etsy / conjecture Goto Github PK

(defn opt [] (doto (FTRLOptimizer.)
               (.setBeta (double 0.1)) 
               (.setAlpha (double 0.1)) 
               (.setGaussianRegularizationWeight (double 0.00000001) )
               (.setLaplaceRegularizationWeight (double  0.00000001))
               (.setExamplesPerEpoch (double  10000.0))
               (.setUseExponentialLearningRate false)
               (.setExponentialLearningRateBase (double  0.99))
               (.setInitialLearningRate (double 0.01) )))

(defn LogRegModel []
  (doto (LogisticRegression. (opt))
    (.setTruncationPeriod (int Integer/MAX_VALUE))
    (.setTruncationThreshold (double 0.0))
    (.setTruncationUpdate (double 0.0))))

;; initialize LogisticRegression Model object:
(def m (LogRegModel))
;; a simple BinaryLabeledInstance
(def ex
  (BinaryLabeledInstance. (double 1.0) ;; label
                          (StringKeyedVector. {"height" 5.11 "weight" 165.0}))) ;; features

;; update the model with the example
(doto m (.update ex))

;; the example feature-values have changed!
(.getVector ex)

;; ==> #<StringKeyedVector {"height":-2.555,"weight":-82.5}>

[error] /Users/prasadch/Git/Conjecture/src/main/scala/com/etsy/scalding/jobs/conjecture/NNMFTest.scala:31: value updateGaussianWeighted is not a member of object com.etsy.conjecture.scalding.NNMF
[error]   val HW_ = NNMF.updateGaussianWeighted(A, HW._1, HW._2, alpha)

Caused by: java.lang.IllegalArgumentException: gaussian regularization weight must be positive, given: %f [0.0]
    at com.google.common.base.Preconditions.checkArgument(Preconditions.java:119)
    at com.etsy.conjecture.model.SGDOptimizer.setGaussianRegularizationWeight(SGDOptimizer.java:148)
    at com.etsy.conjecture.scalding.train.MulticlassModelTrainer.<init>(MulticlassModelTrainer.scala:144)
    at com.etsy.conjecture.demo.LearnMulticlassClassifier.<init>(LearnMulticlassClassifier.scala:27)

;; helper fn to create a BinaryLabeledInstance from a feature->value map
(defn map2labex
  "Create a BinaryLabeledInstance from a map and label"
  [m lab]
  (BinaryLabeledInstance. (double lab)
                          (StringKeyedVector.
                           (into {} (for [[k v] m] [k (double v)]) ) )))

(defn rand-labex
  "create a vector of n random labeled examples with d numerical features in [0,1]"
  [n d]
  (let
      [num-fields (map #(str "n" %) (range d))
       one-ex (fn [] (map2labex (zipmap num-fields (repeatedly d rand))  
                               (if (> 0.5 (rand)) 0 1 )))]  ;; random 0/1 label
    (repeatedly n one-ex)))

;; create 100 random examples with 3 numerical features in [0,1]
(def examples (rand-labex 100 3))

;; update an initial model with all 100 examples
(def final-model (reduce #(doto %1 (.update %2)) (LogRegModel) examples) )

;; model coefficients are huge:
(-> final-model .getParam .getMap)
;;==> {"n2" 5.381797927731191E49, "n1" -2.010128381640754E45, "n0" 1.2177646948602788E44}