TTC will now use local copy of tcc_freq.txt

Author: bact

notebooks/pythainlp-get-started.ipynb

@@ -736,15 +736,15 @@
     {
      "data": {
       "text/plain": [
-       "[('จะ', 51681),\n",
-       " ('เป็น', 51273),\n",
-       " ('ไป', 46567),\n",
-       " ('ก็', 46409),\n",
-       " ('ไม่', 45895),\n",
-       " ('มี', 44899),\n",
-       " ('ได้', 44513),\n",
-       " ('ว่า', 40290),\n",
-       " ('ให้', 38715)]"
+       "[('งวงช้าง', 12),\n",
+       " ('เทิบทาบ', 7),\n",
+       " ('กริน', 3),\n",
+       " ('นาภี', 2),\n",
+       " ('แด่วๆ', 3),\n",
+       " ('คู่ใจ', 7),\n",
+       " ('คุณพ่อ', 732),\n",
+       " ('สิ้น', 755),\n",
+       " ('เยาะ', 150)]"
       ]
      },
      "execution_count": 28,

pythainlp/corpus/tnc.py

@@ -5,15 +5,15 @@
 Credit: Korakot Chaovavanich‎
 https://www.facebook.com/photo.php?fbid=363640477387469&set=gm.434330506948445&type=3&permPage=1
 """
-import os
 import re
 
-from pythainlp.corpus import download as download_data
-from pythainlp.corpus import get_corpus
-from pythainlp.tools import get_full_data_path
 import requests
+from pythainlp.corpus import get_corpus
+
 __all__ = ["word_freq", "word_freqs"]
 
+_FILENAME = "tnc_freq.txt"
+
 
 def word_freq(word, domain="all"):
     """
@@ -56,10 +56,10 @@ def word_freqs():
     """
     Get word frequency from Thai National Corpus (TNC)
     """
-    lines = list(get_corpus("tnc_freq.txt"))
+    lines = list(get_corpus(_FILENAME))
     listword = []
     for line in lines:
-        listindata = line.split("	")
+        listindata = line.split("\t")
         listword.append((listindata[0], int(listindata[1])))
 
     return listword

pythainlp/corpus/ttc.py

@@ -5,29 +5,22 @@
 Credit: Korakot Chaovavanich‎
 https://www.facebook.com/photo.php?fbid=363640477387469&set=gm.434330506948445&type=3&permPage=1
 """
-import os
 
-from pythainlp.corpus import download as download_data
-from pythainlp.tools import get_full_data_path
+from pythainlp.corpus import get_corpus
 
 __all__ = ["word_freqs"]
 
+_FILENAME = "ttc_freq.txt"
+
 
 def word_freqs():
     """
     Get word frequency from Thai Textbook Corpus (TTC)
     """
-    path = get_full_data_path("ttc_freq.txt")  # try local copy first
-    if not os.path.exists(path):  # if fail, download from internet
-        download_data("ttc")
-
-    with open(path, "r", encoding="utf8") as f:
-        lines = f.read().splitlines()
-    f.close()
-
+    lines = list(get_corpus(_FILENAME))
     listword = []
     for line in lines:
-        listindata = line.split("	")
+        listindata = line.split("\t")
         listword.append((listindata[0], int(listindata[1])))
 
     return listword