Created
July 8, 2017 04:59
-
-
Save redwrasse/8b4fc708948330e0bd8b4420ade64548 to your computer and use it in GitHub Desktop.
Naive Bayes v1
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package main | |
import ( | |
"fmt" | |
"strings" | |
"crypto/sha1" | |
"encoding/base64" | |
) | |
type Document struct { | |
Text string | |
ClassLabel string | |
} | |
func (d *Document) GetClassWordCounts() map[string]int { | |
wordsMp := make(map[string]int) | |
words := strings.Split(d.Text, " ") | |
for _, w := range words { | |
wordsMp[w] += 1 | |
} | |
return wordsMp | |
} | |
func ClassWordHash(classLabel string, | |
word string) string { | |
h := sha1.New() | |
h.Write([]byte(classLabel + word)) | |
return base64.URLEncoding.EncodeToString(h.Sum(nil)) | |
} | |
type NaiveBayes struct { | |
ClassLabels map[string]bool | |
ClassWordCounts map[string]int | |
ClassWordProbs map[string]float64 | |
ClassCounts map[string]int | |
ClassProbs map[string]float64 | |
} | |
// Update probabilities upon adding new counts | |
func (nv *NaiveBayes) UpdateProbs() { | |
sm1 := 0.0 | |
for _, v := range nv.ClassWordCounts { | |
sm1 += float64(v) | |
} | |
for k, _ := range nv.ClassWordCounts { | |
nv.ClassWordProbs[k] = float64(nv.ClassWordCounts[k]) / sm1 | |
} | |
sm2 := 0.0 | |
for _, v := range nv.ClassCounts { | |
sm2 += float64(v) | |
} | |
for k, _ := range nv.ClassCounts { | |
nv.ClassProbs[k] = float64(nv.ClassCounts[k]) / sm2 | |
} | |
} | |
func (nv *NaiveBayes) Add(d Document) { | |
newCts := d.GetClassWordCounts() | |
nv.ClassCounts[d.ClassLabel] += 1 | |
nv.ClassLabels[d.ClassLabel] = true | |
for k, v := range newCts { | |
nv.ClassWordCounts[ClassWordHash(d.ClassLabel, k)] += v | |
} | |
nv.UpdateProbs() | |
} | |
func (nv *NaiveBayes) GetClassProbs(words []string) map[string]float64 { | |
classProbs := make(map[string]float64) | |
for cl, _ := range nv.ClassLabels { | |
classProbs[cl] = 1.0 | |
for _, word := range words { | |
hashKey := ClassWordHash(cl, word) | |
p := nv.ClassWordProbs[hashKey] | |
classProbs[cl] *= p | |
} | |
classProbs[cl] *= nv.ClassProbs[cl] | |
} | |
// normalize | |
sm := 0.0 | |
for _, v := range classProbs { | |
sm += v | |
} | |
// if each unnormalized class probability is zero, return zero for each | |
// otherwise normalize | |
if sm != 0.0 { | |
for k, _ := range classProbs { | |
classProbs[k] = classProbs[k] / sm | |
} | |
} | |
return classProbs | |
} | |
func main() { | |
nv := &NaiveBayes{} | |
nv.ClassLabels = make(map[string]bool) | |
nv.ClassWordCounts = make(map[string]int) | |
nv.ClassCounts = make(map[string]int) | |
nv.ClassProbs = make(map[string]float64) | |
nv.ClassWordProbs = make(map[string]float64) | |
d1 := Document{Text: "Foo Bar I", ClassLabel: "foo"} | |
d2 := Document{Text: "I Took The Bar Exam", ClassLabel: "law"} | |
for i := 0; i < 100; i++ { | |
nv.Add(d1) | |
} | |
for j := 0; j < 10; j++ { | |
nv.Add(d2) | |
} | |
words := []string{"Bar", "I"} | |
classProbs := nv.GetClassProbs(words) | |
for classLabel, prob := range classProbs { | |
fmt.Printf("(Words: %v) Class label: %s Prob: %v\n", words, classLabel, prob) | |
} | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment