104 lines
2.2 KiB
Python
Executable File
104 lines
2.2 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
# coding: utf-8
|
|
|
|
print("Step 1")
|
|
|
|
|
|
try:
|
|
_initialized
|
|
except:
|
|
# !pip install spacy
|
|
# !python -m spacy download en_core_web_trf
|
|
import spacy
|
|
from tqdm import tqdm
|
|
|
|
nlp = spacy.load('en_core_web_trf', disable=['parser', 'ner'])
|
|
|
|
_initialized=True
|
|
|
|
import pandas as pd
|
|
import gzip
|
|
import re
|
|
|
|
|
|
print("Step 2")
|
|
|
|
|
|
def get_lines(filename):
|
|
with gzip.open(filename, 'r') as f:
|
|
ret = []
|
|
for l in f:
|
|
if len(ret) > 30_000:
|
|
return ret
|
|
ret.append(str(l).lower())
|
|
return ret
|
|
|
|
|
|
|
|
WORDLIST_SIZE = 8192 + 3
|
|
word_re = re.compile(r"^[A-Za-z]+$")
|
|
|
|
|
|
print("Step 3")
|
|
|
|
|
|
annotated_words=pd.read_excel("annotated_words.ods")
|
|
|
|
excluded_words = list(annotated_words[annotated_words["keep"] != "Yes"]["word"].str.lower())
|
|
excluded_words[0:10]
|
|
|
|
custom_maps = annotated_words[annotated_words["maps_to"].notna()][["word","maps_to"]].assign(maps_to=lambda x: x["maps_to"].map(lambda y: y.split(",")))
|
|
|
|
custom_maps = [
|
|
(m[1]["word"].lower(), mapping.lower())
|
|
for m in custom_maps.iterrows()
|
|
for mapping in m[1]["maps_to"]
|
|
]
|
|
custom_maps
|
|
|
|
|
|
print("Step 4")
|
|
|
|
|
|
# Start parsing the wordlist
|
|
all_words = get_lines("00-frequency-all.txt.gz")
|
|
|
|
# Delete header line
|
|
all_words = all_words[1:]
|
|
|
|
# Get only the word (fixed width)
|
|
all_words = [w[13:36].strip() for w in all_words]
|
|
|
|
# Remove special characters
|
|
all_words = [w for w in all_words if word_re.search(w)]
|
|
|
|
# Remove all removed words
|
|
all_words = [w for w in all_words if w not in excluded_words]
|
|
|
|
# Add all custom mappings
|
|
for m in list(sum(custom_maps, ())):
|
|
if m[0] not in all_words:
|
|
all_words.append(m[0])
|
|
if m[1] not in all_words:
|
|
all_words.append(m[1])
|
|
|
|
|
|
print("Step 5")
|
|
|
|
# Lemmatize all words (plural -> singular)
|
|
# lemmatize_mappings = [(w, nlp(w)[0].lemma_) for w in tqdm(all_words)]
|
|
|
|
with open("01-lemmatized-words.csv", "w") as f:
|
|
f.write("word,lemmatized_word\n")
|
|
|
|
iter = tqdm(all_words[:1000])
|
|
|
|
for w in iter:
|
|
lemmatized_word = nlp(w)[0].lemma_.upper()
|
|
if lemmatized_word == w:
|
|
continue
|
|
if lemmatized_word not in all_words:
|
|
iter.write(f"{lemmatized_word} not in all_words")
|
|
|
|
f.write(f"{w},{lemmatized_word}\n")
|