statsample 0.6.5 → 0.6.7
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +15 -0
- data/Manifest.txt +6 -0
- data/README.txt +30 -12
- data/Rakefile +91 -0
- data/demo/levene.rb +9 -0
- data/demo/multiple_regression.rb +1 -7
- data/demo/polychoric.rb +1 -0
- data/demo/principal_axis.rb +8 -0
- data/lib/distribution/f.rb +22 -22
- data/lib/spss.rb +99 -99
- data/lib/statsample/bivariate/polychoric.rb +32 -22
- data/lib/statsample/bivariate/tetrachoric.rb +212 -207
- data/lib/statsample/bivariate.rb +6 -6
- data/lib/statsample/codification.rb +65 -65
- data/lib/statsample/combination.rb +60 -59
- data/lib/statsample/converter/csv19.rb +12 -12
- data/lib/statsample/converters.rb +1 -1
- data/lib/statsample/dataset.rb +93 -36
- data/lib/statsample/dominanceanalysis/bootstrap.rb +66 -3
- data/lib/statsample/dominanceanalysis.rb +5 -6
- data/lib/statsample/factor/pca.rb +41 -11
- data/lib/statsample/factor/principalaxis.rb +105 -29
- data/lib/statsample/factor/rotation.rb +20 -3
- data/lib/statsample/factor.rb +1 -1
- data/lib/statsample/graph/gdchart.rb +13 -13
- data/lib/statsample/graph/svggraph.rb +166 -167
- data/lib/statsample/matrix.rb +22 -12
- data/lib/statsample/mle/logit.rb +3 -2
- data/lib/statsample/mle/probit.rb +7 -5
- data/lib/statsample/mle.rb +4 -2
- data/lib/statsample/multiset.rb +125 -124
- data/lib/statsample/permutation.rb +2 -1
- data/lib/statsample/regression/binomial/logit.rb +4 -3
- data/lib/statsample/regression/binomial/probit.rb +2 -1
- data/lib/statsample/regression/binomial.rb +62 -81
- data/lib/statsample/regression/multiple/baseengine.rb +1 -1
- data/lib/statsample/regression/multiple/gslengine.rb +1 -1
- data/lib/statsample/regression/multiple/matrixengine.rb +12 -6
- data/lib/statsample/regression/multiple.rb +15 -42
- data/lib/statsample/regression/simple.rb +93 -78
- data/lib/statsample/regression.rb +74 -2
- data/lib/statsample/reliability.rb +117 -120
- data/lib/statsample/srs.rb +156 -153
- data/lib/statsample/test/levene.rb +90 -0
- data/lib/statsample/test/umannwhitney.rb +25 -9
- data/lib/statsample/test.rb +2 -0
- data/lib/statsample/vector.rb +388 -413
- data/lib/statsample.rb +74 -30
- data/po/es/statsample.mo +0 -0
- data/test/test_bivariate.rb +5 -4
- data/test/test_combination.rb +1 -1
- data/test/test_dataset.rb +2 -2
- data/test/test_factor.rb +53 -6
- data/test/test_gsl.rb +1 -1
- data/test/test_mle.rb +1 -1
- data/test/test_regression.rb +18 -33
- data/test/test_statistics.rb +15 -33
- data/test/test_stest.rb +35 -0
- data/test/test_svg_graph.rb +2 -2
- data/test/test_vector.rb +331 -333
- metadata +38 -11
data/test/test_vector.rb
CHANGED
@@ -5,124 +5,124 @@ require 'tempfile'
|
|
5
5
|
class TestStatsample
|
6
6
|
end
|
7
7
|
class TestStatsample::TestVector < Test::Unit::TestCase
|
8
|
+
|
9
|
+
def setup
|
10
|
+
@c = Statsample::Vector.new([5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99], :nominal)
|
11
|
+
@c.missing_values=[-99]
|
12
|
+
|
13
|
+
end
|
14
|
+
def test_save_load
|
15
|
+
outfile=Tempfile.new("vector.vec")
|
16
|
+
@c.save(outfile.path)
|
17
|
+
a=Statsample.load(outfile.path)
|
18
|
+
assert_equal(@c,a)
|
19
|
+
|
20
|
+
end
|
21
|
+
def test_lazy_methods
|
22
|
+
data=[1,2,3,4,5,nil]
|
23
|
+
correct=Statsample::Vector.new(data,:scale)
|
24
|
+
lazy1=data.to_vector(:scale)
|
25
|
+
lazy2=data.to_scale
|
26
|
+
assert_equal(correct,lazy1)
|
27
|
+
assert_equal(correct,lazy2)
|
28
|
+
assert_equal(:scale,lazy2.type)
|
29
|
+
assert_equal([1,2,3,4,5],lazy2.valid_data)
|
30
|
+
end
|
31
|
+
def test_enumerable
|
32
|
+
val=@c.collect {|v| v}
|
33
|
+
assert_equal(val,[5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99])
|
34
|
+
end
|
35
|
+
def test_recode
|
36
|
+
a=@c.recode{|v| @c.is_valid?(v) ? 0 : 1 }
|
37
|
+
exp=[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,1,1].to_vector
|
38
|
+
assert_equal(exp,a)
|
39
|
+
exp.recode!{|v| v==0 ? 1:0}
|
40
|
+
exp2=(([1]*15)+([0]*3)).to_vector
|
41
|
+
assert_equal(exp2,exp)
|
42
|
+
end
|
43
|
+
def test_product
|
44
|
+
a=[1,2,3,4,5].to_vector(:scale)
|
45
|
+
assert_equal(120,a.product)
|
46
|
+
end
|
47
|
+
def test_matrix
|
48
|
+
a=[1,2,3,4,5].to_vector(:scale)
|
49
|
+
mh=Matrix[[1,2,3,4,5]]
|
50
|
+
mv=Matrix.columns([[1,2,3,4,5]])
|
51
|
+
assert_equal(mh,a.to_matrix)
|
52
|
+
assert_equal(mv,a.to_matrix(:vertical))
|
53
|
+
# 3*4 + 2*5 = 22
|
54
|
+
a=[3,2].to_vector(:scale)
|
55
|
+
b=[4,5].to_vector(:scale)
|
56
|
+
assert_equal(22,(a.to_matrix*b.to_matrix(:vertical))[0,0])
|
57
|
+
end
|
58
|
+
def test_missing_values
|
59
|
+
@c.missing_values=[10]
|
60
|
+
assert_equal([-99,-99,1,2,3,4,5,5,5,5,5,6,6,7,8,9], @c.valid_data.sort)
|
61
|
+
assert_equal([5,5,5,5,5,6,6,7,8,9,nil,1,2,3,4,nil,-99,-99], @c.data_with_nils)
|
62
|
+
@c.missing_values=[-99]
|
63
|
+
assert_equal(@c.valid_data.sort,[1,2,3,4,5,5,5,5,5,6,6,7,8,9,10])
|
64
|
+
assert_equal(@c.data_with_nils,[5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,nil,nil])
|
65
|
+
@c.missing_values=[]
|
66
|
+
assert_equal(@c.valid_data.sort,[-99,-99,1,2,3,4,5,5,5,5,5,6,6,7,8,9,10])
|
67
|
+
assert_equal(@c.data_with_nils,[5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99])
|
8
68
|
|
9
|
-
|
10
|
-
|
11
|
-
|
69
|
+
end
|
70
|
+
def test_has_missing_data
|
71
|
+
a=[1,2,3,nil].to_vector
|
72
|
+
assert(a.has_missing_data?)
|
73
|
+
a=[1,2,3,4,10].to_vector
|
74
|
+
assert(!a.has_missing_data?)
|
75
|
+
a.missing_values=[10]
|
76
|
+
assert(a.has_missing_data?)
|
77
|
+
end
|
78
|
+
def test_labeled
|
79
|
+
@c.labels={5=>'FIVE'}
|
80
|
+
assert_equal(["FIVE","FIVE","FIVE","FIVE","FIVE",6,6,7,8,9,10,1,2,3,4,nil,-99, -99],@c.vector_labeled.to_a)
|
81
|
+
end
|
82
|
+
def test_split
|
83
|
+
a = Statsample::Vector.new(["a","a,b","c,d","a,d","d",10,nil],:nominal)
|
84
|
+
assert_equal([%w{a},%w{a b},%w{c d},%w{a d},%w{d},[10],nil], a.splitted)
|
85
|
+
end
|
86
|
+
def test_verify
|
87
|
+
h=@c.verify{|d| !d.nil? and d>0}
|
88
|
+
e={15=>nil,16=>-99,17=>-99}
|
89
|
+
assert_equal(e,h)
|
90
|
+
end
|
91
|
+
def test_split_by_separator
|
92
|
+
a = Statsample::Vector.new(["a","a,b","c,d","a,d",10,nil],:nominal)
|
93
|
+
b=a.split_by_separator(",")
|
94
|
+
assert_kind_of(Hash, b)
|
95
|
+
assert_instance_of(Statsample::Vector,b['a'])
|
96
|
+
assert_instance_of(Statsample::Vector,b['b'])
|
97
|
+
assert_instance_of(Statsample::Vector,b['c'])
|
98
|
+
assert_instance_of(Statsample::Vector,b['d'])
|
99
|
+
assert_instance_of(Statsample::Vector,b[10])
|
100
|
+
assert_equal([1,1,0,1,0,nil],b['a'].to_a)
|
101
|
+
assert_equal([0,1,0,0,0,nil],b['b'].to_a)
|
102
|
+
assert_equal([0,0,1,0,0,nil],b['c'].to_a)
|
103
|
+
assert_equal([0,0,1,1,0,nil],b['d'].to_a)
|
104
|
+
assert_equal([0,0,0,0,1,nil],b[10].to_a)
|
105
|
+
assert_equal({'a'=>3,'b'=>1,'c'=>1,'d'=>2,10=>1}, a.split_by_separator_freq())
|
12
106
|
|
107
|
+
a = Statsample::Vector.new(["a","a*b","c*d","a*d",10,nil],:nominal)
|
108
|
+
b=a.split_by_separator("*")
|
109
|
+
assert_equal([1,1,0,1,0,nil],b['a'].to_a)
|
110
|
+
assert_equal([0,1,0,0,0,nil],b['b'].to_a)
|
111
|
+
assert_equal([0,0,1,0,0,nil],b['c'].to_a)
|
112
|
+
assert_equal([0,0,1,1,0,nil],b['d'].to_a)
|
113
|
+
assert_equal([0,0,0,0,1,nil],b[10].to_a)
|
114
|
+
end
|
115
|
+
def test_types
|
116
|
+
@c.type=:nominal
|
117
|
+
assert_raise NoMethodError do
|
118
|
+
@c.median
|
13
119
|
end
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
a=Statsample.load(outfile.path)
|
18
|
-
assert_equal(@c,a)
|
19
|
-
|
20
|
-
end
|
21
|
-
def test_lazy_methods
|
22
|
-
data=[1,2,3,4,5,nil]
|
23
|
-
correct=Statsample::Vector.new(data,:scale)
|
24
|
-
lazy1=data.to_vector(:scale)
|
25
|
-
lazy2=data.to_scale
|
26
|
-
assert_equal(correct,lazy1)
|
27
|
-
assert_equal(correct,lazy2)
|
28
|
-
assert_equal(:scale,lazy2.type)
|
29
|
-
assert_equal([1,2,3,4,5],lazy2.valid_data)
|
30
|
-
end
|
31
|
-
def test_enumerable
|
32
|
-
val=@c.collect {|v| v}
|
33
|
-
assert_equal(val,[5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99])
|
34
|
-
end
|
35
|
-
def test_recode
|
36
|
-
a=@c.recode{|v| @c.is_valid?(v) ? 0 : 1 }
|
37
|
-
exp=[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,1,1].to_vector
|
38
|
-
assert_equal(exp,a)
|
39
|
-
exp.recode!{|v| v==0 ? 1:0}
|
40
|
-
exp2=(([1]*15)+([0]*3)).to_vector
|
41
|
-
assert_equal(exp2,exp)
|
42
|
-
end
|
43
|
-
def test_product
|
44
|
-
a=[1,2,3,4,5].to_vector(:scale)
|
45
|
-
assert_equal(120,a.product)
|
46
|
-
end
|
47
|
-
def test_matrix
|
48
|
-
a=[1,2,3,4,5].to_vector(:scale)
|
49
|
-
mh=Matrix[[1,2,3,4,5]]
|
50
|
-
mv=Matrix.columns([[1,2,3,4,5]])
|
51
|
-
assert_equal(mh,a.to_matrix)
|
52
|
-
assert_equal(mv,a.to_matrix(:vertical))
|
53
|
-
# 3*4 + 2*5 = 22
|
54
|
-
a=[3,2].to_vector(:scale)
|
55
|
-
b=[4,5].to_vector(:scale)
|
56
|
-
assert_equal(22,(a.to_matrix*b.to_matrix(:vertical))[0,0])
|
57
|
-
end
|
58
|
-
def test_missing_values
|
59
|
-
@c.missing_values=[10]
|
60
|
-
assert_equal([-99,-99,1,2,3,4,5,5,5,5,5,6,6,7,8,9], @c.valid_data.sort)
|
61
|
-
assert_equal([5,5,5,5,5,6,6,7,8,9,nil,1,2,3,4,nil,-99,-99], @c.data_with_nils)
|
62
|
-
@c.missing_values=[-99]
|
63
|
-
assert_equal(@c.valid_data.sort,[1,2,3,4,5,5,5,5,5,6,6,7,8,9,10])
|
64
|
-
assert_equal(@c.data_with_nils,[5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,nil,nil])
|
65
|
-
@c.missing_values=[]
|
66
|
-
assert_equal(@c.valid_data.sort,[-99,-99,1,2,3,4,5,5,5,5,5,6,6,7,8,9,10])
|
67
|
-
assert_equal(@c.data_with_nils,[5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99])
|
68
|
-
|
69
|
-
end
|
70
|
-
def test_has_missing_data
|
71
|
-
a=[1,2,3,nil].to_vector
|
72
|
-
assert(a.has_missing_data?)
|
73
|
-
a=[1,2,3,4,10].to_vector
|
74
|
-
assert(!a.has_missing_data?)
|
75
|
-
a.missing_values=[10]
|
76
|
-
assert(a.has_missing_data?)
|
120
|
+
@c.type=:ordinal
|
121
|
+
assert_raise NoMethodError do
|
122
|
+
@c.mean
|
77
123
|
end
|
78
|
-
|
79
|
-
|
80
|
-
assert_equal(["FIVE","FIVE","FIVE","FIVE","FIVE",6,6,7,8,9,10,1,2,3,4,nil,-99, -99],@c.vector_labeled.to_a)
|
81
|
-
end
|
82
|
-
def test_split
|
83
|
-
a = Statsample::Vector.new(["a","a,b","c,d","a,d","d",10,nil],:nominal)
|
84
|
-
assert_equal([%w{a},%w{a b},%w{c d},%w{a d},%w{d},[10],nil], a.splitted)
|
85
|
-
end
|
86
|
-
def test_verify
|
87
|
-
h=@c.verify{|d| !d.nil? and d>0}
|
88
|
-
e={15=>nil,16=>-99,17=>-99}
|
89
|
-
assert_equal(e,h)
|
90
|
-
end
|
91
|
-
def test_split_by_separator
|
92
|
-
a = Statsample::Vector.new(["a","a,b","c,d","a,d",10,nil],:nominal)
|
93
|
-
b=a.split_by_separator(",")
|
94
|
-
assert_kind_of(Hash, b)
|
95
|
-
assert_instance_of(Statsample::Vector,b['a'])
|
96
|
-
assert_instance_of(Statsample::Vector,b['b'])
|
97
|
-
assert_instance_of(Statsample::Vector,b['c'])
|
98
|
-
assert_instance_of(Statsample::Vector,b['d'])
|
99
|
-
assert_instance_of(Statsample::Vector,b[10])
|
100
|
-
assert_equal([1,1,0,1,0,nil],b['a'].to_a)
|
101
|
-
assert_equal([0,1,0,0,0,nil],b['b'].to_a)
|
102
|
-
assert_equal([0,0,1,0,0,nil],b['c'].to_a)
|
103
|
-
assert_equal([0,0,1,1,0,nil],b['d'].to_a)
|
104
|
-
assert_equal([0,0,0,0,1,nil],b[10].to_a)
|
105
|
-
assert_equal({'a'=>3,'b'=>1,'c'=>1,'d'=>2,10=>1}, a.split_by_separator_freq())
|
106
|
-
|
107
|
-
a = Statsample::Vector.new(["a","a*b","c*d","a*d",10,nil],:nominal)
|
108
|
-
b=a.split_by_separator("*")
|
109
|
-
assert_equal([1,1,0,1,0,nil],b['a'].to_a)
|
110
|
-
assert_equal([0,1,0,0,0,nil],b['b'].to_a)
|
111
|
-
assert_equal([0,0,1,0,0,nil],b['c'].to_a)
|
112
|
-
assert_equal([0,0,1,1,0,nil],b['d'].to_a)
|
113
|
-
assert_equal([0,0,0,0,1,nil],b[10].to_a)
|
114
|
-
end
|
115
|
-
def test_types
|
116
|
-
@c.type=:nominal
|
117
|
-
assert_raise NoMethodError do
|
118
|
-
@c.median
|
119
|
-
end
|
120
|
-
@c.type=:ordinal
|
121
|
-
assert_raise NoMethodError do
|
122
|
-
@c.mean
|
123
|
-
end
|
124
|
-
end
|
125
|
-
def test_nominal
|
124
|
+
end
|
125
|
+
def test_nominal
|
126
126
|
assert_equal(@c[1],5)
|
127
127
|
assert_equal({ 1=>1,2=>1,3=>1,4=>1,5=>5,6=>2,7=>1,8=>1, 9=>1,10=>1},@c.frequencies)
|
128
128
|
assert_equal({ 1=>1,2=>1,3=>1,4=>1,5=>5,6=>2,7=>1,8=>1, 9=>1,10=>1},@c._frequencies)
|
@@ -132,233 +132,231 @@ class TestStatsample::TestVector < Test::Unit::TestCase
|
|
132
132
|
assert_equal([1,2,3,4,5,6,7,8,9,10], @c.factors.sort)
|
133
133
|
assert_equal(@c.mode,5)
|
134
134
|
assert_equal(@c.n_valid,15)
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
135
|
+
end
|
136
|
+
def test_equality
|
137
|
+
v1=[1,2,3].to_vector
|
138
|
+
v2=[1,2,3].to_vector
|
139
|
+
assert_equal(v1,v2)
|
140
|
+
v1=[1,2,3].to_vector(:nominal)
|
141
|
+
v2=[1,2,3].to_vector(:ordinal)
|
142
|
+
assert_not_equal(v1,v2)
|
143
|
+
v1=[1,2,3].to_vector()
|
144
|
+
v2=[1,2,3].to_vector()
|
145
|
+
assert_equal(v1,v2)
|
146
|
+
end
|
147
|
+
def test_ordinal
|
148
|
+
@c.type=:ordinal
|
149
|
+
assert_equal(5,@c.median)
|
150
|
+
assert_equal(4,@c.percentil(25))
|
151
|
+
assert_equal(7,@c.percentil(75))
|
152
152
|
|
153
153
|
v=[200000, 200000, 210000, 220000, 230000, 250000, 250000, 250000, 270000, 300000, 450000, 130000, 140000, 140000, 140000, 145000, 148000, 165000, 170000, 180000, 180000, 180000, 180000, 180000, 180000 ].to_scale
|
154
154
|
assert_equal(180000,v.median)
|
155
|
-
|
156
|
-
|
157
|
-
|
158
|
-
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
155
|
+
|
156
|
+
end
|
157
|
+
def test_ranked
|
158
|
+
v1=[0.8,1.2,1.2,2.3,18].to_vector(:ordinal)
|
159
|
+
expected=[1,2.5,2.5,4,5].to_vector(:ordinal)
|
160
|
+
assert_equal(expected,v1.ranked)
|
161
|
+
end
|
162
|
+
def test_scale
|
163
|
+
a=Statsample::Vector.new([1,2,3,4,"STRING"], :scale)
|
164
|
+
assert_equal(10, a.sum)
|
165
|
+
i=0
|
166
|
+
factors=a.factors.sort
|
167
|
+
[0,1,2,3,4].each{|v|
|
168
|
+
assert(v==factors[i])
|
169
|
+
assert(v.class==factors[i].class,"#{v} - #{v.class} != #{factors[i]} - #{factors[i].class}")
|
170
|
+
i+=1
|
171
|
+
}
|
172
|
+
end
|
173
|
+
def test_vector_standarized
|
174
|
+
v1=[1,2,3,4,nil].to_vector(:scale)
|
175
|
+
sds=v1.sds
|
176
|
+
expected=[((1-2.5).quo(sds)),((2-2.5).quo(sds)),((3-2.5).quo(sds)),((4-2.5).quo(sds)), nil].to_vector(:scale)
|
177
|
+
vs=v1.vector_standarized
|
178
|
+
assert_equal(expected, vs)
|
179
|
+
assert_equal(0,vs.mean)
|
180
|
+
assert_equal(1,vs.sds)
|
181
|
+
end
|
182
|
+
def test_summary
|
183
|
+
@c.type=:nominal
|
184
|
+
assert_match(/Distribution/, @c.summary())
|
185
|
+
@c.type=:ordinal
|
186
|
+
assert_match(/median/, @c.summary())
|
187
|
+
@c.type=:scale
|
188
|
+
assert_match(/mean/, @c.summary())
|
189
|
+
end
|
190
|
+
def test_add
|
191
|
+
a=Statsample::Vector.new([1,2,3,4,5], :scale)
|
192
|
+
b=Statsample::Vector.new([11,12,13,14,15], :scale)
|
193
|
+
assert_equal([3,4,5,6,7], (a+2).to_a)
|
194
|
+
assert_equal([12,14,16,18,20], (a+b).to_a)
|
195
|
+
assert_raise ArgumentError do
|
196
|
+
a + @c
|
172
197
|
end
|
173
|
-
|
174
|
-
|
175
|
-
sds=v1.sds
|
176
|
-
expected=[((1-2.5).quo(sds)),((2-2.5).quo(sds)),((3-2.5).quo(sds)),((4-2.5).quo(sds)), nil].to_vector(:scale)
|
177
|
-
vs=v1.vector_standarized
|
178
|
-
assert_equal(expected, vs)
|
179
|
-
assert_equal(0,vs.mean)
|
180
|
-
assert_equal(1,vs.sds)
|
198
|
+
assert_raise TypeError do
|
199
|
+
a+"string"
|
181
200
|
end
|
182
|
-
|
183
|
-
|
184
|
-
|
185
|
-
|
186
|
-
|
187
|
-
|
188
|
-
|
201
|
+
a=Statsample::Vector.new([nil,1, 2 ,3 ,4 ,5], :scale)
|
202
|
+
b=Statsample::Vector.new([11, 12,nil,13,14,15], :scale)
|
203
|
+
assert_equal([nil,13,nil,16,18,20], (a+b).to_a)
|
204
|
+
assert_equal([nil,13,nil,16,18,20], (a+b.to_a).to_a)
|
205
|
+
end
|
206
|
+
def test_minus
|
207
|
+
a=Statsample::Vector.new([1,2,3,4,5], :scale)
|
208
|
+
b=Statsample::Vector.new([11,12,13,14,15], :scale)
|
209
|
+
assert_equal([-1,0,1,2,3], (a-2).to_a)
|
210
|
+
assert_equal([10,10,10,10,10], (b-a).to_a)
|
211
|
+
assert_raise ArgumentError do
|
212
|
+
a-@c
|
189
213
|
end
|
190
|
-
|
191
|
-
|
192
|
-
b=Statsample::Vector.new([11,12,13,14,15], :scale)
|
193
|
-
assert_equal([3,4,5,6,7], (a+2).to_a)
|
194
|
-
assert_equal([12,14,16,18,20], (a+b).to_a)
|
195
|
-
assert_raise ArgumentError do
|
196
|
-
a + @c
|
197
|
-
end
|
198
|
-
assert_raise TypeError do
|
199
|
-
a+"string"
|
200
|
-
end
|
201
|
-
a=Statsample::Vector.new([nil,1, 2 ,3 ,4 ,5], :scale)
|
202
|
-
b=Statsample::Vector.new([11, 12,nil,13,14,15], :scale)
|
203
|
-
assert_equal([nil,13,nil,16,18,20], (a+b).to_a)
|
204
|
-
assert_equal([nil,13,nil,16,18,20], (a+b.to_a).to_a)
|
214
|
+
assert_raise TypeError do
|
215
|
+
a-"string"
|
205
216
|
end
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
|
217
|
+
a=Statsample::Vector.new([nil,1, 2 ,3 ,4 ,5], :scale)
|
218
|
+
b=Statsample::Vector.new([11, 12,nil,13,14,15], :scale)
|
219
|
+
assert_equal([nil,11,nil,10,10,10], (b-a).to_a)
|
220
|
+
assert_equal([nil,11,nil,10,10,10], (b-a.to_a).to_a)
|
221
|
+
end
|
222
|
+
def test_sum_of_squares
|
223
|
+
a=[1,2,3,4,5,6].to_vector(:scale)
|
224
|
+
assert_equal(17.5, a.sum_of_squared_deviation)
|
225
|
+
end
|
226
|
+
def test_samples
|
227
|
+
srand(1)
|
228
|
+
assert_equal(100,@c.sample_with_replacement(100).size)
|
229
|
+
assert_equal(@c.valid_data.to_a.sort, @c.sample_without_replacement(15).sort)
|
230
|
+
assert_raise ArgumentError do
|
231
|
+
@c.sample_without_replacement(20)
|
221
232
|
end
|
222
|
-
|
223
|
-
|
224
|
-
|
225
|
-
|
226
|
-
def test_samples
|
227
|
-
srand(1)
|
228
|
-
assert_equal(100,@c.sample_with_replacement(100).size)
|
229
|
-
assert_equal(@c.valid_data.to_a.sort, @c.sample_without_replacement(15).sort)
|
230
|
-
assert_raise ArgumentError do
|
231
|
-
@c.sample_without_replacement(20)
|
232
|
-
end
|
233
|
-
@c.type=:scale
|
234
|
-
srand(1)
|
235
|
-
assert_equal(100, @c.sample_with_replacement(100).size)
|
236
|
-
assert_equal(@c.valid_data.to_a.sort, @c.sample_without_replacement(15).sort)
|
237
|
-
|
238
|
-
end
|
239
|
-
def test_valid_data
|
240
|
-
a=Statsample::Vector.new([1,2,3,4,"STRING"])
|
241
|
-
a.missing_values=[-99]
|
242
|
-
a.add(1,false)
|
243
|
-
a.add(2,false)
|
244
|
-
a.add(-99,false)
|
245
|
-
a.set_valid_data
|
246
|
-
exp_valid_data=[1,2,3,4,"STRING",1,2]
|
247
|
-
assert_equal(exp_valid_data,a.valid_data)
|
248
|
-
a.add(20,false)
|
249
|
-
a.add(30,false)
|
250
|
-
assert_equal(exp_valid_data,a.valid_data)
|
251
|
-
a.set_valid_data
|
252
|
-
exp_valid_data_2=[1,2,3,4,"STRING",1,2,20,30]
|
253
|
-
assert_equal(exp_valid_data_2,a.valid_data)
|
254
|
-
end
|
255
|
-
def test_set_value
|
256
|
-
@c[2]=10
|
257
|
-
expected=[5,5,10,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99].to_vector
|
258
|
-
assert_equal(expected.data,@c.data)
|
259
|
-
end
|
260
|
-
def test_gsl
|
261
|
-
if HAS_GSL
|
262
|
-
a=Statsample::Vector.new([1,2,3,4,"STRING"], :scale)
|
263
|
-
assert_equal(2,a.mean)
|
264
|
-
assert_equal(a.variance_sample_slow,a.variance_sample)
|
265
|
-
assert_equal(a.standard_deviation_sample_slow,a.sds)
|
266
|
-
assert_equal(a.variance_population_slow,a.variance_population)
|
267
|
-
assert_equal(a.standard_deviation_population_slow,a.standard_deviation_population)
|
268
|
-
assert_nothing_raised do
|
269
|
-
a=[].to_vector(:scale)
|
270
|
-
end
|
271
|
-
a.add(1,false)
|
272
|
-
a.add(2,false)
|
273
|
-
a.set_valid_data
|
274
|
-
assert_equal(3,a.sum)
|
275
|
-
b=[1,2,nil,3,4,5,nil,6].to_vector(:scale)
|
276
|
-
assert_equal(21, b.sum)
|
277
|
-
assert_equal(3.5, b.mean)
|
278
|
-
assert_equal(6,b.gsl.size)
|
279
|
-
c=[10,20,30,40,50,100,1000,2000,5000].to_scale
|
280
|
-
assert_in_delta(c.skew, c.skew_slow ,0.0001)
|
281
|
-
assert_in_delta(c.kurtosis, c.kurtosis_slow ,0.0001)
|
282
|
-
|
283
|
-
end
|
284
|
-
end
|
285
|
-
def test_vector_matrix
|
286
|
-
v1=%w{a a a b b b c c}.to_vector
|
287
|
-
v2=%w{1 3 4 5 6 4 3 2}.to_vector
|
288
|
-
v3=%w{1 0 0 0 1 1 1 0}.to_vector
|
289
|
-
ex=Matrix.rows([["a", "1", "1"], ["a", "3", "0"], ["a", "4", "0"], ["b", "5", "0"], ["b", "6", "1"], ["b", "4", "1"], ["c", "3", "1"], ["c", "2", "0"]])
|
290
|
-
assert_equal(ex,Statsample.vector_cols_matrix(v1,v2,v3))
|
291
|
-
end
|
292
|
-
def test_marshalling
|
293
|
-
v1=(0..100).to_a.collect{|n| rand(100)}.to_vector(:scale)
|
294
|
-
v2=Marshal.load(Marshal.dump(v1))
|
295
|
-
assert_equal(v1,v2)
|
296
|
-
end
|
297
|
-
def test_dup
|
298
|
-
v1=%w{a a a b b b c c}.to_vector
|
299
|
-
v2=v1.dup
|
300
|
-
assert_equal(v1.data,v2.data)
|
301
|
-
assert_not_same(v1.data,v2.data)
|
302
|
-
assert_equal(v1.type,v2.type)
|
303
|
-
|
304
|
-
v1.type=:ordinal
|
305
|
-
assert_not_equal(v1.type,v2.type)
|
306
|
-
assert_equal(v1.missing_values,v2.missing_values)
|
307
|
-
assert_not_same(v1.missing_values,v2.missing_values)
|
308
|
-
assert_equal(v1.labels,v2.labels)
|
309
|
-
assert_not_same(v1.labels,v2.labels)
|
310
|
-
|
311
|
-
v3=v1.dup_empty
|
312
|
-
assert_equal([],v3.data)
|
313
|
-
assert_not_equal(v1.data,v3.data)
|
314
|
-
assert_not_same(v1.data,v3.data)
|
315
|
-
assert_equal(v1.type,v3.type)
|
316
|
-
v1.type=:ordinal
|
317
|
-
v3.type=:nominal
|
318
|
-
assert_not_equal(v1.type,v3.type)
|
319
|
-
assert_equal(v1.missing_values,v3.missing_values)
|
320
|
-
assert_not_same(v1.missing_values,v3.missing_values)
|
321
|
-
assert_equal(v1.labels,v3.labels)
|
322
|
-
assert_not_same(v1.labels,v3.labels)
|
323
|
-
end
|
324
|
-
def test_paired_ties
|
325
|
-
a=[0,0,0,1,1,2,3,3,4,4,4].to_vector(:ordinal)
|
326
|
-
expected=[2,2,2,4.5,4.5,6,7.5,7.5,10,10,10].to_vector(:ordinal)
|
327
|
-
assert_equal(expected,a.ranked)
|
328
|
-
end
|
329
|
-
def test_dichotomize
|
330
|
-
a= [0,0,0,1,2,3,nil].to_vector
|
331
|
-
exp=[0,0,0,1,1,1,nil].to_scale
|
332
|
-
assert_equal(exp,a.dichotomize)
|
333
|
-
a= [1,1,1,2,2,2,3].to_vector
|
334
|
-
exp=[0,0,0,1,1,1,1].to_scale
|
335
|
-
assert_equal(exp,a.dichotomize)
|
336
|
-
a= [0,0,0,1,2,3,nil].to_vector
|
337
|
-
exp=[0,0,0,0,1,1,nil].to_scale
|
338
|
-
assert_equal(exp,a.dichotomize(1))
|
339
|
-
a= %w{a a a b c d}.to_vector
|
340
|
-
exp=[0,0,0,1,1,1].to_scale
|
341
|
-
assert_equal(exp, a.dichotomize)
|
342
|
-
end
|
343
|
-
def test_can_be_methods
|
344
|
-
a= [0,0,0,1,2,3,nil].to_vector
|
345
|
-
assert(a.can_be_scale?)
|
346
|
-
a=[0,"s",0,1,2,3,nil].to_vector
|
347
|
-
assert(!a.can_be_scale?)
|
348
|
-
a.missing_values=["s"]
|
349
|
-
assert(a.can_be_scale?)
|
233
|
+
@c.type=:scale
|
234
|
+
srand(1)
|
235
|
+
assert_equal(100, @c.sample_with_replacement(100).size)
|
236
|
+
assert_equal(@c.valid_data.to_a.sort, @c.sample_without_replacement(15).sort)
|
350
237
|
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
|
359
|
-
|
360
|
-
|
361
|
-
|
362
|
-
|
238
|
+
end
|
239
|
+
def test_valid_data
|
240
|
+
a=Statsample::Vector.new([1,2,3,4,"STRING"])
|
241
|
+
a.missing_values=[-99]
|
242
|
+
a.add(1,false)
|
243
|
+
a.add(2,false)
|
244
|
+
a.add(-99,false)
|
245
|
+
a.set_valid_data
|
246
|
+
exp_valid_data=[1,2,3,4,"STRING",1,2]
|
247
|
+
assert_equal(exp_valid_data,a.valid_data)
|
248
|
+
a.add(20,false)
|
249
|
+
a.add(30,false)
|
250
|
+
assert_equal(exp_valid_data,a.valid_data)
|
251
|
+
a.set_valid_data
|
252
|
+
exp_valid_data_2=[1,2,3,4,"STRING",1,2,20,30]
|
253
|
+
assert_equal(exp_valid_data_2,a.valid_data)
|
254
|
+
end
|
255
|
+
def test_set_value
|
256
|
+
@c[2]=10
|
257
|
+
expected=[5,5,10,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99].to_vector
|
258
|
+
assert_equal(expected.data,@c.data)
|
259
|
+
end
|
260
|
+
def test_gsl
|
261
|
+
if Statsample.has_gsl?
|
262
|
+
a=Statsample::Vector.new([1,2,3,4,"STRING"], :scale)
|
263
|
+
assert_equal(2,a.mean)
|
264
|
+
assert_equal(a.variance_sample_slow,a.variance_sample)
|
265
|
+
assert_equal(a.standard_deviation_sample_slow,a.sds)
|
266
|
+
assert_equal(a.variance_population_slow,a.variance_population)
|
267
|
+
assert_equal(a.standard_deviation_population_slow,a.standard_deviation_population)
|
268
|
+
assert_nothing_raised do
|
269
|
+
a=[].to_vector(:scale)
|
270
|
+
end
|
271
|
+
a.add(1,false)
|
272
|
+
a.add(2,false)
|
273
|
+
a.set_valid_data
|
274
|
+
assert_equal(3,a.sum)
|
275
|
+
b=[1,2,nil,3,4,5,nil,6].to_vector(:scale)
|
276
|
+
assert_equal(21, b.sum)
|
277
|
+
assert_equal(3.5, b.mean)
|
278
|
+
assert_equal(6,b.gsl.size)
|
279
|
+
c=[10,20,30,40,50,100,1000,2000,5000].to_scale
|
280
|
+
assert_in_delta(c.skew, c.skew_slow ,0.0001)
|
281
|
+
assert_in_delta(c.kurtosis, c.kurtosis_slow ,0.0001)
|
363
282
|
end
|
283
|
+
end
|
284
|
+
def test_vector_matrix
|
285
|
+
v1=%w{a a a b b b c c}.to_vector
|
286
|
+
v2=%w{1 3 4 5 6 4 3 2}.to_vector
|
287
|
+
v3=%w{1 0 0 0 1 1 1 0}.to_vector
|
288
|
+
ex=Matrix.rows([["a", "1", "1"], ["a", "3", "0"], ["a", "4", "0"], ["b", "5", "0"], ["b", "6", "1"], ["b", "4", "1"], ["c", "3", "1"], ["c", "2", "0"]])
|
289
|
+
assert_equal(ex,Statsample.vector_cols_matrix(v1,v2,v3))
|
290
|
+
end
|
291
|
+
def test_marshalling
|
292
|
+
v1=(0..100).to_a.collect{|n| rand(100)}.to_vector(:scale)
|
293
|
+
v2=Marshal.load(Marshal.dump(v1))
|
294
|
+
assert_equal(v1,v2)
|
295
|
+
end
|
296
|
+
def test_dup
|
297
|
+
v1=%w{a a a b b b c c}.to_vector
|
298
|
+
v2=v1.dup
|
299
|
+
assert_equal(v1.data,v2.data)
|
300
|
+
assert_not_same(v1.data,v2.data)
|
301
|
+
assert_equal(v1.type,v2.type)
|
302
|
+
|
303
|
+
v1.type=:ordinal
|
304
|
+
assert_not_equal(v1.type,v2.type)
|
305
|
+
assert_equal(v1.missing_values,v2.missing_values)
|
306
|
+
assert_not_same(v1.missing_values,v2.missing_values)
|
307
|
+
assert_equal(v1.labels,v2.labels)
|
308
|
+
assert_not_same(v1.labels,v2.labels)
|
309
|
+
|
310
|
+
v3=v1.dup_empty
|
311
|
+
assert_equal([],v3.data)
|
312
|
+
assert_not_equal(v1.data,v3.data)
|
313
|
+
assert_not_same(v1.data,v3.data)
|
314
|
+
assert_equal(v1.type,v3.type)
|
315
|
+
v1.type=:ordinal
|
316
|
+
v3.type=:nominal
|
317
|
+
assert_not_equal(v1.type,v3.type)
|
318
|
+
assert_equal(v1.missing_values,v3.missing_values)
|
319
|
+
assert_not_same(v1.missing_values,v3.missing_values)
|
320
|
+
assert_equal(v1.labels,v3.labels)
|
321
|
+
assert_not_same(v1.labels,v3.labels)
|
322
|
+
end
|
323
|
+
def test_paired_ties
|
324
|
+
a=[0,0,0,1,1,2,3,3,4,4,4].to_vector(:ordinal)
|
325
|
+
expected=[2,2,2,4.5,4.5,6,7.5,7.5,10,10,10].to_vector(:ordinal)
|
326
|
+
assert_equal(expected,a.ranked)
|
327
|
+
end
|
328
|
+
def test_dichotomize
|
329
|
+
a= [0,0,0,1,2,3,nil].to_vector
|
330
|
+
exp=[0,0,0,1,1,1,nil].to_scale
|
331
|
+
assert_equal(exp,a.dichotomize)
|
332
|
+
a= [1,1,1,2,2,2,3].to_vector
|
333
|
+
exp=[0,0,0,1,1,1,1].to_scale
|
334
|
+
assert_equal(exp,a.dichotomize)
|
335
|
+
a= [0,0,0,1,2,3,nil].to_vector
|
336
|
+
exp=[0,0,0,0,1,1,nil].to_scale
|
337
|
+
assert_equal(exp,a.dichotomize(1))
|
338
|
+
a= %w{a a a b c d}.to_vector
|
339
|
+
exp=[0,0,0,1,1,1].to_scale
|
340
|
+
assert_equal(exp, a.dichotomize)
|
341
|
+
end
|
342
|
+
def test_can_be_methods
|
343
|
+
a= [0,0,0,1,2,3,nil].to_vector
|
344
|
+
assert(a.can_be_scale?)
|
345
|
+
a=[0,"s",0,1,2,3,nil].to_vector
|
346
|
+
assert(!a.can_be_scale?)
|
347
|
+
a.missing_values=["s"]
|
348
|
+
assert(a.can_be_scale?)
|
349
|
+
|
350
|
+
a=[Date.new(2009,10,10), Date.today(), "2009-10-10", "2009-1-1", nil, "NOW"].to_vector
|
351
|
+
assert(a.can_be_date?)
|
352
|
+
a=[Date.new(2009,10,10), Date.today(),nil,"sss"].to_vector
|
353
|
+
assert(!a.can_be_date?)
|
354
|
+
end
|
355
|
+
def test_date_vector
|
356
|
+
a=[Date.new(2009,10,10), :NOW, "2009-10-10", "2009-1-1", nil, "NOW","MISSING"].to_vector(:date, :missing_values=>["MISSING"])
|
357
|
+
|
358
|
+
assert(a.type==:date)
|
359
|
+
expected=[Date.new(2009,10,10), Date.today(), Date.new(2009,10,10), Date.new(2009,1,1), nil, Date.today(), nil ]
|
360
|
+
assert_equal(expected, a.date_data_with_nils)
|
361
|
+
end
|
364
362
|
end
|