Add simple English ngrams module

Tutor/EnglishNGrams.elm

@@ -0,0 +1,120 @@
+module Tutor.EnglishNGrams where
+
+-- Letters from https://en.wikipedia.org/wiki/Letter_frequency#Relative_frequencies_of_letters_in_the_English_language
+-- Bigrams from https://en.wikipedia.org/wiki/Bigram#Bigram_frequency_in_the_English_language
+-- Trigrams and Tetragrams from http://www.cryptograms.org/letter-frequencies.php#Most_common_trigrams_.28in_order.29
+
+monograms = [(12.702, "e"),
+  (9.056, "t"),
+  (8.167, "a"),
+  (7.507, "o"),
+  (6.966, "i"),
+  (6.749, "n"),
+  (6.327, "s"),
+  (6.094, "h"),
+  (5.987, "r"),
+  (4.253, "d"),
+  (4.025, "l"),
+  (2.782, "c"),
+  (2.758, "u"),
+  (2.406, "m"),
+  (2.361, "w"),
+  (2.228, "f"),
+  (2.015, "g"),
+  (1.974, "y"),
+  (1.929, "p"),
+  (1.492, "b"),
+  (0.153, "j"),
+  (0.150, "x"),
+  (0.978, "v"),
+  (0.772, "k"),
+  (0.095, "q"),
+  (0.074, "z")]
+
+bigrams = [
+  ( 1.52, "th" ),
+  ( 1.28, "he" ),
+  ( 0.94, "in" ),
+  ( 0.94, "er" ),
+  ( 0.82, "an" ),
+  ( 0.68, "re" ),
+  ( 0.63, "nd" ),
+  ( 0.59, "at" ),
+  ( 0.57, "on" ),
+  ( 0.56, "nt" ),
+  ( 0.56, "ha" ),
+  ( 0.56, "es" ),
+  ( 0.55, "st" ),
+  ( 0.55, "en" ),
+  ( 0.53, "ed" ),
+  ( 0.52, "to" ),
+  ( 0.50, "it" ),
+  ( 0.50, "ou" ),
+  ( 0.47, "ea" ),
+  ( 0.46, "hi" ),
+  ( 0.46, "is" ),
+  ( 0.43, "or" ),
+  ( 0.34, "ti" ),
+  ( 0.33, "as" ),
+  ( 0.27, "te" ),
+  ( 0.19, "et" ),
+  ( 0.18, "ng" ),
+  ( 0.16, "of" ),
+  ( 0.09, "al" ),
+  ( 0.09, "de" ),
+  ( 0.08, "se" ),
+  ( 0.08, "le" ),
+  ( 0.06, "sa" ),
+  ( 0.05, "si" ),
+  ( 0.04, "ar" ),
+  ( 0.04, "ve" ),
+  ( 0.04, "ra" ),
+  ( 0.02, "ld" ),
+  ( 0.02, "ur" )]
+
+trigrams = [(3.508232, "the"),
+  (1.593878, "and"),
+  (1.147042, "ing"),
+  (0.822444, "her"),
+  (0.650715, "hat"),
+  (0.596748, "his"),
+  (0.593593, "tha"),
+  (0.560594, "ere"),
+  (0.555372, "for"),
+  (0.530771, "ent"),
+  (0.506454, "ion"),
+  (0.461099, "ter"),
+  (0.460487, "was"),
+  (0.437213, "you"),
+  (0.431250, "ith"),
+  (0.430732, "ver"),
+  (0.422758, "all"),
+  (0.397290, "wit"),
+  (0.394796, "thi"),
+  (0.378058, "tio") ] 
+
+tetragrams = [(0.761242, "that"),
+  (0.604501, "ther"),
+  (0.573866, "with"),
+  (0.551919, "tion"),
+  (0.374549, "here"),
+  (0.369920, "ould"),
+  (0.309440, "ight"),
+  (0.290544, "have"),
+  (0.284292, "hich"),
+  (0.283826, "whic"),
+  (0.276333, "this"),
+  (0.270413, "thin"),
+  (0.262421, "they"),
+  (0.262386, "atio"),
+  (0.260695, "ever"),
+  (0.258580, "from"),
+  (0.253447, "ough"),
+  (0.231089, "were"),
+  (0.229944, "hing"),
+  (0.223347, "ment") ]
+
+ngrams = [ (1, monograms),
+  (2, bigrams),
+  (3, trigrams),
+  (4, tetragrams)]