From b9b368545f70b5b0c7d894cb66349b8baa5a5679 Mon Sep 17 00:00:00 2001 From: Muthiah Annamalai Date: Sat, 18 Aug 2018 09:50:50 -0700 Subject: [PATCH] Tamil Morse code using Project Madurai data --- examples/tamilmorse/madurai_unigram.json | 1 + examples/tamilmorse/tamil_morse_code.py | 28 ++- solthiruthi/data/madurai_unigram.json | 1 + solthiruthi/data/madurai_unigram.txt | 293 +++++++++++++++++++++++ 4 files changed, 317 insertions(+), 6 deletions(-) create mode 100644 examples/tamilmorse/madurai_unigram.json create mode 100644 solthiruthi/data/madurai_unigram.json create mode 100644 solthiruthi/data/madurai_unigram.txt diff --git a/examples/tamilmorse/madurai_unigram.json b/examples/tamilmorse/madurai_unigram.json new file mode 100644 index 0000000..7044762 --- /dev/null +++ b/examples/tamilmorse/madurai_unigram.json @@ -0,0 +1 @@ +{"\u0bb7\u0bcc": 1.0, "\u0b85": 252521.0, "\u0bb9\u0bbf": 422.0, "\u0b89": 114865.0, "\u0bb7\u0bcb": 36.0, "\u0bb7\u0bca": 2.0, "\u0bb5\u0bcd": 21881.0, "\u0bb5\u0bcc": 529.0, "\u0b95": 774635.0, "\u0bb5\u0bc8": 48136.0, "\u0bb5\u0bcb": 11022.0, "\u0bb5\u0bca": 5789.0, "\u0b99": 1530.0, "\u0bb5\u0bc7": 76558.0, "\u0bb5\u0bc6": 53903.0, "\u0bb5\u0bc1": 75941.0, "\u0bb5\u0bc0": 26158.0, "\u0b9c\u0bc8": 438.0, "\u0bb5\u0bc2": 2542.0, "\u0ba4\u0bcc": 180.0, "\u0ba4\u0bcd": 540767.0, "\u0ba4\u0bca": 39591.0, "\u0ba9\u0bbf": 85378.0, "\u0ba4\u0bc8": 74444.0, "\u0baa\u0bcd": 345626.0, "\u0ba9": 242198.0, "\u0ba4\u0bc7": 60822.0, "\u0ba4\u0bc2": 15680.0, "\u0ba4\u0bc0": 22597.0, "\u0ba4\u0bc1": 395602.0, "\u0bb1": 189701.0, "\u0bb5": 472124.0, "\u0bae\u0bbe": 147356.0, "\u0bae\u0bbf": 73393.0, "\u0bb9": 1175.0, "\u0bb0\u0bca": 4135.0, "\u0b9c\u0bcb": 511.0, "\u0bb9\u0bc1": 98.0, "\u0bae\u0bc8": 73801.0, "\u0bae\u0bca": 18422.0, "\u0bae\u0bcb": 12860.0, "\u0bae\u0bcc": 649.0, "\u0bae\u0bcd": 621683.0, "\u0bae\u0bc0": 12201.0, "\u0bae\u0bc1": 166201.0, "\u0bae\u0bc2": 19880.0, "\u0bae\u0bc6": 38364.0, "\u0bae\u0bc7": 53458.0, "\u0ba4\u0bbe": 164244.0, "\u0ba4\u0bbf": 354355.0, "\u0b9e\u0bc7": 41.0, "\u0b9c\u0bc6": 538.0, "\u0bb5\u0bbf": 251004.0, "\u0bb5\u0bbe": 136684.0, "\u0bb1\u0bcc": 1.0, "\u0b9c\u0bc7": 173.0, "\u0b9c\u0bbe": 2153.0, "\u0b9c\u0bbf": 862.0, "\u0b9f\u0bc6": 5798.0, "\u0bb8\u0bbf": 845.0, "\u0b9c\u0bc2": 83.0, "\u0baf\u0bcd": 145377.0, "\u0baf\u0bcc": 66.0, "\u0baf\u0bcb": 24095.0, "\u0baf\u0bca": 9965.0, "\u0b86": 68845.0, "\u0baf\u0bc7": 41717.0, "\u0baf\u0bc6": 28882.0, "\u0b8a": 11458.0, "\u0baf\u0bc2": 4575.0, "\u0baf\u0bc1": 118962.0, "\u0b8e": 112762.0, "\u0b9e\u0bc8": 735.0, "\u0b9e\u0bca": 8.0, "\u0b92": 41876.0, "\u0bb8\u0bbe": 556.0, "\u0b9e\u0bcd": 61923.0, "\u0b9e\u0bc0": 197.0, "\u0b9e\u0bc1": 22.0, "\u0b9e\u0bc2": 59.0, "\u0b9a": 119945.0, "\u0b9e\u0bc6": 350.0, "\u0b9e": 3453.0, "\u0b9f\u0bbf": 199482.0, "\u0b9f\u0bbe": 53287.0, "\u0b9c\u0bcd": 1280.0, "\u0bb7\u0bc2": 63.0, "\u0bb7\u0bc1": 229.0, "\u0bb7\u0bc0": 37.0, "\u0b9c\u0bca": 99.0, "\u0bb7\u0bcd": 4559.0, "\u0baa": 370431.0, "\u0bb0\u0bbe": 61895.0, "\u0bb0\u0bbf": 139808.0, "\u0bae": 299013.0, "\u0b95\u0bcd": 527909.0, "\u0b95\u0bcc": 697.0, "\u0bb2": 199855.0, "\u0b95\u0bc8": 75850.0, "\u0b95\u0bcb": 36032.0, "\u0b95\u0bca": 97975.0, "\u0b95\u0bc7": 33291.0, "\u0b95\u0bc6": 17833.0, "\u0b95\u0bc1": 338725.0, "\u0b95\u0bc0": 7403.0, "\u0b94": 367.0, "\u0b95\u0bc2": 42581.0, "\u0b95\u0bbf": 212583.0, "\u0b95\u0bbe": 145079.0, "\u0bb9\u0bcb": 240.0, "\u0bb0\u0bc2": 3683.0, "\u0b9f\u0bcd": 212838.0, "\u0bb0\u0bc1": 391928.0, "\u0bb0\u0bc6": 10822.0, "\u0bb0\u0bc7": 13756.0, "\u0b9f\u0bc8": 104237.0, "\u0b9f\u0bc7": 11481.0, "\u0bb0\u0bcb": 9739.0, "\u0bb0\u0bc8": 73132.0, "\u0b9f\u0bc2": 1244.0, "\u0b9f\u0bc1": 243848.0, "\u0bb0\u0bcd": 441925.0, "\u0bb8\u0bca": 11.0, "\u0bb8\u0bcb": 44.0, "\u0bb8\u0bc8": 176.0, "\u0b9e\u0bbe": 7297.0, "\u0bb8\u0bcd": 10491.0, "\u0bb8\u0bc2": 119.0, "\u0bb7\u0bc6": 36.0, "\u0bb8\u0bc0": 143.0, "\u0bb8\u0bc1": 261.0, "\u0bb8\u0bc6": 85.0, "\u0bb0\u0bc0": 4011.0, "\u0baf\u0bbf": 169555.0, "\u0baf\u0bbe": 139367.0, "\u0b9f\u0bcc": 24.0, "\u0b9c\u0bc1": 231.0, "\u0b9f\u0bcb": 4948.0, "\u0b9f\u0bca": 3035.0, "\u0b83": 1861.0, "\u0bb9\u0bc2": 61.0, "\u0b87": 162272.0, "\u0ba9\u0bbe": 78966.0, "\u0b99\u0bc2": 2.0, "\u0b8f": 26171.0, "\u0bb1\u0bc1": 169031.0, "\u0bb1\u0bc0": 4199.0, "\u0b93": 16942.0, "\u0bb1\u0bc2": 1336.0, "\u0bb9\u0bc7": 74.0, "\u0bb1\u0bc7": 19030.0, "\u0bb1\u0bc6": 8828.0, "\u0bb1\u0bc8": 65921.0, "\u0bb1\u0bcb": 9447.0, "\u0bb1\u0bca": 5216.0, "\u0bb1\u0bcd": 261277.0, "\u0bb7\u0bc8": 525.0, "\u0b9f": 267257.0, "\u0bb9\u0bc8": 95.0, "\u0ba3": 88135.0, "\u0bb9\u0bca": 30.0, "\u0bb9\u0bcd": 180.0, "\u0bb9\u0bcc": 12.0, "\u0bb7\u0bbf": 1073.0, "\u0bb9\u0bc0": 93.0, "\u0bb2\u0bbe": 85850.0, "\u0bb2\u0bbf": 86421.0, "\u0b9e\u0bcb": 30.0, "\u0ba8\u0bc8": 1052.0, "\u0baf": 328267.0, "\u0bb9\u0bc6": 60.0, "\u0ba8\u0bca": 1900.0, "\u0ba8\u0bcb": 10117.0, "\u0bb3": 101777.0, "\u0bb4\u0bc0": 907.0, "\u0bb7": 6891.0, "\u0ba8\u0bcd": 369333.0, "\u0ba8\u0bc2": 8576.0, "\u0ba8\u0bc0": 36899.0, "\u0ba8\u0bc1": 9398.0, "\u0ba8\u0bc6": 23529.0, "\u0ba8\u0bc7": 10853.0, "\u0b99\u0bcb": 1.0, "\u0b99\u0bca": 11.0, "\u0b99\u0bcd": 241771.0, "\u0ba8\u0bbf": 84254.0, "\u0bb3\u0bcc": 3.0, "\u0b99\u0bc1": 18.0, "\u0b99\u0bbe": 5.0, "\u0b99\u0bc7": 4.0, "\u0bb2\u0bc6": 10211.0, "\u0bb2\u0bc7": 29612.0, "\u0bb2\u0bc0": 2042.0, "\u0bb2\u0bc1": 68471.0, "\u0bb2\u0bc2": 1916.0, "\u0bb9\u0bbe": 1042.0, "\u0bb2\u0bcc": 23.0, "\u0bb2\u0bcd": 403345.0, "\u0baf\u0bc0": 2946.0, "\u0bb2\u0bc8": 121144.0, "\u0bb2\u0bca": 4179.0, "\u0bb2\u0bcb": 10682.0, "\u0b9e\u0bcc": 10.0, "\u0bb8\u0bcc": 26.0, "\u0bb3\u0bca": 1759.0, "\u0bb0\u0bcc": 76.0, "\u0b9e\u0bbf": 130.0, "\u0ba4\u0bcb": 40740.0, "\u0bb1\u0bbf": 135924.0, "\u0bb1\u0bbe": 57305.0, "\u0ba9\u0bc8": 107583.0, "\u0ba9\u0bcb": 11248.0, "\u0ba9\u0bca": 4973.0, "\u0ba9\u0bcd": 657842.0, "\u0ba9\u0bcc": 11.0, "\u0bb7\u0bbe": 541.0, "\u0ba9\u0bc1": 74745.0, "\u0ba9\u0bc0": 3355.0, "\u0ba9\u0bc2": 1994.0, "\u0ba9\u0bc7": 27384.0, "\u0ba9\u0bc6": 13510.0, "\u0b9a\u0bcc": 584.0, "\u0b9a\u0bcd": 120634.0, "\u0b9a\u0bc8": 31470.0, "\u0b9a\u0bca": 30463.0, "\u0b9a\u0bcb": 11006.0, "\u0b88": 9613.0, "\u0b9a\u0bc6": 95350.0, "\u0b9a\u0bc7": 25194.0, "\u0b9a\u0bc0": 12270.0, "\u0b9a\u0bc1": 58661.0, "\u0b9a\u0bc2": 16193.0, "\u0bb8\u0bc7": 71.0, "\u0bb3\u0bcb": 5028.0, "\u0b90": 6967.0, "\u0bb3\u0bc8": 71868.0, "\u0ba3\u0bbf": 60469.0, "\u0ba3\u0bbe": 12196.0, "\u0bb3\u0bcd": 211262.0, "\u0bb3\u0bc2": 942.0, "\u0ba8\u0bbe": 62223.0, "\u0bb3\u0bc1": 49515.0, "\u0bb3\u0bc0": 987.0, "\u0bb3\u0bc7": 11079.0, "\u0bb3\u0bc6": 5783.0, "\u0bb4\u0bbe": 6186.0, "\u0bb4\u0bbf": 68970.0, "\u0b99\u0bbf": 1.0, "\u0ba4": 566469.0, "\u0b9c\u0bc0": 500.0, "\u0ba8": 92960.0, "\u0baf\u0bc8": 46276.0, "\u0b9c": 5714.0, "\u0baa\u0bcc": 387.0, "\u0bb0": 243877.0, "\u0ba8\u0bcc": 18.0, "\u0baa\u0bc8": 12780.0, "\u0bb4": 58801.0, "\u0baa\u0bca": 62712.0, "\u0baa\u0bcb": 82205.0, "\u0bb8": 2250.0, "\u0baa\u0bc6": 66538.0, "\u0baa\u0bc7": 30690.0, "\u0baa\u0bc0": 4219.0, "\u0baa\u0bc1": 146058.0, "\u0baa\u0bc2": 25286.0, "\u0bb7\u0bc7": 478.0, "\u0baa\u0bbe": 116682.0, "\u0baa\u0bbf": 118648.0, "\u0ba4\u0bc6": 47579.0, "\u0bb4\u0bcc": 2.0, "\u0bb4\u0bcd": 56156.0, "\u0bb4\u0bca": 270.0, "\u0bb4\u0bcb": 283.0, "\u0bb4\u0bc8": 23614.0, "\u0bb4\u0bc6": 493.0, "\u0bb4\u0bc7": 758.0, "\u0bb4\u0bc2": 298.0, "\u0b9f\u0bc0": 2902.0, "\u0bb4\u0bc1": 67835.0, "\u0ba3\u0bcb": 1325.0, "\u0ba3\u0bca": 611.0, "\u0ba3\u0bc8": 22128.0, "\u0bb3\u0bbf": 93496.0, "\u0bb3\u0bbe": 28154.0, "\u0ba3\u0bcd": 231490.0, "\u0ba3\u0bc2": 458.0, "\u0ba3\u0bc1": 17030.0, "\u0ba3\u0bc0": 2995.0, "\u0ba3\u0bc7": 1997.0, "\u0ba3\u0bc6": 2372.0, "\u0b9a\u0bbe": 40004.0, "\u0b9a\u0bbf": 123619.0} \ No newline at end of file diff --git a/examples/tamilmorse/tamil_morse_code.py b/examples/tamilmorse/tamil_morse_code.py index 850789f..c2a37d0 100644 --- a/examples/tamilmorse/tamil_morse_code.py +++ b/examples/tamilmorse/tamil_morse_code.py @@ -13,8 +13,17 @@ from solthiruthi import resources from huffman import huffman, print_huffman_code_cwl -def build_morse_code(): +def TVU_morse_code(): + # unigram data from Project Madurai unigram = TamilUnigramStats().unigram + build_morse_code(unigram) + +def Madurai_morse_code(): + # unigram data from Project Madurai + unigram = TamilUnigramStats().unigram + build_morse_code(unigram) + +def build_morse_code(unigram): v_keys = unigram.keys() p = [unigram[k] for k in v_keys] code,_ = huffman(v_keys,p) @@ -32,10 +41,10 @@ def build_morse_code(): fp.write( json.dumps(tamilmorse) ) return -class TamilUnigramStats: - def __init__(self): +class UnigramStats: + def __init__(self,filename): self.unigram = {} # Tamil letter -> probability of occurence - self.unigram_file = resources.mk_path("tvu_unigram.txt") + self.unigram_file = resources.mk_path(filename) with codecs.open(self.unigram_file,"r","utf-8") as fp: for L in fp.readlines(): a,b = L.split("-") @@ -45,8 +54,15 @@ def __init__(self): normalize = 1+sum(self.unigram.values()) for k,v in self.unigram.items(): self.unigram[k] = v/normalize - + +class TamilUnigramStats(UnigramStats): + def __init__(self): + UnigramStats.__init__(self,"tvu_unigram.txt") + +class MaduraiUnigramStats(UnigramStats): + def __init__(self): + UnigramStats.__init__(self,"madurai_unigram.txt") if __name__ == u"__main__": - build_morse_code() + Madurai_morse_code() diff --git a/solthiruthi/data/madurai_unigram.json b/solthiruthi/data/madurai_unigram.json new file mode 100644 index 0000000..7044762 --- /dev/null +++ b/solthiruthi/data/madurai_unigram.json @@ -0,0 +1 @@ +{"\u0bb7\u0bcc": 1.0, "\u0b85": 252521.0, "\u0bb9\u0bbf": 422.0, "\u0b89": 114865.0, "\u0bb7\u0bcb": 36.0, "\u0bb7\u0bca": 2.0, "\u0bb5\u0bcd": 21881.0, "\u0bb5\u0bcc": 529.0, "\u0b95": 774635.0, "\u0bb5\u0bc8": 48136.0, "\u0bb5\u0bcb": 11022.0, "\u0bb5\u0bca": 5789.0, "\u0b99": 1530.0, "\u0bb5\u0bc7": 76558.0, "\u0bb5\u0bc6": 53903.0, "\u0bb5\u0bc1": 75941.0, "\u0bb5\u0bc0": 26158.0, "\u0b9c\u0bc8": 438.0, "\u0bb5\u0bc2": 2542.0, "\u0ba4\u0bcc": 180.0, "\u0ba4\u0bcd": 540767.0, "\u0ba4\u0bca": 39591.0, "\u0ba9\u0bbf": 85378.0, "\u0ba4\u0bc8": 74444.0, "\u0baa\u0bcd": 345626.0, "\u0ba9": 242198.0, "\u0ba4\u0bc7": 60822.0, "\u0ba4\u0bc2": 15680.0, "\u0ba4\u0bc0": 22597.0, "\u0ba4\u0bc1": 395602.0, "\u0bb1": 189701.0, "\u0bb5": 472124.0, "\u0bae\u0bbe": 147356.0, "\u0bae\u0bbf": 73393.0, "\u0bb9": 1175.0, "\u0bb0\u0bca": 4135.0, "\u0b9c\u0bcb": 511.0, "\u0bb9\u0bc1": 98.0, "\u0bae\u0bc8": 73801.0, "\u0bae\u0bca": 18422.0, "\u0bae\u0bcb": 12860.0, "\u0bae\u0bcc": 649.0, "\u0bae\u0bcd": 621683.0, "\u0bae\u0bc0": 12201.0, "\u0bae\u0bc1": 166201.0, "\u0bae\u0bc2": 19880.0, "\u0bae\u0bc6": 38364.0, "\u0bae\u0bc7": 53458.0, "\u0ba4\u0bbe": 164244.0, "\u0ba4\u0bbf": 354355.0, "\u0b9e\u0bc7": 41.0, "\u0b9c\u0bc6": 538.0, "\u0bb5\u0bbf": 251004.0, "\u0bb5\u0bbe": 136684.0, "\u0bb1\u0bcc": 1.0, "\u0b9c\u0bc7": 173.0, "\u0b9c\u0bbe": 2153.0, "\u0b9c\u0bbf": 862.0, "\u0b9f\u0bc6": 5798.0, "\u0bb8\u0bbf": 845.0, "\u0b9c\u0bc2": 83.0, "\u0baf\u0bcd": 145377.0, "\u0baf\u0bcc": 66.0, "\u0baf\u0bcb": 24095.0, "\u0baf\u0bca": 9965.0, "\u0b86": 68845.0, "\u0baf\u0bc7": 41717.0, "\u0baf\u0bc6": 28882.0, "\u0b8a": 11458.0, "\u0baf\u0bc2": 4575.0, "\u0baf\u0bc1": 118962.0, "\u0b8e": 112762.0, "\u0b9e\u0bc8": 735.0, "\u0b9e\u0bca": 8.0, "\u0b92": 41876.0, "\u0bb8\u0bbe": 556.0, "\u0b9e\u0bcd": 61923.0, "\u0b9e\u0bc0": 197.0, "\u0b9e\u0bc1": 22.0, "\u0b9e\u0bc2": 59.0, "\u0b9a": 119945.0, "\u0b9e\u0bc6": 350.0, "\u0b9e": 3453.0, "\u0b9f\u0bbf": 199482.0, "\u0b9f\u0bbe": 53287.0, "\u0b9c\u0bcd": 1280.0, "\u0bb7\u0bc2": 63.0, "\u0bb7\u0bc1": 229.0, "\u0bb7\u0bc0": 37.0, "\u0b9c\u0bca": 99.0, "\u0bb7\u0bcd": 4559.0, "\u0baa": 370431.0, "\u0bb0\u0bbe": 61895.0, "\u0bb0\u0bbf": 139808.0, "\u0bae": 299013.0, "\u0b95\u0bcd": 527909.0, "\u0b95\u0bcc": 697.0, "\u0bb2": 199855.0, "\u0b95\u0bc8": 75850.0, "\u0b95\u0bcb": 36032.0, "\u0b95\u0bca": 97975.0, "\u0b95\u0bc7": 33291.0, "\u0b95\u0bc6": 17833.0, "\u0b95\u0bc1": 338725.0, "\u0b95\u0bc0": 7403.0, "\u0b94": 367.0, "\u0b95\u0bc2": 42581.0, "\u0b95\u0bbf": 212583.0, "\u0b95\u0bbe": 145079.0, "\u0bb9\u0bcb": 240.0, "\u0bb0\u0bc2": 3683.0, "\u0b9f\u0bcd": 212838.0, "\u0bb0\u0bc1": 391928.0, "\u0bb0\u0bc6": 10822.0, "\u0bb0\u0bc7": 13756.0, "\u0b9f\u0bc8": 104237.0, "\u0b9f\u0bc7": 11481.0, "\u0bb0\u0bcb": 9739.0, "\u0bb0\u0bc8": 73132.0, "\u0b9f\u0bc2": 1244.0, "\u0b9f\u0bc1": 243848.0, "\u0bb0\u0bcd": 441925.0, "\u0bb8\u0bca": 11.0, "\u0bb8\u0bcb": 44.0, "\u0bb8\u0bc8": 176.0, "\u0b9e\u0bbe": 7297.0, "\u0bb8\u0bcd": 10491.0, "\u0bb8\u0bc2": 119.0, "\u0bb7\u0bc6": 36.0, "\u0bb8\u0bc0": 143.0, "\u0bb8\u0bc1": 261.0, "\u0bb8\u0bc6": 85.0, "\u0bb0\u0bc0": 4011.0, "\u0baf\u0bbf": 169555.0, "\u0baf\u0bbe": 139367.0, "\u0b9f\u0bcc": 24.0, "\u0b9c\u0bc1": 231.0, "\u0b9f\u0bcb": 4948.0, "\u0b9f\u0bca": 3035.0, "\u0b83": 1861.0, "\u0bb9\u0bc2": 61.0, "\u0b87": 162272.0, "\u0ba9\u0bbe": 78966.0, "\u0b99\u0bc2": 2.0, "\u0b8f": 26171.0, "\u0bb1\u0bc1": 169031.0, "\u0bb1\u0bc0": 4199.0, "\u0b93": 16942.0, "\u0bb1\u0bc2": 1336.0, "\u0bb9\u0bc7": 74.0, "\u0bb1\u0bc7": 19030.0, "\u0bb1\u0bc6": 8828.0, "\u0bb1\u0bc8": 65921.0, "\u0bb1\u0bcb": 9447.0, "\u0bb1\u0bca": 5216.0, "\u0bb1\u0bcd": 261277.0, "\u0bb7\u0bc8": 525.0, "\u0b9f": 267257.0, "\u0bb9\u0bc8": 95.0, "\u0ba3": 88135.0, "\u0bb9\u0bca": 30.0, "\u0bb9\u0bcd": 180.0, "\u0bb9\u0bcc": 12.0, "\u0bb7\u0bbf": 1073.0, "\u0bb9\u0bc0": 93.0, "\u0bb2\u0bbe": 85850.0, "\u0bb2\u0bbf": 86421.0, "\u0b9e\u0bcb": 30.0, "\u0ba8\u0bc8": 1052.0, "\u0baf": 328267.0, "\u0bb9\u0bc6": 60.0, "\u0ba8\u0bca": 1900.0, "\u0ba8\u0bcb": 10117.0, "\u0bb3": 101777.0, "\u0bb4\u0bc0": 907.0, "\u0bb7": 6891.0, "\u0ba8\u0bcd": 369333.0, "\u0ba8\u0bc2": 8576.0, "\u0ba8\u0bc0": 36899.0, "\u0ba8\u0bc1": 9398.0, "\u0ba8\u0bc6": 23529.0, "\u0ba8\u0bc7": 10853.0, "\u0b99\u0bcb": 1.0, "\u0b99\u0bca": 11.0, "\u0b99\u0bcd": 241771.0, "\u0ba8\u0bbf": 84254.0, "\u0bb3\u0bcc": 3.0, "\u0b99\u0bc1": 18.0, "\u0b99\u0bbe": 5.0, "\u0b99\u0bc7": 4.0, "\u0bb2\u0bc6": 10211.0, "\u0bb2\u0bc7": 29612.0, "\u0bb2\u0bc0": 2042.0, "\u0bb2\u0bc1": 68471.0, "\u0bb2\u0bc2": 1916.0, "\u0bb9\u0bbe": 1042.0, "\u0bb2\u0bcc": 23.0, "\u0bb2\u0bcd": 403345.0, "\u0baf\u0bc0": 2946.0, "\u0bb2\u0bc8": 121144.0, "\u0bb2\u0bca": 4179.0, "\u0bb2\u0bcb": 10682.0, "\u0b9e\u0bcc": 10.0, "\u0bb8\u0bcc": 26.0, "\u0bb3\u0bca": 1759.0, "\u0bb0\u0bcc": 76.0, "\u0b9e\u0bbf": 130.0, "\u0ba4\u0bcb": 40740.0, "\u0bb1\u0bbf": 135924.0, "\u0bb1\u0bbe": 57305.0, "\u0ba9\u0bc8": 107583.0, "\u0ba9\u0bcb": 11248.0, "\u0ba9\u0bca": 4973.0, "\u0ba9\u0bcd": 657842.0, "\u0ba9\u0bcc": 11.0, "\u0bb7\u0bbe": 541.0, "\u0ba9\u0bc1": 74745.0, "\u0ba9\u0bc0": 3355.0, "\u0ba9\u0bc2": 1994.0, "\u0ba9\u0bc7": 27384.0, "\u0ba9\u0bc6": 13510.0, "\u0b9a\u0bcc": 584.0, "\u0b9a\u0bcd": 120634.0, "\u0b9a\u0bc8": 31470.0, "\u0b9a\u0bca": 30463.0, "\u0b9a\u0bcb": 11006.0, "\u0b88": 9613.0, "\u0b9a\u0bc6": 95350.0, "\u0b9a\u0bc7": 25194.0, "\u0b9a\u0bc0": 12270.0, "\u0b9a\u0bc1": 58661.0, "\u0b9a\u0bc2": 16193.0, "\u0bb8\u0bc7": 71.0, "\u0bb3\u0bcb": 5028.0, "\u0b90": 6967.0, "\u0bb3\u0bc8": 71868.0, "\u0ba3\u0bbf": 60469.0, "\u0ba3\u0bbe": 12196.0, "\u0bb3\u0bcd": 211262.0, "\u0bb3\u0bc2": 942.0, "\u0ba8\u0bbe": 62223.0, "\u0bb3\u0bc1": 49515.0, "\u0bb3\u0bc0": 987.0, "\u0bb3\u0bc7": 11079.0, "\u0bb3\u0bc6": 5783.0, "\u0bb4\u0bbe": 6186.0, "\u0bb4\u0bbf": 68970.0, "\u0b99\u0bbf": 1.0, "\u0ba4": 566469.0, "\u0b9c\u0bc0": 500.0, "\u0ba8": 92960.0, "\u0baf\u0bc8": 46276.0, "\u0b9c": 5714.0, "\u0baa\u0bcc": 387.0, "\u0bb0": 243877.0, "\u0ba8\u0bcc": 18.0, "\u0baa\u0bc8": 12780.0, "\u0bb4": 58801.0, "\u0baa\u0bca": 62712.0, "\u0baa\u0bcb": 82205.0, "\u0bb8": 2250.0, "\u0baa\u0bc6": 66538.0, "\u0baa\u0bc7": 30690.0, "\u0baa\u0bc0": 4219.0, "\u0baa\u0bc1": 146058.0, "\u0baa\u0bc2": 25286.0, "\u0bb7\u0bc7": 478.0, "\u0baa\u0bbe": 116682.0, "\u0baa\u0bbf": 118648.0, "\u0ba4\u0bc6": 47579.0, "\u0bb4\u0bcc": 2.0, "\u0bb4\u0bcd": 56156.0, "\u0bb4\u0bca": 270.0, "\u0bb4\u0bcb": 283.0, "\u0bb4\u0bc8": 23614.0, "\u0bb4\u0bc6": 493.0, "\u0bb4\u0bc7": 758.0, "\u0bb4\u0bc2": 298.0, "\u0b9f\u0bc0": 2902.0, "\u0bb4\u0bc1": 67835.0, "\u0ba3\u0bcb": 1325.0, "\u0ba3\u0bca": 611.0, "\u0ba3\u0bc8": 22128.0, "\u0bb3\u0bbf": 93496.0, "\u0bb3\u0bbe": 28154.0, "\u0ba3\u0bcd": 231490.0, "\u0ba3\u0bc2": 458.0, "\u0ba3\u0bc1": 17030.0, "\u0ba3\u0bc0": 2995.0, "\u0ba3\u0bc7": 1997.0, "\u0ba3\u0bc6": 2372.0, "\u0b9a\u0bbe": 40004.0, "\u0b9a\u0bbf": 123619.0} \ No newline at end of file diff --git a/solthiruthi/data/madurai_unigram.txt b/solthiruthi/data/madurai_unigram.txt new file mode 100644 index 0000000..e46eb7c --- /dev/null +++ b/solthiruthi/data/madurai_unigram.txt @@ -0,0 +1,293 @@ +க - 774635 +ன் - 657842 +ம் - 621683 +த - 566469 +த் - 540767 +க் - 527909 +வ - 472124 +ர் - 441925 +ல் - 403345 +து - 395602 +ரு - 391928 +ப - 370431 +ந் - 369333 +தி - 354355 +ப் - 345626 +கு - 338725 +ய - 328267 +ம - 299013 +ட - 267257 +ற் - 261277 +அ - 252521 +வி - 251004 +ர - 243877 +டு - 243848 +ன - 242198 +ங் - 241771 +ண் - 231490 +ட் - 212838 +கி - 212583 +ள் - 211262 +ல - 199855 +டி - 199482 +ற - 189701 +யி - 169555 +று - 169031 +மு - 166201 +தா - 164244 +இ - 162272 +மா - 147356 +பு - 146058 +ய் - 145377 +கா - 145079 +ரி - 139808 +யா - 139367 +வா - 136684 +றி - 135924 +சி - 123619 +லை - 121144 +ச் - 120634 +ச - 119945 +யு - 118962 +பி - 118648 +பா - 116682 +உ - 114865 +எ - 112762 +னை - 107583 +டை - 104237 +ள - 101777 +கொ - 97975 +செ - 95350 +ளி - 93496 +ந - 92960 +ண - 88135 +லி - 86421 +லா - 85850 +னி - 85378 +நி - 84254 +போ - 82205 +னா - 78966 +வே - 76558 +வு - 75941 +கை - 75850 +னு - 74745 +தை - 74444 +மை - 73801 +மி - 73393 +ரை - 73132 +ளை - 71868 +ழி - 68970 +ஆ - 68845 +லு - 68471 +ழு - 67835 +பெ - 66538 +றை - 65921 +பொ - 62712 +நா - 62223 +ஞ் - 61923 +ரா - 61895 +தே - 60822 +ணி - 60469 +ழ - 58801 +சு - 58661 +றா - 57305 +ழ் - 56156 +வெ - 53903 +மே - 53458 +டா - 53287 +ளு - 49515 +வை - 48136 +தெ - 47579 +யை - 46276 +கூ - 42581 +ஒ - 41876 +யே - 41717 +தோ - 40740 +சா - 40004 +தொ - 39591 +மெ - 38364 +நீ - 36899 +கோ - 36032 +கே - 33291 +சை - 31470 +பே - 30690 +சொ - 30463 +லே - 29612 +யெ - 28882 +ளா - 28154 +னே - 27384 +ஏ - 26171 +வீ - 26158 +பூ - 25286 +சே - 25194 +யோ - 24095 +ழை - 23614 +நெ - 23529 +தீ - 22597 +ணை - 22128 +வ் - 21881 +மூ - 19880 +றே - 19030 +மொ - 18422 +கெ - 17833 +ணு - 17030 +ஓ - 16942 +சூ - 16193 +தூ - 15680 +ரே - 13756 +னெ - 13510 +மோ - 12860 +பை - 12780 +சீ - 12270 +மீ - 12201 +ணா - 12196 +டே - 11481 +ஊ - 11458 +னோ - 11248 +ளே - 11079 +வோ - 11022 +சோ - 11006 +நே - 10853 +ரெ - 10822 +லோ - 10682 +ஸ் - 10491 +லெ - 10211 +நோ - 10117 +யொ - 9965 +ரோ - 9739 +ஈ - 9613 +றோ - 9447 +நு - 9398 +றெ - 8828 +நூ - 8576 +கீ - 7403 +ஞா - 7297 +ஐ - 6967 +ஷ - 6891 +ழா - 6186 +டெ - 5798 +வொ - 5789 +ளெ - 5783 +ஜ - 5714 +றொ - 5216 +ளோ - 5028 +னொ - 4973 +டோ - 4948 +யூ - 4575 +ஷ் - 4559 +பீ - 4219 +றீ - 4199 +லொ - 4179 +ரொ - 4135 +ரீ - 4011 +ரூ - 3683 +ஞ - 3453 +னீ - 3355 +டொ - 3035 +ணீ - 2995 +யீ - 2946 +டீ - 2902 +வூ - 2542 +ணெ - 2372 +ஸ - 2250 +ஜா - 2153 +லீ - 2042 +ணே - 1997 +னூ - 1994 +லூ - 1916 +நொ - 1900 +ஃ - 1861 +ளொ - 1759 +ங - 1530 +றூ - 1336 +ணோ - 1325 +ஜ் - 1280 +டூ - 1244 +ஹ - 1175 +ஷி - 1073 +நை - 1052 +ஹா - 1042 +ளீ - 987 +ளூ - 942 +ழீ - 907 +ஜி - 862 +ஸி - 845 +ழே - 758 +ஞை - 735 +கௌ - 697 +மௌ - 649 +ணொ - 611 +சௌ - 584 +ஸா - 556 +ஷா - 541 +ஜெ - 538 +வௌ - 529 +ஷை - 525 +ஜோ - 511 +ஜீ - 500 +ழெ - 493 +ஷே - 478 +ணூ - 458 +ஜை - 438 +ஹி - 422 +பௌ - 387 +ஔ - 367 +ஞெ - 350 +ழூ - 298 +ழோ - 283 +ழொ - 270 +ஸு - 261 +ஹோ - 240 +ஜு - 231 +ஷு - 229 +ஞீ - 197 +தௌ - 180 +ஹ் - 180 +ஸை - 176 +ஜே - 173 +ஸீ - 143 +ஞி - 130 +ஸூ - 119 +ஜொ - 99 +ஹு - 98 +ஹை - 95 +ஹீ - 93 +ஸெ - 85 +ஜூ - 83 +ரௌ - 76 +ஹே - 74 +ஸே - 71 +யௌ - 66 +ஷூ - 63 +ஹூ - 61 +ஹெ - 60 +ஞூ - 59 +ஸோ - 44 +ஞே - 41 +ஷீ - 37 +ஷோ - 36 +ஷெ - 36 +ஹொ - 30 +ஞோ - 30 +ஸௌ - 26 +டௌ - 24 +லௌ - 23 +ஞு - 22 +ஙு - 18 +நௌ - 18 +ஹௌ - 12 +ஸொ - 11 +ஙொ - 11 +னௌ - 11 +ஞௌ - 10 +ஞொ - 8 +ஙா - 5 +ஙே - 4 +ளௌ - 3 +ஷொ - 2 +ஙூ - 2 +ழௌ - 2 +ஷௌ - 1 +றௌ - 1 +ஙி - 1 +ஙோ - 1