mirror of
https://github.com/fumiama/jieba.git
synced 2026-06-05 00:32:51 +08:00
tweak SuggestFrequency, added example
This commit is contained in:
@@ -35,6 +35,60 @@ func Example() {
|
||||
// 【搜索引擎模式】: 小明 / 硕士 / 毕业 / 于 / 中国 / 科学 / 学院 / 科学院 / 中国科学院 / 计算 / 计算所 / , / 后 / 在 / 日本 / 京都 / 大学 / 日本京都大学 / 深造 /
|
||||
}
|
||||
|
||||
func Example_suggestFrequency() {
|
||||
var seg jiebago.Segmenter
|
||||
seg.LoadDictionary("dict.txt")
|
||||
|
||||
print := func(ch <-chan string) {
|
||||
for word := range ch {
|
||||
fmt.Printf(" %s /", word)
|
||||
}
|
||||
fmt.Println()
|
||||
}
|
||||
sentence := "超敏C反应蛋白是什么?"
|
||||
fmt.Print("Before:")
|
||||
print(seg.Cut(sentence, false))
|
||||
word := "超敏C反应蛋白"
|
||||
oldFrequency, _ := seg.Frequency(word)
|
||||
frequency := seg.SuggestFrequency(word)
|
||||
fmt.Printf("%s current frequency: %f, suggest: %f.\n", word, oldFrequency, frequency)
|
||||
seg.AddWord(word, frequency)
|
||||
fmt.Print("After:")
|
||||
print(seg.Cut(sentence, false))
|
||||
|
||||
sentence = "如果放到post中将出错"
|
||||
fmt.Print("Before:")
|
||||
print(seg.Cut(sentence, false))
|
||||
word = "中将"
|
||||
oldFrequency, _ = seg.Frequency(word)
|
||||
frequency = seg.SuggestFrequency("中", "将")
|
||||
fmt.Printf("%s current frequency: %f, suggest: %f.\n", word, oldFrequency, frequency)
|
||||
seg.AddWord(word, frequency)
|
||||
fmt.Print("After:")
|
||||
print(seg.Cut(sentence, false))
|
||||
|
||||
sentence = "今天天气不错"
|
||||
fmt.Print("Before:")
|
||||
print(seg.Cut(sentence, false))
|
||||
word = "今天天气"
|
||||
oldFrequency, _ = seg.Frequency(word)
|
||||
frequency = seg.SuggestFrequency("今天", "天气")
|
||||
fmt.Printf("%s current frequency: %f, suggest: %f.\n", word, oldFrequency, frequency)
|
||||
seg.AddWord(word, frequency)
|
||||
fmt.Print("After:")
|
||||
print(seg.Cut(sentence, false))
|
||||
// Output:
|
||||
// Before: 超敏 / C / 反应 / 蛋白 / 是 / 什么 / ? /
|
||||
// 超敏C反应蛋白 current frequency: 0.000000, suggest: 1.000000.
|
||||
// After: 超敏C反应蛋白 / 是 / 什么 / ? /
|
||||
// Before: 如果 / 放到 / post / 中将 / 出错 /
|
||||
// 中将 current frequency: 763.000000, suggest: 494.000000.
|
||||
// After: 如果 / 放到 / post / 中 / 将 / 出错 /
|
||||
// Before: 今天天气 / 不错 /
|
||||
// 今天天气 current frequency: 3.000000, suggest: 0.000000.
|
||||
// After: 今天 / 天气 / 不错 /
|
||||
}
|
||||
|
||||
func Example_loadUserDictionary() {
|
||||
var seg jiebago.Segmenter
|
||||
seg.LoadDictionary("dict.txt")
|
||||
|
||||
34
jieba.go
34
jieba.go
@@ -34,11 +34,25 @@ func (seg *Segmenter) AddWord(word string, frequency float64) {
|
||||
seg.dict.AddToken(dictionary.NewToken(word, frequency, ""))
|
||||
}
|
||||
|
||||
// Delete removes a word from dictionary
|
||||
// DeleteWord removes a word from dictionary
|
||||
func (seg *Segmenter) DeleteWord(word string) {
|
||||
seg.dict.AddToken(dictionary.NewToken(word, 0.0, ""))
|
||||
}
|
||||
|
||||
/*
|
||||
SuggestFrequency returns a suggested frequncy of a word or a long word
|
||||
cutted into several short words.
|
||||
|
||||
This method is useful when a word in the sentence is not cutted out correctly.
|
||||
|
||||
If a word should not be further cutted, for example word "石墨烯" should not be
|
||||
cutted into "石墨" and "烯", SuggestFrequency("石墨烯") will return the maximu
|
||||
frequency for this word.
|
||||
|
||||
If a word should be further cutted, for example word "今天天气" should be
|
||||
further cutted into two words "今天" and "天气", SuggestFrequency("今天", "天气")
|
||||
should return the minimum frequency for word "今天天气".
|
||||
*/
|
||||
func (seg *Segmenter) SuggestFrequency(words ...string) float64 {
|
||||
frequency := 1.0
|
||||
if len(words) > 1 {
|
||||
@@ -48,6 +62,7 @@ func (seg *Segmenter) SuggestFrequency(words ...string) float64 {
|
||||
}
|
||||
frequency /= seg.dict.total
|
||||
}
|
||||
frequency, _ = math.Modf(frequency * seg.dict.total)
|
||||
wordFreq := 0.0
|
||||
if freq, ok := seg.dict.Frequency(strings.Join(words, "")); ok {
|
||||
wordFreq = freq
|
||||
@@ -63,7 +78,8 @@ func (seg *Segmenter) SuggestFrequency(words ...string) float64 {
|
||||
}
|
||||
frequency /= seg.dict.total
|
||||
}
|
||||
frequency = frequency*seg.dict.total + 1
|
||||
frequency, _ = math.Modf(frequency * seg.dict.total)
|
||||
frequency += 1.0
|
||||
wordFreq := 1.0
|
||||
if freq, ok := seg.dict.Frequency(word); ok {
|
||||
wordFreq = freq
|
||||
@@ -223,14 +239,14 @@ func (seg *Segmenter) cutDAGNoHMM(sentence string) <-chan string {
|
||||
if reEng.MatchString(string(frag)) && len(frag) == 1 {
|
||||
buf = append(buf, frag...)
|
||||
x = y
|
||||
} else {
|
||||
if len(buf) > 0 {
|
||||
result <- string(buf)
|
||||
buf = make([]rune, 0)
|
||||
}
|
||||
result <- string(frag)
|
||||
x = y
|
||||
continue
|
||||
}
|
||||
if len(buf) > 0 {
|
||||
result <- string(buf)
|
||||
buf = make([]rune, 0)
|
||||
}
|
||||
result <- string(frag)
|
||||
x = y
|
||||
}
|
||||
if len(buf) > 0 {
|
||||
result <- string(buf)
|
||||
|
||||
Reference in New Issue
Block a user