Chapter 10
In this module, we'll explore the key terms related to data and its study on the internet. We'll also look at the concepts that data scientists use and how to protect your personal information online. Understanding Data: Data comes in different forms like numbers, text, and machine readings. It can be used to support various opinions, so it's crucial to determine its validity. Examples of Data: For instance, test scores (e.g., 34, 56, 74) can be used to calculate an average (e.g., 65.625), giving more meaning to individual scores. Data to Information to Knowledge: Data is collected, and from it, we create information. Understanding and associating data can lead to knowledge. Data Terminology: A dataset is an organized data collection. Valid data represents a concept accurately. Metadata is data about data.
Structured vs. Unstructured Data:
Structured data is well-organized (like spreadsheets or databases). Unstructured data is not organized, like a collection of photos on a phone. Personally Identifiable Information (PII): PII includes information that can identify a person, like a Social Security Number. Tools for Data Scientists: Data Acquisition: Converting real-world measurements into digital data. Data Aggregation: Combining data from various sources. Data Anonymization: Removing personal information for privacy. Data Cleansing: Fixing errors in a dataset. Data Visualization: Creating visual representations for easier understanding.
Data Structures:
Different data structures are used to hold specific data types, like stacks, queues, linked lists, and binary trees. Interface and Implementation: APIs guide interactions with applications. Implementation is how an algorithm is encoded in a program. Social Network Data: Social networks collect, use, and analyze user data. Users should understand how data is collected, what's collected, and how to protect their data. Data Policies: It's vital to know a social network's data policy and that of its partners. Privacy Policies and Data Policies are complex but critical. Do Not Track: An option to avoid website tracking, though not widely supported. Private browsing doesn't prevent sites from saving data about you.