Golang base.NormalizePoint函数代码示例

// same as above but with StochasticGA
func TestThreeDimensionalPlaneNormalizedShouldPass2(t *testing.T) {
	var err error

	model := NewLogistic(base.StochasticGA, .0001, 0, 3000, nX, nY)
	err = model.Learn()
	assert.Nil(t, err, "Learning error should be nil")

	var guess []float64

	for i := -20; i < 20; i++ {
		for j := -20; j < 20; j++ {
			x := []float64{float64(i), float64(j)}
			base.NormalizePoint(x)

			guess, err = model.Predict(x, true)

			if x[0]+x[1] > 5 {
				assert.True(t, guess[0] > 0.5, "Guess should be more likely to be 1")
				assert.True(t, guess[0] < 1.001, "Guess should not exceed 1 ever")
			} else {
				assert.True(t, guess[0] < 0.5, "Guess should be more likely to be 0")
				assert.True(t, guess[0] > 0.0, "Guess should not be below 0 even")
			}

			assert.Len(t, guess, 1, "Length of a Logistic model output from the hypothesis should always be a 1 dimensional vector. Never multidimensional.")
			assert.Nil(t, err, "Prediction error should be nil")
		}
	}
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
func (s *Softmax) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if len(s.Parameters) != 0 && len(x)+1 != len(s.Parameters[0]) {
		return nil, fmt.Errorf("Error: Parameter vector should be 1 longer than input vector!\n\tLength of x given: %v\n\tLength of parameters: %v (len(theta[0]) = %v)\n", len(x), len(s.Parameters), len(s.Parameters[0]))
	}

	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	result := make([]float64, s.k)
	var denom float64

	for i := 0; i < s.k; i++ {
		// include constant term in sum
		sum := s.Parameters[i][0]

		for j := range x {
			sum += x[j] * s.Parameters[i][j+1]
		}

		result[i] = math.Exp(sum)
		denom += result[i]
	}

	for i := range result {
		result[i] /= denom
	}

	return result, nil
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
//
// if normalize is given as true, then the input will
// first be normalized to unit length. Only use this if
// you trained off of normalized inputs and are feeding
// an un-normalized input
func (k *KNN) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if k.K > len(k.trainingSet) {
		return nil, fmt.Errorf("Given K (%v) is greater than the length of the training set", k.K)
	}
	if len(x) != len(k.trainingSet[0]) {
		return nil, fmt.Errorf("Given x (len %v) does not match dimensions of training set", len(x))
	}

	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	// initialize neighbors with first k
	// training examples
	neighbors := make([]nn, k.K)
	length := len(k.trainingSet)
	for i := range neighbors {
		index := rand.Intn(length)
		neighbors[i] = nn{
			X: k.trainingSet[index],
			Y: k.expectedResults[index],

			Distance: k.Distance(x, k.trainingSet[index]),
		}
	}
	// calculate nearest neighbors
	var count int
	for i := range k.trainingSet {
		dist := k.Distance(x, k.trainingSet[i])
		neighbors = insertSorted(nn{
			X: k.trainingSet[i],
			Y: k.expectedResults[i],

			Distance: dist,
		}, neighbors)
		count++
	}

	// take weighted vote
	sum := 0.0
	for i := range neighbors {
		sum += neighbors[i].Y
	}

	return []float64{round(sum / float64(k.K))}, nil
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
func (p *KernelPerceptron) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	var sum float64
	for i := range p.SV {
		sum += p.SV[i].Y[0] * p.Kernel(p.SV[i].X, x)
	}

	result := -1.0
	if sum > 0 {
		result = 1
	}

	return []float64{result}, nil
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
//
// if normalize is given as true, then the input will
// first be normalized to unit length. Only use this if
// you trained off of normalized inputs and are feeding
// an un-normalized input
func (l *LeastSquares) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if len(x)+1 != len(l.Parameters) {
		return nil, fmt.Errorf("Error: Parameter vector should be 1 longer than input vector!\n\tLength of x given: %v\n\tLength of parameters: %v\n", len(x), len(l.Parameters))
	}

	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	// include constant term in sum
	sum := l.Parameters[0]

	for i := range x {
		sum += x[i] * l.Parameters[i+1]
	}

	return []float64{sum}, nil
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
//
// if normalize is given as true, then the input will
// first be normalized to unit length. Only use this if
// you trained off of normalized inputs and are feeding
// an un-normalized input
func (k *TriangleKMeans) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if len(x) != len(k.Centroids[0]) {
		return nil, fmt.Errorf("Error: Centroid vector should be the same length as input vector!\n\tLength of x given: %v\n\tLength of centroid: %v\n", len(x), len(k.Centroids[0]))
	}

	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	var guess int
	minDiff := diff(x, k.Centroids[0])
	for j := 1; j < len(k.Centroids); j++ {
		difference := diff(x, k.Centroids[j])
		if difference < minDiff {
			minDiff = difference
			guess = j
		}
	}

	return []float64{float64(guess)}, nil
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
func (p *Perceptron) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if len(x)+1 != len(p.Parameters) {
		return nil, fmt.Errorf("Error: Parameter vector should be 1 longer than input vector!\n\tLength of x given: %v\n\tLength of parameters: %v\n", len(x), len(p.Parameters))
	}

	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	// include constant term in sum
	sum := p.Parameters[0]

	for i := range x {
		sum += x[i] * p.Parameters[i+1]
	}

	result := -1.0
	if sum > 0 {
		result = 1
	}

	return []float64{result}, nil
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
//
// if normalize is given as true, then the input will
// first be normalized to unit length. Only use this if
// you trained off of normalized inputs and are feeding
// an un-normalized input
func (k *KNN) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if k.K > len(k.trainingSet) {
		return nil, fmt.Errorf("Given K (%v) is greater than the length of the training set", k.K)
	}
	if len(x) != len(k.trainingSet[0]) {
		return nil, fmt.Errorf("Given x (len %v) does not match dimensions of training set", len(x))
	}

	if len(normalize) != 0 && normalize[0] {
		base.NormalizePoint(x)
	}

	// initialize the neighbors as an empty
	// slice of Neighbors. insertSorted will
	// take care of capping the neighbors at
	// K.
	neighbors := []nn{}

	// calculate nearest neighbors
	for i := range k.trainingSet {
		dist := k.Distance(x, k.trainingSet[i])
		neighbors = insertSorted(nn{
			X: k.trainingSet[i],
			Y: k.expectedResults[i],

			Distance: dist,
		}, neighbors, k.K)
	}

	// take weighted vote
	sum := 0.0
	for i := range neighbors {
		sum += neighbors[i].Y
	}

	return []float64{round(sum / float64(k.K))}, nil
}

//.........这里部分代码省略.........
//                         Y: []float64{1.0},
//                     }
//                 } else {
//                     stream <- base.Datapoint{
//                         X: []float64{i-20},
//                         Y: []float64{0},
//                     }
//                 }
//             }
//         }()
//
//      // close the dataset
//      close(stream)
//      for {
//          err, more := <- errors
//          if err != nil {
//              fmt.Printf("Error passed: %v", err)
//          } else {
//              // training is done!
//              break
//          }
//      }
//
//      // now you can predict!!
//      // note that guess is a []float64 of len() == 1
//      // when it isn't nil
//      guess, err := model.Predict([]float64{i})
//      if err != nil {
//           panic("EGATZ!! I FOUND AN ERROR! BETTER CHECK YOUR INPUT DIMENSIONS!")
//      }
func (p *Perceptron) OnlineLearn(errors chan error, dataset chan base.Datapoint, onUpdate func([][]float64), normalize ...bool) {
	if dataset == nil {
		errors <- fmt.Errorf("ERROR: Attempting to learn with a nil data stream!\n")
		close(errors)
		return
	}

	if errors == nil {
		errors = make(chan error)
	}

	fmt.Printf("Training:\n\tModel: Perceptron Classifier\n\tOptimization Method: Online Perceptron\n\tFeatures: %v\n\tLearning Rate α: %v\n...\n\n", len(p.Parameters), p.alpha)

	norm := len(normalize) != 0 && normalize[0]

	var point base.Datapoint
	var more bool

	for {
		point, more = <-dataset

		if more {
			// have a datapoint, predict and update!
			//
			// Predict also checks if the point is of the
			// correct dimensions
			if norm {
				base.NormalizePoint(point.X)
			}

			guess, err := p.Predict(point.X)
			if err != nil {
				// send the error channel some info and
				// skip this datapoint
				errors <- err
				continue
			}

			if len(point.Y) != 1 {
				errors <- fmt.Errorf("The binary perceptron model requires that the data results (y) have length 1 - given %v", len(point.Y))
				continue
			}

			if len(point.X) != len(p.Parameters)-1 {
				errors <- fmt.Errorf("The binary perceptron model requires that the length of input data (currently %v) be one less than the length of the parameter vector (%v)", len(point.X), len(p.Parameters))
				continue
			}

			// update the parameters if the guess
			// is wrong
			if guess[0] != point.Y[0] {
				p.Parameters[0] += p.alpha * (point.Y[0] - guess[0])

				for i := 1; i < len(p.Parameters); i++ {
					p.Parameters[i] += p.alpha * (point.Y[0] - guess[0]) * point.X[i-1]
				}

				// call the OnUpdate callback with the new theta
				// appended to a blank slice so the vector is
				// passed by value and not by reference
				go onUpdate([][]float64{p.Parameters})
			}

		} else {
			fmt.Printf("Training Completed.\n%v\n\n", p)
			close(errors)
			return
		}
	}
}

//.........这里部分代码省略.........
//     // Below here all the learning is completed
//
//     // predict like usual
//     guess, err = model.Predict([]float64{42,6,10,-32})
//     if err != nil {
//         panic("AAAARGGGH! SHIVER ME TIMBERS! THESE ROTTEN SCOUNDRELS FOUND AN ERROR!!!")
//     }
func (s *Softmax) OnlineLearn(errors chan error, dataset chan base.Datapoint, onUpdate func([][]float64), normalize ...bool) {
	if errors == nil {
		errors = make(chan error)
	}
	if dataset == nil {
		errors <- fmt.Errorf("ERROR: Attempting to learn with a nil data stream!\n")
		close(errors)
		return
	}

	fmt.Fprintf(s.Output, "Training:\n\tModel: Softmax Classifier (%v classes)\n\tOptimization Method: Online Stochastic Gradient Descent\n\tFeatures: %v\n\tLearning Rate α: %v\n...\n\n", s.k, len(s.Parameters), s.alpha)

	norm := len(normalize) != 0 && normalize[0]
	var point base.Datapoint
	var more bool

	for {
		point, more = <-dataset

		if more {
			if len(point.Y) != 1 {
				errors <- fmt.Errorf("ERROR: point.Y must have a length of 1. Point: %v", point)
				continue
			}

			if norm {
				base.NormalizePoint(point.X)
			}

			// go over each parameter vector for each
			// classification value
			for k, theta := range s.Parameters {
				dj, err := func(point base.Datapoint, j int) ([]float64, error) {
					grad := make([]float64, len(s.Parameters[0]))

					// account for constant term
					x := append([]float64{1}, point.X...)

					var ident float64
					if abs(point.Y[0]-float64(k)) < 1e-3 {
						ident = 1
					}

					var numerator float64
					var denom float64
					for a := 0; a < s.k; a++ {
						var inside float64

						// calculate theta * x
						for l, val := range s.Parameters[int(k)] {
							inside += val * x[l]
						}

						if a == k {
							numerator = math.Exp(inside)
						}

						denom += math.Exp(inside)
					}

//.........这里部分代码省略.........
//
//     // Below here all the learning is completed
//
//     // predict like usual
//     guess, err = model.Predict([]float64{42,6,10,-32})
//     if err != nil {
//         panic("AAAARGGGH! SHIVER ME TIMBERS! THESE ROTTEN SCOUNDRELS FOUND AN ERROR!!!")
//     }
func (l *Logistic) OnlineLearn(errors chan error, dataset chan base.Datapoint, onUpdate func([][]float64), normalize ...bool) {
	if errors == nil {
		errors = make(chan error)
	}
	if dataset == nil {
		errors <- fmt.Errorf("ERROR: Attempting to learn with a nil data stream!\n")
		close(errors)
		return
	}

	fmt.Fprintf(l.Output, "Training:\n\tModel: Logistic (Binary) Classifier\n\tOptimization Method: Online Stochastic Gradient Descent\n\tFeatures: %v\n\tLearning Rate α: %v\n...\n\n", len(l.Parameters), l.alpha)

	norm := len(normalize) != 0 && normalize[0]
	var point base.Datapoint
	var more bool

	for {
		point, more = <-dataset

		if more {
			if len(point.Y) != 1 {
				errors <- fmt.Errorf("ERROR: point.Y must have a length of 1. Point: %v", point)
			}

			if norm {
				base.NormalizePoint(point.X)
			}

			newTheta := make([]float64, len(l.Parameters))
			for j := range l.Parameters {

				// find the gradient using the point
				// from the channel (different than
				// calling from the dataset so we need
				// to have a new function instead of calling
				// Dij(i, j))
				dj, err := func(point base.Datapoint, j int) (float64, error) {
					prediction, err := l.Predict(point.X)
					if err != nil {
						return 0, err
					}

					// account for constant term
					// x is x[i][j] via Andrew Ng's terminology
					var x float64
					if j == 0 {
						x = 1
					} else {
						x = point.X[j-1]
					}

					var gradient float64
					gradient = (point.Y[0] - prediction[0]) * x

					// add in the regularization term
					// λ*θ[j]
					//
					// notice that we don't count the

func TestLinearKernelTwoDXNormalizedShouldPass1(t *testing.T) {
	// create the channel of data and errors
	stream := make(chan base.Datapoint, 100)
	errors := make(chan error)

	model := NewKernelPerceptron(base.LinearKernel())

	go model.OnlineLearn(errors, stream, func(supportVector [][]float64) {}, true)

	for i := -200.0; abs(i) > 1; i *= -0.57 {
		for j := -200.0; abs(j) > 1; j *= -0.57 {
			x := []float64{i, j}
			base.NormalizePoint(x)

			if 5*x[0]+10*x[1]-4 > 0 {
				stream <- base.Datapoint{
					X: x,
					Y: []float64{1.0},
				}
			} else {
				stream <- base.Datapoint{
					X: x,
					Y: []float64{-1.0},
				}
			}
		}
	}

	// close the dataset
	close(stream)

	for {
		err, more := <-errors
		assert.False(t, more, "There should not be any errors!")

		if more {
			assert.Nil(t, err, "Learning error should be nil")
		} else {
			break
		}
	}

	var count int
	var incorrect int

	for i := -200.0; abs(i) > 1; i *= -0.53 {
		for j := -200.0; abs(j) > 1; j *= -0.53 {
			x := []float64{i, j}
			base.NormalizePoint(x)

			guess, err := model.Predict([]float64{i, j}, true)
			assert.Nil(t, err, "Prediction error should be nil")
			assert.Len(t, guess, 1, "Guess should have length 1")

			if 5*x[0]+10*x[1]-4 > 0 && guess[0] != 1.0 {
				incorrect++
			} else if 5*x[0]+10*x[1]-4 <= 0 && guess[0] != -1.0 {
				incorrect++
			}

			count++
		}
	}

	fmt.Printf("Predictions: %v\n\tIncorrect: %v\n\tAccuracy Rate: %v percent\n", count, incorrect, 100*(1.0-float64(incorrect)/float64(count)))
	assert.True(t, float64(incorrect)/float64(count) < 0.14, "Accuracy should be greater than 86%")
}

// Predict takes in a variable x (an array of floats,) and
// finds the value of the hypothesis function given the
// current parameter vector θ
//
// if normalize is given as true, then the input will
// first be normalized to unit length. Only use this if
// you trained off of normalized inputs and are feeding
// an un-normalized input
func (l *LocalLinear) Predict(x []float64, normalize ...bool) ([]float64, error) {
	if len(x)+1 != len(l.Parameters) {
		err := fmt.Errorf("ERROR: Parameter vector should be 1 longer than input vector!\n\tLength of x given: %v\n\tLength of parameters: %v\n", len(x), len(l.Parameters))
		print(err.Error())
		return nil, err
	}

	norm := len(normalize) != 0 && normalize[0]
	if norm {
		base.NormalizePoint(x)
	}

	if l.trainingSet == nil || l.expectedResults == nil {
		err := fmt.Errorf("ERROR: Attempting to learn with no training examples!\n")
		print(err.Error())
		return nil, err
	}

	examples := len(l.trainingSet)
	if examples == 0 || len(l.trainingSet[0]) == 0 {
		err := fmt.Errorf("ERROR: Attempting to learn with no training examples!\n")
		print(err.Error())
		return nil, err
	}
	if len(l.expectedResults) == 0 {
		err := fmt.Errorf("ERROR: Attempting to learn with no expected results! This isn't an unsupervised model!! You'll need to include data before you learn :)\n")
		print(err.Error())
		return nil, err
	}

	fmt.Printf("Training:\n\tModel: Locally Weighted Linear Regression\n\tOptimization Method: %v\n\tCenter Point: %v\n\tTraining Examples: %v\n\tFeatures: %v\n\tLearning Rate α: %v\n\tRegularization Parameter λ: %v\n...\n\n", l.method, x, examples, len(l.trainingSet[0]), l.alpha, l.regularization)

	var iter int
	features := len(l.Parameters)

	if l.method == base.BatchGA {
		for ; iter < l.maxIterations; iter++ {
			newTheta := make([]float64, features)
			for j := range l.Parameters {
				dj, err := l.Dj(x, j)
				if err != nil {
					return nil, err
				}

				newTheta[j] = l.Parameters[j] + l.alpha*dj
			}

			// now simultaneously update Theta
			for j := range l.Parameters {
				newθ := newTheta[j]
				if math.IsInf(newθ, 0) || math.IsNaN(newθ) {
					return nil, fmt.Errorf("Sorry! Learning diverged. Some value of the parameter vector theta is ±Inf or NaN")
				}
				l.Parameters[j] = newθ
			}
		}
	} else if l.method == base.StochasticGA {
		for ; iter < l.maxIterations; iter++ {
			newTheta := make([]float64, features)
			for i := 0; i < examples; i++ {
				for j := range l.Parameters {
					dj, err := l.Dij(x, i, j)
					if err != nil {
						return nil, err
					}

					newTheta[j] = l.Parameters[j] + l.alpha*dj
				}

				// now simultaneously update Theta
				for j := range l.Parameters {
					newθ := newTheta[j]
					if math.IsInf(newθ, 0) || math.IsNaN(newθ) {
						return nil, fmt.Errorf("Sorry! Learning diverged. Some value of the parameter vector theta is ±Inf or NaN")
					}
					l.Parameters[j] = newθ
				}
			}
		}
	} else {
		return nil, fmt.Errorf("Chose a training method not implemented for LocalLinear regression")
	}

	fmt.Printf("Training Completed. Went through %v iterations.\n%v\n\n", iter, l)

	// include constant term in sum
	sum := l.Parameters[0]

	for i := range x {
		sum += x[i] * l.Parameters[i+1]
	}

//.........这里部分代码省略.........

func TestOnlineTwoDXNormalizedShouldPass1(t *testing.T) {
	// create the channel of data and errors
	stream := make(chan base.Datapoint, 10000)
	errors := make(chan error, 20)

	var updates int

	model := NewLogistic(base.StochasticGA, .0001, 0, 0, nil, nil, 2)

	go model.OnlineLearn(errors, stream, func(theta [][]float64) {
		updates++
	}, true)

	var iter int
	for i := -200.0; abs(i) > 1; i *= -0.82 {
		for j := -200.0; abs(j) > 1; j *= -0.82 {
			x := []float64{i, j}
			base.NormalizePoint(x)

			if x[0]/2+2*x[1]-4 > 0 {
				stream <- base.Datapoint{
					X: []float64{i, j},
					Y: []float64{1.0},
				}
			} else {
				stream <- base.Datapoint{
					X: []float64{i, j},
					Y: []float64{-1.0},
				}
			}

			iter++
		}
	}

	// close the dataset
	close(stream)

	err, more := <-errors
	assert.Nil(t, err, "Learning error should be nil")
	assert.False(t, more, "There should be no errors returned")

	assert.True(t, updates > 100, "There should be more than 100 updates of theta")

	for i := -200.0; i < 200; i += 100 {
		for j := -200.0; j < 200; j += 100 {
			x := []float64{i, j}
			base.NormalizePoint(x)

			guess, err := model.Predict([]float64{i, j}, true)
			assert.Nil(t, err, "Prediction error should be nil")
			assert.Len(t, guess, 1, "Guess should have length 1")

			if x[0]/2+2*x[1]-4 > 0 {
				assert.True(t, 1.0 > guess[0] && guess[0] > 0.5, "Guess should be 1 for %v, %v", i, j)
			} else {
				assert.True(t, 0.0 < guess[0] && guess[0] < 0.5, "Guess should be 0 for %v, %v", i, j)
			}
		}
	}
}