325 lines
10 KiB
Plaintext
325 lines
10 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "f73a28ea",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"KENLM_BUILD_PATH='/home/haskell/kenlm/build'"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "9fc5cda3",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Preprocessing danych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "d42ddd87",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import csv\n",
|
|
"import regex as re"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "f84be210",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def clean_text(text):\n",
|
|
" text = text.lower().replace('-\\\\n', '').replace('\\\\n', ' ')\n",
|
|
" text = re.sub(r'\\p{P}', '', text)\n",
|
|
"\n",
|
|
" return text"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "de0c12d6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"train_data = pd.read_csv('train/in.tsv.xz', sep='\\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)\n",
|
|
"train_labels = pd.read_csv('train/expected.tsv', sep='\\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)\n",
|
|
"\n",
|
|
"train_data = train_data[[6, 7]]\n",
|
|
"train_data = pd.concat([train_data, train_labels], axis=1)\n",
|
|
"\n",
|
|
"train_data['text'] = train_data[6] + train_data[0] + train_data[7]\n",
|
|
"train_data = train_data[['text']]\n",
|
|
"\n",
|
|
"with open('processed_train.txt', 'w') as file:\n",
|
|
" for _, row in train_data.iterrows():\n",
|
|
" text = clean_text(str(row['text']))\n",
|
|
" file.write(text + '\\n')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "846b6b42",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Model kenLM"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "3c74d4be",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"=== 1/5 Counting and sorting n-grams ===\n",
|
|
"Reading /home/haskell/Desktop/challenging-america-word-gap-prediction-kenlm/processed_train.txt\n",
|
|
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
|
|
"********************************Warning: <s> appears in the input. All instances of <s>, </s>, and <unk> will be interpreted as whitespace.\n",
|
|
"********************************************************************\n",
|
|
"Unigram tokens 135911223 types 4381594\n",
|
|
"=== 2/5 Calculating and sorting adjusted counts ===\n",
|
|
"Chain sizes: 1:52579128 2:896866240 3:1681624320 4:2690598656 5:3923790080\n",
|
|
"Statistics:\n",
|
|
"1 4381594 D1=0.841838 D2=1.01787 D3+=1.21057\n",
|
|
"2 26800631 D1=0.836734 D2=1.01657 D3+=1.19437\n",
|
|
"3 69811700 D1=0.878562 D2=1.11227 D3+=1.27889\n",
|
|
"4 104063034 D1=0.931257 D2=1.23707 D3+=1.36664\n",
|
|
"5 119487533 D1=0.938146 D2=1.3058 D3+=1.41614\n",
|
|
"Memory estimate for binary LM:\n",
|
|
"type MB\n",
|
|
"probing 6752 assuming -p 1.5\n",
|
|
"probing 7917 assuming -r models -p 1.5\n",
|
|
"trie 3572 without quantization\n",
|
|
"trie 2120 assuming -q 8 -b 8 quantization \n",
|
|
"trie 3104 assuming -a 22 array pointer compression\n",
|
|
"trie 1652 assuming -a 22 -q 8 -b 8 array pointer compression and quantization\n",
|
|
"=== 3/5 Calculating and sorting initial probabilities ===\n",
|
|
"Chain sizes: 1:52579128 2:428810096 3:1396234000 4:2497512816 5:3345650924\n",
|
|
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
|
|
"####################################################################################################\n",
|
|
"=== 4/5 Calculating and writing order-interpolated probabilities ===\n",
|
|
"Chain sizes: 1:52579128 2:428810096 3:1396234000 4:2497512816 5:3345650924\n",
|
|
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
|
|
"####################################################################################################\n",
|
|
"=== 5/5 Writing ARPA model ===\n",
|
|
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
|
|
"****************************************************************************************************\n",
|
|
"Name:lmplz\tVmPeak:9201752 kB\tVmRSS:2564 kB\tRSSMax:7648448 kB\tuser:506.342\tsys:106.578\tCPU:612.92\treal:1564.6\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"!$KENLM_BUILD_PATH/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model/model.arpa"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "dc65780b",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Reading model/model.arpa\n",
|
|
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
|
|
"****************************************************************************************************\n",
|
|
"SUCCESS\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"!$KENLM_BUILD_PATH/bin/build_binary model/model.arpa model/model.binary"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "2087eb80",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"!rm processed_train.txt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "4ba1e592",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"!rm model/model.arpa"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "e41f7951",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Predykcje"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 32,
|
|
"id": "6865301b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import kenlm\n",
|
|
"import csv\n",
|
|
"import pandas as pd\n",
|
|
"import regex as re\n",
|
|
"from math import log10\n",
|
|
"from nltk import word_tokenize\n",
|
|
"from english_words import english_words_alpha_set"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "e32de662",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"model = kenlm.Model('model/model.binary')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 28,
|
|
"id": "c2535482",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def clean_text(text):\n",
|
|
" text = text.lower().replace('-\\\\n', '').replace('\\\\n', ' ')\n",
|
|
" text = re.sub(r'\\p{P}', '', text)\n",
|
|
"\n",
|
|
" return text"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 29,
|
|
"id": "2308ccad",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def predict_probs(w1, w2, w4):\n",
|
|
" best_scores = []\n",
|
|
" for word in english_words_alpha_set:\n",
|
|
" text = ' '.join([w1, w2, word, w4])\n",
|
|
" text_score = model.score(text, bos=False, eos=False)\n",
|
|
" if len(best_scores) < 20:\n",
|
|
" best_scores.append((word, text_score))\n",
|
|
" else:\n",
|
|
" is_better = False\n",
|
|
" worst_score = None\n",
|
|
" for score in best_scores:\n",
|
|
" if not worst_score:\n",
|
|
" worst_score = score\n",
|
|
" else:\n",
|
|
" if worst_score[1] > score[1]:\n",
|
|
" worst_score = score\n",
|
|
" if worst_score[1] < text_score:\n",
|
|
" best_scores.remove(worst_score)\n",
|
|
" best_scores.append((word, text_score))\n",
|
|
" probs = sorted(best_scores, key=lambda tup: tup[1], reverse=True)\n",
|
|
" pred_str = ''\n",
|
|
" for word, prob in probs:\n",
|
|
" pred_str += f'{word}:{prob} '\n",
|
|
" pred_str += f':{log10(0.99)}'\n",
|
|
" return pred_str"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 30,
|
|
"id": "7245cf38",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"dev_data = pd.read_csv('dev-0/in.tsv.xz', sep='\\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)\n",
|
|
"test_data = pd.read_csv('test-A/in.tsv.xz', sep='\\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 35,
|
|
"id": "ac24ff37",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"with open('dev-0/out.tsv', 'w') as file:\n",
|
|
" for index, row in dev_data.iterrows():\n",
|
|
" left_text = clean_text(str(row[6]))\n",
|
|
" right_text = clean_text(str(row[7]))\n",
|
|
" left_words = word_tokenize(left_text)\n",
|
|
" right_words = word_tokenize(right_text)\n",
|
|
" if len(left_words) < 2 or len(right_words) < 2:\n",
|
|
" prediction = ':1.0'\n",
|
|
" else:\n",
|
|
" prediction = predict_probs(left_words[len(left_words) - 2], left_words[len(left_words) - 1], right_words[0])\n",
|
|
" file.write(prediction + '\\n')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 37,
|
|
"id": "a18b6ebd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"with open('test-A/out.tsv', 'w') as file:\n",
|
|
" for index, row in test_data.iterrows():\n",
|
|
" left_text = clean_text(str(row[6]))\n",
|
|
" right_text = clean_text(str(row[7]))\n",
|
|
" left_words = word_tokenize(left_text)\n",
|
|
" right_words = word_tokenize(right_text)\n",
|
|
" if len(left_words) < 2 or len(right_words) < 2:\n",
|
|
" prediction = ':1.0'\n",
|
|
" else:\n",
|
|
" prediction = predict_probs(left_words[len(left_words) - 2], left_words[len(left_words) - 1], right_words[0])\n",
|
|
" file.write(prediction + '\\n')"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.8.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|