wygladzanie

run.py

@@ -1,80 +1,80 @@
-from nltk import tris, word_tokenize
+from re import T
 import pandas as pd
 import csv
-import regex as re
 from collections import Counter, defaultdict
+from nltk.tokenize import RegexpTokenizer
+from nltk import trigrams
+import regex as re
+import lzma
 
 
-train = pd.read_csv(
-    'train/in.tsv.xz',
-    sep='\t',
-    on_bad_lines='skip',
-    header=None,
-    quoting=csv.QUOTE_NONE,
-    nrows=40000)
+class GapEssa:
 
+    def __init__(self):
+        self.alpha = 0.0001
+        self.vocab = set()
+        self.model = defaultdict(lambda: defaultdict(lambda: 0))       
+        self.tokenizer = RegexpTokenizer(r"\w+")      
 
-labels = pd.read_csv(
-    'train/expected.tsv',
-    sep='\t',
-    on_bad_lines='skip',
-    header=None,
-    quoting=csv.QUOTE_NONE,
-    nrows=40000)
-
-
-def data_preprocessing(text):
-    return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
-
-
-def predict(before, after):
-    prediction = dict(Counter(dict(tri[before, after])).most_common(5))
-    result = ''
-    prob = 0.0
-    for key, value in prediction.items():
-        prob += value
-        result += f'{key}:{value} '
-    if prob == 0.0:
-        return 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
-    result += f':{max(1 - prob, 0.01)}'
-    return result
-
-
-def make_prediction(file):
-    data = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
-    with open(f'{file}/out.tsv', 'w', encoding='utf-8') as file_out:
-        for _, row in data.iterrows():
-            before, after = word_tokenize(data_preprocessing(str(row[6]))), word_tokenize(data_preprocessing(str(row[7])))
-            if len(before) < 3 or len(after) < 3:
-                prediction = 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
+    def read_file(self, f, mode=0):
+        for line in f:  
+            text = line.split("\t") 
+            if(mode==0):
+                yield re.sub(r"[^\w\d'\s]+", '', re.sub(' +', ' ', ' '.join([text[6], text[7]]).replace("\\n"," ").replace("\n","").lower()))
             else:
-                prediction = predict(before[-1], after[0])
-            file_out.write(prediction + '\n')
+                yield re.sub(r"[^\w\d'\s]+", '', re.sub(' +', ' ', text[7].replace("\\n"," ").replace("\n","").lower()))
+        
+    def train(self, f):
+        with lzma.open(f, mode='rt') as file:
+            for index, text in enumerate(self.read_file(file)):
+                tokens = self.tokenizer.tokenize(text)
+                for w1, w2, w3 in trigrams(tokens, pad_right=True, pad_left=True):
+                    if w1 and w2 and w3:
+                        self.model[(w2, w3)][w1] += 1
+                        self.vocab.add(w1)
+                        self.vocab.add(w2)
+                        self.vocab.add(w3)
+                if index == 40000:
+                    break
+            
+            for pair in self.model:
+                num_n_grams = float(sum(self.model[pair].values()))
+                for word in self.model[pair]:
+                    self.model[pair][word] = (self.model[pair][word] + self.alpha) / (num_n_grams + self.alpha*len(self.vocab))
 
+    def out(self, input_f, output_f):        
+        with open(output_f, 'w') as out_f:
+            with lzma.open(input_f, mode='rt') as in_f:
+                for _, text in enumerate(self.read_file(in_f, mode=1)):
+                    t = self.tokenizer.tokenize(text)
+                    if len(t) < 4:
+                        # p = 'the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1'
+                        p = 'the:0.03 be:0.03 to:0.03 of:0.025 and:0.025 a:0.025 in:0.020 that:0.020 have:0.015 I:0.010 it:0.010 for:0.010 not:0.010 on:0.010 with:0.010 he:0.010 as:0.010 you:0.010 do:0.010 at:0.010 :0.77'
+                    else:
+                        p = self.pred(t[0], t[1])
+                    out_f.write(p + '\n')
 
-train = train[[6, 7]]
-train = pd.concat([train, labels], axis=1)
-train['line'] = train[6] + train[0] + train[7]
+    def pred(self, w1, w2):
+        total = 0.0
+        line = ''
+        
+        p = dict(self.model[w1, w2])
+        m = dict(Counter(p).most_common(6))
+        
+        for word, prob in m.items():
+            total += prob
+            line += f'{word}:{prob} '
 
+        if total == 0.0:
+            return 'the:0.03 be:0.03 to:0.03 of:0.025 and:0.025 a:0.025 in:0.020 that:0.020 have:0.015 I:0.010 it:0.010 for:0.010 not:0.010 on:0.010 with:0.010 he:0.010 as:0.010 you:0.010 do:0.010 at:0.010 :0.77'
+        if 1 - total >= 0.01:
+            line += f":{1-total}"
+        else:
+            line += f":0.01"
+        
+        return line
 
-tri = defaultdict(lambda: defaultdict(lambda: 0))
-
-rows = train.iterrows()
-rows_len = len(train)
-for index, (_, row) in enumerate(rows):
-    text = data_preprocessing(str(row['line']))
-    words = word_tokenize(text)
-    for word_1, word_2, word_3 in tris(words, pad_right=True, pad_left=True):
-        if word_1 and word_2 and word_3:
-            tri[(word_1, word_3)][word_2] += 1
-
-model_len = len(tri)
-for index, words_1_3 in enumerate(tri):
-    count = sum(tri[words_1_3].values())
-    for word_2 in tri[words_1_3]:
-        tri[words_1_3][word_2] += 0.25
-        tri[words_1_3][word_2] /= float(count + 0.25 + len(word_2))
-
-
-make_prediction('test-A')
-make_prediction('dev-0')
+wp = GapEssa()
+wp.train('train/in.tsv.xz')
+wp.out('dev-0/in.tsv.xz', 'dev-0/out.tsv')
+wp.out('test-A/in.tsv.xz', 'test-A/out.tsv')

run_old.py

@@ -0,0 +1,81 @@
+from nltk import trigram as tris
+from nltk import word_tokenize
+import pandas as pd
+import csv
+import regex as re
+from collections import Counter, defaultdict
+
+
+train = pd.read_csv(
+    'train/in.tsv.xz',
+    sep='\t',
+    on_bad_lines='skip',
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    nrows=30000)
+
+
+labels = pd.read_csv(
+    'train/expected.tsv',
+    sep='\t',
+    on_bad_lines='skip',
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    nrows=30000)
+
+
+def data_preprocessing(text):
+    return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
+
+
+def predict(before, after):
+    prediction = dict(Counter(dict(tri[before, after])).most_common(5))
+    result = ''
+    prob = 0.0
+    for key, value in prediction.items():
+        prob += value
+        result += f'{key}:{value} '
+    if prob == 0.0:
+        return 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
+    result += f':{max(1 - prob, 0.01)}'
+    return result
+
+
+def make_prediction(file):
+    data = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
+    with open(f'{file}/out.tsv', 'w', encoding='utf-8') as file_out:
+        for _, row in data.iterrows():
+            before, after = word_tokenize(data_preprocessing(str(row[6]))), word_tokenize(data_preprocessing(str(row[7])))
+            if len(before) < 3 or len(after) < 3:
+                prediction = 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
+            else:
+                prediction = predict(before[-1], after[0])
+            file_out.write(prediction + '\n')
+
+
+train = train[[6, 7]]
+train = pd.concat([train, labels], axis=1)
+train['line'] = train[6] + train[0] + train[7]
+
+
+tri = defaultdict(lambda: defaultdict(lambda: 0))
+
+rows = train.iterrows()
+rows_len = len(train)
+for index, (_, row) in enumerate(rows):
+    text = data_preprocessing(str(row['line']))
+    words = word_tokenize(text)
+    for word_1, word_2, word_3 in tris(words, pad_right=True, pad_left=True):
+        if word_1 and word_2 and word_3:
+            tri[(word_1, word_3)][word_2] += 1
+
+model_len = len(tri)
+for index, words_1_3 in enumerate(tri):
+    count = sum(tri[words_1_3].values())
+    for word_2 in tri[words_1_3]:
+        tri[words_1_3][word_2] += 0.25
+        tri[words_1_3][word_2] /= float(count + 0.25 + len(word_2))
+
+
+make_prediction('test-A')
+make_prediction('dev-0')