Unit Nine: Inheritance

Cleaning Data

a process that makes the data uniform without changing its meaning (e.g., replacing all equivalent abbreviations, spellings, and capitalizations with the same word).

Correlation

a relationship between two pieces of data, typically referring to the amount that one

Crowdsourcing

the practice of obtaining input or information from a large number of people via the Internet.

Information

the collection of facts and patterns extracted from data

Data Filtering

choosing a smaller subset of a data set to use for analysis, for example by eliminating / keeping only certain rows in a table

Metadata

data about data

Metadata

This can be changed without impacting the primary data

Metadata

This is used for finding, organizing, and managing data

Metadata

This increases the effective use of data by providing extra information

Metadata

This allows data to be structured and organized

Causation

correlation does not equal

Correlation

similarities, patterns

Causation

This thing that caused that thing

Visualizations of Data

This helps to look a lot of data at once and see patterns that are "invisible" if you just look at a table

Data Analysis Process

1. collect or choose data

2. Clean and/or filter data

3. Visualize and Find Patterns

4. Generate new information

Collect or Choose data

What is the first step of the data analysis process

Clean and/or filter

What is the second step of the data analysis process

visualize and find patterns

What is the third step of the data analysis process

generate new information

What is the fourth step of the data analysis process

Bar chart

What chart counts how many times each value in the column appears and then makes a bar at that height?

Bar Chart

Which chart shows what value(s) are most and least common?

Histogram

What type of chart puts numbers in buckets?

Histogram

What type of chart shows what range of value(s) are most or least common?

Cleaning Data

What would need to happen if data is incomplete, invalid, or if multiple tables could be combined into one?

Cleaning Data

What happens first cleaning data or filtering the data?

Data Filtering

What would need to happen if the user wanted to look at a subset of the data?

Bar charts and histograms

What types of charts are useful for looking at one column of data?

Crosstab chart

What chart counts how often pairs of values in two column appear?

Crosstab chart

What type of chart is useful for finding the most and least common combinations of values in two columns, finding patters, and exploring two columns when one or both are strings?

Scatter chart

What shows combinations of values from two columns?

Scatter chart

What type of chart is useful for seeing patterns and trends between two values, and numeric data with lots of different values?

1

1 column or 2: Knowing what is in the data set, what values are present, what's the range, where are the clusters of values

2

1 column or 2: see how changed to one value impacts another

Open Data

What is sharing data with others so they can analyze it?

Medical Journals

What is an example of open data?

Citizen Science and Crowdsourcing

What is collecting data from others so you can analyze it?

Citizen Science

What is the data collection that is done by members of the public using their own computing devices?

Big Data

What is collecting huge amounts of data so we can learn even more from it?

Machine Learning

What is a computer that can recognize patterns and make decisions without explicitly being programmed?

Data Bias

What is data that does not accurately reflect the full population or phenomenon being studied?