Question

我有2个这样的功能：

import requests
from bs4 import BeautifulSoup
import datetime
import xlwt
from xlwt import Formula


today = datetime.date.today().strftime("%Y%m%d")

keywords = ('PNC', 'Huntington', 'KeyCorp', 'Fifth Third')

for keyword in keywords:
    keyword.replace("+", " ")

headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64)       AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}

def article_fetch(keyword):
    url = 'https://www.americanbanker.com/search?query={}'.format(keyword)
    r = requests.get(url, headers = headers)

    soup = BeautifulSoup(r.text, 'html.parser')

    mylist = []
    cols = "KeyWord", "Article", "URL", "Publication Date"
    mylist.append(cols)
    for articles in soup.find_all("div", "feed-item"):
        article = articles.find("h4").text.strip()
        timestamp = articles.find("span", "timestamp").text.strip()
        article_url = 'https://{}'.format(articles.find("a")["href"][2:])
        link = 'HYPERLINK("{}", "Link" )'.format(article_url)
        item = [keyword, article, Formula(link), timestamp]
        mylist.append(item)


        book = xlwt.Workbook()
        sheet = book.add_sheet("Articles")
        for i, row in enumerate(mylist):
            for j, col in enumerate(row):
                sheet.write(i, j, col)
        book.save("C:\Python\American Banker\American Banker {}.xls".format(today))


for keyword in keywords:
    article_fetch(keyword)

print('Workbook Saved')

当我尝试应用此功能时：

def wind_index(result):
    if result > 10:
        return 1
    elif (result > 0) & (result <= 5):
        return 1.5
    elif (result > 5) & (result <= 10):
        return 2


def get_thermal_index(temp, hum):

    return wind_index(temp - 0.4*(temp-10)*((1-hum)/100))

我收到此错误：ValueError：系列的真值不明确。使用a.empty，a.bool（），a.item（），a.any（）或a.all（）。

使用这些功能，我还能做什么来为我的DataFrame获取新列？

Answer 1

您可以使用Series.apply：

def get_thermal_index(temp, hum):
    return (temp - 0.4*(temp-10)*((1-hum)/100)).apply(wind_index)

将函数应用于带有熊猫的多列

1 个答案: