我有两个csv。一个csv包含用户数据，一个csv包含公司数据。用户数据中的每个人都会有一个company_code。公司数据中的每个公司还将有一个company_code。用户数据中的每个人都与特定的公司ID相关联。
目标是创建一个csv，列出从最新到最旧的公司。我想针对每个每家公司显示未登录用户的百分比和数量，不到一周前，不到2周前，少于1个用户的登录百分比一个月前，不到2个月前，不到4个月前和超过4个月。
我拥有输出所需的所有计算/数据，我只是在努力遍历companyInfo嵌套字典。我希望 csv输出看起来像：
输出csv的标题 =公司名称，not_logged_in，percent_not_logged_in，percent_within_1_week，percent_within_2_weeks，percent_within_1_month，percent_within_1_month，percent_within_2_months，percent_within_4_months，percent_within
这些行将成为每个公司的汇总数据。
以下是我到目前为止的脚本。
import csv
import time
from datetime import datetime, timedelta, date
import pprint
# This is opening userdata csv and reading it in as a list.
with open('user_data_outreach.csv') as f:
reader = csv.reader(f)
next(reader)
rawUserData = list(reader)
userData = []
# This is creating a dictionary within the empty userData list.
for user in rawUserData:
userData.append({
'first_name': user[0].title(),
'last_name': user[1].title(),
'person_id': user[2],
'company_id': user[3],
'email': user[4],
'permission': user[5],
'accepted_invite': user[6],
'last_login': user[7]
})
# This is opening companydata csv and reading it in as a list.
with open('company_data.csv') as f:
reader = csv.reader(f)
next(reader)
rawCompanyData = list(reader)
companyData = []
# This is creating a dictionary within the empty companyData list.
for company in rawCompanyData:
companyData.append({
'name': company[0].title(),
'company_id': company[1],
'created_at': company[2],
'has_qr_codes': company[3],
'has_custom_fields': company[4]
})
# function used to
def notLoggedIn():
companyInfo = {}
currentTime = datetime.now()
companyCount = 0
for company in companyData:
companyCount += 1
companyInfo[company['company_id']] = {
'name': company['name'],
'not_logged_in': 0,
'within_1_week': 0,
'within_2_weeks': 0,
'within_1_month': 0,
'within_2_months': 0,
'within_4_months': 0,
'over_4_months': 0,
'people': 0
}
for person in userData:
if len(person['last_login']) > 0:
lastLogin = datetime.fromtimestamp(int((person['last_login'])) / 1000)
td = (currentTime - lastLogin).days
td = int(td)
person['days_since_login'] = td
for person in userData:
if person['company_id'] in companyInfo:
if person['last_login'] == '':
companyInfo[person['company_id']]['not_logged_in'] += 1
companyInfo[person['company_id']]['people'] += 1
elif person['days_since_login'] < 7:
companyInfo[person['company_id']]['within_1_week'] += 1
companyInfo[person['company_id']]['within_2_weeks'] += 1
companyInfo[person['company_id']]['within_1_month'] += 1
companyInfo[person['company_id']]['within_2_months'] += 1
companyInfo[person['company_id']]['within_4_months'] += 1
companyInfo[person['company_id']]['people'] += 1
elif 7 <= person['days_since_login'] < 14:
companyInfo[person['company_id']]['within_2_weeks'] += 1
companyInfo[person['company_id']]['within_1_month'] += 1
companyInfo[person['company_id']]['within_2_months'] += 1
companyInfo[person['company_id']]['within_4_months'] += 1
companyInfo[person['company_id']]['people'] += 1
elif 14 <= person['days_since_login'] < 31:
companyInfo[person['company_id']]['within_1_month'] += 1
companyInfo[person['company_id']]['within_2_months'] += 1
companyInfo[person['company_id']]['within_4_months'] += 1
companyInfo[person['company_id']]['people'] += 1
elif 31 <= person['days_since_login'] < 62:
companyInfo[person['company_id']]['within_2_months'] += 1
companyInfo[person['company_id']]['within_4_months'] += 1
companyInfo[person['company_id']]['people'] += 1
elif 62 <= person['days_since_login'] < 120:
companyInfo[person['company_id']]['within_4_months'] += 1
companyInfo[person['company_id']]['people'] += 1
else:
companyInfo[person['company_id']]['over_4_months'] += 1
companyInfo[person['company_id']]['people'] += 1
# Not logged in.
companyInfo[person['company_id']]['percent_not_logged_in'] = round(100 * (float(
companyInfo[person['company_id']]['not_logged_in'])) / float(companyInfo[person['company_id']]['people']))
# Within 1 week.
companyInfo[person['company_id']]['percent_within_1_week'] = round(100 * (float(
companyInfo[person['company_id']]['within_1_week'])) / float(companyInfo[person['company_id']]['people']))
# Within 2 weeks.
companyInfo[person['company_id']]['percent_within_2_weeks'] = round(100 * (float(
companyInfo[person['company_id']]['within_2_weeks'])) / float(companyInfo[person['company_id']]['people']))
# Within 1 month.
companyInfo[person['company_id']]['percent_within_1_month'] = round(100 * (float(
companyInfo[person['company_id']]['within_1_month'])) / float(companyInfo[person['company_id']]['people']))
# Within 2 months.
companyInfo[person['company_id']]['percent_within_2_months'] = round(100 * (float(
companyInfo[person['company_id']]['within_2_months'])) / float(companyInfo[person['company_id']]['people']))
# Within 4 months.
companyInfo[person['company_id']]['percent_within_4_months'] = round(100 * (float(
companyInfo[person['company_id']]['within_4_months'])) / float(companyInfo[person['company_id']]['people']))
# Over 4 months.
companyInfo[person['company_id']]['percent_over_4_months'] = round(100 * (float(
companyInfo[person['company_id']]['over_4_months'])) / float(companyInfo[person['company_id']]['people']))
notLoggedIn()
因此剩下的就是将数据写入csv。
我知道这个脚本可能很笨拙，但是我正在学习！
在此先感谢您的帮助！