kenlm init

.gitignore

@@ -7,4 +7,5 @@
 .DS_Store
 .token
 geval
-*in.tsv
+*in.tsv
+train_file.txt

run.py

@@ -1,80 +1,39 @@
 #%%
 import pandas as pd
-from collections import defaultdict, Counter
-
-from sqlalchemy import true
-from nltk import trigrams, word_tokenize, bigrams
+import kenlm
 import csv
 
 #%%
-class Model:
-    def __init__(self):
-        self.model = defaultdict(lambda: defaultdict(lambda: 0))
-        self.model_bi = defaultdict(lambda: defaultdict(lambda: 0))
-        train_in = pd.read_csv("train/in.tsv.xz", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)[[6, 7]]
-        train_expected = pd.read_csv("train/expected.tsv", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)
-        data = pd.concat([train_in, train_expected], axis=1)
-        self.data = data[6] + data[0] + data[7]
-        self.data = self.data.apply(self.clean)
+def clean(text):
+    text = str(text).lower().strip().replace("’", "'").replace('\\n', " ").replace("'t", " not").replace("'s", " is").replace("'ll", " will").replace("'m", " am").replace("'ve", " have").replace(",", "").replace("-", "")
+    return text
 
+train_in = pd.read_csv("train/in.tsv.xz", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)[[6, 7]]
+train_expected = pd.read_csv("train/expected.tsv", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)
+data = pd.concat([train_in, train_expected], axis=1)
+data = data[6] + data[0] + data[7]
+data = data.apply(clean)
 
-    def clean(self, text):
-        text = str(text).lower().strip().replace("’", "'").replace('\\n', " ").replace("'t", " not").replace("'s", " is").replace("'ll", " will").replace("'m", " am").replace("'ve", " have").replace(",", "").replace("-", "")
-        return text
-
-    def train(self):
-        alpha = 0.6
-        vocab = set()
-        for text in model.data:
-            words = word_tokenize(text)
-            for w1, w2, w3 in trigrams(words):
-                self.model[w1, w2][w3] += 1
-                vocab.add(w1)
-                vocab.add(w2)
-                vocab.add(w3)
-            for w1, w2 in bigrams(words):
-                self.model_bi[w1][w2] +=1
-        for w1, w2 in self.model:
-            total_count = float(sum(self.model[w1, w2].values()))
-            for w in self.model[w1, w2]:
-                self.model[w1, w2][w] = (self.model[w1, w2][w] / total_count) * alpha
-        for w1 in self.model_bi:
-            total_count = float(sum(self.model_bi[w1].values()))
-            for w in self.model_bi[w1]:
-                self.model_bi[w1][w] = (self.model_bi[w1][w] / total_count) * (1-alpha)
-
-    def predict(self, words):
-        trigrams = Counter(dict(self.model[words]))
-        bigrams = Counter(dict(self.model_bi[words[-1]]))
-        predictions = dict((trigrams + bigrams).most_common(6))
-        total_prob = 0
-        
-        result = ""
-        for word, prob in predictions.items():
-            total_prob += prob
-            result += f"{word}:{prob} "
-
-        if len(result) == 0:
-            return "a:0.2 the:0.2 to:0.2 of:0.1 and:0.1 of:0.1 :0.1"
-        return result + f":{max(1-total_prob, 0.01)}"
-
-model = Model()
+with open("train_file.txt", "w+") as f:
+    for text in data:
+        f.write(text + "\n")
 
 #%%
-model.data
-model.train()
+KENLM_BUILD_PATH='../kenlm/build'
+!$KENLM_BUILD_PATH/bin/lmplz -o 4 < train_file.txt > model.arpa
+!rm train_file.txt
+
 
 #%%
-def predict(model, path, result_path):
+model = kenlm.Model("model.arpa")
+#%%
+def predict(path, result_path):
     data = pd.read_csv(path, sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE)[7]
     with open(result_path, "w+", encoding="UTF-8") as f:
         for text in data:
-            words = word_tokenize(model.clean(text))
-            if len(words) < 2:
-                prediction = "a:0.2 the:0.2 to:0.2 of:0.1 and:0.1 of:0.1 :0.1"
-            else:
-                prediction = model.predict((words[-2], words[-1]))
-            f.write(prediction + "\n")
+            #test
+            print(model.score(text, bos = True, eos = True))
+            break
 
-predict(model, "dev-0/in.tsv.xz", "dev-0/out.tsv")
-predict(model, "test-A/in.tsv.xz", "test-A/out.tsv")
+predict("dev-0/in.tsv.xz", "dev-0/out.tsv")
+predict("test-A/in.tsv.xz", "test-A/out.tsv")