run.py

@@ -1,118 +1,73 @@
-#!/usr/bin/env python
+from nltk import trigrams, word_tokenize
-# coding: utf-8
+from collections import defaultdict, Counter
-
-# In[1]:
-
-
 import pandas as pd
 import csv
 import regex as re
-import kenlm
-from english_words import english_words_alpha_set
-from math import log10
-from nltk import trigrams, word_tokenize
-
-
-# In[2]:
-
 
 default_pred = 'to:0.02 be:0.02 the:0.02 or:0.01 not:0.01 and:0.01 a:0.01 :0.9'
 
 
-# In[3]:
-
-
 def preprocess(text):
     text = text.lower().replace('-\\n', '').replace('\\n', ' ')
     return re.sub(r'\p{P}', '', text)
 
 
-# In[4]:
+class Model():
-
+    def __init__(self, alpha, test_file_name):
-
+        train_data = pd.read_csv('train/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE,
-train_data = pd.read_csv('train/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE,
                                  nrows=20000)
-train_labels = pd.read_csv('train/expected.tsv', sep='\t', on_bad_lines='skip', header=None,
+        train_labels = pd.read_csv('train/expected.tsv', sep='\t', on_bad_lines='skip', header=None,
                                    quoting=csv.QUOTE_NONE, nrows=20000)
-data = pd.concat([train_data, train_labels], axis=1)
+        train_data = train_data[[6, 7]]
-data=train_data[6] + train_data[0] + train_data[7]
+        train_data = pd.concat([train_data, train_labels], axis=1)
-data = data.apply(preprocess)
+        train_data['line'] = train_data[6] + train_data[0] + train_data[7]
 
-with open("train_file.txt", "w+") as f:
+        self.file = train_data[['line']]
-    for text in data:
+        self.test_file_name = test_file_name
-        f.write(text + "\n")
+        self.alpha = alpha;
+        self.model = defaultdict(lambda: defaultdict(lambda: 0))
 
+    def train(self):
+        rows = self.file.iterrows()
+        rows_len = len(self.file)
+        for index, (_, row) in enumerate(rows):
+            text = preprocess(str(row['line']))
+            words = word_tokenize(text)
+            for word_1, word_2, word_3 in trigrams(words, pad_right=True, pad_left=True):
+                if word_1 and word_2 and word_3:
+                    self.model[(word_1, word_3)][word_2] += 1
+        model_len = len(self.model)
+        for index, words_1_3 in enumerate(self.model):
+            count = sum(self.model[words_1_3].values())
+            for word_2 in self.model[words_1_3]:
+                self.model[words_1_3][word_2] += self.alpha
+                self.model[words_1_3][word_2] /= float(count + self.alpha + len(word_2))
 
-# In[5]:
+    def predict(self, before, after):
+        prediction = dict(Counter(dict(self.model[before, after])).most_common(5))
+        result = []
+        prob = 0.0
+        for key, value in prediction.items():
+            prob += value
+            result.append(f'{key}:{value} ')
+        if prob == 0.0:
+            return default_pred
+        result.append(f':{max(1 - prob, 0.01)}')
+        return ''.join(result)
 
-
+    def make_prediction(self):
-KENLM_BUILD_PATH='../kenlm/kenlm/build'
+        data = pd.read_csv(f'{self.test_file_name}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
-get_ipython().system('$KENLM_BUILD_PATH/bin/lmplz -o 4 < train_file.txt > model.arpa')
+        with open(f'{self.test_file_name}/out.tsv', 'w', encoding='utf-8') as file_out:
-get_ipython().system('rm train_file.txt')
-
-
-# In[6]:
-
-
-model = kenlm.Model("model.arpa")
-
-
-# In[7]:
-
-
-def predict(before, after):
-    best_scores = []
-    for word in english_words_alpha_set:
-        text = ' '.join([before, word, after])
-        text_score = model.score(text, bos=False, eos=False)
-        if len(best_scores) < 12:
-            best_scores.append((word, text_score))
-        else:
-            is_better = False
-            worst_score = None
-            for score in best_scores:
-                if not worst_score:
-                    worst_score = score
-                else:
-                    if worst_score[1] > score[1]:
-                        worst_score = score
-            if worst_score[1] < text_score:
-                best_scores.remove(worst_score)
-                best_scores.append((word, text_score))
-    probs = sorted(best_scores, key=lambda tup: tup[1], reverse=True)
-    pred_str = ''
-    for word, prob in probs:
-        pred_str += f'{word}:{prob} '
-    pred_str += f':{log10(0.99)}'
-    return pred_str
-
-
-# In[8]:
-
-
-def make_prediction(path, result_path):
-    data = pd.read_csv(path, sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
-    with open(result_path, 'w', encoding='utf-8') as file_out:
             for _, row in data.iterrows():
                 before, after = word_tokenize(preprocess(str(row[6]))), word_tokenize(preprocess(str(row[7])))
-            if len(before) < 2 or len(after) < 2:
+                if len(before) < 3 or len(after) < 3:
                     prediction = default_pred
                 else:
-                prediction = predict(before[-1], after[0])
+                    prediction = self.predict(before[-1], after[0])
                 file_out.write(prediction + '\n')
 
 
-# In[9]:
+alpha = 0.1
-
+model = Model(alpha, 'test-A')
-
+model.train()
-make_prediction("dev-0/in.tsv.xz", "dev-0/out.tsv")
+model.make_prediction()
-
-
-# In[10]:
-
-
-make_prediction("test-A/in.tsv.xz", "test-A/out.tsv")
-
-
-
-