func makeSingleFloatTargets(floats ...float64) []slice.Slice {
columnTypes, columnTypesError := columntype.StringsToColumnTypes([]string{"0"})
Ω(columnTypesError).ShouldNot(HaveOccurred())
targets := make([]slice.Slice, len(floats))
for i, f := range floats {
target, err := slice.SliceFromRawValues(true, []int{0}, columnTypes, []float64{f})
Ω(err).ShouldNot(HaveOccurred())
targets[i] = target
}
return targets
}
func DatasetFromPath(filepath string, targetStartInclusive, targetEndExclusive int) (dataset.Dataset, error) {
file, err := os.Open(filepath)
if err != nil {
return nil, csvparseerrors.NewUnableToOpenFileError(filepath, err)
}
reader := csv.NewReader(file)
_, err = reader.Read()
line, err := reader.Read()
if err != nil {
return nil, csvparseerrors.NewUnableToReadTwoLinesError(filepath, err)
}
columnTypes, err := columntype.StringsToColumnTypes(line)
if err != nil {
return nil, csvparseerrors.NewUnableToParseColumnTypesError(filepath, err)
}
numColumns := len(columnTypes)
if targetOutOfBounds(targetStartInclusive, targetEndExclusive, numColumns) {
return nil, csvparseerrors.NewTargetOutOfBoundsError(filepath, targetStartInclusive, targetEndExclusive, numColumns)
}
newDataset := dataset.NewDataset(
featureColumnIndices(targetStartInclusive, targetEndExclusive, numColumns),
targetColumnIndices(targetStartInclusive, targetEndExclusive, numColumns),
columnTypes,
)
for ; err == nil; line, err = reader.Read() {
err = newDataset.AddRowFromStrings(line)
if err != nil {
return nil, csvparseerrors.NewUnableToParseRowError(filepath, err)
}
}
if err != nil && err != io.EOF {
return nil, csvparseerrors.NewGenericError(filepath, err)
}
return newDataset, nil
}
package columntype_test
import (
"github.com/amitkgupta/goodlearn/data/columntype"
. "github.com/onsi/ginkgo"
. "github.com/onsi/gomega"
)
var _ = Describe("Column Type", func() {
Describe("StringsToColumnTypes", func() {
It("Determines whether entires are floats or strings", func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{"hi", "9.0"})
Ω(err).ShouldNot(HaveOccurred())
Ω(isStringColumnType(columnTypes[0])).Should(BeTrue())
Ω(isFloatColumnType(columnTypes[1])).Should(BeTrue())
})
It("Handles scientific notation correctly as floats", func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{"1.0e308"})
Ω(err).ShouldNot(HaveOccurred())
Ω(isFloatColumnType(columnTypes[0])).Should(BeTrue())
})
It("Handles quoted numerals correctly as strings", func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{`"9.0"`})
Ω(err).ShouldNot(HaveOccurred())
Ω(isStringColumnType(columnTypes[0])).Should(BeTrue())
trainingSet dataset.Dataset
testSet dataset.Dataset
err error
)
JustBeforeEach(func() {
trainingSet, testSet, err = crossvalidation.SplitDataset(
originalSet,
trainingRatio,
rand.NewSource(5330), // SEED
)
})
BeforeEach(func() {
columnTypes, columnTypesError := columntype.StringsToColumnTypes([]string{"0"})
Ω(columnTypesError).ShouldNot(HaveOccurred())
originalSet = dataset.NewDataset([]int{}, []int{0}, columnTypes)
})
Context("when the training ratio negative", func() {
BeforeEach(func() {
trainingRatio = -0.67
})
It("errors", func() {
Ω(err).Should(HaveOccurred())
})
})
Ω(stc.MaxDistance()).Should(Equal(initialMin - 1))
})
})
})
})
Describe("Vote", func() {
var stc knnutilities.SortedTargetCollection
Context("When the collection is not empty", func() {
var target1, target2, target3 slice.Slice
BeforeEach(func() {
stc = knnutilities.NewKNNTargetCollection(5)
columnTypes, err := columntype.StringsToColumnTypes([]string{"1.0"})
Ω(err).ShouldNot(HaveOccurred())
raw1, err := columnTypes[0].PersistRawFromString("1.0")
Ω(err).ShouldNot(HaveOccurred())
raw2, err := columnTypes[0].PersistRawFromString("2.0")
Ω(err).ShouldNot(HaveOccurred())
raw3, err := columnTypes[0].PersistRawFromString("3.0")
Ω(err).ShouldNot(HaveOccurred())
target1, err = slice.SliceFromRawValues(true, []int{0}, columnTypes, []float64{raw1})
target2, err = slice.SliceFromRawValues(true, []int{0}, columnTypes, []float64{raw2})
target3, err = slice.SliceFromRawValues(true, []int{0}, columnTypes, []float64{raw3})
})
_, err := knn.NewKNNClassifier(5)
Ω(err).ShouldNot(HaveOccurred())
})
})
})
Describe("Train", func() {
var trainingData dataset.Dataset
BeforeEach(func() {
kNNClassifier, _ = knn.NewKNNClassifier(1)
})
Context("When the dataset is empty", func() {
BeforeEach(func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{"hi", "0", "0"})
Ω(err).ShouldNot(HaveOccurred())
trainingData = dataset.NewDataset([]int{1, 2}, []int{0}, columnTypes)
})
It("Returns an error", func() {
err := kNNClassifier.Train(trainingData)
Ω(err).Should(HaveOccurred())
Ω(err).Should(BeAssignableToTypeOf(knnerrors.EmptyTrainingDatasetError{}))
})
})
Context("When the dataset's features are not all floats", func() {
BeforeEach(func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{"hi", "bye", "0"})
)
var _ = Describe("Slice", func() {
Describe("SliceFromRawValues and Values", func() {
var columnIndices []int
var columnTypes []columntype.ColumnType
var err error
var s slice.Slice
BeforeEach(func() {
columnIndices = []int{1, 4, 3}
})
Context("When all the relevant columns store float data", func() {
BeforeEach(func() {
columnTypes, err = columntype.StringsToColumnTypes([]string{"x", "1.0", "1.0", "1.0", "1.0", "1.0"})
})
Describe("When told all entires are floats", func() {
BeforeEach(func() {
s, err = slice.SliceFromRawValues(true, columnIndices, columnTypes, []float64{1.2, 0, 0, 1, 4.9, 2.2})
})
It("Does not return an error", func() {
Ω(err).ShouldNot(HaveOccurred())
})
It("Returns a float slice with the correct values", func() {
floatSlice, ok := s.(slice.FloatSlice)
Ω(ok).Should(BeTrue())
. "github.com/onsi/gomega"
)
var _ = Describe("LinearRegressor", func() {
var linearRegressor regressor.Regressor
Describe("Train", func() {
var trainingData dataset.Dataset
BeforeEach(func() {
linearRegressor = linear.NewLinearRegressor()
})
Context("When the dataset's features are not all floats", func() {
BeforeEach(func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{"3.3", "bye", "0"})
Ω(err).ShouldNot(HaveOccurred())
trainingData = dataset.NewDataset([]int{1, 2}, []int{0}, columnTypes)
})
It("Returns an error", func() {
err := linearRegressor.Train(trainingData)
Ω(err).Should(HaveOccurred())
Ω(err).Should(BeAssignableToTypeOf(linearerrors.NonFloatFeaturesTrainingSetError{}))
})
})
Context("When the dataset's targets are not all floats", func() {
BeforeEach(func() {
columnTypes, err := columntype.StringsToColumnTypes([]string{"hi", "2.3", "0"})