wannaphong

# -*- coding: utf-8 -*-
"""Print most frequent N-grams in given file.

Usage: python ngrams.py filename

Problem description: Build a tool which receives a corpus of text,
analyses it and reports the top 10 most frequent bigrams, trigrams,
four-grams (i.e. most frequently occurring two, three and four word
consecutive combinations).

wannaphong

>>> import spacy
>>> th_nlp = spacy.load('th')
>>> text="คุณรักผมไหม"
>>> a= th_nlp(text)
>>> a
คุณรักผมไหม
>>> list(a)
[คุณ, รัก, ผม, ไหม]

wannaphong

คน
เล่น
แกม
ตา
จน

wannaphong

>>> from spacy.lang.th import Thai
>>> nlp = Thai()
>>> text="คุณรักผมไหม"
>>> a = nlp(text)
>>> a
คุณรักผมไหม
>>> list(a)
[คุณ, รัก, ผม, ไหม]

wannaphong

import face_recognition
picture_of_Steve_Jobs = face_recognition.load_image_file("Steve_Jobs_Headshot_2010-CROP.jpg") # ไฟล์ต้นแบบ
face_encoding = face_recognition.face_encodings(picture_of_Steve_Jobs)[0] # เข้ารหัสหน้าตา
unknown_picture = face_recognition.load_image_file("0x600.jpg") # ไฟล์ที่ต้องการตรวจสอบ
unknown_face_encoding = face_recognition.face_encodings(unknown_picture)[0] # เข้ารหัสหน้าตา
results = face_recognition.compare_faces([face_encoding], unknown_face_encoding) # ทำการเปรียบเทียบด้วย Face Recognition
if results[0] == True:
  print("It's a picture of Steve Jobs!")
else:
  print("It's not a Steve Jobs!")

wannaphong

from nltk.corpus import wordnet
class thaiwordnet:
  def __init__(self):
    self._wordnet = wordnet
  def synsets(self, word, pos=None, lang="tha"):
    return self._wordnet.synsets(lemma=word,pos=pos,lang=lang)
  def synset(self,name_synsets):
    return self._wordnet.synset(name_synsets)
  def all_lemma_names(self,pos=None, lang="tha"):
    return self._wordnet.all_lemma_names(pos=pos, lang=lang)

wannaphong

<div class='post-share-buttons'>
<iframe allowTransparency='true' expr:src='&quot;https://www.facebook.com/plugins/like.php?href=&quot; + data:post.canonicalUrl + &quot;&amp;layout=box_count&amp;show_faces=false&amp;width=100&amp;action=like&amp;font=arial&amp;colorscheme=light&quot;' frameborder='0' scrolling='no' style='border:none; overflow:hidden; width:55px; height:62px;'/>
<iframe allowTransparency='true' expr:src='&quot;https://www.facebook.com/plugins/share_button.php?href=&quot; + data:post.canonicalUrl + &quot;&amp;layout=box_count&amp;show_faces=false&amp;width=100&amp;action=like&amp;font=arial&amp;colorscheme=light&quot;' frameborder='0' scrolling='no' style='border:none; overflow:hidden; width:55px; height:62px;'/>
<br />
<b:include data='post' name='shareButtons'/>
</div>

wannaphong

<provider
            android:name="android.support.v4.content.FileProvider"
            android:authorities="${applicationId}.provider"
            android:exported="false"
            android:grantUriPermissions="true">
            <meta-data
                android:name="android.support.FILE_PROVIDER_PATHS"
                android:resource="@xml/provider_paths"/>
        </provider>

wannaphong

# -*- coding: utf-8 -*-
"""Implementation of Rapid Automatic Keyword Extraction algorithm.

As described in the paper `Automatic keyword extraction from individual
documents` by Stuart Rose, Dave Engel, Nick Cramer and Wendy Cowley.

Thai language by Mr.Wannaphong Phatthiyaphaibun <wannaphong@kkumail.com>
"""

import string

wannaphong

// เดติดต้นฉบับจาก http://vuthi.blogspot.com.au/2004/08/java.html
public String icu_word_segmentation(String txt){
        Locale thaiLocale = new Locale("th");
        BreakIterator boundary = BreakIterator.getWordInstance(thaiLocale);
        boundary.setText(txt);
        StringBuffer strout = new StringBuffer();
        int start = boundary.first();
        for (int end = boundary.next();
            end != BreakIterator.DONE;
            start = end, end = boundary.next()) {