[Python知识库]【无标题】英文文本词性识别

from textblob import TextBlob
import pandas as pd

#报错Resource averaged_perceptron_tagger not found. Please use the NLTK Downloade的解决方法
import nltk
nltk.download('averaged_perceptron_tagger')

#读入数据
Idea=pd.read_csv(r"E:\1.csv",encoding="utf-8")
i=len(Idea)
print(i)

content=[]
content
for x in range(0,i):
    j=Idea['Summary'][x]
    #print(j)
    blob=TextBlob(j)
    tag=blob.tags
    content.append([tag])
    dd=pd.DataFrame(content,columns=['tag'])
    dd.to_csv(r"E:\tag.csv")
    
#得到了以下结果，需要分开[('The', 'DT'), ('3-D', 'JJ'), ('printed', 'JJ'), ('TicTac', 'NNP'), ('gun', 'NN'), ('I', 'PRP'), ('made', 'VBD'), ('as', 'IN'), ('an', 'DT'), ('idea', 'NN'), ('me', 'PRP'), ('and', 'CC'), ('my', 'PRP$'), ('kids', 'NNS'), ('came', 'VBD'), ('up', 'RP'), ('with', 'IN'), ('the', 'DT'), ('reason', 'NN')]
#剩下的统计每个词性可以用excel计算，计算函数如下：=(LEN(B2)-LEN(SUBSTITUTE(B2,"DT","")))/LEN("DT")


'''
将结果分开
'''

import openpyxl
from collections import Counter
import csv

wb = openpyxl.load_workbook(r"E:/tag.xlsx")  # 文件位置 xlsx文件
wb = wb.active

for i in range(2, 27):  # 第几行到第几行
    a = eval(wb.cell(row=i, column=2).value)  # 第i行 第2列
    list = []  # 放词性

    for tag in a:
        list.append(tag[1])
    res = Counter(list)  # 统计每个词性的
    res = dict(res)  # 转换成字典格式

    with open("E:/NLTK.txt", mode='r', encoding='utf-8') as f:
        nltk = eval(f.read())  # 所有词性字典

    for key in res.keys():
        nltk[key] = res[key]  # 保存统计结果到词性字典

    with open("E:/tagCount1.csv", mode='a', encoding='utf-8', newline='') as f1:
        csv_writer1 = csv.writer(f1)
        csv_writer1.writerow(nltk.values())  # 写入csv

    # break
    print(i)

#最后表格首行CC	CD	DT	EX	FW	IN	JJ	JJR	JJS	LS	MD	NN	NNS	NNP	NNPS	PDT	POS	PRP	PRP$	RB	RBR	RBS	RP	SYM	TO	UH	VB	VBD	VBG	VBN	VBP	VBZ	WDT	WP	WP$	WRB