Week 7: 10/17 -10/23

This week I worked on the code trying to get a visual out put for our working code. At the weekly meeting one of our group members gave a presentation on how to use GitHub, a website we are sharing our code on. We also got confirmation that we are able to access Groupons API so we can get the data.

This upcoming week:

  1. Continue to work on code. Try to get visual output.
  2. Try out Groupons API data get-er.

 

“As knowledge increases, wonder deepens”

-Charles Morgan

Week 6: 10/9-10/16

HOUSTON WE HAVE NO PROBLEMS! With help from our advisor we have our code working! This has been what we have working on for the past couple weeks and its nice to see that we have finally made some progress towards it.

Looking forward:

  • Keep on messing around with the code, try to get a visual output for what we got.
  • Continue reading about recommender systems.

“The heights by great men reached and kept, were not attained by sudden flight, but they, while their companions slept, were toiling upward in the night. ”

-Henry Wadsworth Longfellow

Week 4:9/25-9/31

Week 4 down! We keep on chugging along. This week I continued coding our association rules project. Since I was still struggling with it I asked Elizabeth, one of my research-mates who is a computer science major, for help. Elizabeth helped me with one part and I am still working on the rest. Hopefully next week when I write my blog I will be able to say the coding is completed!

Our weekly to do list was once again to:

  • Code Alice recommender program in Python.

“Failure will never overtake me if my determination to succeed is strong enough.”

-Og Mandino

Week 3: 9/17 – 9/24

Week three down! This week I started to begin coding for the Alice problem we have been working on for the last two weeks. This has been the biggest struggle thus far as I am still learning python.

Our weekly to do list was pretty short, but don’t let that confuse you it was still a hard task. Like my dad always says “Quality over quantity”:

  • Code the Alice recommender program in python.

 

So I began by writing the pseudo-code for the program and the steps seemed relatively easy:

  1. Upload data
  2.  Complete confidence and support for all data points.
  3.  Arrange the confidence and support in descending order.
  4. Get the suggestions

So After I had written my pseudo code I began to try to code this in python. The only step I have fully completed was to upload my data.

Now moving forward this week at the team meeting I will talk to  my peers and try to see if anyone has any help they can give me about this program moving on.

“Our greatest glory is not in never falling, but in rising every time we fall”

— Confucius

 

 

 

Week 2: 9/12- 9/17

Week two down! This week I had more time to look at the nitty and gritty of recommender programs and got to work more on the problem I was working on last week.

Our Weekly to-do list from our adviser was:

  • Turn in all documents.
  • Watch the webinar.
  • Continue to learn a priori and lift.

So, during this week, I have read more on recommender systems, specifically lift and , and worked on the same Alice problem that I was working on last week. This week I have also completed and turned in all of my paperwork! The webinar wasn’t shown so that wasn’t completed.

I have continued to try to figure out an ordered list of deals as a recommendation for Alice, and next week I should be able to answer that question, and share it with all of you.

Looking forward:

  1. Finish the Alice Problem.
  2. Continue reading up on recommender programs especially lift and a priori.
  3. Keep on keeping on.

“Success is not final, failure is not fatal: it is the courage to continue that counts.”

-Winston Churchill

 

Week 1: 9/5 – 9/12

I have successfully completed week one of the CREU blog. During this time I have met the other 3 members of my team and our two advisers. We were tasked with reading a couple papers about recommender systems.

  • Association Rules- Support and Confidence.
  • Data Mining: Apriori Algorithm
  • Mining Association Rules

Once we were done reading those papers we were given our first real assignment:

  1. Use association rules to develop an ordered list of deals as a recommendation for Alice.

One big struggle of mine is procrastination, and so its 10pm the night before the meeting with the CREU team to discuss our answers and I am unsure on how to finish the problem. I think I have figured the first 3/4th of the problem but am stuck on the last 1/4th. This is a small problem as I have had a week to look over it and figure it out. Tomorrow before our team meeting I plan on asking the adviser to look over my work and give me a small nudge in the right direction.

 

Moving onward I plan on:

  • Looking at the research more than the day before it is due.
  • Read more papers and learn more about recommender systems.
  • Talk more with the group members and bounce ideas off of one another.

All in all I would say it was a successful first week!

 

“With the new day comes new strength and new thoughts.” – Eleanor Roosevelt