following script is used to lemmatize a given input column with text:
%%time
import pandas as pd
from gensim.utils import lemmatize
from gensim.parsing.preprocessing import STOPWORDS
STOPWORDS = list(STOPWORDS)
data = pd.read_csv('https://pastebin.com/raw/0SEv1RMf')
def lemmatization(s):
result = []
# lowercase, tokenize, remove stopwords, len>3, lemmatize
for token in lemmatize(s, stopwords=STOPWORDS, min_length=3):
result.append(token.decode('utf-8').split('/')[0])
# print(len(result)) <- This didn't work.
return result
X_train = data.apply(lambda r: lemmatization(r['text']), axis=1)
print(X_train)
Question:
How can I print the progress of the lemmatization progress?
You could pass a variable into the lemmatization function to keep track of the number of times it was called - and then print it every 1000 iterations or so. I have wrapped it in a list below so the int can be passed by reference rather than by value.
%%time
import pandas as pd
from gensim.utils import lemmatize
from gensim.parsing.preprocessing import STOPWORDS
STOPWORDS = list(STOPWORDS)
data = pd.read_csv('https://pastebin.com/raw/0SEv1RMf')
iteration_count = [0]
def lemmatization(s, iteration_count):
result = []
# lowercase, tokenize, remove stopwords, len>3, lemmatize
for token in lemmatize(s, stopwords=STOPWORDS, min_length=3):
result.append(token.decode('utf-8').split('/')[0])
# print(len(result)) <- This didn't work.
iteration_count[0] += 1
if iteration_count[0] % 1000 == 0:
print(iteration_count[0])
return result
X_train = data.apply(lambda r: lemmatization(r['text'], iteration_count), axis=1)
print(X_train)