wygladzanie

run.py

@@ -1,80 +1,87 @@
+from collections import defaultdict, Counter
 from nltk import trigrams, word_tokenize
-import pandas as pd
 import csv
 import regex as re
-from collections import Counter, defaultdict
+import pandas as pd
 
-
-train_set = pd.read_csv(
+X_train = pd.read_csv(
     'train/in.tsv.xz',
     sep='\t',
-    on_bad_lines='skip',
     header=None,
     quoting=csv.QUOTE_NONE,
-    nrows=50000)
+    nrows=70000,
+    on_bad_lines='skip')
 
-
-train_labels = pd.read_csv(
+Y_train = pd.read_csv(
     'train/expected.tsv',
     sep='\t',
-    on_bad_lines='skip',
     header=None,
     quoting=csv.QUOTE_NONE,
-    nrows=50000)
+    nrows=70000,
+    on_bad_lines='skip')
+
+X_train = X_train[[6, 7]]
+X_train = pd.concat([X_train, Y_train], axis=1)
+X_train['row'] = X_train[6] + X_train[0] + X_train[7]
 
 
-def data_preprocessing(text):
-    return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
+def preprocess(row):
+    return re.sub(r'\p{P}', '', row.lower().replace('-\\n', '').replace('\\n', ' '))
 
 
-def predict(before, after):
-    prediction = dict(Counter(dict(trigram[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 train(X_train, alpha):
+    model = defaultdict(lambda: defaultdict(lambda: 0))
+    vocabulary = set()
+
+    for _, (_, row) in enumerate(X_train.iterrows()):
+        text = preprocess(str(row['row']))
+        words = word_tokenize(text)
+        for w1, w2, w3 in trigrams(words, pad_right=True, pad_left=True):
+            if w1 and w2 and w3:
+                model[(w1, w3)][w2] += 1
+                vocabulary.add(w1)
+                vocabulary.add(w2)
+                vocabulary.add(w3)
+
+    for _, w13 in enumerate(model):
+        count = float(sum(model[w13].values()))
+        denominator = count + alpha * len(vocabulary)
+        for w2 in model[w13]:
+            nominator = model[w13][w2] + alpha
+            model[w13][w2] = nominator / denominator
+    return model
 
 
-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 predict_word(before, after, model):
+    output = ''
+    p = 0.0
+    Y_pred = dict(Counter(dict(model[before, after])).most_common(7))
+
+    for key, value in Y_pred.items():
+        p += value
+        output += f'{key}:{value} '
+    if p == 0.0:
+        output = 'the:0.04 be:0.04 to:0.04 and:0.02 not:0.02 or:0.02 a:0.02 :0.8'
+        return output
+    output += f':{max(1 - p, 0.01)}'
+
+    return output
+
+
+def prediction(file, model):
+    X_test = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', header=None, quoting=csv.QUOTE_NONE, on_bad_lines='skip')
+
+    with open(f'{file}/out.tsv', 'w', encoding='utf-8') as output_file:
+        for _, row in X_test.iterrows():
+            before, after = word_tokenize(preprocess(str(row[6]))), word_tokenize(preprocess(str(row[7])))
+            if len(before) < 2 or len(after) < 2:
+                output = 'the:0.04 be:0.04 to:0.04 and:0.02 not:0.02 or:0.02 a:0.02 :0.8'
             else:
-                prediction = predict(before[-1], after[0])
-            file_out.write(prediction + '\n')
+                output = predict_word(before[-1], after[0], model)
+            output_file.write(output + '\n')
 
 
-train_set = train_set[[6, 7]]
-train_set = pd.concat([train_set, train_labels], axis=1)
-train_set['line'] = train_set[6] + train_set[0] + train_set[7]
+model = train(X_train, 0.0002)
 
-
-trigram = defaultdict(lambda: defaultdict(lambda: 0))
-
-rows = train_set.iterrows()
-rows_len = len(train_set)
-for index, (_, row) in enumerate(rows):
-    text = data_preprocessing(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:
-            trigram[(word_1, word_3)][word_2] += 1
-
-model_len = len(trigram)
-for index, words_1_3 in enumerate(trigram):
-    count = sum(trigram[words_1_3].values())
-    for word_2 in trigram[words_1_3]:
-        trigram[words_1_3][word_2] += 0.25
-        trigram[words_1_3][word_2] /= float(count + 0.25 + len(word_2))
-
-
-make_prediction('test-A')
-make_prediction('dev-0')
+prediction('dev-0', model)
+prediction('test-A', model)