recsys_spark icon indicating copy to clipboard operation
recsys_spark copied to clipboard

关于usercf

Open DoubleYing opened this issue 4 years ago • 2 comments

在u2u2i的过程中,没有看到找相似user的过程。或者说, val df_user_prefer2 = df_user_prefer1.withColumn("score", col("pref") * col("similar") * (lit(1) / log(col("sum_item") * hot_item_regular + math.E))).select("useridJ", "itemid", "score") 这一行,为什么可以直接去掉useridI这一项呢?

DoubleYing avatar Jun 09 '20 12:06 DoubleYing

df_sales8就是用户相似矩阵 把useridI去掉是因为他是桥梁,join之后就不需要他了

---原始邮件--- 发件人: "DoubleYing"<[email protected]> 发送时间: 2020年6月9日(周二) 晚上8:09 收件人: "xiaogp/recsys_spark"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: [xiaogp/recsys_spark] 关于usercf (#2)

在u2u2i的过程中,没有看到找相似user的过程。或者说, val df_user_prefer2 = df_user_prefer1.withColumn("score", col("pref") * col("similar") * (lit(1) / log(col("sum_item") * hot_item_regular + math.E))).select("useridJ", "itemid", "score") 这一行,为什么可以直接去掉useridI这一项呢?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

xiaogp avatar Jun 09 '20 12:06 xiaogp

嗯,好像看懂了,谢谢您的回复

DoubleYing avatar Jun 09 '20 12:06 DoubleYing