<?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 Nwajagu Stanley Ifeanyi on Medium]]></title>
        <description><![CDATA[Stories by Nwajagu Stanley Ifeanyi on Medium]]></description>
        <link>https://medium.com/@nwajagustanley?source=rss-d4a27cb13d18------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*1zzecRiOkcYgmo-3ZU-CIA.jpeg</url>
            <title>Stories by Nwajagu Stanley Ifeanyi on Medium</title>
            <link>https://medium.com/@nwajagustanley?source=rss-d4a27cb13d18------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 06:13:09 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@nwajagustanley/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[The Next Step for Data Analysts Isn’t More Tools — It’s Understanding the Data Pipeline]]></title>
            <link>https://medium.com/@nwajagustanley/the-next-step-for-data-analysts-isnt-more-tools-it-s-understanding-the-data-pipeline-85ee280aa436?source=rss-d4a27cb13d18------2</link>
            <guid isPermaLink="false">https://medium.com/p/85ee280aa436</guid>
            <category><![CDATA[sql]]></category>
            <category><![CDATA[data-engineering]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[dbt]]></category>
            <dc:creator><![CDATA[Nwajagu Stanley Ifeanyi]]></dc:creator>
            <pubDate>Sun, 26 Apr 2026 16:41:14 GMT</pubDate>
            <atom:updated>2026-04-26T16:41:14.854Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*IZtnKBvhfcYB9L6v92bP2Q.png" /><figcaption>The modern data pipeline…most analysts only ever see the last step</figcaption></figure><p>You already know SQL.</p><p>You can build a dashboard. You’ve cleaned messy datasets at 11pm. You probably know your way around Excel, Power BI, maybe even Python.</p><p>And yet… something still feels like it’s missing.</p><p>Here’s the uncomfortable truth nobody tells you when you’re learning data:</p><p><em>The tools got you in the door. But they won’t make you stand out anymore.</em></p><h4><strong>The Baseline Problem</strong></h4><p>Thousands of analysts today can write SQL queries, build dashboards, and wrangle data. These skills used to be rare. Now they’re table stakes.</p><p>So, the real question isn’t “what tools should I learn next?”</p><p>It’s this: <em>what actually makes a data analyst valuable today?</em></p><p>The answer isn’t another certification. It isn’t Tableau vs. Power BI. It isn’t even Python.</p><p>It’s understanding how data actually flows inside a business.</p><h4><strong>The Hidden Limitation Most Analysts Never Notice</strong></h4><p>Think about your typical workday.</p><p>You get a cleaned dataset. You run your queries. You build your visuals. Done.</p><p>But here’s what you’re probably not asking:</p><p>Where did that data come from? Who defined the logic behind those tables? What happens when the numbers look wrong…and you have no idea why?</p><p>If you can’t answer those questions, you’re not really working <em>with</em> data.</p><p>You’re working <em>at the end</em> of it.</p><p>And in today’s market, that’s a ceiling…not a career.</p><h4><strong>The Shift: From Dashboard Analyst to End-to-End Thinker</strong></h4><p>The most valuable analysts today don’t just analyze data. They understand the entire journey…where it comes from, how it’s transformed, how it reaches a dashboard, and how it drives a real decision.</p><p>They don’t think in reports.</p><p>They think in <strong><em>systems.</em></strong></p><p>This doesn’t mean becoming a data engineer. It means becoming an analyst who operates with more independence, more context, and more impact. <strong>There’s a big difference.</strong></p><h4><strong>The 4 Capabilities That Actually Set Modern Analysts Apart</strong></h4><p>Forget chasing tools. Build these instead.</p><p><strong><em>1. Understanding Data Sources — Beyond “Just Give Me the Table”</em></strong></p><p>Most real-world data doesn’t live in a neat Excel file. It comes from cloud databases, CRMs, payment systems, marketing platforms, third-party APIs…systems that each have their own quirks and limitations.</p><p>When all you ever see is the final table, you’re missing the story behind the numbers.</p><p>High-value analysts ask: what system generated this data? How reliable is that source? What does this field actually mean in the real world?</p><p>That shift, from consuming data to <em>reasoning about</em> data…changes everything about how you analyze.</p><p><strong><em>2. Owning Data Transformation, Not Waiting for “Clean Data”</em></strong></p><p>You’ve heard it before: <em>“The data isn’t ready yet. I’m waiting on the data team.”</em></p><p>That sentence is where a lot of analyst careers stall.</p><p>Stronger analysts don’t wait for clean tables. They take ownership of the logic behind them. They define how metrics are calculated, how tables should be structured, what “clean” actually means for their business context.</p><p>Tools like dbt exist to help with this. But the tool isn&#39;t the point.</p><blockquote><em>I am responsible for how this data becomes usable.</em></blockquote><p>Once you own that, you stop being dependent. And dependence is the enemy of impact.</p><p><strong><em>3. Working with APIs…Expanding Beyond Your Company’s Data</em></strong></p><p>If your analysis only touches your internal database, your insights will always be limited by what your company already knows.</p><p>APIs change that. They let you pull external data, market trends, financial benchmarks, third-party enrichment, and combine it with what you already have. Suddenly you’re not just reporting on the past. You’re bringing in new context.</p><p>You’re no longer restricted to what’s given to you.</p><p>You can <strong><em>create</em></strong> datasets.</p><p>That’s a fundamentally different kind of value.</p><p><strong><em>4. Building Automated Workflows. Stop Doing the Same Thing Twice</em></strong></p><p>Here’s a pattern that’s more common than anyone admits:</p><p>Monday: update the report. Tuesday: run the same query. Wednesday: export the file, send the email, repeat.</p><p>That’s not analysis. That’s manual labor with a fancy job title.</p><p>Modern analysts ask a different question: <em>how do I do this once… and never do it again?</em></p><p>They build scheduled data updates. Automated reports. Alert systems that flag anomalies before anyone asks. This doesn’t require deep engineering skills. It requires thinking in <strong><em>systems</em> </strong>instead of <strong><em>tasks</em></strong><em>.</em></p><p>And once you start, your productivity…and your reputation…compounds fast.</p><p><strong><em>5. Becoming Tool-Agnostic. Your Value Is in Your Thinking</em></strong></p><p>A lot of analysts wrap their identity around a tool.</p><p><em>“I’m a Power BI analyst.” “I use Tableau.”</em></p><p>But tools change. Companies migrate. Budgets get cut. The tool you built your career on might be gone in three years.</p><p>What doesn’t change: how data flows, how decisions get made, how people interact with insights.</p><p>If you understand those fundamentals, you can pick up any tool: Power BI, Metabase, Redash, whatever comes next, and be productive within weeks.</p><p>Your value stops being tied to software.</p><p>It becomes tied to <strong><em>thinking</em></strong><em>.</em></p><h4><strong>This Is Not About Becoming a Data Engineer</strong></h4><p>Let’s be honest about what this article is <em>not</em> saying.</p><p>You don’t need to build complex pipelines from scratch. You don’t need to manage infrastructure or dive deep into backend systems.</p><p>What you do need is awareness. The ability to understand how data moves, take ownership where it matters, and reduce the unnecessary dependencies that slow you down.</p><p>You’re still a data analyst.</p><p>Just a more complete one.</p><h4><strong>The Gap Is Where the Opportunity Lives</strong></h4><p>Right now, the market is full of analysts who can write SQL, build dashboards, and clean data.</p><p>Far fewer can understand data end-to-end, define transformation logic, bring in new sources, and automate their own workflows.</p><p>That gap isn’t a problem.</p><p>It’s an opening.</p><h4><strong>Final Thought</strong></h4><p>The future data analyst isn’t the one who knows the most tools.</p><p>It’s the one who understands the <em>journey</em> of data — from source to decision.</p><p>Because businesses don’t actually care about dashboards.</p><p>They care about clarity.</p><blockquote>And the analysts who can create that clarity, independently, consistently, and without waiting to be handed clean data, are the ones who become truly irreplaceable.</blockquote><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=85ee280aa436" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Changing Face of Data Analytics]]></title>
            <link>https://medium.com/@nwajagustanley/the-changing-face-of-data-analytics-473603599b24?source=rss-d4a27cb13d18------2</link>
            <guid isPermaLink="false">https://medium.com/p/473603599b24</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[2026]]></category>
            <dc:creator><![CDATA[Nwajagu Stanley Ifeanyi]]></dc:creator>
            <pubDate>Mon, 22 Dec 2025 18:48:03 GMT</pubDate>
            <atom:updated>2025-12-22T18:48:03.732Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*QKLShLYSc4X2sKTG-bAvrA.jpeg" /><figcaption>AI in Data Analytics</figcaption></figure><p><strong>What It Really Means to Be a Data Professional in 2026</strong></p><h4>Introduction</h4><p>We used to stay up late building dashboards in Power BI…now our managers ask, ‘Can’t we automate this?’ before even seeing the report.</p><p>I could still remember a friend of mine, a brilliant data analyst while growing once told me something that stopped me in my tracks. After being laid off, she said:</p><blockquote>“<em>I thought being great at Excel, SQL, and Power BI was enough. But one morning, I watched AI do in 30 seconds what used to take me hours. That moment broke me, not because I wasn’t good enough, but because the game had changed, and no one warned us.”</em></blockquote><p>And I realized…every analyst I know is either asking the same question silently or pretending not to.</p><p>Over the past few years, I’ve watched data analytics evolve before my eyes…what once took hours of manual cleaning and endless Excel sheets now happens in seconds, all thanks to the power of AI.</p><p>Automation is rewriting the rules.<br> New tools appear every month.<br> Dashboards update themselves.<br> Insights arrive at the click of a button.</p><p>And yet… something is missing.</p><p>Because while machines can crunch numbers faster than ever, they still can’t replace human judgment, empathy, and context.</p><h4>The New Role of The Analyst</h4><p>Today, being a data analyst is no longer about just running queries or building reports. It’s about understanding why those numbers matter.</p><p>It’s no longer enough to say:</p><blockquote>“Sales increased by 20%.”</blockquote><p>The real question is why?</p><p>Was it a marketing campaign?<br> A pricing strategy?<br> Customer loyalty?</p><p>Modern data professionals are moving from being reporters of what happened to being interpreters of why it happened, and what to do next…</p><p>Sometimes that means sitting in meetings where everyone’s waiting for you to explain a number that doesn’t make sense. Or being the one people turn to when sales drop, marketing panics, and leadership wants answers fast.</p><p>In those moments, you realize that analytics isn’t just about data anymore. It’s about trust…</p><p>That shift is everything.</p><h4>Soft Skills are now Hard Skills</h4><p>And let’s talk about something we don’t emphasize enough…</p><p><strong>Soft skills are now the hardest skills to master.</strong></p><p>The analysts who rise fastest aren’t always the ones who write the most complex SQL or DAX. They’re the ones who can take a complex idea and make it so clear that even someone outside the data team says,</p><blockquote>“Now I get it.”</blockquote><p>Curiosity.<br> Communication.<br> Storytelling.<br> Empathy.</p><p>There were times I stayed up all night trying to make a dashboard perfect, only to realize the next morning that what my manager really needed wasn’t another chart, it was clarity.</p><p>Sometimes, we forget that behind every Power BI visual, there’s a person just trying to make sense of the story.</p><p>Communication and storytelling aren’t buzzwords anymore, they are the skills that keep you relevant in a world where tools evolve faster than job titles.</p><p>And then there’s AI.</p><h4>AI: The Analyst’s New Partner</h4><p>Let’s be honest. It’s intimidating.</p><p>It feels like it’s doing everything we spent years learning. But here’s the truth.</p><p>AI isn’t coming for your job.<br> The person who knows how to use AI is.</p><p>Look at me, more than 3 years in the game, but AI still helps me build slides, write SQL snippets, even clean messy names in a dataset.</p><p>AI is not your enemy.<br> It’s your amplifier.</p><p>Sometimes I just sit back and watch it work, how it connects patterns I would’ve missed, how it cleans chaos into order and I feel grateful. Not threatened. Because what if this was never about AI replacing us, but about freeing us to think bigger?</p><p>It can clean messy data in seconds, summarize insights instantly, or even help you build a presentation draft. But it still needs you…your judgment, your creativity, your ability to see patterns that numbers alone can’t explain.</p><p>I still double-check every AI summary, because once, it confidently told me profit went up when in fact, expenses were misclassified.</p><p>The future belongs to analysts who <strong>know how to collaborate with machines</strong>, not compete with them.</p><h4>The Power of Data Storytelling</h4><p>And this brings us to what I think is our new superpower as analysts:</p><p><strong>DATA STORYTELLING</strong>.</p><p>Because numbers alone don’t move people, <em>stories do.</em></p><p>If you tell a manager,</p><blockquote>“Our conversion rate dropped by 10%,”</blockquote><p>…it’s just a number.</p><p>But if you say,</p><blockquote>“We lost 200 potential customers this week because users struggled on our checkout page,”</blockquote><p>suddenly, it becomes real.</p><p>Storytelling helps executives see beyond charts.<br>A good story makes a stakeholder say:</p><blockquote>“We need to fix this today”.</blockquote><p>That’s the art of translating data into emotion. The moment your work starts to change minds and drive action.</p><h4>What This Means for You</h4><p>So, what does all this mean for you…for all of us, really?</p><p>It means learning fast and unlearning faster.<br>It means asking better questions, not just getting faster answers.<br>It means focusing less on memorizing tools and more on mastering thinking.</p><p>It means remembering that behind every dataset, there are people…customers, patients, students, users, whose lives are shaped by the decisions your insights influence.</p><p>It could be…</p><p>A patient who didn’t receive care in time.<br>A student who dropped out unnoticed.<br>A customer who left because the data said “low engagement,” but no one asked why.</p><p>These aren’t just numbers, they’re people, emotions, and stories hidden in plain sight.</p><p>And that’s why our work as analysts matters more than ever.</p><h4>The Human Side of Data</h4><p>At the end of the day, data is more than numbers.<br>It’s a reflection of human lives, choices, and opportunities.</p><p>The future of data analytics isn’t about racing against machines, it’s about walking alongside them and using their power to amplify our humanity.</p><p>Behind every line of code is a story waiting to be told.<br>Behind every number, a heartbeat.<br>Behind every dashboard, a decision that could change someone’s life.</p><p>AI can process information.<br>Only humans can feel the weight of its meaning.</p><p>And that is our greatest edge…and our greatest responsibility.</p><p>As we step into 2026 and beyond, remember this:</p><p>The real power of data isn’t in the numbers.<br>It’s in the story they tell, and the impact they create.</p><p>Because in the end, data doesn’t change the world.<br>People do.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=473603599b24" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Clarity and Consistency: Unlocking Your Dream Data Analyst Job in 2025]]></title>
            <link>https://medium.com/@nwajagustanley/clarity-and-consistency-unlocking-your-dream-data-analyst-job-in-2025-3287498bdd1f?source=rss-d4a27cb13d18------2</link>
            <guid isPermaLink="false">https://medium.com/p/3287498bdd1f</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[new-year-resolution]]></category>
            <category><![CDATA[jobs]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Nwajagu Stanley Ifeanyi]]></dc:creator>
            <pubDate>Sun, 05 Jan 2025 21:02:13 GMT</pubDate>
            <atom:updated>2025-01-05T21:02:13.346Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*SW5F49hDrn0YZMpcrkthRg.png" /></figure><p>The start of a new year brings with it a buzz of excitement. <em>“New year, new me”</em> vibes are everywhere lol, and it’s easy to feel inspired by the promises of a fresh start. But let’s be honest,</p><blockquote>how many of us truly stick to those grand resolutions?</blockquote><p>By February, the gym memberships are forgotten, the reading lists are abandoned, and we slip back into old habits.</p><p>If you’re an aspiring data analyst or looking to elevate your career in 2025, let me offer you two words that can guide your journey: <strong>CLARITY AND CONSISTENCY</strong>. These aren’t just buzzwords; they’re actionable principles that can transform your year and help you land that dream job or become a better analyst.</p><h3>The Power of Clarity</h3><p>Clarity is like the lens of a camera, when you adjust it, everything comes into sharp focus. Without it, you’re left with blurry ambitions and unfulfilled goals. So how do you sharpen your vision for 2025?</p><blockquote>Clarity isn’t just about knowing what you want; it’s about making every step purposeful. With clarity, you don’t just move — you move in the right direction.</blockquote><h4>Here’s how clarity can work magic in your life</h4><ol><li><strong>Define Your Destination</strong><br>Think of your career as a journey. What’s your destination? Is it landing your first data analyst job, becoming a SQL expert, or building a standout portfolio? Write it down — it’s your north star!</li><li><strong>Create Your Map</strong><br>Break your big goal into smaller, achievable milestones. If you want to get hired, ask yourself: Do I need a new certification? A portfolio project? Better networking? Plot these steps on your map.</li><li>Picture yourself achieving your dream. Feel the excitement of opening that job offer email or presenting your first analysis to a team. This vision keeps you energized and focused.</li></ol><h3>The Magic of Consistency</h3><p>Consistency is the heartbeat of success. It’s not about giant leaps; it’s about the rhythm of small, intentional actions. In a world full of distractions, consistency is what keeps you grounded and growing.</p><h4>Why consistency is your superpower:</h4><ol><li><strong>Tiny Steps, Massive Impact</strong><br>Learning data analysis isn’t about cramming; it’s about steady, daily progress. Spend 30 minutes daily practicing SQL or building a Power BI dashboard, and watch your confidence soar.</li><li><strong>Momentum Builds Motivation</strong><br>Starting is the hardest part, but once you establish a routine, it gets easier. Momentum becomes your ally, turning effort into habit.</li><li><strong>Resilience Through Routine</strong><br>Consistency helps you bounce back. Stuck on a tricky Python problem? Show up again tomorrow. Success isn’t about never failing — it’s about never giving up.</li></ol><p>January is full of energy, but it’s easy to overcommit. Instead of trying to master everything at once, focus on one skill or goal at a time. Celebrate small victories — a completed project, a new connection on LinkedIn, or a recruiter’s positive feedback. These moments add up.</p><p>Remember, progress isn’t about doing it all; it’s about doing what matters most, consistently.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3287498bdd1f" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[HG Data Analysis Internship Task]]></title>
            <link>https://medium.com/@nwajagustanley/hg-data-analysis-internship-task-14f97a44e91d?source=rss-d4a27cb13d18------2</link>
            <guid isPermaLink="false">https://medium.com/p/14f97a44e91d</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[titanic-dataset]]></category>
            <category><![CDATA[tech]]></category>
            <category><![CDATA[hg-internship]]></category>
            <category><![CDATA[internships]]></category>
            <dc:creator><![CDATA[Nwajagu Stanley Ifeanyi]]></dc:creator>
            <pubDate>Tue, 02 Jul 2024 10:16:35 GMT</pubDate>
            <atom:updated>2024-07-02T10:20:21.108Z</atom:updated>
            <content:encoded><![CDATA[<h4>Stage Zero: Titanic Dataset Analysis</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lrS10J4-6WZAFY41.jpg" /></figure><h4>INTRODUCTION</h4><p>This article will talk about the analysis of the Titanic dataset as part of the HG internship task. You can learn more about the internship by visiting <a href="https://hng.tech/internship">https://hng.tech/internship</a>. They offer the best talents in any tech field. Go to <a href="https://hng.tech/hire">https://hng.tech/hire</a> to find and hire top talents.</p><p>The purpose of this analysis is to examine the dataset, uncover insights, and write a brief technical report of findings.</p><p><strong>DATA STRUCTURE</strong></p><p>The data contains:</p><p>3 categorical variables</p><p>9 numerical variables</p><p><strong>OVERVIEW OF DATASET</strong></p><p><strong>Before Cleaning</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/965/1*udq6cSY2vI08ngElc15FAg.png" /></figure><p><strong>After Cleaning</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Sz5TE-9gXtn-CI4EmPlZBA.png" /></figure><p><strong>Tools</strong></p><ol><li>Excel</li><li>Power BI</li></ol><h4>OBSERVATION</h4><p>Below are the insights that can be obtained from the dataset.</p><ol><li><strong>Survival of Passengers Onboard</strong></li></ol><p>From the dataset containing <strong>714</strong> passengers, only <strong>290</strong> passengers survived, making up approximately <strong>41%</strong> of the total passengers. The remaining <strong>424</strong> passengers which made up <strong>59%</strong> of the rest passengers did not survive. Below is a chart to show the distribution of passengers</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/414/1*KiiGo4xIE1r0DGVFoweMaA.png" /></figure><p><strong>2. Relationship Between Survival and Gender</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/327/1*6ZwYn057hOY8fTiXzwm9dQ.png" /></figure><p>From the table seen above, it can be deduced that a large number of surviving passengers were <strong>female</strong>, and a large number of passengers that died were <strong>male</strong>. The reason behind this could be that females and children were given priority first before male passengers.</p><p><strong>3. Relationship Between Survival and Socio-economic Class /Gender of Passengers</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/325/1*k9cFsGRYWLibzoV_K9juFA.png" /></figure><p>The table above shows that a large number of passengers who survived were from <strong>First class </strong>(82 female, 40 male), while a large number of passengers who lost their lives were from <strong>Third class</strong>.</p><p><strong>4. Relationship Between Survival and Embarkation</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/428/1*-3r9bMnuhUb7M_21KVBJ6w.png" /></figure><p>At first glance, this table reads that more than half of the passengers were picked up from <strong>point S</strong> (Southampton). A look into why Southampton has a large number of passengers can be seen below</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/599/1*ZLZ4L7XrHzHF6WwQsVkMag.png" /></figure><p>The table above shows that a large number of passengers who embarked on Southampton were <strong>Third class</strong> passengers.</p><h4>CONCLUSION</h4><p>The following conclusion can be drawn from the dataset</p><ol><li>Only 41% of passengers survived the Titanic</li><li>Among the survivors, 67.9% were female while 32.1% were male</li><li>Most of the surviving passengers were First-class</li><li>77.8% of Total passengers on board were from Southampton</li><li>52% of passengers that embarked from Southampton were Third-class.</li></ol><p>Important to note that these observations were made based on <strong>first glance, </strong>and such would require further analysis into which percentage of males or females were children and how many of the survived were elderly.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=14f97a44e91d" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Cleaning: The Unsung Hero of Data Analytics]]></title>
            <link>https://medium.com/@nwajagustanley/data-cleaning-the-unsung-hero-of-data-analytics-829a9c6eab12?source=rss-d4a27cb13d18------2</link>
            <guid isPermaLink="false">https://medium.com/p/829a9c6eab12</guid>
            <category><![CDATA[data-cleaning-with-python]]></category>
            <category><![CDATA[data-cleaning-with-excel]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-analysis]]></category>
            <dc:creator><![CDATA[Nwajagu Stanley Ifeanyi]]></dc:creator>
            <pubDate>Sun, 30 Jun 2024 14:14:22 GMT</pubDate>
            <atom:updated>2024-09-09T23:54:11.641Z</atom:updated>
            <content:encoded><![CDATA[<h3>Data Cleaning: The Unsung Hero of Data Analysis</h3><p>When it comes to data analysis, people remember the flashy dashboards, the nice-looking charts, and the perfect-looking table in Excel… people often forget the hard work behind making these tables and charts perfect. Data cleaning is not only an essential part of data analysis, but also an integral part of data analysis. It is what makes data valid and reliable.</p><blockquote><em>Data cleaning, also known as data cleansing, is the meticulous process of correcting or removing inaccurate, incomplete, or irrelevant data from a dataset.</em></blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/0*-yeGWHLMwwE5V1NR" /><figcaption><strong>Data Cleaning</strong></figcaption></figure><p>The significance of this process cannot be overstated, as it directly influences the accuracy of the data analysis results. If your data is not clean, then your results are affected, it’s as simple as that.</p><p>While I talk about the various aspects involved in data cleaning, I&#39;m going to explain how I clean my data and the process I follow to ensure that data is complete, accurate, and reliable.</p><h4>Aspects Involved in Data Cleaning</h4><p>Aspects involved in data cleaning are those processes of identifying and correcting errors, inconsistencies and inaccuracies in a dataset. These aspects are as follows:</p><ol><li><strong>Removing Duplicates</strong></li></ol><p>Duplicate entries can skew your analysis, making identifying and removing them essential. Most people will like to remove duplicates by clicking the “Data” tab on Excel and going to “Remove duplicates”. But I don’t always remove duplicates like that, especially when I think it may contain sensitive data. Rather, I go to “conditional formatting” and <em>highlight cell values that have duplicates…</em>that way, I can be able to see the duplicates and know whether they need removing or not.</p><p>2. <strong>Handling Missing Values</strong></p><p>Missing data can be managed by either removing incomplete entries, filling gaps with estimates, or using other imputation techniques or statistical calculations. Personally, this is how I handle missing values, if it’s a non-numerical value, I calculate the most frequent value in the column and use it to replace the missing values. when it’s a numerical value, I calculate the median of the column and replace it with the missing value.</p><p>3. <strong>Correcting Errors</strong></p><p>This involves finding and fixing inaccuracies in the data, such as typos, incorrect values, or mismatched records.</p><p>4. <strong>Standardizing the data</strong></p><p>Standardizing data is all about ensuring consistency in data formats, such as dates, phone numbers, addresses, and units of measure, to facilitate seamless analysis. Some important date functions I use to format dates are <em>date</em>, <em>date value</em>, and <em>value</em>. Standardizing data ensures consistency in all your columns</p><p>5. <strong>Managing Outliers</strong></p><p>This involves identifying and addressing outliers that may distort analysis results.</p><blockquote>Outliers are data points or values that differ significantly from other observations. They may be unusually high or low values and they stand out from the rest of the dataset.</blockquote><p>Outliers can skew averages and standard deviations but also they can indicate rare events that need further investigation. Personally, i manage outliers by either using boxplots or statistical methods like z-scores or interquartile range(IQR). Managing outliers involves deciding whether to transform or exclude them entirely, depending on the context of your analysis.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/0*ICPJfvoNf4j8E4E4.jpg" /><figcaption><strong>Data Cleaning</strong></figcaption></figure><h4>IMPORTANCE OF DATA CLEANING</h4><ol><li><strong>Accuracy</strong>: Clean data leads to more accurate analysis and reliable conclusions.</li><li><strong>Efficiency</strong>: Well-organized data saves time and resources in the analysis phase.</li><li><strong>Reliability</strong>: High-quality data builds trust in your findings and the decisions based on them.</li><li><strong>Compliance</strong>: Clean data helps maintain compliance with data protection and governance standards.</li></ol><h4>CONCLUSION</h4><p>Data cleaning is an essential step in the data analysis process. It transforms raw, messy data into a reliable foundation for accurate and insightful analysis. Your insights are only as good as the effort you put behind them.</p><p>Take for instance, I want to find out how many customers came to the store today. If I have data of 5 customers that shows 4 duplicate names of customers, we would be deceived to think that 5 customers came to the store…when in truth, it was only one. Data cleaning makes sure the data used does not lack quality or integrity.</p><p>This is why it is important to invest time and effort in data cleaning as it not only enhances the quality of your analysis but also paves the way for more informed decision-making and business success.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=829a9c6eab12" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>