Data Science Terms
Getting a mop and a bottle of windex will help. I'm trying to...
What is data cleaning?
This type of graph uses different lengths to show a property of the data. (It's not about beer!)
What is a bar chart?
CSV files separate values using this character
What is a comma?
It's not quite a flying dinosaur, but a lot of kids think they are
What is a pteroDACtyl?
This 2004 movie was about average girls
What is "Mean Girls"?
You won't catch any fish here, but it's full of data.
What is a data lake?
This type of plot uses dots to show how two variables relate
What is a scatter plot?
We abbreviate this term by "NaN" to represent missing or undefined values in a dataset.
What is "Not a Number"?
This mountain range is good for a nice hike
What are the "AdironDACks"?
This 1999 movie's title is also about the type of algebra we need for ML
What is "The Matrix"?
Getting Stephane's help in learning is not exactly this, but it has the same name.
What is supervised learning?
This chart type is made of slices to show proportions
What is a pie chart?
We can "go dutch" on a dataset using this -- not to split the bill, but to assess a model's performance
What is data splitting?
We can't let see anyone see that! We have to __ it in the document
What is "reDACt"?
Gosset and Stephane's favorite beer
What is Guinness?
My car's battery is shot! Also, my model needs to combine many weak learners. I need...
What is boosting?
Help! I have too many vars. This type of EDA plot can help tell which are similar to one another.
What is a correlogram?
When you're learning in the Mariana Trench, you're doing this
What is "Deep Learning"?
We have five fingers. We are ___
What is "pentaDACtyl"?
We're always asking our clients for more of this Lieutenant Commander in Star Trek
What/who is Data?
Mark Carney may be building one of these to the west (and Hilda's always talking about them)
What is a pipeline?
A map that uses colors to represent data values in specific geographic areas
What is a choropleth map?
Some people think it's when the pope agrees with you
What is "cross validation"?
What is "diDACtics"?
This 1984 Schwarzenegger movie is also how you close a stalled R script