叶柖的博客

RFM模型是衡星客户价值和客户创利能力的重要工具和手段。通过一个客户的近期购买行为、购买的总体频率以及花了多少钱三项指标来描该客户的价值状况。●R：最近一次消费时间(最近一次消费到参考时间的间隔)●F：消费的频次●M：消费的金额(总消费金额)数据格式df.shape(541909, 8)df.info()统计缺失率df.apply(lambda x:sum(x.isnull()).len(x),axis=0)...

Measurements for Shenyang, Chengdu, Beijing, Guangzhou, and Shanghai数据来源：https://www.kaggle.com/uciml/pm25-data-for-five-chinese-cities北京PM2.5随时间变化情况数据列The time period for this data is between Jan 1st, 2010 to Dec 31st, 2015. Missing data are denoted

Ten thousand books, one million ratings. Also books marked to read, and tags.数据来源：https://www.kaggle.com/zygmunt/goodbooks-10k统计图书出版年份与数量及评分的关系会用到book_id original_publication_year average_ratingimport pandas as pdfrom matplotlib import pyplot as plt

数据来源：https://www.kaggle.com/starbucks/store-locations/data

数据来源：https://www.kaggle.com/damianpanek/sunday-eda/data数据列名1.电影时长分布import pandas as pdfrom matplotlib import pyplot as pltfile_path = './IMDB-Movie-Data.csv'df = pd.read_csv(file_path)time_data = df['Runtime (Minutes)'].valuesmax_time = time_da

数据来源：https://www.kaggle.com/datasnaek/youtube1.视频点赞数与评论数的关系刚开始使用np.loadtxt()处理数据出错Wrong number of columns at line %d原因1：使用,作分隔符，数据中,产生干扰，将,替换为、或者其他字符原因2：comments默认为#，之后的字符默认都被注释掉，将comments设置为None之后还是有其他行报错改为用np.genfromtxt()，可以处理缺失数据等信息（如果知道其他报错的原因还请各