盘点一个英文文本中统计关键词的方法

# coding: utf-8
import pandas as pd
df = pd.read_excel('./文本.xlsx')
# print(df.head())
# df['专业关键词']
for text in df['工作要求']:
    # print(text)
    if text is not None:
        with open('工作要求.txt', mode='a', encoding='utf-8') as file:
            file.write(str(text))

print('写入完成')

from collections import Counter
import pandas as pd
df = pd.read_excel('./文本.xlsx')
# print(df.head())

words = []

with open('工作要求.txt', 'r', encoding='utf-8') as f:
    line = f.readlines()
    for word in line[0].split(' '):
        words.append(word)

print(len(words))

counter = Counter(words)
# print(counter)

# df['专业关键词']
for text in df['专业关键词']:
    for k, v in counter.items():
        if k == text:
            print(k, v)

from collections import Counter # 统计词频
from pyecharts.charts import Bar
from pyecharts import options as opts
from snownlp import SnowNLP
import jieba   # 分词
with open('text_分词后_outputs.txt', 'r',encoding='utf-8') as f:
    read = f.read()
with open('stop_word.txt', 'r', encoding='utf-8') as f:
    stop_word = f.read()
word = jieba.cut(read)
words = []
for i in list(word):
    if i not in stop_word:
        words.append(i)

columns = []
data = []
for k, v in dict(Counter(words).most_common(10)).items():

    columns.append(k)
    data.append(v)
bar = (
        Bar()
        .add_xaxis(columns)
        .add_yaxis("词频", data)
        .set_global_opts(title_opts=opts.TitleOpts(title="词频top10"))
    )
bar.render("词频.html")