Perform Jieba word segmentation on the required content and output EXCEL documents according to word frequency

Read in excel data structure ：

import pandas as pd
import jieba

df = pd.read_excel('xuqiufenxi.xls')
print(df)

# Create a new column to store word segmentation results 
df['fenci'] = ''

# Traverse the text of each line , And save the word segmentation results into the new column 
for i in range(len(df)):
    print(i)
    df['fenci'][i] = ' '.join(jieba.cut(df[' Content of requirements '][i]))
    print(df['fenci'][i])
    # Count the number of times each word appears 
    word_count = {
    }
    for word in df['fenci'][i].split():
        if word in word_count:
            word_count[word] += 1
        else:
            word_count[word] = 1
    #  take word_count The dictionary is converted into dataframe
    word_count_df = pd.DataFrame(word_count.items(), columns=['word', 'count'])
    #  according to count Value descending sort 
    word_count_df = word_count_df.sort_values(by='count', ascending=False)
    # Output excel
    word_count_df.to_excel(f"{
      df[' function '][i]}.xlsx", index=False)

Output ：