<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Akwamfon Eventus on Medium]]></title>
        <description><![CDATA[Stories by Akwamfon Eventus on Medium]]></description>
        <link>https://medium.com/@akwamfoneventus?source=rss-3d98526c1e10------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*SYjtkAKCzMDQ1QGFMeuN-g.jpeg</url>
            <title>Stories by Akwamfon Eventus on Medium</title>
            <link>https://medium.com/@akwamfoneventus?source=rss-3d98526c1e10------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 03:36:42 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@akwamfoneventus/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[A Peek into the Android App Market Before COVID-19]]></title>
            <link>https://medium.com/@akwamfoneventus/a-peek-into-the-android-app-market-before-covid-19-144bb917aeb3?source=rss-3d98526c1e10------2</link>
            <guid isPermaLink="false">https://medium.com/p/144bb917aeb3</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[marketing]]></category>
            <category><![CDATA[android]]></category>
            <dc:creator><![CDATA[Akwamfon Eventus]]></dc:creator>
            <pubDate>Sat, 10 Sep 2022 15:35:38 GMT</pubDate>
            <atom:updated>2022-09-11T16:04:58.032Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/900/1*npmX3b3-ByYjXhTOXONctw.png" /></figure><p>It is an indisputable fact that the emergence of smartphones has reshaped the narratives of many things in human endeavour and generally modern cultures, smartphones offer almost limitless possibilities right in the palm of our hands as we can get nearly anything done with just a few taps on our screens.</p><p>Aside from durable hardware, it is true that a smartphone is as good as its software, if smartphones were magic wands, mobile apps would be the magic spells, these days there is almost an app for everything.</p><p>In the short history of smartphones and mobile apps, there have been 2 major players leading the smartphone technology, namely Android Inc (Google owned) and iOS (Apple Inc. owned).</p><p>At 71% Android has been leading the Mobile Operating System Market Share Worldwide since 2009 and as recent as August 2022 (source — <a href="https://gs.statcounter.com/os-market-share/mobile/worldwide">© StatCounter</a>).</p><p>This report aims at telling the story of the Google Playstore as the number one android apps market, this data analysis reports answers some insightful questions about android apps on Google Playstore before the COVID-19 years, effectively from 2010–2018.</p><p>PS: This analysis does not cover the complete Playstore app population but is a worthy sample of over 10,000 apps. The data for this analysis can be found on <a href="https://www.kaggle.com/datasets/lava18/google-play-store-apps">Kaggle</a> alongside the programming <a href="https://www.kaggle.com/code/akwamfoneventus/google-play-store-app-prep-cleaning-r">R-script</a> used for analysis.</p><p>The <a href="https://app.powerbi.com/view?r=eyJrIjoiYjM5NjdjNGItMGI2Ni00ZWI4LThhZWEtNmMwNTliYmMzMmZhIiwidCI6IjNmM2VjZDFlLTQ5OGQtNDYyNy1hZDA0LWIxMDk1YjE5NzYwYSIsImMiOjh9">interactive visual</a> report of this project can be found <a href="https://app.powerbi.com/view?r=eyJrIjoiYjM5NjdjNGItMGI2Ni00ZWI4LThhZWEtNmMwNTliYmMzMmZhIiwidCI6IjNmM2VjZDFlLTQ5OGQtNDYyNy1hZDA0LWIxMDk1YjE5NzYwYSIsImMiOjh9">here</a> for in-depth insights and comparison. While you are yet to do that allow me to share with you the major events of this market story below;</p><p><strong>ANDROID MARKET SIZE &amp; ADOPTION</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tIC1xQ98fkanlJzxtTb7sg.png" /><figcaption>Report snippet — the trend of total apps published from 2010– 2018</figcaption></figure><p>As seen in the chart above the android app market recorded linear growth over the years with a 71% change between 2016 and 2018 with a total of above 10k apps published.</p><p>Consequently, over 146 billion apps have been downloaded in a period of 8 years with significant growth from 2017- 2018.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*MKHfMB6dQiRVYoIFQNfuYA.png" /><figcaption>Report snippet — Trend of average apps downloaded from 2010– 2018</figcaption></figure><p><strong>QUICK PLAYSTORE MATHS</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*dQpAbLOsig5MxLRrf3yUSw.png" /><figcaption>Report snippet — Data Aggregates</figcaption></figure><p>Above is a quick stats on the total apps published(10,357), total app category(34), total app genres(120), and total installation(146.6 billion+ downloads).</p><p><strong>APP PERFORMANCE ANALYSIS</strong></p><p>The following visuals will share insight into how different apps perform agast each other based on featured criteria and metrics but first let’s see how the app categories performed.</p><p>The highest number of published apps came from the Family category.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Iqegp3TFOh46kZ9jncs2-Q.png" /><figcaption>Report snippet — the best performing category by published apps</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*VP6XGRKDas6iPiEyv-QUIA.png" /><figcaption>Report snippet — the best performing category by downloads</figcaption></figure><p>The highest number of downloaded apps came from the Game category, this would be quite expected as the population of young people using smartphones increases and their affinity towards video gaming can only be enabled by technology such as flexible smartphones.</p><p><strong>MOST DOWNLOADED APP</strong></p><p>You may be wondering which app came out as the most downloaded app in this analysis, it&#39;s not hard to guess, Google Photos came out most downloaded, in fact, the only apps performing above 3 billion downloads were all Google apps.</p><p>The theory behind these numbers might be that some of them come in pre-installed or are part of the requisite apps for the operating system to function optimally.</p><p>The runner-ups either fell into communications or gaming categories which rightly to the category insights earlier stated.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/574/1*woOKgzg7QBGS9PJWOAYIBw.png" /></figure><p><strong>MOST DOWNLOADED APP</strong></p><p>What would make an app rank the most based on the number of reviews?</p><p>That should be a worthy question for another analysis, but the findings from this analysis present the most reviewed apps on Playstore in the visuals below —</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/536/1*oVFz5rPQBATv7ORWxUFErA.png" /></figure><p>Furthermore to answer the question of why my theory would be that the most reviewed apps be assessed based on user rating and sentiment analysis to draw more insights.</p><p><strong>CORRELATION ANALYSIS</strong></p><p>The only positive correlation between the variables of this dataset is the relationship between size and rating as shown below</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/564/1*GWTZdNbvxb_KHTbeyUMrkw.png" /></figure><p><strong>CONCLUSION</strong></p><p>This analysis has been able to bring some first-hand information on the pre covid years of android apps on Playstore, as earlier stated, the insights from this analysis is is based on a worthy sample, thus this might not statistically reflect the actual state of the Paystore app market up to date.</p><p>But more or less this is a peek into the probable state of the android market and as such can serve as a guide to further comprehensive research that can be useful in marketing analytics and feasibility studies for product designs.</p><p>Above all, I thank you for your patience to read this to the end, do follow me for more related content.</p><p>Cheers!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=144bb917aeb3" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How Does a Bike-Share Navigate Speedy Success?]]></title>
            <link>https://medium.com/@akwamfoneventus/how-does-a-bike-share-navigate-speedy-success-370935f9f652?source=rss-3d98526c1e10------2</link>
            <guid isPermaLink="false">https://medium.com/p/370935f9f652</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[r]]></category>
            <category><![CDATA[cycling]]></category>
            <category><![CDATA[documentation]]></category>
            <category><![CDATA[power-bi]]></category>
            <dc:creator><![CDATA[Akwamfon Eventus]]></dc:creator>
            <pubDate>Mon, 22 Aug 2022 01:52:40 GMT</pubDate>
            <atom:updated>2022-08-22T02:05:59.545Z</atom:updated>
            <content:encoded><![CDATA[<p>A Google Data Analytics Capstone Project</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DTmRsRR7xseacdw4lwMDkw.jpeg" /><figcaption>Bike Image — source: Pixabay</figcaption></figure><p>This is a Data Analysis documentation for my Google Data Analytics Capstone Project, this Documentation will cover the following Phases of Data Analysis processes and related project documentation.</p><p>Case Study Scenario</p><p><strong>Ask</strong></p><p><strong>Prepare</strong></p><p><strong>Process</strong></p><p><strong>Analyze</strong></p><p><strong>Share</strong></p><p><strong>Case Study &amp; Scenario</strong></p><p><strong>Case Study Title:</strong> How Does a Bike-Share Navigate Speedy Success?</p><p>Scenario: You are a junior data analyst working in the marketing analyst team at Cyclistic, a bike-share company in Chicago.<br>The director of marketing believes the company’s future success depends on maximizing the number of annual memberships.</p><p>Therefore, your team wants to understand how casual riders and annual members use Cyclistic bikes differently.</p><p>From these insights, your team will design a new marketing strategy to convert casual riders into annual members. But first, Cyclistic executives must approve your recommendations, so they must be backed up with compelling data insights and professional data<br>visualizations.</p><p><strong>Ask</strong></p><p>Three questions will guide the future marketing program, and have been distilled into the following business task;<br>1. How do annual members and casual riders use Cyclistic bikes differently?<br>2. Why would casual riders buy Cyclistic annual memberships?<br>3. How can Cyclistic use digital media to influence casual riders to become members?</p><p>I am also tasked to produce a report with the following deliverables:<br>1. A clear statement of the business task<br>2. A description of all data sources used<br>3. Documentation of any cleaning or manipulation of data<br>4. A summary of your analysis<br>5. Supporting visualizations and key findings<br>6. Your top three recommendations based on your analysis</p><p><strong>Statement of Bussiness task</strong></p><p>This analysis aims to identify and understand how the member and casual customers use Cyclistic bikes differently, and how these differences would affect casual riders buying annual memberships.</p><p><strong>Data Sources &amp; Organization</strong></p><p>The data set for this case study is organized in a tabular structure of 12 columns and 4,190,052 rows(merged records). Data sets are hosted in a public domain, stored as CSV flat files and uploaded as zip files. The archive can be accessed at [<a href="https://divvy-tripdata.s3.amazonaws.com/index.html](Link)">https://divvy-tripdata.s3.amazonaws.com/index.html](Link)</a></p><p><strong>Cleaning &amp; Manipulation documentation</strong></p><p><strong>— Merging of unique datasets</strong></p><p>A total of 10 unique CSV files were merged using R, resulting in a total of 12 columns and 4,190,052 rows.</p><p><strong>— Dropping of missing values, variables and records.</strong><br>I calculated 658,541, 238 missing (“NA”) value, 238,579 missing records(rows) and 3,951,473 complete records(row)</p><p><strong>— Regularization of merged data</strong><br>Missing values and records were dropped from the dataset to make it consistent and complete.</p><p><strong>— Adding a new variable</strong><br>Four new columns with the title (month,week_day,day_n, hour, ride_length) were created with mutate() function and lubridate library to prep data ahead of visualisation, and day_n was to assist sort the visuals by day of the week (Sunday — Saturday),</p><p><strong>Checking data for integrity</strong></p><p>This data meets the ROCC standards of integrity:</p><p><strong>— Reliability:</strong> The sample size is above 30 and is statistically credible to reflect the overall behaviour of the total population.</p><p><strong>— Originality:</strong> Dataset is originally provided by Motivate International Inc.</p><p><strong>— Comprehensive:</strong> Data seems comprehensive as it provides a time stamp entry of all the related information for each unique trip, this provides the variables needed to deduce credible insight.</p><p><strong>— Current:</strong> Data is up to date for all the months of 2020, each day across the year is captured in the dataset.</p><p><strong>— Licensing:</strong> This project has adhered to the clauses and terms of the license provided [here](<a href="https://www.divvybikes.com/data-license-agreement">https://www.divvybikes.com/data-license-agreement</a>)</p><p><strong>Analyze</strong></p><p>The following are problems identified and addressed in the course of analysing the data</p><p><strong>— Missing Values and Records:</strong> A total of 238,579 missing records representing 6% of the total sample were identified and dropped.</p><p><strong>— Measures of central tendency:</strong> Due to the possibility of extreme values the charts for ride duration were plotted using median instead of sum and average, this was employed because the median is better immune to extreme values as a statistical measure.</p><p><strong>— Manipulation of data to create new variables</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*hTyZI2ea1wS3a_lAUA69uA.png" /><figcaption>Code Snippet from the projecct’s R Markdown Workbook</figcaption></figure><ol><li><strong><em>month </em></strong>— Months of the year as text</li><li><strong><em>week_day </em></strong>— Days of the week as text</li><li><strong><em>day_n </em></strong>Days of the week as an integer</li><li><strong><em>hour </em></strong>— Hours of the day as an integer</li><li><strong><em>ride_length </em></strong>— Duration of ride by minutes as an integer</li></ol><p><strong>How does it help you answer your question?</strong></p><p>This data set helps to answer the questions of trends amongst different metric points.</p><p>As a time series data, this dataset has offered useful data points to uncover detailed insights on the activities of Bike users at hourly, daily, weekly and monthly summaries</p><p>This has helped uncover the patterns amongst users to understand their preferences and motivations for using the services.</p><p><strong>Share</strong></p><p>The full R Notebook with the detailed codes prior to visualization can be reviewed <a href="https://www.kaggle.com/code/akwamfoneventus/google-data-analytics-capstone-project-akwaire">here</a> on <a href="https://www.kaggle.com/code/akwamfoneventus/google-data-analytics-capstone-project-akwaire">Kaggle</a></p><p>The findings of this case study are shared with the embedded Power BI report below:</p><figure><a href="https://app.powerbi.com/reportEmbed?reportId=f8d50c54-17b8-44ce-9fb5-142e2b1990a3&amp;autoAuth=true&amp;ctid=3f3ecd1e-498d-4627-ad04-b1095b19760a"><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*u1vHhPENWLJ9Tjhi5loA7Q.png" /></a><figcaption>Power BI Report Snippet</figcaption></figure><p><strong>Conclusion</strong><br>If you have read this far congratulations and thank you for your time. I hope this case study was rewarding and resourceful to you, kindly leave your thoughts and observations in the comment in the comments, like and follow if you wish to hear more from echoes of data.</p><p>Cheers!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=370935f9f652" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Ethics, Bias and Privacy — Getting it right beyond the syntax.]]></title>
            <link>https://medium.com/@akwamfoneventus/data-ethics-bias-and-privacy-getting-it-right-beyond-the-syntax-f361daca1137?source=rss-3d98526c1e10------2</link>
            <guid isPermaLink="false">https://medium.com/p/f361daca1137</guid>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[privacy]]></category>
            <category><![CDATA[ethics-in-tech]]></category>
            <dc:creator><![CDATA[Akwamfon Eventus]]></dc:creator>
            <pubDate>Sun, 15 May 2022 09:21:51 GMT</pubDate>
            <atom:updated>2022-05-15T09:21:51.738Z</atom:updated>
            <content:encoded><![CDATA[<h3>Data Ethics, Bias and Privacy — Getting it right beyond the syntax.</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*HuhxSDsUgq2BKE_FYtfg4w.jpeg" /><figcaption>Road Sign (Image Source — Pixabay)</figcaption></figure><p>Data has become an inescapable phenomenon in human existence, so tangled woven into our daily lives and continually increasing by the bytes, significant responsibilities indeed come with great power.</p><p>The power of data is beyond disputes and so is its risk of mismanagement thus it has become a thing of great concern to many, consumers, professionals and governments are of concern about how best to manage, regulate and maintain this fast-paced diverse entity.</p><p>This article intends to guide the reader towards an understanding of Data Ethics, Data Bias and Data privacy and also to place this concept in a relatable context, this article engages the following talk points:</p><ul><li>What is data bias?</li><li>Types of Data Bias.</li><li>Data ethics and why is it important.</li><li>Data ethics principles.</li><li>Data ethics policy.</li></ul><p><strong>What is Data Bias?</strong></p><p>Data bias can present itself in many different ways, data bias happens when data analysts exhibit consciously or unconsciously some level of preference or favour for one thing or group against another in a dataset. Bias can happen at any point in the data analysis phase and can systematically skew results in a certain direction thus making them unreliable for business decisions.</p><p><strong>Types of Bias</strong></p><p>Data bias can happen in different shades and sizes and the consequences of this error can be very severe regardless of type, below is a list of the common types of data bias and examples of how they can happen.</p><p><strong>Sampling Bias:</strong> When collected samples fail at serving as a representative of a complete population it is said the sampling is biased. Sampling bias can be avoided by random sampling which gives all parts of the population an equal chance of being included and allows you as an analyst to hear all sides of the story.</p><p>A good example will be sampling 10 female students in a mixed-gender class of 50 to complete a survey to determine what subject students enjoy the most. 10 is not a true representation of the whole population of 50 thus the result is biased and unreliable.</p><p><strong>Observer Bias: </strong>This is also called experimenter or research bias, this happens when two or more the observer or researcher sees or experience a single dataset differently, a good example will be the differences in commentary between two football commentators about the same event, hardly anyone is wrong but both are different and lacking.</p><p><strong>Interpretation Bias: </strong>Interpretation bias is the propensity to always interpret unclear circumstances in a positive, or negative way, meaning two people can interpret a dataset differently. A good scenario will be two people responding to rap lyrics, one might be empathetic about the artist’s story and one might be offended by the artist’s choice of words and position.</p><p><strong>Confirmation Bias: </strong>Confirmation bias, is the inclination to search for, or interpret information in ways that seek to confirm preexisting beliefs. It is easy to want to confirm a gut feeling or previous conviction such that we only notice things that support it at the expense of every other signal or fact.</p><p>The above-listed biases are some of the most common biases encountered during data analysis but they are not the only ones you may discover in your experience, each data has its unique challenge point, and it is recommended that analysts keep their bias radars sharp to detect these and other biases, one useful practice is visualizing the data at an early stage to spot anomalies and inconsistent distributions.</p><p><strong>What is Data Ethics?</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*oTqwrYmnJ82XjvdUkKwynw.jpeg" /></figure><p>Ethics typically refer to well-founded standards of right and wrong that prescribe what humans ought to do, usually in terms of obligations, rights, benefits to society, fairness or specific virtues. Just like humans, data has standards to live up to as well.</p><p>These refer to well-founded standards of right and wrong that stipulate what humans ought to do, usually in terms of rights, obligations, benefits to society, fairness or specific virtues.</p><p>Data ethics refers to well-founded standards of right and wrong that dictate how data is collected, shared, and used.</p><p>Data ethics attempts to address some concerns as it affects the collection, use and sharing of data and the following aspects are considered as the principles of data ethics</p><ol><li>Ownership :</li><li>Transaction transparency</li><li>Consent</li><li>Currency</li><li>Privacy</li><li>Openness</li></ol><p>For data ethics to be well understood it is important for the understanding of data bias to be established, of which we have already had a good look. Now we look into brief details of what each principle means and aims to achieve.</p><p><strong>Ownership:</strong> This answers the question of who owns data? As much as organizations and companies invest significant time, money and resources into collecting, storing, processing, and analyzing data, this does not make such an organization the owner of such data.</p><p>The ownership of data belongs to individuals who own and provide the raw data, this means they reserve the right and power of primary control over how it is used, processed and shared. Though this may look true only in a hypothetical sense, this is what data ownership and as part of data ethics is and should be in real practice.</p><p><strong>Transaction Transparency: </strong>This is the concept that all data processing actions and algorithms, and processes should be fully explained and understood by the person providing the data.</p><p>This is a direct response to the concerns of data bias, which can systematically skew the results of data analysis. Biased outcomes can lead to grave and negative consequences. This allows people to assess if the decision is fair and impartial, as well as raise any potential problems.</p><p><strong>Consent: </strong>This means that before agreeing to share personal data, an individual has the right to know exactly how and why it will be used and for what. This element of data ethics should be able to address questions such as “why is the data being collected?” “How will it be used?” and “How long will it be stored?”.</p><p>The most common and regular form of consent these days appears in the form of a terms and conditions checkbox with links to long and unreadable details, and if we must be honest, most users don’t read through those terms but still agree to it regardless.</p><p>Consent is vital because it protects all populations from being unfairly targeted, which is especially critical for underrepresented groups, who are frequently misrepresented by biased statistics.</p><p><strong>Currency:</strong> This explains and advocates for individuals to be notified about financial transactions originating from the use of their personal information, as well as the magnitude of these transactions.</p><p>Practically it means, If your personal information is being used to fund a company’s activities, you should be informed about the nature of those activities and given the option to opt-out.</p><p><strong>Openness: </strong>Data Openness refers to the freely available data that is available on the Internet for anyone to access, modify, and distribute without legal or financial restraints.</p><p>Open data is:</p><ul><li>Available: The data should be available for download in its entirety via the Internet at no cost other than reproduction expenses.</li><li>Accessible: Data should be provided in an easily modifiable format.</li><li>Reusable: this should be included under the terms given with the data.</li><li>Redistributable: the data provided should be compatible in combination with data from other research.</li><li>Unrestricted: Anyone using open data should be able to use, make changes, and share the data, irrespective of the purpose of their use(e.g. for educational, non-educational, or commercial purposes)</li></ul><p>The last two aspects of data ethics, privacy and openness are worthy of a little emphasis and close attention in the data world, the reasons for this will probably be obvious after it is done, without much introduction</p><p><strong>Data Privacy</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*FkCTHVyx24RVfQanqIW6hA.png" /><figcaption><a href="https://www.snia.org/education/what-is-data-privacy">https://www.snia.org/education/what-is-data-privacy</a></figcaption></figure><p>Data privacy is a big part of global culture today especially when the questions of trust are raised between users and big companies, with technology spreading fast and data-dependent digital solutions sprouting everywhere around the world, there is a need for both the users and services providers to understand not just in theory but in practice the concepts of data privacy and its applications.</p><p><strong><em>What is Data Privacy?</em></strong></p><p>“Data privacy means preserving a data subject’s information and activity any time a data transaction occurs. This is sometimes called information privacy or data protection.” — Hallie (Google Data Analytics Instructor)</p><p>Data privacy is an area of data protection that relates to the proper management of sensitive data, such as personal data but also other private data, to comply with regulatory obligations while simultaneously safeguarding the data’s confidentiality and immutability.</p><p>It’s all about access, use, and collection of data. It also covers a person’s legal right to their data.</p><p>This means you and I have protection from unauthorized access to our private data, freedom from inappropriate use of our data, the right to inspect, update, or correct our data, power to give consent to the use of our data, and legal right to access our data.</p><p><strong>Data Privacy Policy</strong></p><p>Governments all over the world have recognized the importance of data privacy, and have made palpable efforts toward creating data protection legislation to help protect people and their data. People need to stay abreast of the data policies and legislation as it concerns their jurisdiction, this is important in educating users to understand better the facts and expectations of how their private data should be used, this will create a more accountable and transparent environment where questions can be asked and concerns can be raised for a good change.</p><p><strong>Why It Matters</strong></p><p>It is easy to miss the importance of all these concepts discussed so far, but we must remind ourselves categorically why data ethics and privacy is important in our current societies and fast-paced technological developments.</p><p>The following are a few examples of the importance of data ethics and data privacy:</p><p><strong>1. Business Asset Management:</strong> Data is arguable the most influential asset any business can own. We are living in a data economy where companies find immense value in collecting, sharing and using data about customers or users, especially from social media.</p><p>Transparency is the way businesses solicit consent to keep private data, manage the data they have collected and observed privacy policies since this is essential in building trust with customers that naturally expect privacy as a part of their human right.</p><p><strong>2. Confidence &amp; Trust:</strong> Customers must have some level of trust in the transparency and ethics of the company to whom they entrust their data with, with trust it is much easy to participate in useful data collections and surveys that can have a significant impact on the improvement of products or even something novel and new, without trust in the companies data ethics, people can give false or unreliable data, in attempt to protect themselves from unethical data use.</p><p><strong>Conclusion</strong></p><p>Data ethics are well-founded standards of right and wrong that dictate how data is collected, shared, and used. Data bias is a predisposed position an analyst has towards a part of the data against others, this skews the results and makes the outcome of such analysis unreliable for decision making. Thus analysts need to be conscious of bias and actively watch out and avoid the same.</p><p>Both companies and users must stay abreast with both the concepts of data ethics and privacy as well as the policies and legislation to promote accountability and transparency.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=f361daca1137" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Cleansing Explained — A DIY Guide for data cleaning and verification.]]></title>
            <link>https://medium.com/@akwamfoneventus/data-cleansing-explained-a-diy-guide-for-data-cleaning-and-verification-c806954ada0a?source=rss-3d98526c1e10------2</link>
            <guid isPermaLink="false">https://medium.com/p/c806954ada0a</guid>
            <category><![CDATA[documentation]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[spreadsheets]]></category>
            <category><![CDATA[sql]]></category>
            <category><![CDATA[data-cleaning]]></category>
            <dc:creator><![CDATA[Akwamfon Eventus]]></dc:creator>
            <pubDate>Thu, 05 May 2022 15:32:31 GMT</pubDate>
            <atom:updated>2022-05-15T13:21:57.929Z</atom:updated>
            <content:encoded><![CDATA[<h3>Data Cleansing Explained — A DIY Guide for data cleaning and verification.</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*UF6JqwI5_EYsPhfUi1wgZg.jpeg" /></figure><p>Data cleaning involves determining and correcting any incorrect, incomplete, or irrelevant data in a dataset so that it aligns with business goals and is ready for analysis.</p><p>This is a comprehensive article that will discuss the following outlines:</p><ul><li>What is dirty data?</li><li>Types of dirty data.</li><li>Potential harms of dirty data</li><li>What is Data Cleansing?</li><li>Data Cleaning Tools.</li><li>Data-cleaning techniques.</li><li>What is a Spreadsheet?</li><li>Spreadsheet Data Cleaning Techniques</li><li>What is SQL?</li><li>SQL cleaning techniques resources.</li><li>Data Cleaning Best Practices.</li><li>Data Cleaning Verification and Validation.</li><li>Documentation &amp; Reports</li><li>Changelog</li><li>Why documentation is critical</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*0-3-EkmQ-UCntq1EXj0BnQ.jpeg" /><figcaption>**Article Mind Map</figcaption></figure><h4><strong>What is Dirty Data?</strong></h4><p>The aptest analogy would be that no matter how valuable your ingredients are, you still won’t use them for your recipe without washing them first. This will improve hygiene and ensure it is ready for use.</p><p>The same measure applies to data in a dataset as it relates to data analysis. It is a fact that regardless of how valuable or authentic a dataset may be it most likely contains some “dirt”.</p><p>It will thus be reasonable to describe dirty data as data that is incomplete, incorrect, or irrelevant to the problems and questions the analyst is trying to answer. Dirty data may contain the following:</p><h4><strong>Types of Dirty Data</strong></h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1015/1*grMgjrWw5wRySctzbZxd_g.jpeg" /><figcaption>Types of dirty data snapshot from Google Data Analytic Certificate Course</figcaption></figure><ol><li>Duplicate Data: This is a record in a dataset that appears more than once. An example will be a duplicate entry of a single person’s name into a “customer information” table in a CSV file. The common cause for this is usually manual data entry, batch data imports, or data migration</li><li>Outdated Data: Data that is not timely relevant to the question or problems of concern. A suitable example would be having a 2003 sales record data inside a 2022 annual sales record. This data is irrelevant to the purpose of the annual sales report for the year 2022. This usually happens when people change roles or companies, or software and systems become obsolete.</li><li>Incomplete Data: This is a dataset with incomplete records and attributes, that are missing an important field. This can be a missing column, row or cell in a table or dataset. Possible causes include improper data collection or incorrect data entry.</li><li>Incorrect Data: Any data that is complete but inaccurate. Incorrect data happens when inaccurate facts and records occur in a dataset. An example would be having a column for “total sales” calculated with a faulty formula. Causes include human error inserted during data input, fake information, or mock data.</li><li>Inconsistent Data: Any data that uses different formats to represent the same thing. A common example would be the use of multiple date formats in one column. Possible causes include incorrectly stored data or errors inserted during data transfer.</li></ol><h4><strong>Potential Harms of Dirty Data</strong></h4><p>Just as good hygiene is to health so is data integrity in a dataset. In the same way, a slice of unwashed meat or apple could be the cause of another pandemic, so lies the power of dirty data on credible analysis, reliable insights, and ultimately business decisions. Dirty data can lead to the following problems:</p><ul><li>Metrics or analyses that are skewed, exaggerated or erroneous counts or projections, or data retrieval that is confusing.</li><li>Inaccurate insights, decision-making, and analytics.</li><li>Decreased productivity, or inability to complete essential services.</li><li>Inaccurate decision-making based on faulty data can result in revenue loss or life loss, depending on the stakes.</li><li>Confusion or inability to classify or segment clients is caused by conflicting data points.</li></ul><h4><strong>What is Data Cleansing?</strong></h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*zzaib_cUdNoN_i01MkX5Cw.jpeg" /><figcaption>basic cleaning toolkit</figcaption></figure><p>It is safe to assume that we already know what dirty data is, therefore we can rightly answer the question of data cleaning — <br>Data cleaning can be described as transforming and organizing data within a dataset or multiple datasets by verifying that the information within them is correct complete, consistent and free from duplicates and inconsistencies.</p><p>This might include additions, deletions, reformatting, merging, sorting, filtering and several other standard practices to ensure compliance with data integrity principles.</p><h4><strong>Data Cleaning</strong></h4><p>Data cleaning can be achieved with both automation and/or manual process that identifies these “dirt” points and cleans them accordingly. There are several tools for the data cleaning process but ultimately the tools and techniques for data cleaning will be different depending on the specific dataset(s) you’re working with.</p><h4><strong>Data Cleaning Tools</strong></h4><p>Data can be cleaned with several tools and technologies including but not limited to:</p><p><strong>Programming Languages: </strong>By using command scripts, for example, Python, R.</p><p><strong>Spreadsheet Software:</strong> Business intelligence software like Google Sheets, Microsoft Excel and Power BI, offers analysts the advantage of manipulating datasets with prebuilt features and functions with the aid of an interactive Graphic User Interface.</p><p><strong>Database and Database Technologies:</strong> Databases especially relational databases and tools can be a suitable place for data cleaning, especially with the advantage of SQL(Structured Query Language) it becomes easier to query databases for specific and complex results.</p><p>This article however will be maintaining a focus on Spreadsheets and SQL. These are the 2 most widely used tools and technologies of data cleaning that have found widespread success and adoption amongst data professionals and industries working with data.</p><h4><strong>Data Cleaning Techniques</strong></h4><p>It is understood that experiments may differ in procedures in a chemical laboratory. However, certain laboratory techniques and practices are prerequisites to successful credible experiments. An example of such would be separation techniques.</p><p>To put this into perspective, just as each dataset may be unique in content and purpose, certain techniques should be deployed to ensure quality.</p><p>Below is an example of how to clean data in a step-by-step fashion:</p><ul><li>Organize your datasets: It is standard practice as an analyst to organize your data within safe storage, rename them if necessary, backup your copies, and be sure that your work can be found and recovered.</li><li>Create a working Worksheet: Make duplicates of the original before beginning to clean, this copy will serve as a control copy during verification.</li><li>Understand the problem: Take time to understand the problem at hand to align the business objective with the cleaning exercise</li><li>Study the data: To understand its attributes and how to explore it to find answers in the context of your problem a good place to start is usually the metadata, (dataset summary and schema)</li></ul><p>After careful study, and understanding of the data, the next step is to assess the data to ensure data integrity principles, this includes :</p><ul><li><strong>Confirm for Consistency: </strong>Consistency is the degree to which a set of measures is equivalent across systems. Check data to ensure that the data types in each column match the data types specified for the column attributes. An example would be to examine a “Date” column to make sure that all the records are date values and confirm if the format is consistent.</li><li><strong>Confirm for Validity:</strong> Validity is the concept of using data integrity principles to ensure measures conform to defined business rules or constraints. An example of validity confirmation will be reviewing a 0–5 star rating column to verify that there are no entries greater than 5, or lesser than 0.</li><li><strong>Check for Accuracy:</strong> Accuracy is the degree of conformity of a measure to a standard or a true value. Having the word “Truck” in a column that describes a colour is an example of inaccurate data. The value can be considered valid because it is a string value. However, it is inaccurate because it is out of conformity with what the values of colour should be.</li><li><strong>Check for Completeness:</strong> Completeness is the degree to which all required measures are known. A suitable scenario would be to check if all the columns needed for calculation are complete without blanks and invalid data.</li><li><strong>Check for Duplicates:</strong> Duplication happens when there is an occurrence of more than 1 record in a data set, say for example multiple entries of a single staff on the staff payroll sheet or duplication of a customer’s order for pizza.</li></ul><p><em>PS: The order of these techniques can change depending on the type of data set and the nature of the analysis to be done.</em></p><h4><strong>What is Spreadsheet?</strong></h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3HiA3ElflMtyxiDS3w8lcA.jpeg" /><figcaption>Snipshot of a dataset on Google Spreadsheet.</figcaption></figure><p>According to <a href="https://en.wikipedia.org/wiki/Spreadsheet">Wikipedia</a> “Spreadsheet” is “a computer application for computation, organization, analysis and storage of data in tabular form.”</p><p>There is quite some spreadsheet software out there but for this article, we will be using Google Spreadsheet for the illustration of techniques and processes.</p><h4><strong>Spreadsheet Data Cleaning Techniques(Google Spreadsheet)</strong></h4><p>Many functions and formulas within the spreadsheet can be used for data cleaning. This section will cover the essential functions, formulas and features. And below is a curated list of the highest quality resources and documentation on how to clean data with spreadsheets.</p><blockquote><a href="https://support.microsoft.com/en-us/office/top-ten-ways-to-clean-your-data-2844b620-677c-47a7-ac3e-c2e157d1db19"><strong>Top ten ways to clean your data</strong></a></blockquote><blockquote><a href="https://support.google.com/a/users/answer/9604139?hl=en#zippy="><strong>10 Google Workspace tips to clean up data</strong></a></blockquote><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2FqGIYA04ZlWc%3Fstart%3D1%26feature%3Doembed%26start%3D1&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DqGIYA04ZlWc&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2FqGIYA04ZlWc%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/9b3240e23d7c1ab2836bed60ed53f35c/href">https://medium.com/media/9b3240e23d7c1ab2836bed60ed53f35c/href</a></iframe><h4><strong>What is SQL?</strong></h4><p>SQL (Structured Query Language) is a language used to query databases to retrieve insightful data. SQL is a powerful and useful tool for a vast number of reasons. Top of the list is SQL’s ability to handle large volumes of data more efficiently and effectively than spreadsheets. Below are selected resources on how to perform data cleaning using SQL.</p><h4>SQL Data Cleaning Techniques</h4><p>This is a hand-picked curation of the best SQL resources on how to clean data with SQL:</p><p><a href="https://www.datacamp.com/tutorial/cleaning-data-sql">Cleaning Data in SQL</a></p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2Fr7GDQt3lZxs%3Ffeature%3Doembed&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Dr7GDQt3lZxs&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fr7GDQt3lZxs%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/659519a82f8e1fe20c2e66ab77f2792b/href">https://medium.com/media/659519a82f8e1fe20c2e66ab77f2792b/href</a></iframe><h4><strong>Best Practices</strong></h4><p>Other than hand-on tool cleaning techniques, there are other best practices to always consider during data cleaning. They include the following:</p><p><strong>Data Verification: </strong>This process involves comparing the quality of the cleaned data with a copy of the original and dirty data to assess whether they are compliant with data integrity principles.</p><p>Below is an excerpt from Google’s Data Cleaning Checklist</p><p>“Make sure you identified the most common problems and corrected them, including:</p><ul><li><strong>Sources of errors: </strong>Did you use the right tools and functions to find the source of the errors in your dataset?</li><li><strong>Null data:</strong> Did you search for NULLs using conditional formatting and filters?</li><li><strong>Misspelt words:</strong> Did you come across any misspellings?</li><li><strong>Mistyped numbers:</strong> Did you double-check that your numerical data has been entered correctly?</li><li><strong>Extra spaces and characters: </strong>Did you remove any extra spaces or characters using the TRIM function?</li><li><strong>Duplicates:</strong> Did you remove duplicates in spreadsheets using the Remove Duplicates function or DISTINCT in SQL?</li><li><strong>Mismatched data types:</strong> Did you check that numeric, date, and string data are typecast correctly?</li><li><strong>Messy (inconsistent) strings:</strong> Did you make sure that all of your strings are consistent and meaningful?</li><li><strong>Messy (inconsistent) date formats:</strong> Did you format the dates consistently throughout your dataset?</li><li><strong>Misleading variable labels (columns):</strong> Did you name your columns meaningfully?</li><li><strong>Truncated data:</strong> Did you check for truncated or missing data that needs correction?</li><li><strong>Business Logic:</strong> Did you check that the data makes sense given your knowledge of the business?</li></ul><h4>Review the goal of your project</h4><p>Once you have finished these data cleaning tasks, it is a smart idea to review the goal of your project. This will enable you to confirm that your data is still aligned with that goal. This is a continuous process that you will do throughout your project — but here are three steps you can keep in mind while thinking about this:</p><ul><li>Confirm the business problem</li><li>Confirm the goal of the project</li><li>Verify that data can solve the problem and is aligned to the goal”</li></ul><h4><strong>Data Cleaning Documentation</strong></h4><p>Documentation is the practice of recording and tracking your cleaning process. This can be achieved with the use of a Changelog and Automated Version History. Most software applications have a kind of history tracking built-in.</p><p>Data analysts also use changelogs to keep track of data transformation and cleaning. In addition, they keep track of the reason behind those changes, since the automated version history may fail to capture that.</p><p>Reports: Proper documentation and helpful practices like changelog are useful in reporting to stakeholders about data cleaning processes. They also offer useful insights on how to better optimize the cleaning of data for similar file structures and data types.</p><h4><strong>Conclusion</strong></h4><p>This article has covered data cleaning, dirty data, data cleaning tools and data cleaning techniques. We have also covered the best practices for data cleaning in addition to the techniques. Understanding of data-cleaning verification has been established with a handy checklist from the Google Data Analytic Certificate Course.</p><p>In addition to having all this under our belts as Data Analysts, it is imperative to always understand the defined problem and business objective. This is because it is easier to choose the tools that fit the job from a place of understanding rather than routine or guesswork. It is also wise to follow a company’s SOP(Standard Operating Procedures) for data cleaning if they have one, as this will clean the data in alignment with the business objective.</p><p>Pro Tip: It is an excellent practice to freeze column headers. This helps you keep track of context and structure through the cleaning process.</p><p>In the end, as we practice and make improvements, we should all know and remember that “persistence breeds success”.</p><p>Thank you for the time, please leave your thoughts in the comment, subscribe to the channel and kindly follow me on <a href="https://twitter.com/AkEventus">Twitter</a></p><p>Cheers!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c806954ada0a" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[…and so the journey began — My Data Analytics journey with Google]]></title>
            <link>https://medium.com/@akwamfoneventus/and-so-the-journey-began-my-data-analytics-journey-with-google-36e3ce6784d3?source=rss-3d98526c1e10------2</link>
            <guid isPermaLink="false">https://medium.com/p/36e3ce6784d3</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[coursera]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[google]]></category>
            <dc:creator><![CDATA[Akwamfon Eventus]]></dc:creator>
            <pubDate>Thu, 14 Apr 2022 15:18:42 GMT</pubDate>
            <atom:updated>2022-04-16T09:09:41.706Z</atom:updated>
            <content:encoded><![CDATA[<h3>…and so the journey began — My Data Analytics journey with Google</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xD3amc0CGikrlu8D6CYosw.jpeg" /><figcaption>a ready traveller (image source — <a href="https://pixabay.com/photos/travel-airport-boarding-pass-5219496/">pixabay.com</a>)</figcaption></figure><p>Hello there, I will be sharing a little background of what happened before my data analytics journey with google, then I will move into sharing what has been learnt so far since the decision to enrol, and so the journey began after an awful bankruptcy, I decided and admitted that investment is not for people without income, why so? you might ask, it is so because investments ideally shouldn’t be your basic source of income and livelihood, that was my mistake and I paid for that lesson with every remaining penny at the time and I learnt it without any iota of confusion.</p><p>So yes in an attempt to fill the vacuum of a troubled mind, I decided to try out my saved courses on LinkedIn learning, in what would be a discouraging effort to get skilled, and boy did I struggle with it? until I decided to try other resources and the effort of that search took me to Coursera where I discovered Google Data Analytics professional certification course.</p><p>This would be is the difference between my experience with the LinkedIn learning path for data analysis and that of Google professional certification on Coursera, in 5,4,3,2,1… Action!</p><p>I was able to understand the prospects and promises of becoming a data analyst, the resources took time to explain in applaudable length the details of the course and the objectives of each lesson and material, I was able to have a timeframe as to when I might or should finish the course as every resource was given precise time tags.</p><p>My progress and efforts seemed more and better quantifiable than with LinkedIn Learning, this gave me the morale and encouragement to continue with the course with the solid confidence that I can finish it, aside from the general premium experience that Coursera offers as a learning service, the course on its own was just the perfect fit for a newbie who probably will get to understand what data means for the first time, though I wasn’t one of such.</p><p>I would recommend based on experience that people looking for structured learning resources for Data Analysis should sign up for Coursera and enrol for the course, as concepts are well explained and placed in a context that allows the learner to relate practically with the ideas being taught.</p><p>The certification course is structured into 8 courses, within these courses are weekly scheduled learning resources and activities, with each course having an average of 4 weeks, the learning delivery is 100% online and with a flexible schedule, giving the learner liberty to choose their schedule because it self-paced, among the benefits of this course includes a sharable certificate that comes after the completion of each course and a final certification to mark the completion of the entire program.</p><p>This course is offered in English and the difficulty level is ranked at the beginners level, so it should be pretty easy for anyone with good English understanding and communication skills to follow through the estimated 6 months of 10 hours weekly workload, though I personally believe a focused learner can complete the course in half that time or even lesser.</p><p>So now that you have an idea of what to expect from this course, It’s time to tell you what my learning experience was during the first week looked and felt like.</p><p><strong><em>Google Data Analytics Course — Course 1, Week 1</em></strong></p><p>Aside from the sizable introduction videos, what happens to be the core part of the distinctive concepts covered in the week 1 content are discussed below.</p><p><strong><em>What is Data Analysis?</em></strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gv0baw6JQMv3stzgbSo2-g.jpeg" /><figcaption>screen showing a dashboard (image source — <a href="https://pixabay.com/photos/travel-airport-boarding-pass-5219496/">pixabay.com</a>)</figcaption></figure><p>To better understand the term “Data Analysis” it is necessary to understand the constitutive words that build it, with the first word being data, in its most basic remark, the word data is a “collection of facts or information”. Analysis on the other hand is the detailed examination of the nature and state of something to reveal insights and useful information.</p><p>Therefore combining the two concepts together, would mean that “data analysis” is the process of detailedly examining data to uncover even more information, reveal deeper insights and identify patterns, for the purpose of making better and informed decisions. It is even more useful to understand that all this should happen within the context of concern for the insights to be meaningful, this concept would be discussed more and better in later publications so watch out for more content.</p><p><strong><em>Difference between Data Analytics and Data Analysis</em></strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*mLR6lC56lGNLPmERmvFUPg.jpeg" /><figcaption>AI illustration (image source — <a href="https://pixabay.com/photos/travel-airport-boarding-pass-5219496/">pixabay.com</a>)</figcaption></figure><p>It can be so easy to interchange the two terms, either in meaning or even spellings, but that won’t happen because I am here to help draw a clear line between the two, despite the fact that both terms are closely “related” they are not the same and should be understood distinctly, and here is the difference;</p><p>The difference between data analytics and data analysis, will be that the former (Data Analytics) is a term broadly used to encompass everything around the “science of data “ as a field, and this cuts across a broad spectrum of computer science and computing fields, methods and professions, while the latter(Data Analysis) is concerned with the actual job of data analysis as a data analyst professional would go about it, this has already been explained above.</p><p><strong><em>Data Ecosystems</em></strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*RBfgzVPE9gwOh-zpaCyk5g.jpeg" /><figcaption>Data Ecosystem (image source — <a href="https://pixabay.com/photos/travel-airport-boarding-pass-5219496/">pixabay.com</a>)</figcaption></figure><p>The term “Ecosystem” might have an easy natural feel to it, of course, it does but the very concept around it is beyond the animate world of living things and can be rightly borrowed to explain the interactions between data in the computer and data world.</p><p>The term “ecosystem” is used to describe the interactions of elements (things) with each other and the environments of such elements, typically in a closed system. A data ecosystem, therefore, is the interactions of data with data and other elements as well as the environment of the said data, putting it in context will be that — A data ecosystem consists of infrastructure, analytics, and applications that are used to collect and analyze data and deploy solutions.</p><p>In the practical description, in order to produce, manage, store, organise, analyze, and share data, an ecosystem is needed for such to be possible. In the context of this course, the data ecosystem was discussed with the objective that the student will better understand where data analysis fits into the data ecosystem.</p><p>As it’s been widely said, “every good dancer should know when to take a bow”, I would love to take a bow at this moment, but before I do so, here is one last glance at what I have been saying in the length of this story;</p><p>I think people should not invest if they do not have an income that they can live off of separately from the investment,</p><p>I do recommend the Google Professional Certification course on Coursera for newbies who are seeking for structured beginners resources to learn Data Analysis, data analysis is not the same as data analytics since the former is part of the latter and the latter is a much broader term for the science of data, that data is at basic a collection of facts and information and data analysis is the job of making those collection makes sense in specific contexts.</p><p>If you found this to be a good read, kindly give a clap, leave your thoughts in the comments and subscribe for more and better content in subsequent publications</p><p>Cheers!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=36e3ce6784d3" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>