Introduction to Data Analytics | Week 3

Course Link: https://in.coursera.org/learn/introduction-to-data-analytics/

Gathering Data

Practice Quiz

1. What are the requirements in order for data to be reliable? (Select all that apply)

Data should be free of all errors 

Data should be easy to collect 

Data should be structured

Data should be relevant 

2. What type of data is produced by wearable devices, smart buildings, and medical devices?

Observation study data

Sensor data

Census data

Survey data

3. What type of data is semi-structured and has some organizational properties but not a rigid schema?

 Online forms 

 Web logs

 Emails

Data from OLTP systems

Graded Quiz

1. What are some of the steps in the process of “Identifying Data”? (Select all that apply)

Determine the visualization tools that you will use

 Define a plan for collecting data 

 Determine the information you want to collect 

 Define the checkpoints 

2. What type of data refers to information obtained directly from the source?

 Primary data 

 Sensor data 

 Third-party data 

 Secondary data 

3. Web scraping is used to extract what type of data? 

Data from news sites and NoSQL databases

Images, videos, and data from NoSQL databases

Text, videos, and data from relational databases

Text, videos, and images

4. Data obtained from an organization’s internal CRM, HR, and workflow applications is classified as:

Copyright-free data

Primary data

Third-party data

Secondary data

5. Which of the provided options offers simple commands to specify what is to be retrieved from a relational database?

Web Scraping

RSS Feed

SQL

API

Wrangling Data

Practice Quiz

1. What is one of the common structural transformations used for combining data from one or more tables?

Denormalization

Joins

Cleaning

 Normalization 

2. What tool allows you to discover, cleanse, and transform data with built-in operations?

Watson Studio Refinery

Google DataPrep

Trifacta Wrangler

OpenRefine

 3. What is data called that does not fit within the context of the use case?

 Duplicate data 

 Irrelevant data 

 Relevant data

 Missing data 

Graded Quiz

1. What does a typical data wrangling workflow include?

Using mathematical techniques to identify correlations in data

Predicting probabilities

Validating the quality of the transformed data 

Recognizing patterns

2. OpenRefine is an open-source tool that allows you to: 

Automatically detect schemas, data types, and anomalies

Use add-ins such as Microsoft Power Query to identify issues and clean data

Transform data into a variety of formats such as TSV, CSV, XLS, XML, and JSON

Enforces applicable data governance policies automatically

3. What is one of the steps in a typical data cleaning workflow? 

Inspecting data to detect issues and errors

Building classification models

Clustering data

Establishing relationships between data events

4. When you’re combining rows of data from multiple source tables into a single table, what kind of data transformation are you performing?

Denormalization

Unions

Normalization

Joins

5. When you detect a value in your data set that is vastly different from other observations in the same data set, what would you report that as?

Outlier

Syntax error

Missing value

Irrelevant data