채린's datascience

You did go to the ballet last night, didn't you?: 어제 밤에 결국 발레를 보러 갔죠? 

I just got a call from office.: 방금 사무실로부터 전화가 왔어요.

He wants to meet. He insisted Gassip girl be there.: 그가 보길 원하네요. 가십걸도 같이요. 

I don't know how it happened. I don't want to know.: 어떻게 한건지 알지도 못하고 알고싶지도 않네요. 

But I need you to be less.: 그러니 자중하세요. 

How about you do you. I will do me?: 저는 저대로 실비는 실비대로 하는게 어떨까요? 

And how about a one-way ticket back to Chicago?: 시카고로 돌아가는 편도를 알아보는건 어떨까요? 

Got it. a lot less.: 네 자중할게요. 

Do I know you?: 우리 구면인가요?

It's the ringarde from the marketing firm the other day.: 저번에 만난 마케팅 회사의 링가르드네요.

I just came here to apologize for the other day, for offending you.: 저번에 무례하게 군거 사과하러 왔어요. 

This box is only for VIP guests: 이곳은 귀빈석입니다. 

I don't think Gabriel likes me.: 가브리엘은 내가 싫은가봐. 

What makes you say that?: 왜 그렇게 생각해요? 

I could just tell that he's jealous that I'm with you.: 내가 당신 곁에 있는게 질투가 나나봐요.

I don't think that's true.: 그럴리가 없어요.

We just have to try to be quieter tonight.: 오늘은 조용히 해야해요. 

anyone?: 누구 없나요? 

I'm suprised. All the chefs I know roll their own.: 놀랍네요. 제가 아는 셰프들은 모두 말아피던데. 

Well, now you know one who dosen't.: 그렇지 않은 사람도 한명 알게 됐네요. 

Gabriel, you picked really great wine.: 정말 좋은 와인을 골랐네요.  

Oh, thank you. It's a small organic producer from Rioja.: 고마워요. 리오하에 소규모 유기농 와이너리죠. 

Gabriel knows his wine inside and out.: 가브리엘이라면 와인은 훤히알아요.

Excepts champagne. That is Camile's specialty.: 샴페인 빼고요 그건 카미엘 전문이에요. 

Introduce us to your friend.: 친구분 소개해주세요. 

Thomas, this is my friend, Camile. And her boyfirend, Gabriel.: 제 친구 카밀과 남자친구 가브리엘이에요. 

Gabriel is the chef at the restaurant across the square.: 가브리엘은 길건너 레스토랑의 셰프에요. 

You should join us?: 같이 가실래요? 

No, we wouldn't wanna crash your dinner.: 아뇨 데이트를 망칠 수 없죠. 

It would totally be fun. Please.: 정말 재밌을거에요. 

I love spanish wine. Why not?: 스페인 와인 좋아하니 괜찮겠죠? 

It's great. It's double date then.: 그럼 더블데이트네요. 

I can't believe that I got demoted becasue of accessory.: 악세서리로 좌천되다니 믿을수가 없어요.

He refused to take a shower afterwards he wanted a reminder on him.: 내 향기를 남기고 싶다고 끝나고 샤워를 안 하더라고요. 

Is that weird?: 이상한가요?

I went down a drunk rabbit hole of googling jazz club in Paris.: 술마시고 밤새 재즈클럽을 찾았어요. 

I figured I was going to try singing thing again, I might as well do it here, where no one knows me.: 노래를 다시 시작한다면, 나를 모르는곳에서 하는게 낫다고 생각했어요.

I saw that there is an open audition at Crazy Hole.: 크레이지 홀에서 공개 오디션을 하는걸 봤어요. 

You need to get over it and sing.: 다 잊고 노래해봐요. 

Honestly, sometimes I don't think I'll ever sing again.: 가끔은 영영 노래를 못할거라는 생각이 들어요. 

What about for me?: 날 위해 하는건 어때요?

Not right now.: 지금은 싫어요.

Why not right now? No one pay attention.: 왜 지금은 안되요? 아무도 관심 없는데요.

Just pick any song that you want. I don't gonna judge you.: 평가 안할게요. 아무 노래나 불러봐요.

What do you want me to sing?: 무슨 노래 부르길 원해요? 

I don't know. Whatever you want.: 몰라요. 원하는거요.  

Dont' go down the rabbit hole.: 어렵게 하려고 하지마. 

get over: 넘어가다. 이겨내다. 

Are you sure you don't wanna use my shower?: 정말 안 씻고 가도 되요? 

I don't want to wash you off yet.: 아직 당신을 씻어내기 싫어요. 

Please tell me we will see each other again tonight.: 오늘 저녁에 다시 본다고 말해주세요. 

Who is he?: 누구세요? 

A professor I met last night. I've never done anything like that.: 어제 만난 교수에요. 이런 적 처음이에요. 

For all I know, he could have been murderer.: 그가 살인마였을지도 모르잖아. 

For all I kwow: ~일지도 모른다. 잘 모르지만 내 짐작에는~

Do you think he's son or her lover? : 그는 아들일까요 사랑하는 사람일까요? 

I was just watching to see if the salad is really worth 20 euros.: 그냥 저 샐러드가 20유로인지 정말 궁금해서 봤어요.

She is forceful. Bit controlling. Like a mother.: 그녀는 좀 세네요. 강압적이고 엄마처럼요. 

Now she is feeding him. Like a lover.: 이번엔 애인처럼 먹여주는데요. 

Loser buys the next bottle of wine?: 지는사람이 다음 와인 사기할까요? 

You're so sure. You're right?: 확신이 있네요.

So, how are we gonna know who wins this little wager?: 내기에서 누가 이긴지는 어떻게 알죠? 

I guess we have to sit here until they reveal themselves.: 저들이 뭔지 알때까지 앉아있죠. 

Who's that third guy?: 저 남잔 뭐죠? 

We will never gonna know who won the bet.: 누가 이겼는지 모르겠네요. 

I don't care about the bet. I just wanted to keep talking to you.: 누가 이겼는지는 안중요하교요. 계속 얘기하고 싶어요.

We could talk someplce else?: 다른데서 더 얘기할래요? 

Let’s start with an example: Suppose you're given a dataset that contains the size (in terms of area) of different houses and their market price. Your goal is to come up with an algorithm that will take the size of the house as its input and return its market price as the output.

In this example, the input variable i.e the size of the house, is called the independent variable (X), the output variable i.e house price is called the dependent variable (Y), and this algorithm is an example of supervised learning. 

In supervised learning, algorithms are trained using "labeled" data (in this example, the dependent variable - house price, is considered a label for each house), and trained on that basis, the algorithm can predict an output for instances where this label (house price) is not known. "Labeled data" in this context simply means that the data is already tagged with the correct output. So in the above example, we already know the correct market price for each house, and that data is used to teach the algorithm so that it can correctly predict the house price for any future house for which the price may not be known.

The reason this paradigm of machine learning is known as supervised learning, is because it is similar to the process of supervision that a teacher would conduct on the test results of a student on an examination, for example. The answers the student gives (predictions) are evaluated against the correct answers (the labels) that the teacher knows for those questions, and the difference (error) is what the student would need to minimize to score perfectly on the exam. This is exactly how machine learning algorithms of this category learn, and that is why the class of techniques is known as supervised learning.

There are mainly 2 types of supervised learning algorithms:

1. Regression, where your output variable is a continuous variable, for example, the price of a house.
2. Classification, where your output variable is categorical, for example, approve the loan or not i.e. yes or no categories.

In this lecture, we will be learning about regression algorithms, which obviously find great use in the machine learning prediction of several numerical variables we would be interested in estimating, such as price, income, age, etc.

Linear Regression

Linear Regression is useful for finding the linear relationship between the independent and dependent variables of a dataset. In the previous example, the independent variable was the size of the house and the dependent variable its market price.

This relationship is given by the linear equation: 

Where 

 is the constant term in the equation, 

 is the coefficient of the variable 

, 

is the difference between the actual value 

 and the predicted value (

).

 and 

 are called the parameters of the linear equation, while 

 and 

 are the independent and dependent variables respectively.

What is an error?

With given 

 and 

 in the training data, the aim is to estimate 

 and 

 in such a way that the given equation fits the training data the best. The difference between the actual value and the predicted value is called the error or residual. Mathematically, it can be given as follows:

In order to estimate the best fit line, we need to estimate the values of 

 and 

  which requires minimizing the mean squared error. To calculate the mean squared error, we add the square of each error term and divide the sum with the total number of records: 

The equation of that best fit line can be given as follows: 

Where 

 is the predicted value, 

 are the estimated parameters.

This equation is called the linear regression model. The above explanation is demonstrated in the below picture:

Before applying the model over unseen data, it is important to check its performance to make it reliable. There are a few metrics to measure the performance of a regression model.

1. R-squared: R-squared is a useful performance metric to understand how well the regression model has fitted over the training data. For example, an R-squared of 80% reveals that 80% of the training data fit the regression model. A higher R-squared value generally indicates a better fit for the model.
   
   
2. Adjusted R-squared: The adjusted R-squared is a modified version of R-squared that takes into account the number of independent variables present in the model. When a new variable is added, adjusted R-squared increases if that variable adds value to the model, and decreases if it does not. Hence, adjusted R-squared is a better choice of metric than R-squared to evaluate the quality of a regression model with multiple independent variables, because adjusted R-squared only remains high when all those independent variables are required to predict the value of the dependent variable well; it decreases if there are any independent variables which don't have a significant effect on the predicted variable.
   
   
3. RMSE: RMSE stands for Root Mean Squared Error. It is calculated as the square root of the mean of the squared differences between actual outputs and predictions. The lower the RMSE the better the performance of the model. 
   Mathematically it can be given as follows: