added kenlm model solution

LICENSE

@@ -0,0 +1,9 @@
+MIT License
+
+Copyright (c) <year> <copyright holders>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -0,0 +1,9 @@
+Challenging America word-gap prediction
+===================================
+
+Guess a word in a gap.
+
+Evaluation metric
+-----------------
+
+LikelihoodHashed is the metric

alpha_test.md

@@ -0,0 +1,16 @@
+## Tested on 10k rows
+
+|alpha|result|
+|---|---|
+|__0.0001__|__603.35__|
+|0.001|656.93|
+|0.1|933.45|
+|0.2|962.28|
+|0.3|975.78|
+|0.4|983.92|
+|0.5|989.45|
+|0.6|993.51|
+|0.7|996.63|
+|0.8|999.11|
+|0.9|1001.13|
+|1.0|1002.83|

config.txt

@@ -0,0 +1 @@
+--metric PerplexityHashed --precision 2  --in-header in-header.tsv  --out-header out-header.tsv

in-header.tsv

@@ -0,0 +1 @@
+FileId	Year	LeftContext	RightContext

kenlm.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+KENLM_BUILD_PATH='/home/dawid/kenlm/build'
+$KENLM_BUILD_PATH/bin/lmplz -o 3 < train_data.txt > kenlm_model.arpa
+$KENLM_BUILD_PATH/bin/build_binary   kenlm_model.arpa kenlm_model.binary

out-header.tsv

@@ -0,0 +1 @@
+Word

run.py

@@ -0,0 +1,126 @@
+from cmath import log10
+import csv
+import pandas as pd
+import regex as re
+import os
+import kenlm
+
+from nltk import  word_tokenize
+from collections import Counter, defaultdict
+from english_words import english_words_set
+
+# nltk.download("punkt")
+
+# train set
+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,
+    nrows=100_000
+)
+
+# training labels
+train_labels = pd.read_csv(
+    "train/expected.tsv",
+    sep="\t",
+    error_bad_lines=False,
+    warn_bad_lines=False,
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    nrows=100_000
+)
+
+# dev set
+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 set
+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,
+)
+
+def prepare_text(text):
+    text = text.lower().replace("-\\n", "").replace("\\n", " ")
+    text = re.sub(r"\p{P}", "", text)
+
+    return text
+
+def predict(word1, word2):
+    predictions = []
+    for word in english_words_set:
+        sentence = word1 + ' ' + word + ' ' + word2
+        text_score = model.score(sentence, bos=False, eos=False)
+
+        if len(predictions) < 12:
+            predictions.append((word, text_score))
+        else:
+            worst_score = None
+            for score in predictions:
+                if not worst_score:
+                    worst_score = score
+                else:
+                    if worst_score[1] > score[1]:
+                        worst_score = score
+            if worst_score[1] < text_score:
+                predictions.remove(worst_score)
+                predictions.append((word, text_score))
+    probs = sorted(predictions, 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
+
+def write_output():
+    with open("dev-0/out.tsv", "w") as file:
+        for _, row in dev_data.iterrows():
+            text = prepare_text(str(row[7]))
+            words = word_tokenize(text)
+            if len(words) < 3:
+                prediction = "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
+            else:
+                prediction = predict(words[0], words[1])
+            file.write(prediction + "\n")
+
+    with open("test-A/out.tsv", "w") as file:
+        for _, row in test_data.iterrows():
+            text = prepare_text(str(row[7]))
+            words = word_tokenize(text)
+            if len(words) < 3:
+                prediction = "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
+            else:
+                prediction = predict(words[0], words[1])
+            file.write(prediction + "\n")
+                
+if __name__ == "__main__":
+    print("Preparing data...")
+    train_data = train_data[[6, 7]]
+    train_data = pd.concat([train_data, train_labels], axis=1)
+    train_data["final"] = train_data[6] + train_data[0] + train_data[7]
+    train = train_data[['final']]
+
+    with open("./train_data.txt", 'a') as f:
+        for _, row in train_data.iterrows():
+            text = prepare_text(str(row["final"]))
+            f.write(text + '\n')
+    
+    print("Preparing model...")
+    os.system('sh ./kenlm.sh')
+    model=kenlm.Model("kenlm_model.binary")
+
+    print("Writing outputs...")
+    write_output()