Well, Pandas keeps making it easy for us, and has a corrwith function that you can see in the following code that we can use:

similarMovies = movieRatings.corrwith(starWarsRatings) 
similarMovies = similarMovies.dropna() 
df = pd.DataFrame(similarMovies) 
df.head(10) 

That code will go ahead and correlate a given column with every other column in the DataFrame, and compute the correlation scores and give that back to us. So, what we're doing here is using corrwith on the entire movieRatings DataFrame, that's that entire matrix of user movie ratings, correlating it with just the starWarsRatings column, and then dropping all of the missing results with dropna. So, that just leaves us with items that had a correlation, where there was more than one person that viewed it, and we create a new DataFrame based on those results and then display the top 10 results. So again, just to recap:

1. We're going to build the correlation score between Star Wars and every other movie.
2. Drop all the NaN values, so that we only have movie similarities that actually exist, where more than one person rated it.
3. And, we're going to construct a new DataFrame from the results and look at the top 10 results.

And here we are with the results shown in the following screenshot:

We ended up with this result of correlation scores between each individual movie for Star Wars and we can see, for example, a surprisingly high correlation score with the movie 'Til There Was You (1997), a negative correlation with the movie 1-900 (1994), and a very weak correlation with 101 Dalmatians (1996).

Now, all we should have to do is sort this by similarity score, and we should have the top movie similarities for Star Wars, right? Let's go ahead and do that.

similarMovies.sort_values(ascending=False) 

Just call sort_values on the resulting DataFrame, again Pandas makes it really easy, and we can say ascending=False, to actually get it sorted in reverse order by correlation score. So, let's do that:

Okay, so Star Wars (1977) came out pretty close to top, because it is similar to itself, but what's all this other stuff? What the heck? We can see in the preceding output, some movies such as: Full Speed (1996), Man of the Year (1995), The Outlaw (1943). These are all, you know, fairly obscure movies, that most of them I've never even heard of, and yet they have perfect correlations with Star Wars. That's kinda weird! So, obviously we're doing something wrong here. What could it be?

Well, it turns out there's a perfectly reasonable explanation, and this is a good lesson in why you always need to examine your results when you're done with any sort of data science task-question the results, because often there's something you missed, there might be something you need to clean in your data, there might be something you did wrong. But you should also always look skeptically at your results, don't just take them on faith, okay? If you do so, you're going to get in trouble, because if I were to actually present these as recommendations to people who liked Star Wars, I would get fired. Don't get fired! Pay attention to your results! So, let's dive into what went wrong in our next section.