yogsototh/clj-ml
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

standardizes how attributes can be asked for (by index or name)

Browse source
This commit is contained in:
Ben Mabey 2010-12-07 14:14:20 -07:00
parent 99048715f1
commit 652c54aaf7
2 changed files with 34 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
src/clj_ml/data.clj
View file

@ -30,13 +30,6 @@
(instance? weka.core.Instances dataset)) (instance? weka.core.Instances dataset))
(defn attribute-name-at
"Returns the name of an attribute situated at the provided position in
the attributes definition of an instance or class"
[dataset-or-instance pos]
(let [class-attr (.attribute dataset-or-instance pos)]
(.name class-attr)))
(defn index-attr (defn index-attr
"Returns the index of an attribute in the attributes definition of an "Returns the index of an attribute in the attributes definition of an
instance or dataset" instance or dataset"
@ -46,6 +39,19 @@
(let [attr-name (name attr-name)] (let [attr-name (name attr-name)]
(find-first #(= attr-name (.name (.attribute dataset %))) (range (.numAttributes dataset)))))) (find-first #(= attr-name (.name (.attribute dataset %))) (range (.numAttributes dataset))))))
(defn attribute-at
"Returns the name of an attribute situated at the provided position in
the attributes definition of an instance or class"
[dataset-or-instance index-or-name]
(.attribute dataset-or-instance (index-attr dataset-or-instance index-or-name)))
(defn attribute-name-at
"Returns the name of an attribute situated at the provided position in
the attributes definition of an instance or class"
[dataset-or-instance index-or-name]
(let [^Attribute class-attr (attribute-at dataset-or-instance index-or-name)]
(.name class-attr)))
(defn attributes (defn attributes
"Returns the attributes (weka.core.Attribute) of the dataset or instance" "Returns the attributes (weka.core.Attribute) of the dataset or instance"
[dataset-or-instance] [dataset-or-instance]
@ -196,17 +202,32 @@
(conj acum {(keyword val) index}))) (conj acum {(keyword val) index})))
acum)))) acum))))
(defn dataset-labels-at [dataset-or-instance pos] (defn dataset-labels-at [dataset-or-instance index-or-name]
"Returns the lables (possible values) for a nominal attribute at the provided position" "Returns the lables (possible values) for a nominal attribute at the provided position"
(let [class-attr (.attribute dataset-or-instance pos) (let [attr (attribute-at dataset-or-instance index-or-name)
values (.enumerateValues class-attr)] values (.enumerateValues attr)]
(if (nil? values) (if (nil? values)
:not-nominal :not-nominal
(loop [continue (.hasMoreElements values) (loop [continue (.hasMoreElements values)
acum {}] acum {}]
(if continue (if continue
(let [val (.nextElement values) (let [val (.nextElement values)
index (.indexOfValue class-attr val)] index (.indexOfValue attr val)]
(recur (.hasMoreElements values)
(conj acum {(keyword val) index})))
acum)))))
#_(defn dataset-labels-at [dataset-or-instance index-or-name]
"Returns the lables (possible values) for a nominal attribute at the provided position"
(let [attr (attribute-at dataset-or-instance index-or-name)
values (.enumerateValues attr)]
(if (nil? values)
:not-nominal
(loop [continue (.hasMoreElements values)
acum {}]
(if continue
(let [val (.nextElement values)
index (.indexOfValue attr val)]
(recur (.hasMoreElements values) (recur (.hasMoreElements values)
(conj acum {(keyword val) index}))) (conj acum {(keyword val) index})))
acum))))) acum)))))

3
test/clj_ml/data_test.clj
View file

@ -136,6 +136,7 @@
(let [ds (make-dataset "test" [:a :b {:c [:d :e]}] [{:a 1 :b 2 :c :d} [4 5 :e]]) (let [ds (make-dataset "test" [:a :b {:c [:d :e]}] [{:a 1 :b 2 :c :d} [4 5 :e]])
attrs (attributes ds)] attrs (attributes ds)]
(is (every? #(instance? weka.core.Attribute %) attrs)) (is (every? #(instance? weka.core.Attribute %) attrs))
(is (= (first attrs) (attribute-at ds 0) (attribute-at ds :a)))
(is (= '("a" "b" "c") (map #(.name %) attrs))) (is (= '("a" "b" "c") (map #(.name %) attrs)))
(is (= '("a" "b" "c") (map #(.name %) (attributes (dataset-at ds 0))))) (is (= '("a" "b" "c") (map #(.name %) (attributes (dataset-at ds 0)))))
(is (= [(.attribute ds 2)] (nominal-attributes ds))) (is (= [(.attribute ds 2)] (nominal-attributes ds)))
@ -151,4 +152,4 @@
(let [ds (make-dataset "test" [:a :b {:c [:d :e]}] (let [ds (make-dataset "test" [:a :b {:c [:d :e]}]
[{:a 1 :b 2 :c :d} [4 5 :e]])] [{:a 1 :b 2 :c :d} [4 5 :e]])]
(dataset-set-class ds :c) (dataset-set-class ds :c)
(is (= {:d 0 :e 1} (dataset-class-labels ds) (dataset-labels-at ds 2))))) (is (= {:d 0 :e 1} (dataset-class-labels ds) (dataset-labels-at ds :c)))))