This is the first course in the Google Data Analytics Certificate. These courses will equip you with the skills you need to apply to introductory-level data analyst jobs. Organizations of all kinds need data analysts to help them improve their processes, identify opportunities and trends, launch new products, and make thoughtful decisions. In this course, you’ll be introduced to the world of data analytics through hands-on curriculum developed by Google. The material shared covers plenty of key data analytics topics, and it’s designed to give you an overview of what’s to come in the Google Data Analytics Certificate. Current Google data analysts will instruct and provide you with hands-on ways to accomplish common data analyst tasks with the best tools and resources. Learners who complete this certificate program will be equipped to apply for introductory-level jobs as data analysts. No previous experience is necessary. By the end of this course, you will: - Gain an understanding of the practices and processes used by a junior or associate data analyst in their day-to-day job. - Learn about key analytical skills (data cleaning, data analysis, data visualization) and tools (spreadsheets, SQL, R programming, Tableau) that you can add to your professional toolbox. - Discover a wide variety of terms and concepts relevant to the role of a junior data analyst, such as the data life cycle and the data analysis process. - Evaluate the role of analytics in the data ecosystem. - Conduct an analytical thinking self-assessment. - Explore job opportunities available to you upon program completion, and learn about best practices in the job search. View Discussion Improve Article Save Article Like Article In this article, we are going to discuss life cycle phases of data analytics in which we will cover various life cycle phases and will discuss them one by one. Data Analytics Lifecycle :
1) Fill in the blank: A business decides what kind of data it needs, how the data will be managed, and who will be responsible for it during the _____ stage of the data life cycle. Ans: Plan 2) The destroy stage of the data life cycle might involve which of the following actions? Select all that apply. Ans:
3) A data analyst uses a spreadsheet function to aggregate data. Then, they add a pivot table to show totals from least to greatest. This would happen during which stage of the data life cycle? Ans: Analyze 4) The data life cycle deals with the stages that data goes through; data analysis involves following a process to analyze data. Ans: True 5) What actions might a data analytics team take in the act phase of the data analysis process? Select all that apply. Ans:
6) What is the main difference between a formula and a function? Ans: A formula is a set of instructions used to perform a specified calculation; a function is a preset command that automatically performs a specified process 7) Fill in the blank: A query is used to _____ information from a database. Select all that apply. Ans: 8) Structured query language (SQL) enables data analysts to communicate with a database. Ans: True 9) A data analyst has finished an analysis project that involved private company data. They erase the digital files in order to keep the information secure. This describes which stage of the data life cycle? Ans: destroy 10) Data analysts use queries to request, retrieve, and update information within a database. Ans: True 11) Fill in the blank: The data life cycle has six stages, whereas data analysis has six _____. Ans: process steps 12) Fill in the blank: A function is a predefined operation, whereas a formula is _____. Ans: a set of instructions used to perform a specified calculation. 13) Fill in the blank: To request, retrieve, and update information in a database, data analysts use a ____. Ans: query 14) Fill in the blank: Structured query language (SQL) enables data analysts to _____ the information in a database. Select all that apply. Ans: When we think about data and analytics the first thing that comes to mind is data, graphs, reports, and metrics. A more fundamental question is how do we get there? Analytics just doesn’t happen. There are clearly defined steps that need to occur as we embark on our analytics journey. Let’s look at how data and analytics drives informed decision making. We will do this by looking at the analytics process to understand how to get the most of data and analytics. Data Analysis: The first thing to understand is that data analysis and analytics is driven by a well-defined lifecycle. The steps in that lifecycle lead to the development of a solution that is in alignment with business outcomes. The CRISP-DM® process is an industry-accepted approach for data analysis and data mining. Don’t be put off by the term data mining, it simply means the extraction of usable data from a larger set of data for the purpose of analysis. Now, back to the CRISP-DM process. Let’s delve into the process and understand the implication of the steps: Business Understanding: Business understanding and the desired business outcomes define the data requirements from sourcing, quality, relevance and timeliness perspectives. The level of business understanding defines the likelihood of success or failure for a data analysis initiative. Data Understanding: This is where the characteristics are uncovered. Questions answered at this stage are:
Note that the reciprocal relationship between “Business Understanding” and “Data Understanding.” As business needs change so may the required data; conversely, the available data may provide a deeper business understanding. Data Preparation: Data preparation can be the most underestimated and overlooked process step. Approximately 75% of data analysis can be tied to data collection and preparation. Not surprisingly, a large portion of this time is tied to the resolution of data quality issues. The remainder of the time is used to prepare data for further analysis. It should be noted that the same data may be prepared in different ways depending upon its usage. Data quality is one of the most significant issues that lead to bad decision making and extremely detrimental to an organization. This raises the question of how much effort is required to develop and deploy and data quality remediation strategy. Addressing major data quality issues should be of primary importance and any decisions related to data quality remediation or data transformation should be documented to maintain a record of data lineage. Modeling: Whether it is a financial model, statistical or machine learning model, all the hard work begins to come to fruition in this step. The key point is to choose some model(s) appropriate for the type, quantity, and nature of the data. If multiple models are used, their overall performance must be evaluated to determine the most suitable model. There is a reciprocal relationship between the Data “Preparation” steps and “Modeling.” This means that the data preparation step may be revisited to support changing model requirements. Evaluation: Now that all the modeling is completed, it is time for model evaluation. Each model is evaluated to determine how well it meets overall “Business Understanding” and the associated business outcomes. The model evaluation will drive “Business Understanding” which will, in turn, drive the “Data Understanding,” “Data Preparation” and “Modeling” steps. Data visualization should also be included in the evaluation step. Visualizing the results of the modeling step provides makes it easier to evaluate the overall performance of the model and may. It also may uncover previously unknown insights. Deployment: The final step is deployment. This is where the results are shared with business partners for review and comment. During the deployment phase, consideration needs to be given to: Review of the final analytics solution to determine how well it matched expected business outcomes:
Summary: The data mining and analytics lifecycle (CRISP®) is a framework for successful data analysis and deployment of analytic solutions. Some may view this process as time-consuming, however; without a well-defined approach, much more time can be wasted trying to figure out how to get started and how to proceed with the development and deployment of a data mining/analytics solution. |