v0

.gitignore

@@ -0,0 +1 @@
+kenlm

run2.py

@@ -0,0 +1,60 @@
+import pandas as pd
+import csv
+import regex as re
+import kenlm
+from english_words import english_words_alpha_set
+from nltk import trigrams, word_tokenize
+
+from pathlib import  Path
+import os
+
+
+KENLM_BUILD_PATH = Path("/home/bartek/Pulpit/challenging-america-word-gap-prediction/kenlm/build")
+KENLM_LMPLZ_PATH = KENLM_BUILD_PATH / "bin" / "lmplz"
+KENLM_BUILD_BINARY_PATH = KENLM_BUILD_PATH / "bin" / "build_binary"
+SUDO_PASSWORD = ""
+
+def clean(text):
+    text = str(text).lower().replace("-\\n", "").replace("\\n", " ")
+    return re.sub(r"\p{P}", "", text)
+
+
+def create_train_data():
+    data = pd.read_csv(
+        "train/in.tsv.xz",
+        sep="\t",
+        error_bad_lines=False,
+        header=None,
+        quoting=csv.QUOTE_NONE,
+        nrows=10000
+    )
+    train_labels = pd.read_csv(
+        "train/expected.tsv",
+        sep="\t",
+        error_bad_lines=False,
+        header=None,
+        quoting=csv.QUOTE_NONE,
+        nrows=10000
+    )
+
+    train_data = data[[6, 7]]
+    train_data = pd.concat([train_data, train_labels], axis=1)
+
+    return train_data[6] + train_data[0] + train_data[7]
+
+
+def create_train_file(filename="train.txt"):
+    with open(filename, "w") as f:
+        for line in create_train_data():
+            f.write(clean(line) + "\n")
+    
+
+def train_model():
+    lmplz_command = f"{KENLM_LMPLZ_PATH} -o 4 < train.txt > model.arpa"
+    build_binary_command = f"{KENLM_BUILD_BINARY_PATH} model.arpa model.binary"
+    os.system('echo %s|sudo -S %s' % (SUDO_PASSWORD, lmplz_command))
+    os.system('echo %s|sudo -S %s' % (SUDO_PASSWORD, build_binary_command))
+    
+
+# create_train_file()
+# train_model()