From 020c748f998c20c4c28ee40b6b9845396fed8b29 Mon Sep 17 00:00:00 2001
From: alesad7 <sadurszczak@gmail.com>
Date: Sun, 3 Apr 2022 22:23:38 +0200
Subject: [PATCH] 434780

---
 run.py | 41 ++++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/run.py b/run.py
index 4d9c614..1d18d04 100644
--- a/run.py
+++ b/run.py
@@ -1,13 +1,30 @@
 from nltk import trigrams, word_tokenize
-from collections import defaultdict, Counter
 import pandas as pd
 import csv
 import regex as re
+from collections import Counter, defaultdict
 
 
-def preprocess(text):
-    text = text.lower().replace('-\\n', '').replace('\\n', ' ')
-    return re.sub(r'\p{P}', '', text)
+train_set = pd.read_csv(
+    'train/in.tsv.xz',
+    sep='\t',
+    on_bad_lines='skip',
+    header=None,
+    uoting=csv.QUOTE_NONE,
+    nrows=20000)
+
+
+train_labels = pd.read_csv(
+    'train/expected.tsv',
+    sep='\t',
+    on_bad_lines='skip',
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    nrows=20000)
+
+
+def data_preprocessing(text):
+    return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
 
 
 def predict(before, after):
@@ -27,7 +44,7 @@ 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(preprocess(str(row[6]))), word_tokenize(preprocess(str(row[7])))
+            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:0.02 be:0.02 the:0.02 or:0.01 not:0.01 and:0.01 a:0.01 :0.9'
             else:
@@ -35,19 +52,17 @@ def make_prediction(file):
             file_out.write(prediction + '\n')
 
 
-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, quoting=csv.QUOTE_NONE, nrows=20000)
-train_data = train_data[[6, 7]]
-train_data = pd.concat([train_data, train_labels], axis=1)
-train_data['line'] = train_data[6] + train_data[0] + train_data[7]
+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]
 
 
 trigram = defaultdict(lambda: defaultdict(lambda: 0))
 
-rows = train_data.iterrows()
-rows_len = len(train_data)
+rows = train_set.iterrows()
+rows_len = len(train_set)
 for index, (_, row) in enumerate(rows):
-    text = preprocess(str(row['line']))
+    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: