How do I create a new dataset when I need to add new variables?

Question

5b. Time Series Average by Month and Year

You'll need to do a little data prep for this one:

- First figure out the top 5 reviewed coffee shops (by number of reviews ~ hint frequency of coffee_shop_name)

- Create a new dataset for containing those 5 shops, review month and year(numeric?), and the mean num_rating and mean vibe_sent

- The result should look something like this

Month_Year Coffee Shop Mean Rating Mean Vibe Sent

----------- ------------ ------------ ----------------

Jan 2017 Mike's Coffee 4.5 4.3

This is what I tried so far and I'm getting errors:

```{r}

yelp_prep %>%

count(coffee_shop_name)

top_five_coffee <-yelp_prep %>%

filter(coffe_shop_name=="The factory - Cafe with a Soul","Halcyon","Epoch Coffee", "Caffee Medici", "Houndstooth Coffee")

Answer 1

Top 5 Coffee shops:

data %>%

group_by (coffee_shop_name) %>%

summarize(N = n()) %>%

top_n(5)

Create a new dataset for containing those 5 shops:

data %>%

filter(coffee_shop_name %in% c("1st coffee shop", "2nd coffee shop", "3rd coffee shop", "4th coffee

shop", "5th coffee shop")) %>%

group_by(Month_Year, coffee_shop_name) %>%

summarize(Mean_Rating = mean(rating column),

Mean_Vibe_Sent = mean(vibes sent column))