显示柠檬化进程

您可以将一个变量传递到lemmatization函数中,以跟踪它被调用的次数,然后每隔1000次左右打印一次。我将它包装在下面的列表中,这样int可以通过引用而不是通过值传递。

%%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)