Repository where I mostly put random python scripts.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 

41 lines
824 B

import shutil
from shutil import copyfile
copyfile(src = "../input/cleantext/cleantext.py", dst = "../working/cleantext.py")
# import all our functions
from cleantext import *
#!pylint cleantext
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
training = [
" I am master of all",
"I am a absolute learner"
]
generalization = [
"I am absolute learner learner"
]
vectorization = CountVectorizer(
stop_words = "english",
preprocessor = process.master_clean_text)
vectorization.fit(training)
build_vocab = {
value:key
for key , value in vectorization.vocabulary_.items()
}
vocab = [build_vocab[i] for i in range(len(build_vocab))]
pd.DataFrame(
data = vectorization.transform(generalization).toarray(),
index=["generalization"],
columns=vocab
)