s434708/challenging-america-word-gap-prediction-kenlm
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

final solution

Browse Source
This commit is contained in:
Łukasz Jędyk 2022-04-21 22:17:46 +02:00
parent 3dd8f4130a
commit dbc2815e28
8 changed files with 18344 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
.ipynb_checkpoints/
model/
geval
processed_train.txt

150
.ipynb_checkpoints/run-checkpoint.ipynb
View File

@ -2,12 +2,12 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 1,
"id": "f73a28ea", "id": "f73a28ea",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"KENLM_BUILD_PATH='/home/students/s434708/kenlm/build'" "KENLM_BUILD_PATH='/home/haskell/kenlm/build'"
] ]
}, },
{ {
@ -20,7 +20,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 2,
"id": "d42ddd87", "id": "d42ddd87",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -32,7 +32,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 3,
"id": "f84be210", "id": "f84be210",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -46,7 +46,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 4,
"id": "de0c12d6", "id": "de0c12d6",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -85,13 +85,13 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"=== 1/5 Counting and sorting n-grams ===\n", "=== 1/5 Counting and sorting n-grams ===\n",
"Reading /home/students/s434708/Desktop/Modelowanie Języka/challenging-america-word-gap-prediction-kenlm/processed_train.txt\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", "----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", "********************************Warning: <s> appears in the input. All instances of <s>, </s>, and <unk> will be interpreted as whitespace.\n",
"********************************************************************\n", "********************************************************************\n",
"Unigram tokens 135911223 types 4381594\n", "Unigram tokens 135911223 types 4381594\n",
"=== 2/5 Calculating and sorting adjusted counts ===\n", "=== 2/5 Calculating and sorting adjusted counts ===\n",
"Chain sizes: 1:52579128 2:1295655936 3:2429355008 4:3886967808 5:5668495360\n", "Chain sizes: 1:52579128 2:896866240 3:1681624320 4:2690598656 5:3923790080\n",
"Statistics:\n", "Statistics:\n",
"1 4381594 D1=0.841838 D2=1.01787 D3+=1.21057\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", "2 26800631 D1=0.836734 D2=1.01657 D3+=1.19437\n",
@ -116,21 +116,18 @@
"####################################################################################################\n", "####################################################################################################\n",
"=== 5/5 Writing ARPA model ===\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", "----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"----------------------------------------------------------------------------------------------------Last input should have been poison. The program should end soon with an error. If it doesn't, there's a bug.\n", "****************************************************************************************************\n",
"terminate called after throwing an instance of 'util::FDException'\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"
" what(): /home/students/s434708/kenlm/util/file.cc:228 in void util::WriteOrThrow(int, const void*, std::size_t) threw FDException because `ret < 1'.\n",
"No space left on device in /home/students/s434708/Desktop/Modelowanie Języka/challenging-america-word-gap-prediction-kenlm/model.arpa while writing 8189 bytes\n",
"/bin/bash: line 1: 26725 Aborted /home/students/s434708/kenlm/build/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model.arpa\n"
] ]
} }
], ],
"source": [ "source": [
"!$KENLM_BUILD_PATH/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model.arpa" "!$KENLM_BUILD_PATH/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model/model.arpa"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 5,
"id": "dc65780b", "id": "dc65780b",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -138,22 +135,20 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Reading model.arpa\n", "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", "----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"****************************************************************************************************\n", "****************************************************************************************************\n",
"/home/students/s434708/kenlm/util/file.cc:86 in int util::CreateOrThrow(const char*) threw ErrnoException because `-1 == (ret = open(name, 0100 | 01000 | 02, 0400 | 0200 | (0400 >> 3) | ((0400 >> 3) >> 3)))'.\n", "SUCCESS\n"
"No space left on device while creating model.binary Byte: 94\n",
"ERROR\n"
] ]
} }
], ],
"source": [ "source": [
"!$KENLM_BUILD_PATH/bin/build_binary model.arpa model.binary" "!$KENLM_BUILD_PATH/bin/build_binary model/model.arpa model/model.binary"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 6,
"id": "2087eb80", "id": "2087eb80",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -163,12 +158,12 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 7,
"id": "4ba1e592", "id": "4ba1e592",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"!rm model.arpa" "!rm model/model.arpa"
] ]
}, },
{ {
@ -181,36 +176,127 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 32,
"id": "6865301b", "id": "6865301b",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import kenlm" "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", "cell_type": "code",
"execution_count": null, "execution_count": 4,
"id": "e32de662", "id": "e32de662",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"test_str = 'really good'\n", "model = kenlm.Model('model/model.binary')"
"\n",
"model = kenlm.Model('model.binary')\n",
"print(model.score(test_str, bos = True, eos = True))"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "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", "id": "a18b6ebd",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"for i in model.full_scores(test_str):\n", "with open('test-A/out.tsv', 'w') as file:\n",
" print(i)" " 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')"
] ]
} }
], ],

10519
dev-0/out.tsv Normal file
View File

File diff suppressed because it is too large Load Diff

0
geval Normal file → Executable file
View File

25
process_test.py
View File

@ -1,25 +0,0 @@
import pandas as pd
import csv
import regex as re
def clean_text(text):
text = text.lower().replace('-\\n', '').replace('\\n', ' ')
text = re.sub(r'\p{P}', '', text)
return text
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)
train_labels = pd.read_csv('train/expected.tsv', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)
train_data = train_data[[6, 7]]
train_data = pd.concat([train_data, train_labels], axis=1)
train_data['text'] = train_data[6] + train_data[0] + train_data[7]
train_data = train_data[['text']]
with open('processed_train.txt', 'w') as file:
for _, row in train_data.iterrows():
text = clean_text(str(row['text']))
file.write(text + '\n')

150
run.ipynb
View File

@ -2,12 +2,12 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 1,
"id": "f73a28ea", "id": "f73a28ea",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"KENLM_BUILD_PATH='/home/students/s434708/kenlm/build'" "KENLM_BUILD_PATH='/home/haskell/kenlm/build'"
] ]
}, },
{ {
@ -20,7 +20,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 2,
"id": "d42ddd87", "id": "d42ddd87",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -32,7 +32,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 3,
"id": "f84be210", "id": "f84be210",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -46,7 +46,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 4,
"id": "de0c12d6", "id": "de0c12d6",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -85,13 +85,13 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"=== 1/5 Counting and sorting n-grams ===\n", "=== 1/5 Counting and sorting n-grams ===\n",
"Reading /home/students/s434708/Desktop/Modelowanie Języka/challenging-america-word-gap-prediction-kenlm/processed_train.txt\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", "----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", "********************************Warning: <s> appears in the input. All instances of <s>, </s>, and <unk> will be interpreted as whitespace.\n",
"********************************************************************\n", "********************************************************************\n",
"Unigram tokens 135911223 types 4381594\n", "Unigram tokens 135911223 types 4381594\n",
"=== 2/5 Calculating and sorting adjusted counts ===\n", "=== 2/5 Calculating and sorting adjusted counts ===\n",
"Chain sizes: 1:52579128 2:1295655936 3:2429355008 4:3886967808 5:5668495360\n", "Chain sizes: 1:52579128 2:896866240 3:1681624320 4:2690598656 5:3923790080\n",
"Statistics:\n", "Statistics:\n",
"1 4381594 D1=0.841838 D2=1.01787 D3+=1.21057\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", "2 26800631 D1=0.836734 D2=1.01657 D3+=1.19437\n",
@ -116,21 +116,18 @@
"####################################################################################################\n", "####################################################################################################\n",
"=== 5/5 Writing ARPA model ===\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", "----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"----------------------------------------------------------------------------------------------------Last input should have been poison. The program should end soon with an error. If it doesn't, there's a bug.\n", "****************************************************************************************************\n",
"terminate called after throwing an instance of 'util::FDException'\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"
" what(): /home/students/s434708/kenlm/util/file.cc:228 in void util::WriteOrThrow(int, const void*, std::size_t) threw FDException because `ret < 1'.\n",
"No space left on device in /home/students/s434708/Desktop/Modelowanie Języka/challenging-america-word-gap-prediction-kenlm/model.arpa while writing 8189 bytes\n",
"/bin/bash: line 1: 26725 Aborted /home/students/s434708/kenlm/build/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model.arpa\n"
] ]
} }
], ],
"source": [ "source": [
"!$KENLM_BUILD_PATH/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model.arpa" "!$KENLM_BUILD_PATH/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model/model.arpa"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 5,
"id": "dc65780b", "id": "dc65780b",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -138,22 +135,20 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Reading model.arpa\n", "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", "----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"****************************************************************************************************\n", "****************************************************************************************************\n",
"/home/students/s434708/kenlm/util/file.cc:86 in int util::CreateOrThrow(const char*) threw ErrnoException because `-1 == (ret = open(name, 0100 | 01000 | 02, 0400 | 0200 | (0400 >> 3) | ((0400 >> 3) >> 3)))'.\n", "SUCCESS\n"
"No space left on device while creating model.binary Byte: 94\n",
"ERROR\n"
] ]
} }
], ],
"source": [ "source": [
"!$KENLM_BUILD_PATH/bin/build_binary model.arpa model.binary" "!$KENLM_BUILD_PATH/bin/build_binary model/model.arpa model/model.binary"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 6,
"id": "2087eb80", "id": "2087eb80",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -163,12 +158,12 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 7,
"id": "4ba1e592", "id": "4ba1e592",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"!rm model.arpa" "!rm model/model.arpa"
] ]
}, },
{ {
@ -181,36 +176,127 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 32,
"id": "6865301b", "id": "6865301b",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import kenlm" "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", "cell_type": "code",
"execution_count": null, "execution_count": 4,
"id": "e32de662", "id": "e32de662",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"test_str = 'really good'\n", "model = kenlm.Model('model/model.binary')"
"\n",
"model = kenlm.Model('model.binary')\n",
"print(model.score(test_str, bos = True, eos = True))"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "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", "id": "a18b6ebd",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"for i in model.full_scores(test_str):\n", "with open('test-A/out.tsv', 'w') as file:\n",
" print(i)" " 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')"
] ]
} }
], ],

171
run.py Normal file
View File

@ -0,0 +1,171 @@
#!/usr/bin/env python
# coding: utf-8
# In[1]:
KENLM_BUILD_PATH='/home/haskell/kenlm/build'
# ### Preprocessing danych
# In[2]:
import pandas as pd
import csv
import regex as re
# In[3]:
def clean_text(text):
text = text.lower().replace('-\\n', '').replace('\\n', ' ')
text = re.sub(r'\p{P}', '', text)
return text
# In[4]:
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)
train_labels = pd.read_csv('train/expected.tsv', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)
train_data = train_data[[6, 7]]
train_data = pd.concat([train_data, train_labels], axis=1)
train_data['text'] = train_data[6] + train_data[0] + train_data[7]
train_data = train_data[['text']]
with open('processed_train.txt', 'w') as file:
for _, row in train_data.iterrows():
text = clean_text(str(row['text']))
file.write(text + '\n')
# ### Model kenLM
# In[4]:
get_ipython().system('$KENLM_BUILD_PATH/bin/lmplz -o 5 --skip_symbols < processed_train.txt > model/model.arpa')
# In[5]:
get_ipython().system('$KENLM_BUILD_PATH/bin/build_binary model/model.arpa model/model.binary')
# In[6]:
get_ipython().system('rm processed_train.txt')
# In[7]:
get_ipython().system('rm model/model.arpa')
# ### Predykcje
# In[32]:
import kenlm
import csv
import pandas as pd
import regex as re
from math import log10
from nltk import word_tokenize
from english_words import english_words_alpha_set
# In[4]:
model = kenlm.Model('model/model.binary')
# In[28]:
def clean_text(text):
text = text.lower().replace('-\\n', '').replace('\\n', ' ')
text = re.sub(r'\p{P}', '', text)
return text
# In[29]:
def predict_probs(w1, w2, w4):
best_scores = []
for word in english_words_alpha_set:
text = ' '.join([w1, w2, word, w4])
text_score = model.score(text, bos=False, eos=False)
if len(best_scores) < 20:
best_scores.append((word, text_score))
else:
is_better = False
worst_score = None
for score in best_scores:
if not worst_score:
worst_score = score
else:
if worst_score[1] > score[1]:
worst_score = score
if worst_score[1] < text_score:
best_scores.remove(worst_score)
best_scores.append((word, text_score))
probs = sorted(best_scores, key=lambda tup: tup[1], reverse=True)
pred_str = ''
for word, prob in probs:
pred_str += f'{word}:{prob} '
pred_str += f':{log10(0.99)}'
return pred_str
# In[30]:
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)
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)
# In[35]:
with open('dev-0/out.tsv', 'w') as file:
for index, row in dev_data.iterrows():
left_text = clean_text(str(row[6]))
right_text = clean_text(str(row[7]))
left_words = word_tokenize(left_text)
right_words = word_tokenize(right_text)
if len(left_words) < 2 or len(right_words) < 2:
prediction = ':1.0'
else:
prediction = predict_probs(left_words[len(left_words) - 2], left_words[len(left_words) - 1], right_words[0])
file.write(prediction + '\n')
# In[37]:
with open('test-A/out.tsv', 'w') as file:
for index, row in test_data.iterrows():
left_text = clean_text(str(row[6]))
right_text = clean_text(str(row[7]))
left_words = word_tokenize(left_text)
right_words = word_tokenize(right_text)
if len(left_words) < 2 or len(right_words) < 2:
prediction = ':1.0'
else:
prediction = predict_probs(left_words[len(left_words) - 2], left_words[len(left_words) - 1], right_words[0])
file.write(prediction + '\n')

7414
test-A/out.tsv Normal file
View File

File diff suppressed because it is too large Load Diff