<?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 Oluwaseyiton on Medium]]></title>
        <description><![CDATA[Stories by Oluwaseyiton on Medium]]></description>
        <link>https://medium.com/@oluwaseyiton?source=rss-cad412ee1edf------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*jSa91TSC2GqebsUb</url>
            <title>Stories by Oluwaseyiton on Medium</title>
            <link>https://medium.com/@oluwaseyiton?source=rss-cad412ee1edf------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 11:42:39 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@oluwaseyiton/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[Beyond the Numbers: Learning to See the Story in Data]]></title>
            <link>https://medium.com/@oluwaseyiton/beyond-the-numbers-learning-to-see-the-story-in-data-2456e844d917?source=rss-cad412ee1edf------2</link>
            <guid isPermaLink="false">https://medium.com/p/2456e844d917</guid>
            <dc:creator><![CDATA[Oluwaseyiton]]></dc:creator>
            <pubDate>Sun, 01 Nov 2026 11:37:07 GMT</pubDate>
            <atom:updated>2026-11-01T11:37:07.620Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/610/1*R3ivaSulF1s8hC-PLcdzGw.png" /></figure><p>This week has been an interesting one. The Week 8 modules were quite easy to digest, so I got into the tasks without spending too much time trying to understand the concepts. The focus was on two important aspects of data analysis: aggregation and visualisation.</p><p>I spent some time working with milk trade data, practising how to summarise information and make it easier to interpret. Data aggregation helped me see how individual records could be brought together to reveal broader patterns, while visualisation showed me how those patterns could be communicated more effectively.</p><p>Then came the plotting exercises.</p><p>I worked with Matplotlib and Seaborn to recreate different visualisations, including histograms, KDE plots, box plots, violin plots, regression plots and heatmaps. I found the possibilities quite exciting, but I also noticed something: there are so many functions, parameters and lines of code involved in creating these charts. Sometimes, I wondered whether there was a simpler way to achieve the same results with fewer lines of code. Perhaps that is something I will understand better with more practice.</p><p>One challenge was working with the milk trade summary, which contained only four aggregated records. This meant that some visualisations, particularly the KDE and regression plots, had limited statistical value. It was a useful reminder that creating a chart is not enough; the data behind it must also be suitable for the conclusion we want to draw.</p><p>Beyond learning the syntax, this week’s work helped me appreciate that visualisation is not just about making data look attractive. It is about making information understandable, identifying patterns and communicating findings in a way that makes sense to others.</p><p>There is still a lot to learn, especially when it comes to choosing the right chart and getting comfortable with the different plotting functions. But I am beginning to see how aggregation and visualisation bring analysis together. We don’t just work with numbers; we learn to make sense of them.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=2456e844d917" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Learning to Think Like a Data Analyst: Reflections from Another Week of Growth]]></title>
            <link>https://medium.com/@oluwaseyiton/learning-to-think-like-a-data-analyst-reflections-from-another-week-of-growth-82e07113597c?source=rss-cad412ee1edf------2</link>
            <guid isPermaLink="false">https://medium.com/p/82e07113597c</guid>
            <dc:creator><![CDATA[Oluwaseyiton]]></dc:creator>
            <pubDate>Sun, 25 Oct 2026 21:18:56 GMT</pubDate>
            <atom:updated>2026-10-25T21:18:56.443Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/610/1*R3ivaSulF1s8hC-PLcdzGw.png" /></figure><p>This week was another opportunity to learn, experiment, and remind myself that data analytics is not just about writing code. It is about asking meaningful questions, solving problems, and discovering stories hidden in data.</p><p>One of the major things I worked on was using <strong>Python and Pandas</strong> to organise and analyse data. I explored how to work with datasets, select relevant information, handle missing values, and prepare data for analysis. I also practised creating visualisations to make patterns easier to understand. These activities helped me appreciate how tools such as Pandas and Matplotlib can turn raw numbers into useful insights.</p><p>My main project for the week was exploring the relationship between two World Bank indicators: agriculture’s contribution to GDP and GDP per capita. Given my background in Agricultural and Resource Economics, this topic felt particularly relevant to my interests.</p><p>The idea was simple: <strong>Do countries with a higher agricultural contribution to their economies also have higher income per person?</strong></p><p>To investigate this, I planned to retrieve data from the World Bank, combine the two indicators, calculate their correlation, and use a scatter plot to examine the relationship. It was exciting to see how my interest in agriculture could connect with the practical application of data analytics.</p><p>Of course, the process was not entirely smooth. Working with unfamiliar datasets, understanding indicator codes, combining information from different sources, and making sure the data was suitable for comparison required patience. I also had to think beyond simply getting the code to run. What did the data actually represent? Were the indicators comparable? What could a correlation tell me, and what could it not tell me?</p><p>These questions reminded me that successful analysis requires more than technical skills. It also demands curiosity, critical thinking, and attention to detail.</p><p>My biggest takeaway this week is that <strong>data analytics becomes more meaningful when it is connected to a real-world problem</strong>. I am beginning to see how I can combine my agricultural economics background with data science to investigate issues affecting agriculture and economic development.</p><p>I still have much to learn, but each project is helping me build confidence. I am learning to be patient with the process, ask better questions, and focus on understanding the story behind the numbers.</p><p>One dataset, one question, and one lesson at a time. That is how I intend to keep growing.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=82e07113597c" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Challenges Along the Way]]></title>
            <link>https://medium.com/@oluwaseyiton/the-challenges-along-the-way-769507c2bc47?source=rss-cad412ee1edf------2</link>
            <guid isPermaLink="false">https://medium.com/p/769507c2bc47</guid>
            <dc:creator><![CDATA[Oluwaseyiton]]></dc:creator>
            <pubDate>Sun, 18 Oct 2026 20:21:51 GMT</pubDate>
            <atom:updated>2026-10-18T20:21:51.134Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/553/1*qM1ii7F8lJfTGmXUbbixuQ.png" /></figure><h3>Finding My Flow Again: A Week of Learning SQL, NumPy and Pandas</h3><p>There is something interesting about returning to something you once enjoyed. You may not remember everything, and the process might feel slower than you expected, but somewhere along the way, things begin to make sense again. That has been my experience this week as I continue my data science learning journey with DataRaflow.</p><p>This week was about strengthening my foundation in data analysis, particularly SQL, NumPy and Pandas. It was a mix of querying databases, working with arrays, manipulating data, and solving practical problems. More importantly, it reminded me that learning data science is not just about knowing the tools but understanding how to use them to answer questions.</p><h3>What I Learnt</h3><p>I continued practising SQL, learning how to retrieve and organise data from relational databases. Working with the weather datasets for six cities introduced me to combining data from multiple tables using UNION ALL. I also learnt why the columns being combined must have compatible data types and appear in the same order. A seemingly small difference in column names, such as GMT in one table and Date in another, was enough to make me rethink how I approached the query.</p><p>With NumPy, I practised creating arrays, identifying missing values such as NaN, comparing elements, and checking how much memory an array occupies.</p><p>Pandas introduced me to more ways of manipulating data. I worked with Series and DataFrames, performed arithmetic operations, converted dictionaries and NumPy arrays into Series, changed data types, sorted values, and filtered records using specific conditions.</p><p>Together, these tools helped me understand different stages of data analysis: SQL helps retrieve and combine data, NumPy supports numerical operations, and Pandas makes it easier to clean, organise and explore datasets using Python.</p><h3>What I Solved</h3><p>My work this week involved several practical exercises. In SQL, I attempted to combine weather data from London, Beijing, Brasilia, Cape Town, Delhi and Moscow into a single dataset. The goal was to organise the information in a format that would make comparisons across cities easier.</p><p>I also worked through NumPy and Pandas exercises that required me to compare arrays, handle values that could not be converted to numbers, extract specific rows and columns, and filter records based on multiple conditions.</p><p>These exercises helped me move beyond simply recognising Python functions to understanding when and why to use them.</p><h3>The Challenges Along the Way</h3><p>Not everything worked on the first attempt. SQL presented its own frustrations, particularly when a query failed because of differences in column names or when my database connection became unstable. I had to distinguish between a problem with my SQL query and a problem with the database connection itself.</p><p>In Python, I sometimes struggled with syntax, indexing and mixed data types. For example, filtering a DataFrame using multiple conditions requires the correct operators and parentheses. These details can easily be overlooked when you are focused on getting the answer.</p><h3>How I Worked Through Them</h3><p>I learnt to approach errors more systematically. Instead of assuming that everything was wrong, I began testing smaller queries, checking table structures and confirming that my database connection worked before running more complex operations.</p><p>For Python exercises, I focused on understanding what each function returned and how the output related to the original problem. This made debugging less about guessing and more about identifying where things went wrong.</p><p>I am also learning that there is value in slowing down. Sometimes, revisiting a basic concept is exactly what is needed to understand a more advanced one.</p><h3>Slowly Getting Back Into It</h3><p>I would not say I have mastered SQL, NumPy or Pandas. There is still a lot to learn, and I expect to encounter more confusing problems as I progress. But I can feel myself becoming more comfortable with the process.</p><p>One thing this week has reinforced is that data analysis is a collection of connected skills. Writing a query is useful, but understanding the data it returns is just as important. Knowing a Pandas function is helpful, but knowing whether it is the right tool for the problem matters more.</p><p>Perhaps the biggest lesson is that progress does not always come as a major breakthrough. Sometimes, it is simply sitting down, working through a difficult problem, understanding a mistake, and trying again.</p><p>I am still learning, still making mistakes, and still figuring things out. But slowly, I am finding my flow again.</p><p>And for now, that is enough to keep me going.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=769507c2bc47" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Wake-Up Call I Didn’t Know I Needed]]></title>
            <link>https://medium.com/@oluwaseyiton/the-wake-up-call-i-didnt-know-i-needed-a8660e9710b8?source=rss-cad412ee1edf------2</link>
            <guid isPermaLink="false">https://medium.com/p/a8660e9710b8</guid>
            <dc:creator><![CDATA[Oluwaseyiton]]></dc:creator>
            <pubDate>Tue, 13 Oct 2026 21:01:41 GMT</pubDate>
            <atom:updated>2026-10-13T23:18:46.549Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/278/1*r2jnTtFkk5GOng9ZVFN2wg.png" /></figure><p><strong>The Wake-Up Call I Didn’t Know I Needed</strong></p><p>There’s a particular kind of silence that comes with staring at a blank page, knowing you have to choose one idea out of a hundred that excite you. That was me, for most of this past month.</p><p>I have always been drawn to the idea that data can feed people. Agriculture is where numbers meet real life: soil, rainfall, harvests, and the farmers whose livelihoods depend on all three. So when DataraFlow gave me a platform to explore that interest through research, I thought the hard part was getting the opportunity. I was wrong. The hard part was choosing.</p><p>Do I study crop yield prediction? Pest detection? Climate patterns and planting seasons? Every direction felt important, and every time I settled on one, doubt crept in. Is it too broad? Has it been done to death? Can I actually pull this off? I changed my topic more times than I’d like to admit, and some nights I wondered if I was cut out for this at all.</p><p>Eventually, I stopped searching for the perfect topic and started looking for the one I couldn’t stop thinking about. That’s how I landed on mine. It felt like exhaling.</p><p>Then came another humbling part: relearning how to write a research paper. I used to think I knew how. But research writing has its own discipline. You can’t just say what you believe; you have to show why, with structure, evidence, and a clear question guiding every line. I had to unlearn lazy habits and start again from the foundations: problem statement, objectives, literature review, methodology.</p><p>Learning to write a research proposal changed something in me. For the first time in a long while, I felt that old spark again, the curiosity that made me love research in the first place. Seeing my scattered ideas turn into a clear, structured plan was deeply satisfying.</p><p>Maybe this is the wake-up call I needed. A reminder that passion needs direction, and that discomfort is often just growth wearing a heavy coat.</p><p>Week 5 was hard, but I’m grateful for it. The proposal is written, the path is clearer, and I’m more excited than ever to see where this goes.</p><p>Next week, we dig in.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a8660e9710b8" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Learning to Move Forward: My Journey Through Python and Data Science]]></title>
            <link>https://medium.com/@oluwaseyiton/learning-to-move-forward-my-journey-through-python-and-data-science-9ddc17f6a1eb?source=rss-cad412ee1edf------2</link>
            <guid isPermaLink="false">https://medium.com/p/9ddc17f6a1eb</guid>
            <dc:creator><![CDATA[Oluwaseyiton]]></dc:creator>
            <pubDate>Sat, 26 Sep 2026 20:41:25 GMT</pubDate>
            <atom:updated>2026-09-26T20:41:25.811Z</atom:updated>
            <content:encoded><![CDATA[<p>There is something interesting about learning a skill you once thought you understood.</p><p>You remember the words. You recognise some of the concepts. You may even look at a piece of code and think, <em>“I have seen this before.”</em> But when it is time to actually use that knowledge, things suddenly become less familiar.</p><p>That has been my experience so far in my <strong>Data Science course at Datara Flow</strong>.</p><p>My previous exposure was mainly in <strong>Data Analytics,</strong> something I encountered and studied when I was younger. Coming back to the world of data through Data Science has therefore felt like returning to a place I once visited, but with a completely different map.</p><h3>Returning to Something Familiar</h3><p>Coming into this course, I expected some things to come naturally because of my previous experience with data analytics.</p><p>That assumption did not last very long.</p><p>I quickly realised that remembering a concept is very different from being able to apply it. Some things felt familiar, while others required me to stop, go back, read again, and try things for myself.</p><p><strong>That was my first real lesson: previous knowledge is a foundation, not a shortcut.</strong></p><p>I had to accept that I was not starting completely from zero, but I also could not rely entirely on what I remembered.</p><h3>Python Became the Reality Check</h3><p>The Python module has been particularly interesting because it introduced me to several areas that are essential when working with data.</p><p>I worked through topics such as:</p><ul><li><strong>Python Modules</strong> — understanding how code can be organised and reused.</li><li><strong>Python Date and Time</strong> — learning how dates and timestamps can be handled programmatically.</li><li><strong>Python Math</strong> — working with mathematical operations and functions.</li><li><strong>Python JSON</strong> — understanding structured data and how Python can work with it.</li><li><strong>Python pip</strong> — getting introduced to the wider ecosystem of Python packages and tools.</li></ul><p>Individually, these topics might not seem overwhelming.</p><p>The real challenge came when I had to use them in assignments.</p><p>That is when theory meets reality.</p><h3>Week 2 — The Part I Couldn’t Complete</h3><p>Week 2 was where things became uncomfortable.</p><p>I did not complete Week 2 successfully.</p><p>That experience was frustrating, especially because I had already encountered data-related concepts earlier in my learning journey. There was a temptation to think, <em>“I should know this already.”</em></p><p>But that thought did not help me solve the problem.</p><p>Instead, I had to confront something I think many learners experience but do not always talk about:</p><p><strong>Sometimes, you know enough to recognise a problem but not enough to solve it yet.</strong></p><p>That distinction matters.</p><p>Failing to complete Week 2 did not mean I had failed at learning. It showed me exactly where my knowledge needed attention.</p><h3>Tackling Week 3 Anyway</h3><p>The interesting part of this journey is that Week 2 was still unfinished when I moved into Week 3.</p><p>At first, that felt strange.</p><p>How do you move forward when you still have unfinished work behind you?</p><p>I eventually realised that learning does not always happen in a perfectly organised sequence.</p><p>I tackled Week 3 while keeping the gaps from Week 2 in mind.</p><p>I was not suddenly an expert. I still had moments where I had to revisit concepts, troubleshoot errors, and spend more time than I expected on assignments.</p><p>But this time, I approached the challenge differently.</p><p>Instead of seeing difficulty as evidence that I could not do it, I started seeing difficulty as information.</p><p><strong>An error is not always a roadblock. Sometimes, it is a sign pointing toward what you need to learn next.</strong></p><h3>What the Assignments Are Teaching Me</h3><p>The assignments have probably been more valuable than simply reading through the lessons.</p><p>Why?</p><p>Because assignments expose the difference between <em>recognising</em> something and <em>understanding</em> it.</p><p>You can watch someone write Python code and understand every line.</p><p>Then you open your own editor and suddenly wonder:</p><p><em>“Wait… how do I actually do this myself?”</em></p><p>That has happened to me more than once.</p><p>And honestly, I think that is part of the process.</p><p>The assignments force me to think, experiment, make mistakes, search for answers, revisit lessons, and try again.</p><p>That process is slowly rebuilding the knowledge I had lost.</p><h3>Learning While Still Catching Up</h3><p>I am still catching up.</p><p>Week 2 remains unfinished, while Week 3 has been tackled.</p><p>That might not sound like the perfect learning journey, but it is my actual experience — and I think there is value in being honest about that.</p><p>Learning is rarely as clean as the tutorials make it appear.</p><p>Sometimes you understand something immediately.</p><p>Sometimes you need five attempts.</p><p>Sometimes you finish an assignment feeling proud.</p><p>Other times, you close your laptop wondering what just happened.</p><p>And sometimes, you have to continue moving while knowing there is still something behind you that needs attention.</p><p><strong>The important thing is not to confuse being behind with being incapable.</strong></p><h3>What I Am Taking Forward</h3><p>My biggest lesson so far has not been a particular Python function or command.</p><p>It has been learning how to respond when I do not understand something.</p><p>I am learning to slow down without giving up.</p><p>I am learning to revisit old concepts without feeling ashamed that I forgot them.</p><p>I am learning that asking questions, debugging code, making mistakes, and trying again are not signs that I am failing at Data Science.</p><p>They are part of learning Data Science.</p><p>My previous experience with data analytics gave me a starting point, but this course is forcing me to rebuild that foundation in a different way.</p><p>And maybe that is exactly what I need.</p><h3>The Journey Continues</h3><p>I have not completed every challenge.</p><p>I have not mastered Python.</p><p>I have not magically recovered everything I once knew about data analytics.</p><p>But I have started moving again.</p><p>Week 2 taught me that I have gaps.</p><p>Week 3 reminded me that gaps do not have to stop progress.</p><p>And the assignments are teaching me that <strong>real understanding comes from doing, struggling, correcting, and doing it again.</strong></p><p>For now, I am taking the journey one concept, one assignment, one error message, and one breakthrough at a time.</p><p><strong>I am not trying to prove that I already know everything. I am trying to become someone who knows how to keep learning when I don’t.</strong></p><p>Abdulazeez Ijaoba</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9ddc17f6a1eb" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Learning Data Science: What I’m Beginning to Understand]]></title>
            <link>https://medium.com/@oluwaseyiton/learning-data-science-what-im-beginning-to-understand-3313658ce5e8?source=rss-cad412ee1edf------2</link>
            <guid isPermaLink="false">https://medium.com/p/3313658ce5e8</guid>
            <category><![CDATA[python]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[beginners-guide]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Oluwaseyiton]]></dc:creator>
            <pubDate>Thu, 10 Sep 2026 22:40:27 GMT</pubDate>
            <atom:updated>2026-09-10T22:40:27.327Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/610/1*R3ivaSulF1s8hC-PLcdzGw.png" /></figure><p>I recently started taking my data science learning more seriously, all thanks to Datara flow, but one thing I have quickly realized is that learning data science is not as straightforward as I initially thought.</p><p>At first, I thought it was mostly about learning Python, SQL, building dashboards, and working with datasets.</p><p>But the more I learn, the more I realize that the tools are only one part of the journey.</p><p>The bigger challenge is learning <strong>how to think about data</strong>.</p><p>Coming from an Agricultural and Resource Economics background, I have some experience with statistics, econometrics, and research. However, working with data practically feels different from learning the concepts in school.</p><p>Sometimes I understand what a piece of code is supposed to do but still struggle to write it myself. Other times, I can get the code to work but don’t fully understand what the result is telling me.</p><p>And honestly, that can be frustrating.</p><p>One thing I’m beginning to understand is that <strong>learning by following tutorials is not the same as solving problems independently</strong>.</p><p>So I’m trying to spend less time simply watching and more time practicing — working with datasets, making mistakes, searching for solutions, and trying again.</p><p>I’m also beginning to understand that data science isn’t just about writing code.</p><p>It’s about asking questions.</p><p>What am I trying to find out?</p><p>What data do I need?</p><p>How reliable is the data?</p><p>What does the analysis actually mean?</p><p>And how can the result help solve a real problem?</p><p>This is where my background in agriculture and economics makes the journey particularly interesting for me.</p><p>I want to eventually explore how data can help us better understand issues around agriculture, farmers, food security, markets, and livelihoods.</p><p>I’m still at the beginning, and I definitely don’t have everything figured out.</p><p>But I think that’s the point of documenting this journey.</p><p>I’m learning, getting stuck, figuring things out, and slowly developing a better understanding of what working with data really means.</p><p>If you’re also starting out, one thing I hope we both remember is this:</p><p><strong>You don’t have to know everything before you start. You just have to keep learning, practicing, and asking better questions.</strong></p><p>This is only the beginning of my data science journey, and I’m looking forward to seeing where it takes me.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3313658ce5e8" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>