tetragram

predict.py

@@ -0,0 +1,100 @@
+import lzma
+import matplotlib.pyplot as plt
+from math import log
+from collections import OrderedDict
+from collections import Counter
+import regex as re
+from itertools import islice
+import json
+import pdb
+
+model_v = "4000"
+PREFIX_VALID = 'test-A'
+probabilities = {}
+with open(f'model_{model_v}.tsv', 'r') as f:
+
+    for line in f:
+        line = line.rstrip()
+        splitted_line = line.split('\t')
+
+        probabilities[tuple(splitted_line[:4])] = (float(splitted_line[4]), float(splitted_line[5]))
+vocab = set()
+with open(f"vocab_{model_v}.txt", 'r') as f:
+    for l in f:
+        vocab.add(l.rstrip())
+
+def count_probabilities(_probabilities, _chunk_left, _chunk_right):
+
+    for index, (l, r) in enumerate(zip( _chunk_left, _chunk_right)):
+        if l not in vocab:
+            _chunk_left[index] = "<UNK>"
+        if r not in vocab:
+            _chunk_right[index] = "<UNK>"
+
+    results_left = {}
+    best_ = {}
+    for tetragram, probses in _probabilities.items():
+        if tetragram[-1] == "<UNK>":
+            return best_
+
+        if len(results_left) > 2:
+            break
+        if list(tetragram[:3]) == _chunk_left:
+            # for tetragram_2, probses_2 in _probabilities.items():
+            #     if list(tetragram_2[1:]) == _chunk_right:
+            #             best_[tetragram[-1]] = probses[0] * probses_2[1]
+
+            if tetragram[-1] not in best_:
+                best_[tetragram[-1]] = probses[0] * 0.7
+            
+    items = best_.items()
+    
+    return OrderedDict(sorted(items, key=lambda t:t[1], reverse=True))
+
+
+with lzma.open(f'{PREFIX_VALID}/in.tsv.xz', 'r') as train:
+    for t_line in train:
+        t_line = t_line.decode("utf-8")
+
+        t_line = t_line.rstrip()
+
+        t_line = t_line.lower()
+        
+        t_line_splitted_by_tab = t_line.split('\t')
+        
+        words_before = t_line_splitted_by_tab[-2]
+
+        words_before = re.findall(r'\p{L}+', words_before)
+
+        words_after = t_line_splitted_by_tab[-1]
+        words_after = re.findall(r'\p{L}+', words_after)
+
+        chunk_left = words_before[-3:]
+        chunk_right = words_after[0:3]
+
+        probs_ordered = count_probabilities(probabilities, chunk_left, chunk_right)
+
+        # if len(probs_ordered) !=0:
+        #     print(probs_ordered)
+
+        if len(probs_ordered) ==0:
+            print(f"the:0.1 to:0.1 a:0.1 :0.7")
+            continue
+        result_string = ''
+        counter_ = 0
+        for word_, p in probs_ordered.items():
+            if counter_>4:
+                break
+            re_ = re.search(r'\p{L}+', word_)
+            if re_:
+                word_cleared = re_.group(0)
+                result_string += f"{word_cleared}:{str(p)} "
+            else:
+                if result_string == '':
+                    result_string = f"the:0.5 a:0.3 "
+                continue
+
+            counter_+=1
+        result_string += ':0.2'
+        print(result_string)
+        a=1

run.py

@@ -1,153 +0,0 @@
-import lzma
-import matplotlib.pyplot as plt
-from math import log
-from collections import OrderedDict
-from collections import Counter
-import regex as re
-from itertools import islice
-
-def freq_list(g, top=None):
-    c = Counter(g)
-
-    if top is None:
-       items = c.items()
-    else:
-       items = c.most_common(top)
-
-    return OrderedDict(sorted(items, key=lambda t: -t[1]))
-
-def get_words(t):
-    for m in re.finditer(r'[\p{L}0-9-\*]+', t):
-        yield m.group(0)
-
-def ngrams(iter, size):
-  ngram = []
-  for item in iter:
-    ngram.append(item)
-    if len(ngram) == size:
-        yield tuple(ngram)
-        ngram = ngram[1:]
-
-PREFIX_TRAIN = 'train' 
-words = []
-
-counter_lines = 0
-with lzma.open(f'{PREFIX_TRAIN}/in.tsv.xz', 'r') as train, open(f'{PREFIX_TRAIN}/expected.tsv', 'r') as expected:
-    for t_line, e_line in zip(train, expected):
-        t_line = t_line.decode("utf-8")
-
-        t_line = t_line.rstrip()
-        e_line = e_line.rstrip()
-
-        t_line_splitted_by_tab = t_line.split('\t')
-        
-        t_line_cleared = t_line_splitted_by_tab[-2] + ' ' + e_line + ' ' + t_line_splitted_by_tab[-1]
-
-        words += t_line_cleared.split()
-
-        counter_lines+=1
-        if counter_lines > 90000:
-            break
-
-# lzmaFile = lzma.open('dev-0/in.tsv.xz', 'rb')
-
-# content = lzmaFile.read().decode("utf-8")
-# words = get_words(trainset)
-
-ngrams_ = ngrams(words, 2)
-
-
-def create_probabilities_bigrams(w_c, b_c):
-    probabilities_bigrams = {}
-    for bigram, bigram_amount in b_c.items():
-        if bigram_amount <=2:
-            continue
-        p_word_before = bigram_amount / w_c[bigram[0]] 
-        p_word_after = bigram_amount / w_c[bigram[1]]
-        probabilities_bigrams[bigram] = (p_word_before, p_word_after)
-
-    return probabilities_bigrams
-
-words_c = Counter(words)
-word_=''
-bigram_c = Counter(ngrams_)
-ngrams_=''
-probabilities = create_probabilities_bigrams(words_c, bigram_c)
-
-
-items = probabilities.items()
-probabilities = OrderedDict(sorted(items, key=lambda t:t[1], reverse=True))
-items=''
-# sorted_by_freq = freq_list(ngrams)
-
-PREFIX_VALID = 'test-A'
-
-def count_probabilities(w_b, w_a, probs, w_c, b_c):
-    results_before = {}
-    results_after = {}
-    for bigram, probses in probs.items():
-        if len(results_before) > 20 or len(results_after) > 20:
-            break
-        if w_b == bigram[0]:
-            results_before[bigram] = probses[0]
-        if w_a == bigram[1]:
-            results_after[bigram] = probses[1]
-    a=1
-    best_ = {}
-
-    for bigram, probses in results_before.items():
-        for bigram_2, probses_2 in results_after.items():
-            best_[bigram[1]] = probses * probses_2
-
-    for bigram, probses in results_after.items():
-            for bigram_2, probses_2 in results_before.items():
-                if bigram[0] in best_:
-                    if probses * probses_2 < probses_2:
-                        continue
-                best_[bigram[0]] = probses * probses_2
-
-    items = best_.items()
-    return OrderedDict(sorted(items, key=lambda t:t[1], reverse=True))
-
-
-with lzma.open(f'{PREFIX_VALID}/in.tsv.xz', 'r') as train:
-    for t_line in train:
-        t_line = t_line.decode("utf-8")
-
-        t_line = t_line.rstrip()
-        t_line = t_line.replace('\\n', ' ')
-
-
-        t_line_splitted_by_tab = t_line.split('\t')
-        
-
-        words_pre = t_line_splitted_by_tab[-2].split()
-
-        words_po = t_line_splitted_by_tab[-1].split()
-
-        w_pre = words_pre[-1]
-        w_po = words_po[0]
-
-        probs_ordered = count_probabilities(w_pre, w_po,probabilities, words_c, bigram_c)
-        if len(probs_ordered) ==0:
-            print(f"the:0.5 a:0.3 :0.2")
-            continue
-        result_string = ''
-        counter_ = 0
-        for word_, p in probs_ordered.items():
-            if counter_>4:
-                break
-            re_ = re.search(r'\p{L}+', word_)
-            if re_:
-                word_cleared = re_.group(0)
-                result_string += f"{word_cleared}:{str(p)} "
-
-            else:
-                if result_string == '':
-                    result_string = f"the:0.5 a:0.3 "
-                continue
-
-            counter_+=1
-        result_string += ':0.1'
-        print(result_string)
-        a=1

train.py

@@ -0,0 +1,111 @@
+import lzma
+import matplotlib.pyplot as plt
+from math import log
+from collections import OrderedDict
+from collections import Counter
+import regex as re
+from itertools import islice
+import json
+import tqdm
+ignore_rare = 4000
+model_v = '4000'
+
+
+def freq_list(g, top=None):
+    c = Counter(g)
+
+    if top is None:
+       items = c.items()
+    else:
+       items = c.most_common(top)
+
+    return OrderedDict(sorted(items, key=lambda t: -t[1]))
+
+def get_words(t):
+    for m in re.finditer(r'[\p{L}0-9-\*]+', t):
+        yield m.group(0)
+
+def ngrams(iter, size, w_counter):
+  ngram = []
+  for item in iter:
+    if w_counter[item] < ignore_rare:
+        ngram.append('<UNK>')
+    else:
+        ngram.append(item)
+    
+    if len(ngram) == size:
+        yield tuple(ngram)
+        ngram = ngram[1:]
+
+PREFIX_TRAIN = 'train' 
+words = []
+
+
+counter_lines = 0
+with lzma.open(f'{PREFIX_TRAIN}/in.tsv.xz', 'r') as train, open(f'{PREFIX_TRAIN}/expected.tsv', 'r') as expected:
+    for t_line, e_line in zip(train, expected):
+        t_line = t_line.decode("utf-8")
+
+        t_line = t_line.rstrip()
+        e_line = e_line.rstrip()
+
+
+        t_line_splitted_by_tab = t_line.split('\t')
+        
+        t_line_cleared = t_line_splitted_by_tab[-2] + ' ' + e_line + ' ' + t_line_splitted_by_tab[-1]
+
+        t_line_cleared = t_line_cleared.lower()
+
+
+
+        words += re.findall(r'\p{L}+', t_line_cleared)
+
+        # t_line_splitted =  t_line_cleared.split()
+        # words += t_line_splitted 
+
+        if counter_lines % 100000 == 0:
+            print(counter_lines)
+
+        counter_lines+=1
+        if counter_lines > 70000: # 50000 12gb ram
+            break
+
+words_c = Counter(words)
+
+with open(f'vocab_{model_v}.txt', 'w') as f:
+    for word, amount in words_c.items():
+        if amount < ignore_rare:
+            continue
+        f.write(word + '\n')
+
+
+trigrams_ = ngrams(words, 3, words_c)
+tetragrams_ = ngrams(words, 4, words_c)
+
+
+def create_probabilities_bigrams(trigrams, tetragrams):
+    probabilities_grams = {}
+    for tetragram, gram_amount in tetragrams.items():
+        # if bigram_amount <=2:
+            # continue
+        p_word_right = gram_amount / trigrams[tetragram[:-1]] 
+        p_word_left = gram_amount / trigrams[tetragram[1:]]
+        probabilities_grams[tetragram] = (str(p_word_right), str(p_word_left))
+
+    return probabilities_grams
+
+trigram_c = Counter(trigrams_)
+word_=''
+tetragrams_ = Counter(tetragrams_)
+probabilities = create_probabilities_bigrams(trigram_c, tetragrams_)
+
+
+items = probabilities.items()
+probabilities = OrderedDict(sorted(items, key=lambda t:t[1], reverse=True))
+items=''
+
+
+with open(f'model_{model_v}.tsv', 'w') as f:
+    for tetragram, left_right_p in probabilities.items():
+        f.write("\t".join(tetragram) + "\t" + "\t".join(left_right_p) + '\n')
+