hey, everyone , am working on a movie data sets of different domain. I have use java to calculate the top ratings number, but wanted to use R to calculate how the average rating of each genre change over time in each dataset.
but I can only access, one dataset genre information while the second dataset has it own as character.
Article In-memory, distributed content-based recommender system
Perhaps you could describe the data some more. For example, what are row and column meanings, and what do the entry numbers mean? Also, what does "has to be merge" mean? MM was being very generous in his detailed answer.
Very interesting work!
A full and useful answer to this question depends on a lot of things:
1. What format is your data in BEFORE you import it into R? This will determine how you want R to read it. (i.e. what code to use). Generally, read.table() works for ordered data, readLines() works for almost any. There are specific packages for Excel files and other specialty files.
2. What are the values of the matrix/data frame? Are the values all numeric or are some character? This will determine what class of object you should use to represent the data in R.
3. If you can get the data into R, then index the data to obtain these columns (also depends on the layout of your data): col 1. rating, col 2. genre, col 3. year. The index you use depends on the layout of the data.
4. Depending on the form of your data, you will want to use a matrix or even a list. You can use apply() functions over the list.
5. Finally, plot() the data.
Without knowing the structure of your data, it is very difficult to recommend specific R functions and scripts to you (sorry!). Please attach a sample of the data and a description and people can recommend to you some functions and/or packages to use.
Thanks!
Matthew
hello mattew,
attached are the dataset for the work,
both files has to be merge in order to produce the complete dataset that contain, genre information and rating month.
thanks for your contribution
Perhaps you could describe the data some more. For example, what are row and column meanings, and what do the entry numbers mean? Also, what does "has to be merge" mean? MM was being very generous in his detailed answer.
I agree with Dan. Without any further description nobody will be able to help. I see that moviedetails.tsv contains the movie names associated with the row numbers of moviegenre.tsv. But the rows (1 to 1682) appear twice in moviegenre.tsv. This seems rather odd.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package