38
|
end
|
34
39
|
alias g stat
|
35
40
|
|
41
|
+
##
|
42
|
+
# Computes the groups each observation belongs to.
|
43
|
+
# Potential groups for G are:
|
44
|
+
# [H] High
|
45
|
+
# [L] Low
|
46
|
+
#
|
47
|
+
# Group is high when standardized z is positive, low otherwise.
|
48
|
+
#
|
49
|
+
# @return [Array] groups for each observation
|
50
|
+
def groups
|
51
|
+
z.standardize.map do |val|
|
52
|
+
if val.positive?
|
53
|
+
'H'
|
54
|
+
else
|
55
|
+
'L'
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
36
60
|
##
|
37
61
|
# Values of the +field+ queried from the +scope+
|
38
62
|
#
|
@@ -50,7 +74,7 @@ module SpatialStats
|
|
50
74
|
# @return [Boolean] of star
|
51
75
|
def star?
|
52
76
|
if @star.nil?
|
53
|
-
@star = weights.
|
77
|
+
@star = weights.dense.trace.positive?
|
54
78
|
else
|
55
79
|
@star
|
56
80
|
end
|
@@ -67,25 +91,29 @@ module SpatialStats
|
|
67
91
|
x_lag_i / denominators[idx]
|
68
92
|
end
|
69
93
|
|
70
|
-
def
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
94
|
+
def mc_observation_calc(stat_i_orig, stat_i_new, permutations)
|
95
|
+
# GetisOrd cannot be negative, so we have to use this technique from
|
96
|
+
# ESDA to determine if we should select p or 1-p.
|
97
|
+
# https://github.com/pysal/esda/blob/master/esda/getisord.py#L388
|
98
|
+
num_larger = (stat_i_new >= stat_i_orig).count
|
99
|
+
is_low = (permutations - num_larger) < num_larger
|
100
|
+
if is_low
|
101
|
+
permutations - num_larger
|
102
|
+
else
|
103
|
+
num_larger
|
77
104
|
end
|
78
105
|
end
|
79
106
|
|
107
|
+
def calc_weights
|
108
|
+
@weights = if star?
|
109
|
+
weights.window.standardize
|
110
|
+
else
|
111
|
+
weights.standardize
|
112
|
+
end
|
113
|
+
end
|
114
|
+
|
80
115
|
def z_lag
|
81
|
-
|
82
|
-
@z_lag ||= begin
|
83
|
-
if star?
|
84
|
-
SpatialStats::Utils::Lag.window_sum(w, x)
|
85
|
-
else
|
86
|
-
SpatialStats::Utils::Lag.neighbor_sum(w, x)
|
87
|
-
end
|
88
|
-
end
|
116
|
+
@z_lag ||= SpatialStats::Utils::Lag.neighbor_sum(weights, x)
|
89
117
|
end
|
90
118
|
alias x_lag z_lag
|
91
119
|
|
@@ -55,12 +55,11 @@ module SpatialStats
|
|
55
55
|
# @return [Array] of variances for each observation
|
56
56
|
def variance
|
57
57
|
# formula is A - B - (E[I])**2
|
58
|
-
wt = w.row_standardized
|
59
58
|
exp = expectation
|
60
59
|
|
61
60
|
vars = []
|
62
|
-
a_terms = a_calc
|
63
|
-
b_terms = b_calc
|
61
|
+
a_terms = a_calc
|
62
|
+
b_terms = b_calc
|
64
63
|
|
65
64
|
a_terms.each_with_index do |a_term, idx|
|
66
65
|
vars << (a_term - b_terms[idx] - (exp**2))
|
@@ -68,6 +67,21 @@ module SpatialStats
|
|
68
67
|
vars
|
69
68
|
end
|
70
69
|
|
70
|
+
##
|
71
|
+
# Computes the groups each observation belongs to.
|
72
|
+
# Potential groups for Moran's I are:
|
73
|
+
# [HH] High-High
|
74
|
+
# [HL] High-Low
|
75
|
+
# [LH] Low-High
|
76
|
+
# [LL] Low-Low
|
77
|
+
#
|
78
|
+
# This is the same as the +#quads+ method in the +Stat+ class.
|
79
|
+
#
|
80
|
+
# @return [Array] groups for each observation
|
81
|
+
def groups
|
82
|
+
quads
|
83
|
+
end
|
84
|
+
|
71
85
|
##
|
72
86
|
# Values of the +field+ queried from the +scope+
|
73
87
|
#
|
@@ -85,7 +99,7 @@ module SpatialStats
|
|
85
99
|
def z_lag
|
86
100
|
# w is already row_standardized, so we are using
|
87
101
|
# neighbor sum instead of neighbor_average to save cost
|
88
|
-
@z_lag ||= SpatialStats::Utils::Lag.neighbor_sum(
|
102
|
+
@z_lag ||= SpatialStats::Utils::Lag.neighbor_sum(weights, z)
|
89
103
|
end
|
90
104
|
|
91
105
|
private
|
@@ -102,6 +116,15 @@ module SpatialStats
|
|
102
116
|
z[idx] * z_lag_i
|
103
117
|
end
|
104
118
|
|
119
|
+
def mc_observation_calc(stat_i_orig, stat_i_new, _permutations)
|
120
|
+
# Since moran can be positive or negative, go by this definition
|
121
|
+
if stat_i_orig.positive?
|
122
|
+
(stat_i_new >= stat_i_orig).count
|
123
|
+
else
|
124
|
+
(stat_i_new <= stat_i_orig).count
|
125
|
+
end
|
126
|
+
end
|
127
|
+
|
105
128
|
def si2
|
106
129
|
# @si2 ||= z.sample_variance
|
107
130
|
# we standardize so sample_variance is 1
|
@@ -109,20 +132,27 @@ module SpatialStats
|
|
109
132
|
end
|
110
133
|
|
111
134
|
# https://pro.arcgis.com/en/pro-app/tool-reference/spatial-statistics/h-local-morans-i-additional-math.htm
|
112
|
-
|
113
|
-
|
135
|
+
# TODO: sparse
|
136
|
+
def a_calc
|
137
|
+
n = weights.n
|
114
138
|
b2i = b2i_calc
|
139
|
+
|
140
|
+
wts = weights.sparse.values
|
141
|
+
row_index = weights.sparse.row_index
|
142
|
+
|
115
143
|
a_terms = []
|
116
144
|
|
117
145
|
(0..n - 1).each do |idx|
|
118
|
-
|
146
|
+
row_range = row_index[idx]..(row_index[idx + 1] - 1)
|
147
|
+
wt = wts[row_range]
|
148
|
+
sigma_term = wt.sum { |v| v**2 }
|
119
149
|
a_terms << (n - b2i) * sigma_term / (n - 1)
|
120
150
|
end
|
121
151
|
a_terms
|
122
152
|
end
|
123
153
|
|
124
|
-
def b_calc
|
125
|
-
n =
|
154
|
+
def b_calc
|
155
|
+
n = weights.n
|
126
156
|
b2i = b2i_calc
|
127
157
|
b_terms = []
|
128
158
|
|
@@ -23,7 +23,7 @@ module SpatialStats
|
|
23
23
|
def initialize(scope, fields, weights)
|
24
24
|
@scope = scope
|
25
25
|
@fields = fields
|
26
|
-
@weights = weights
|
26
|
+
@weights = weights.standardize
|
27
27
|
end
|
28
28
|
attr_accessor :scope, :fields, :weights
|
29
29
|
|
@@ -60,37 +60,47 @@ module SpatialStats
|
|
60
60
|
# of indices, which will return a list of new orders for the fields.
|
61
61
|
# They will then be shuffled corresponding to the new indices.
|
62
62
|
rng = gen_rng(seed)
|
63
|
-
|
64
|
-
indices = (0..(n - 1)).to_a
|
65
|
-
shuffles = crand(indices, permutations, rng)
|
63
|
+
rids = crand(permutations, rng)
|
66
64
|
|
65
|
+
n_1 = weights.n - 1
|
66
|
+
sparse = weights.sparse
|
67
|
+
row_index = sparse.row_index
|
68
|
+
ws = sparse.values
|
69
|
+
wc = weights.wc
|
67
70
|
stat_orig = stat
|
68
|
-
rs = [0] * n
|
69
71
|
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
72
|
+
ids = (0..n_1).to_a
|
73
|
+
observations = Array.new(weights.n)
|
74
|
+
(0..n_1).each do |idx|
|
75
|
+
idsi = ids.dup
|
76
|
+
idsi.delete_at(idx)
|
77
|
+
idsi.shuffle!(random: rng)
|
78
|
+
idsi = Numo::Int32.cast(idsi)
|
79
|
+
sample = rids[idsi[rids[true, 0..wc[idx] - 1]]]
|
80
|
+
|
81
|
+
# account for case where there are no neighbors
|
82
|
+
row_range = row_index[idx]..(row_index[idx + 1] - 1)
|
83
|
+
if row_range.size.zero?
|
84
|
+
observations[idx] = permutations
|
85
|
+
next
|
86
|
+
end
|
87
|
+
|
88
|
+
wi = Numo::DFloat.cast(ws[row_range])
|
89
|
+
stat_i_new = mc_i(wi, sample, idx)
|
74
90
|
stat_i_orig = stat_orig[idx]
|
75
|
-
|
76
|
-
|
77
|
-
# for each field, compute the C value at that index.
|
78
|
-
stat_i_new = mc_i(wi, shuffles[idx], idx)
|
79
|
-
|
80
|
-
rs[idx] = if stat_i_orig.positive?
|
81
|
-
(stat_i_new >= stat_i_orig).count
|
82
|
-
else
|
83
|
-
(stat_i_new <= stat_i_orig).count
|
84
|
-
end
|
85
|
-
|
86
|
-
idx += 1
|
91
|
+
observations[idx] = mc_observation_calc(stat_i_orig, stat_i_new,
|
92
|
+
permutations)
|
87
93
|
end
|
88
94
|
|
89
|
-
|
95
|
+
observations.map do |ri|
|
90
96
|
(ri + 1.0) / (permutations + 1.0)
|
91
97
|
end
|
92
98
|
end
|
93
99
|
|
100
|
+
def groups
|
101
|
+
raise NotImplementedError, 'groups not implemented'
|
102
|
+
end
|
103
|
+
|
94
104
|
private
|
95
105
|
|
96
106
|
def mc_i(wi, perms, idx)
|
@@ -108,6 +118,19 @@ module SpatialStats
|
|
108
118
|
cs.mean(0)
|
109
119
|
end
|
110
120
|
|
121
|
+
def mc_observation_calc(stat_i_orig, stat_i_new, _permutations)
|
122
|
+
# Geary cannot be negative, so we have to use this technique from
|
123
|
+
# GeoDa to determine p values. Note I slightly modified it to be inclusive
|
124
|
+
# on both tails not just the lower tail.
|
125
|
+
# https://github.com/GeoDaCenter/geoda/blob/master/Explore/LocalGearyCoordinator.cpp#L981 mean = stat_i_new.mean
|
126
|
+
mean = stat_i_new.mean
|
127
|
+
if stat_i_orig <= mean
|
128
|
+
(stat_i_new <= stat_i_orig).count
|
129
|
+
else
|
130
|
+
(stat_i_new >= stat_i_orig).count
|
131
|
+
end
|
132
|
+
end
|
133
|
+
|
111
134
|
def field_data
|
112
135
|
@field_data ||= fields.map do |field|
|
113
136
|
SpatialStats::Queries::Variables.query_field(@scope, field)
|