<?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 Adewunmi Oluwaseun Asegun on Medium]]></title>
        <description><![CDATA[Stories by Adewunmi Oluwaseun Asegun on Medium]]></description>
        <link>https://medium.com/@Crownthirst?source=rss-81d654006080------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*mbq5z1EChpa2wBCrwMWSYQ.jpeg</url>
            <title>Stories by Adewunmi Oluwaseun Asegun on Medium</title>
            <link>https://medium.com/@Crownthirst?source=rss-81d654006080------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 23:25:18 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@Crownthirst/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[Waiting in Line]]></title>
            <link>https://medium.com/@Crownthirst/waiting-in-line-262a13ae6f31?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/262a13ae6f31</guid>
            <category><![CDATA[operations-management]]></category>
            <category><![CDATA[queuing-theory]]></category>
            <category><![CDATA[operations]]></category>
            <category><![CDATA[queue-management]]></category>
            <category><![CDATA[queue-management-system]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Tue, 25 Jul 2023 16:35:36 GMT</pubDate>
            <atom:updated>2023-07-25T16:35:36.851Z</atom:updated>
            <content:encoded><![CDATA[<h4>An Introduction to Queueing Models</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*jrhDCOQthJhi8zEIrXErFw.jpeg" /><figcaption>Metropolis queue | <a href="https://www.flickr.com/photos/alper/">Alper Çuğun</a> on Flickr</figcaption></figure><p>At one point in our lives, we must have been waiting in line. Either at a bank, a supermarket, a store or anywhere. Sometimes we’re pissed by the amount of time we have to spend waiting, sometimes we leave.</p><p><em>This is the exact reason queueing models are built.</em></p><p>In its simplest form, queueing models are mathematical models that are used to evaluate and enhance the functionality of systems that requires you to wait or stand on a queue.</p><p>Queueing models seek to understand how system efficiency is influenced by the number of service providers, the service time, and the arrival rate of customer.</p><p>Two important parameters are:</p><ol><li>Arrival rate</li><li>Service rate</li></ol><p>A business can assess its system to determine the number of service providers it needs to operate efficiently while it also improves customer experience by reducing wait time once these parameters are known. I would not like to dig deep into the computations of these metrics as it requires lots and lots of formulas, so we will focus on the business side of things to tell where this model fits in and the problem it solves.</p><p>To better contextualize this discussion, we must first comprehend the significance of the crucial metrics shown in the snapshot below.</p><ul><li>Arrival rate</li><li>Service rate</li><li>Average server utilization e.t.c</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/795/1*eUxsn8GZR45oqLeBWNtZ1Q.png" /><figcaption>Input and operating characteristics of a queueing model</figcaption></figure><ul><li>The arrival rate refers to the rate at which customers arrive into the system, as seen in the snapshot above the business expects 50 customers per/hr.</li><li>The service rate is the rate at which the customers who arrive into the system are served/attended to</li></ul><p><em>In queueing theory, the relationship between the arrival rate and the service rate is a key factor in determining the behavior of the system. If the arrival rate is greater than the service rate, a queue will be formed, on the other hand if the service rate is greater than the arrival rate, we find no queue at all, in-fact the system will be underutilized.</em></p><ul><li>The Average server utilization measures how active/busy the system is, it is the ratio of arrival rate to service rate.</li><li>P0 pronounced as (P naught) is the probability that the system is idle, i.e the probability that there are no customers to be served by the servers.</li><li>Lq refers to the length of queue the expected number of customers on the queue waiting to be served.</li><li>L refers to the average number of customers expected to be present according to our arrival rate.</li><li>Wq is the average time a customer spends waiting on the queue. (in reality you want to reduce this to its barest minimum).</li><li>W refers to the average time the customer spends in our system, i.e from the minute he enters into the system, till he joins the queue, gets served and leaves the system. (This is different from “Wq”)</li></ul><p>Having established the meaning to all these metrics. we might hop on a little practical example to visualize the potency of this model and its application in performance evaluation/management.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/881/1*2_cbcg_P4I9VgBbkQuoFaA.png" /></figure><p>Plugging in these figures into our model, we can view the current level of performance in our superstore.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/1*6YoJlERpMXHFqnFRRhuzrA.png" /></figure><ul><li>With 81% server utilization we can say our servers are well utilized, but it could also mean that we are overworking our cashiers meaning little or no rest time for them.</li><li>The probability that we have no customers in our system is just 5%.</li><li>With an Lq of 2.8167 the expected number of people waiting in queue (the length of the queue) equals 3 approximately.</li><li>Every hour the store expects an average of 5 customers in its system.</li><li>The average time a customer spends waiting on the queue in this store equals 2minutes approximately. (When 0.0331/hr is converted to minutes).</li><li>If the current service rate and arrival rate is maintained, the average time every customer spends in our system equals 4minutes approximately.</li></ul><p><em>It is crucial to note that there will always be a trade-off between server utilization and wait time. If there are more servers in the system, the servers will be significantly underutilized, but the customers will have short wait times. On the other hand, if there are few servers in the system, the servers will be well utilized but the customers will experience long wait times.</em></p><p>After assessment, it is crucial to take into account the management’s goal and its objectives.</p><p>Is the main objective to reduce customer wait times? or the management’s top objective is to maximize server utilization. Our analysis and recommendations will then be guided by the management’s goal and objective.</p><p>Supposing the management is looking to keep wait time under one minute, then they can add one more cashier to the mix. Plugging the figures in.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/792/1*n8GyLaYq6j13rNUoSJJD-w.png" /></figure><p>THE EFFECT</p><ul><li>This will drop the server utilization to 61% meaning less work plus possible idle time for our cashiers.</li><li>The average number of customers on the queue is now close to zero as against 3.</li><li>The average number of customers expected in the system drops to 3 against 5.</li><li>The average time a customer spends waiting in line is well under 1 minute (When 0.0054/hr is converted to minutes)</li><li>Finally, the average time a consumer spends in the system is now 2 minutes, down from 4 minutes stated earlier.</li></ul><p><em>We observe how the management must choose between spending more money to hire an additional clerk and giving customers a better experience by cutting down on wait times.</em></p><p>There is more to queueing models than meets the eye, and of course i have just scratched the surface. Behind these calculations are many assumptions and formulas, and if it picks your interest, you can dive deep into the world of queueing theory.</p><p>In the meantime, you can download the model used in this writeup from my <a href="https://github.com/Crownthirst/Queueing-Model">Github repository</a>.</p><p>Abientot.</p><p>You can also connect with me <a href="https://twitter.com/CrownThirst">here</a> on twitter.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=262a13ae6f31" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Science of Making Sense:]]></title>
            <link>https://medium.com/@Crownthirst/the-science-of-making-sense-c59b91be7c50?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/c59b91be7c50</guid>
            <category><![CDATA[statistics]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[statistical-analysis]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Mon, 01 May 2023 19:09:46 GMT</pubDate>
            <atom:updated>2023-05-01T19:09:46.425Z</atom:updated>
            <content:encoded><![CDATA[<h3>The Science of Making Sense</h3><h4>Statistical Analysis: The Key to Understanding Complex Data</h4><p>The world is now a global village, and in this data-driven village, you will agree with me that we are swamped with a tremendous volume of information, even more than we can consume. Every day we continue to generate data at a breakneck pace, and it appears we won’t be stopping soon.</p><p>In September 2022, Statista put together this <a href="https://www.statista.com/statistics/871513/worldwide-data-created/#:~:text=Over%20the%20next%20five%20years%20up%20to%202025%2C,data%20created%20and%20replicated%20reached%20a%20new%20high.">article</a> where it highlighted the volume of data created, captured, and consumed worldwide, projecting the volume to hit 181 zettabytes by 2025. Put that into some context: with about 4.66 billion active internet users worldwide, <a href="http://google.com/">Google</a> processes about 99,000 searches every second, which is more than 8.5 billion searches a day; on twitter approximately 500 million tweets are sent per day; and as of 2021, the number of messages shared on WhatsApp daily stands at approximately 100 billion.</p><p>With so much information available at our fingertips, data has emerged as the lynchpin of decision-making and comprehension of the world that surrounds us, one major distinction between businesses that have succeeded and those that have failed can be seen in how they have chosen to use the data at their disposal to their advantage. How they have found underlying trends, connected some dots, uncovered patterns, evaluated risks in form of probabilities before finally reaching meaningful conclusions.</p><h3>Statistics the Vocal cord</h3><p>Yes, numbers have a story to tell too, and it is statistics who gives the voice. Statistics is defined as the science of <em>collecting</em>, <em>organizing</em>, <em>presenting</em>, <em>analyzing</em> and <em>interpreting</em> data. Statistical analysis proves to be the part that gives meaning to the meaningless numbers. It refers to the process of applying statistical techniques to data to extract useful insights that can be used to make informed decisions.</p><p>The beauty of statistical analysis lies in its ability to help quantify uncertainty and variability enabling us to base our choices on more accurate predictions, it helps establish the foundation for assessing the validity and importance of our findings, enables us to grasp the likelihood of certain events and assists us in navigating the world of probabilities.</p><h3>A Journey through the steps</h3><p>Consider a moment when you were going to embark on a journey or visit an area you had never been to or knew nothing about. Starting a statistical analysis project is likened to embarking on that journey of discovery. On our journey to making sense of the data, and in our effort to uncover the underlying truth within the numbers, we might face problems, hit a stumbling block, or even miss our way. As a result, we must arm ourselves with a roadmap- a clear understanding of the procedures involved in carrying out statistical analysis. Here I will be taking you on a short guided tour outlining the fundamental steps that lead to an effective and insightful analysis. So buckle up as we guide you through the process of <em>making sense out of no sense</em>.</p><h4>Step1: Write out your research objective and state your hypotheses.</h4><p>Every journey should begin with a destination and goal in mind, and in statistical analysis, the definition of the research objective is a critical first step. This step sets the direction for everything that follows ensuring our analysis is in tandem with the goals of the research. Typically, the goal of any research will be to investigate patterns, explore relationships between variables, and make valid forecasts. Statistical hypotheses refer to the assumptions or predictions made about a population. In statistics we have two of them: the null hypotheses (H0) and the alternative hypotheses (Ha)</p><p>The <em>null hypotheses </em>as the name might have implied assumes there are no relationships, difference or effect between the variables, while the <em>alternative hypotheses </em>represent a direct opposite confirming there is a significant relationship, difference or effect between the variables being studied.</p><blockquote><strong>Null hypotheses:</strong> There is no difference between the prices of houses with a parking lot and the houses without.</blockquote><blockquote><strong>Alternative hypotheses</strong>: There is a significant difference between the prices is houses with a parking lot and houses without</blockquote><p>After all these have been established, then the stage is set to go.</p><h4>Step 2: Data Collection and Preparation</h4><p>Data in our study is analogous to what gasoline and diesel are to a car’s engine. With our research objective penned down, we set sail to collect the data needed to fuel our analysis. Here we identify variables of interest, we determine the type of data required to answer our questions, the method of collection, or the source from which to extract the data needed. We also need to ensure the data is relevant and representative of the phenomenon we aim to study, because in most cases it can be difficult or expensive to collect data from every member of the population, hence the need to employ sampling as a technique is emphasized.</p><p>After gathering the data, we begin the process of data cleansing and preparation. <strong>You can refer to my previous </strong><a href="https://medium.com/@Crownthirst/data-cleaning-and-why-it-is-important-fe758cc32b5b"><strong>article</strong></a><strong> for guidance.</strong></p><h4>Step 3: Explore your data</h4><p>All of our efforts up to this point have been directed toward preparing our vehicle, fueling our engine, and having a firm grasp on where we are headed. Here is the stage where we start our engine and head out to our journey of discovery, we delve deeply into the data, trying to solve its puzzles and reveal insightful information. Descriptive statistics can help us with informative summaries of our data, examine its distributions making it easy to identify outliers and variations. A normal distribution indicates that your data is symmetrically distributed around the center where the majority of the values are concentrated, with values decreasing off towards the tail ends. A skewed distribution, on the other hand, is asymmetric and contains more values on one end than the other, it can be positively skewed (left) or negatively skewed(right) as depicted below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/981/1*mMKepk9H8FcUkn9MKqQKWA.png" /><figcaption>Picture from Acrobatiq on Pinterest</figcaption></figure><p>This stage not only establishes the framework for our research to come, but it also acts as a compass, pointing us in the correct direction and indicating prospective directions for further exploration.</p><h4>Step 4: Applying Statistical Analysis Techniques</h4><p>With a sense of direction provided by our understanding of the data, we can choose the appropriate statistical analysis technique based off our research objective, the data collected and the nature of the variables to be analyzed. The aforementioned factors will determine the technique you choose, whether it be regression analysis, hypothesis testing, cluster analysis, or time series analysis.</p><blockquote>It is beyond the purview of this article to go into the specifics of each technique; instead, it just aims to provide a glimpse into the vast field of statistics.</blockquote><p>Whichever technique we select, advances us towards a better understanding of the relationships, patterns and trends that exists within our data, allowing us to move towards our goal of meaningful analysis.</p><h4>Step 5: Interpretation of Results</h4><p>We are at the end of our journey and arrived at our destination. This is where we park our car. In this last phase, we examine the statistical results, interpreting them in light of our research topic before coming to logical conclusions. In hypothesis testing, the primary standard for drawing inferences is <em>“Statistical significance”</em>. To determine if your results are statistically significant or not, you must compare your p value to a predetermined significance threshold (often 0.05).</p><p>Statistically significant results are thought to be unlikely to have happened by chance alone and are depicted by a p value less than or equal to 0.05 and vice versa. To avoid errors, it is crucial to correctly interprete the results.</p><blockquote>Type I error occurs when we reject the null hypothesis when it’s actually true</blockquote><blockquote>Type II error occurs when we fail to reject the null hypothesis when it’s false</blockquote><p>After assessing the statistical significance, effect sizes, and application of our findings, we could turn all that complicated statistical lingo into useful information for decision making.</p><p>In conclusion, I believe we have shown that embarking on a statistical analysis journey requires not just technical expertise but also a strategic roadmap. But if we follow the steps outlined in this article, we can avoid challenges, make big discoveries, and unleash the revolutionary power of data.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c59b91be7c50" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[From Numbers to Narrative]]></title>
            <link>https://medium.com/@Crownthirst/from-numbers-to-narrative-67da667bb28f?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/67da667bb28f</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[storytelling]]></category>
            <category><![CDATA[visualization]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Sat, 22 Apr 2023 17:39:25 GMT</pubDate>
            <atom:updated>2023-04-23T11:19:12.140Z</atom:updated>
            <content:encoded><![CDATA[<h4>Data Visualization: The art of storytelling</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/750/1*oIsGo4hRSPQEuEB38c6Y6Q.jpeg" /><figcaption>Mapping America: Every City, Every Block. A New York Times Project.</figcaption></figure><p>Allow me tell a short story about <em>“how to tell a compelling story”</em> In 2012, the New York Times released <em>“Mapping America: Every City, Every Block”</em> an interactive data visualization that uses information from the U.S. Census Bureau to produce a thorough map of race and ethnicity across the country. The project was a part of a broader series called “<em>The Census: Who We Are, How We Live</em>” which used a range of data visualizations and articles to investigate the outcomes of the 2010 U.S. Census. The collaboration between the New York Times and the Census Bureau on this series, aimed to provide readers a thorough and understandable look at how the country’s demographics are evolving.</p><p>Thanks to this data visualization, users were able to examine racial and ethnic diversity in various communities across the country, with each dot on the map denoting an individual and each color denoting a distinct race or ethnic group. Users have the option to compare several cities and communities side by side and also zoom in to the numbers at the neighborhood level.</p><p>But you know that’s not even the crux of the matter, what really made the visualization really powerful was the accompanying article, <em>“The Changing Face of America”</em> where <a href="https://en.wikipedia.org/wiki/Sabrina_Tavernise">Sabrina Tavernise</a> used personal experiences and historical context to help readers grasp the relevance of the data. It was quite interesting seeing how she employed storytelling as a tool to help to achieve this feat. For instance, the article emphasized how Queens, a borough in New York, has changed demographically and become more diverse over the years. It described how Jackson Heights’ neighborhood, which was formerly predominately white, is now a thriving center of South Asian and Latinx culture.</p><p>The article included statistics on the shifting demographics of Queens and other American cities in addition to using facts to support its narrative. The New York Times was able to convey intricate findings about race and ethnicity in America in a captivating and relatable way by fusing personal stories with data visualization.</p><h3>Beyond Bar charts</h3><p>Data visualization is the process of transforming data into visual representations such as maps, charts and graphs. In today’s data-driven world it has developed into an important tool for assisting individuals, stakeholders and even business owners in understanding complex data and making valid judgments. However, it is more than simply creating attractive visuals; it involves transforming data into stories that elicit strong emotions. It goes beyond simply making data accessible; rather, it extends to making it more relatable. It goes beyond simply sewing bar charts and line graphs together on a PowerBI/Tableau canvas; but rather creating a narrative and a compelling tale to enhance understanding.</p><blockquote>“In school we learn a lot about language and math. On the language side we learn how to put words together into sentences and stories. With math, we learn to make sense of numbers. But it’s rare that these two sides are paired. No one tells us how to tell stories with numbers … this leaves us poorly prepared for an important task that is increasingly in demand.” — <a href="https://www.linkedin.com/in/colenussbaumer/">Cole Nussbaumer Knaflic</a></blockquote><p>Without a doubt, all indications point to the fact that the strength of data visualization dwells in its capacity to transform numbers into compelling, informative, and inspirational stories. A good data viz is meant to help investigate complex data, spot patterns, and produce captivating narratives to demystify or understand a problem/situation.</p><p>It is also crucial to keep in mind that in addition to the data and the story, there are other elements that should be taken into account while creating a visualization. David McCandless in his method lists four elements of good data visualization as follows:</p><ol><li><strong>Information</strong>: the data you are working with</li><li><strong>Story</strong>: a clear and compelling narrative or concept</li><li><strong>Goal</strong>: a specific objective or function for the visual</li><li><strong>Visual form</strong>: an effective use of metaphor or visual expression</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YvUcmewTokf8IkrLAROgqA.png" /><figcaption>The McCandless Method of effective visualization</figcaption></figure><p>While we have scratched the first two, it is important to explain the third element. <strong>The Goal</strong>.</p><h3>Start with the end in mind</h3><p>The team of journalists, designers, and developers at The New York Times knew from the onset exactly what it is they were looking to achieve. The project <em>“The Census: Who We Are, How We Live”</em> in this instance sought to give readers an in-depth and clear view of how the nation’s demographics have been changing, it also sought to help users examine racial and ethnic diversity in various American localities. By concentrating on the end result, the team was able to create a visual that was not only informative, but engaging and to put the cherry on top they supported the visual with an interesting article that drove home the point.</p><h3>Colors, Sizes, Shapes- as emphatic tools</h3><p>Colors, shapes and sizes are sometimes considered to be just aesthetic choices, but in the realm of data visualization and storytelling, they play a critical role in determining how we comprehend and perceive data. A fascinating story may be told with data by strategically using these marks to express feelings, emphasize important findings, direct audience attention, and create memorable visuals.</p><p>Color may also be used to highlight differences between data points and generate contrasts. In a case of performance, it may be easy for viewers to spot regions that need improvement if a chart employs red and green to indicate good and negative performance for regions. Similar to that, employing a brighter color to highlight a particular data point or outlier may make it stand out and catch the eye. We can think back to the project introduced earlier, where each dot on the map represented a person, and each color stood for a certain race or ethnicity, green was assigned to the white population, blue to the black population, yellow to the Hispanic population, etc. It becomes fairly obvious that the use of color is the best way to show the distinctions in this ethnic mix.</p><p>Beyond contrasts and hierarchy, colors may be used to express attitudes and feelings. Red might signify danger or urgency, while blue frequently connotes trust and dependability. The viewer’s experience may be made more memorable and impactful by using color to set the tone or atmosphere for the data visualization.</p><p>Much like colors, shapes may be an effective tool for emphasizing and communicating key information. The differences between multiple categories or subcategories can be highlighted with shapes. For example, while displaying the gender category, one may decide to represent it with shapes that the users are already familiar with. So doing, the visualization could help in delivering important information, while also making the data intuitive and engaging for the user.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*EUa23O9Z2UKQQBnM33hPqA.jpeg" /></figure><p>Lastly, size describes how large, tiny, long, or tall a mark is. I like to think about it in terms of the weight the data point bears. For example, in a scatter plot, bigger data points represented by larger sizes may be used to indicate higher values, while smaller data points represented by smaller sizes may be used to represent lower values.</p><p>Additionally, the use of sizes may be employed to convey a feeling of scale or proportionality in data visualization and storytelling. For instance, while creating a map visual, analysts can use markers of various sizes to depict various population densities or economic development levels. This can facilitate the development of a visual perception of the relative size or significance of various regions or locations.</p><h3>Embrace the art</h3><p>Speaking of art, <em>Pablo Picasso</em> is renowned for his daring use of color, form, and texture, and his exploration of themes such as love, war, and identity. His innovative approach to painting, sculpture, and printing completely transformed the field of art by rejecting conventional methods and providing fresh ways of expressing oneself.</p><p>Similarly, <em>William Shakespeare</em> was a master of language and a genius storyteller whose writings continue to capture readers’ attention centuries after they have been written. His ability to develop complex characters, explore universal topics, and employ poetic language has made him a towering presence in literature.</p><p>Now “you” are “<em>William Picasso</em>” the hybrid, because as an analyst you have to continue borrowing from the storytelling prowess of <em>“William Shakespeare”,</em> take that, add it to the artistic prowess of <em>“Pablo Picasso” </em>make it your own<em> </em>then use it to tell the <em>“tale of numbers”</em>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=67da667bb28f" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Cleaning and why it is important?]]></title>
            <link>https://medium.com/@Crownthirst/data-cleaning-and-why-it-is-important-fe758cc32b5b?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/fe758cc32b5b</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-preparation]]></category>
            <category><![CDATA[data-cleaning]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Tue, 18 Apr 2023 19:02:00 GMT</pubDate>
            <atom:updated>2023-04-20T22:16:25.035Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/474/1*Ol0-8-bbrZEBmrHtTw9e7Q.jpeg" /><figcaption>Dirty data is inevitable, so know when you have to clean it, how to clean it and how to make it stay clean. ~ J.D. Power</figcaption></figure><p>Have you ever killed a chicken and had to defeather and butcher it? The most crucial question is: did you remember to remove the gall bladder? Yes, of course! Similar to how a gallbladder may destroy the flavor of meat and make the meat unfit for consumption, dirty data will similarly render all of your analysis pointless and lead you to make the wrong conclusions.</p><p>Data cleaning also known as data scrubbing, is the process of locating and fixing mistakes, discrepancies, and inaccuracies in datasets. It could be as little as restructuring wrongly formatted data, removing duplicates or finding solutions to incomplete datasets. It is a crucial step for guaranteeing accurate and trustworthy analysis and is a necessary stage in the data preparation process.</p><p>According to several sources, analysts spend between 45 and 80 percent of their time cleaning and getting the data ready for analysis. The percentage of time experts spend on this stage highlights the significance of this stage even more. In the real-world data rarely comes clean, infact some will argue clean data is a myth. According to Dean Abbott, Co-founder and Chief Data Scientist, Smarter HQ, <em>“No data is clean, but most is useful”.</em> The usefulness of data is in its cleanliness combined with the analyst&#39;s ability to torture the data to yield valuable insights.</p><h3>Now you might ask, How is data cleaned?</h3><p>Data cleaning may be done in a variety of ways; there is no one size fit all technique. The method to use depends heavily on the type of data that has to be cleaned. But you can follow these basic steps.</p><p><strong>Step 1 — Inspect your data and identify the parts that needs cleaning.</strong></p><p>To establish the quality of the data and to draw attention to any issues, take time to examine the data. Here you look out for missing values, outliers, duplicates, inconsistencies and structural issues. This stage lays the foundation for everything you’ll do after that and how you approach it.</p><p><strong>Step 2— Determine how to handle the issues detected.</strong></p><p>After identifying the issues with the data, the next stage is to decide how to deal with or fix the problems with the data. Should you remove duplicates? or get rid of outliers? What format will help the analysis of your data? e.t.c</p><p><strong>Step 3 — Drop duplicates or remove irrelevant observations.</strong></p><p>You must exclude irrelevant observations from your dataset that do not suit the context of what you are attempting to do, much as you cannot enjoy your excellent fried chicken if it still has its feathers, gut, and gall bladder. For instance, it is advisable to eliminate an observation from an undergraduate if you are attempting to analyze data that relates to university graduates. This is because the observation does not pertain to the particular issue you are trying to investigate. Additionally, it’s crucial to look for duplicates because they might skew results and exaggerate figures, leading to incorrect conclusions.</p><p><strong>Step 3— Fix structural issues.</strong></p><p>Common during data entry, you could encounter some structural issues in your dataset, these issues could range from typographical errors, poor naming conventions, inconsistencies or multiple representations, for example “California” and “CA” in the state column or “Female” and “F” in the gender column of your dataset, primarily these variables should fall within the same category and should be analyzed together. It’s also a good idea to watch out for underscores, dashes, and other unwanted characters that might cause problems with analysis.</p><p>Consider the format of your data as well; certain data are better analyzed in long format, while others are best analyzed in wide format. You should think about the structure that will benefit your analysis the most.</p><p><strong>Step 4— Keep or remove outliers</strong></p><p>Data points in a dataset that deviate significantly from the rest are known as outliers. As mentioned earlier inaccuracies in data collection, measurement mistakes, or actual abnormalities in the data can all lead to outliers. You can remove an outlier if you have a strong reason to or if it is obvious the outlier exists owing to any of the mistakes mentioned before.</p><p>But sometimes, outliers can prove to be interesting and unique observations which should be kept for analysis. The presence of an outlier does not necessarily mean it is incorrect, as a result, it is crucial to carefully evaluate how to manage outliers while analyzing data, because it depends on the circumstances.</p><p><strong>Step 5— Handling missing values</strong></p><p>If you ask a random analyst how they handle missing values, most often than not their first suggestion will be to fill in the missing values with the mean of the dataset. This is just one of the common ways of imputation. Imputation involves estimating missing values based on the values of other variables in the dataset. There are several methods of imputation like</p><ul><li>Mean imputation (most common as earlier mentioned)</li><li>Regression imputation: here, to impute values when a variable’s value is absent, a regression model is first constructed to predict observed values of the variable based on other variables.</li><li>KNN or K nearest neighbor: This is used for datasets in machine learning. To estimate the missing values for a row with missing data. It is predicated on the idea that values in related rows would be similar.</li></ul><p>Lastly, if you do not find all the methods mentioned above useful, you may deal with missing values by removing the rows or columns that have null values, or by removing the entire column if more than half of the rows have null values.</p><p><strong>Step 6— Verify your data</strong></p><p>In the same way that you have examined the dataset for problems, you must confirm that all of the steps you took, corrections you made, and standardizations you’ve established have all been performed. Only then can you say your <em>tasty fried chicken</em> is ready to be served.</p><h3>Why is data cleaning even important at all?</h3><p>According to this <a href="https://hbr.org/2016/09/bad-data-costs-the-u-s-3-trillion-per-year">article</a> from Havard Business Review written by IBM in 2016, Bad data costs the US $3trillion per year. Similarly in 2017 in an <a href="https://www.businessinsider.com/uber-paying-nyc-drivers-tens-of-millions-accounting-error-2017-5?international=true&amp;r=US&amp;IR=T">article</a> written by business insider, Uber admitted their drivers were underpaid as a result of an accounting system error that overestimated the commission cut. A change to Uber’s terms of service in 2014 was the cause of the mistake. They failed to deduct taxes and fees before taking a 25% commission, Uber had to pay back “tens of millions” of dollars to its drivers as a result of the accounting error, it did cost Uber $900 for each driver. It was discovered that Uber’s accounting department lacked a method for evaluating the accuracy of the data it used in calculating it’s commission.</p><p>The <em>“high cost” </em>of <em>“low quality”</em> data cannot be over emphasized, with the increase in the tons of data generated today and the invasion of artificial intelligence, business leaders are beginning to understand the impact of bad data and how it affects their bottom lines. As businesses are rapidly adopting data-driven systems, processes, and strategies, the importance of maintaining data quality has never been greater.</p><p>The problem of bad data is pervasive, dirty data is everywhere, and infact squeaky-clean data is nothing but a myth, so whenever you are handed data, or you collect your own data for analysis always remember to remove the <em>gall bladder.</em></p><p>or better still, <em>give me a call.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fe758cc32b5b" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Perfection is nothing but a myth]]></title>
            <link>https://medium.com/@Crownthirst/perfection-is-nothing-but-a-myth-5f8cf246be5d?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/5f8cf246be5d</guid>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[consistency]]></category>
            <category><![CDATA[perfectionism]]></category>
            <category><![CDATA[perfection]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Mon, 25 Jul 2022 11:13:44 GMT</pubDate>
            <atom:updated>2024-06-09T22:45:59.042Z</atom:updated>
            <content:encoded><![CDATA[<p>I was going to delete this draft</p><p>Beautiful Imperfection — she said, so I’m posting this. First things first I’m not here to write you a professional looking blog post, and I’m probably going to have about 10–15 people proof-read this before I send it out, because I can’t even state for a fact that I can beat a 10year old in a spelling bee as it stands, Asuu you do this one. Or maybe I’d just send it out anyway, <em>“He who is perfect let him cast the first stone”. </em>You are not going to have me debugging English language like we do with codes.</p><p>Speaking of codes, naturally I leaned towards perfectionism before delving into that field, truly it has been one hell of a ride and I love it. But this programming thing is <em>“Trial-error-learn-unlearn-relearn-practice” </em>rinse and repeat. You can boldly tell it is a game of practice and NOT intelligence like people presume. I do appreciate the fact that it teaches you problem solving, logical thinking and above all builds your analytical skills, but no doubt you’d need a lot of patience and consistency if you want to thrive.</p><p><em>Consistency- to practice and master the concepts</em></p><p><em>Patience- not to smash your laptop in frustration</em></p><p>You’d definitely need patience as one of your virtues, it is the main reason I’m here ranting anyway, George Mount in his book <em>Advancing into analytics</em> said “Machines are dumb” and they need you to point them to everything they should do without leaving a single coma or even full stop out of it, YES!! one misplaced coma, quotation mark or semi colon could ruin 200 lines of code, leaving you looking like a clown, now you look at the code it seems perfect, you are annoyed, your anger is brewing, slight headache sprinkled with frustration, you want to smash your laptop?? you remember the current dollar to naira rate pegged at N650/$1, you then calmly sit to <a href="http://google.com/">google</a> and <a href="http://stackoverflow.com/">stackoverflow</a>. You figure out it’s one semi colon on the 90th line, how dumb can you be not to realize this semi colon was a mistake, arghh!!</p><p>I’d really like to have my code stainless, perfect and bug free, but it seems you just can’t, even the best programmers they say run into bugs and that’s it my perfectionism out the window the past few months.</p><p>And honestly there may be moments of frustration and impostor syndrome; it happens to all of us, it feels overwhelming, and you feel lost in it, I mean there are tons and tons of resources out there and how do you digest all of it?</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/899/1*nb40snbCp71Y0zwQ5jaZnw.png" /><figcaption>Programming ya weyrey gan oooo, mi o ni paro</figcaption></figure><p>The last line is what you should find solace in. <strong>Slow and steady</strong>, maybe I’d add a third <strong>filter.</strong></p><p><em>Slow- because the concepts take time to sink in</em></p><p><em>Steady- learning is best done actively; without putting what you’ve read into immediate practice, you’re likely to forget it.</em></p><p><em>filter- ignore all the noise, pick a roadmap and stick to it.</em></p><p>If you are looking to start your tech journey, this post was actually not intended to motivate you, <em>we no dey motivate for here</em>. There is no point as motivation I believe is intrinsic than extrinsic. We all have different motivating factors which drives our thoughts and activities, so you can go in your closet search your heart then decide if you really want to do this.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*hCkQiqFyXjdciHmqqbmIjQ.jpeg" /></figure><p>But I kid you not I have had few exchanges with brothers in line, above and beneath, words have it that there are two leading motivating factors driving people to <em>antiblue light glasses</em> and <em>print(“Hello World!”)</em> with SAPA topping the list stacking up 3/4 of the votes already. No lies “E choke”.</p><p>The more reason I’m actively searching for a <em>“tech sis”</em> that can sponsor my baby boy lifestyle, at least in the meantime. I swear I will pay back.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/816/1*gKKl80fqnKfMgb5uWHO3lA.png" /><figcaption>Interswitch on Linkedin</figcaption></figure><p>I heard Interswitch is where life is happening at the moment, can I add preferably from interswitch please. I need me some of those spouse allowance because we are going to the altar <em>babygirl, I mean we have to.</em></p><p>All in all, it feels good to pen something down again, the last time I wrote anything on here was in 2020 during my learning experience with <a href="https://www.passionvector.com/">passion vector</a>, Did I stop learning? No, I just hated the idea of having to proof-read a write up 5–10 times before sending it out. I read one of my posts on my learning experience from the pandemic year few weeks ago and I was surprised at how far I have come, documenting your progress and coming back to it when you are finally where you want to be adds some kind of richness and originality to your success stories, <em>or what do you think?</em></p><p>So I picked up my laptop today <em>1:34am, 23rd July 2022</em> to pour out a little from the moonless midnight of my thoughts. I’d be waiting for the perfect time to write again since 2020 and it never came, we really should stop waiting or trying to attain perfection maybe we will never reach it. God willing, I will be using this <em>medium (no pun intended)</em> to share tips, rant and discuss issues that matter to me. But remember FOCUS!!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*LRUmcEJ0T91-lpNMceYqRw.jpeg" /></figure><p>Stay disciplined and consistent, <em>worry less about perfection for it is nothing but a myth, you’d never be perfect</em>, so keep grinding, show up, put yourself out there, own your shit. I can keep going but then.</p><p><em>Sleepy eyes. fades out.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5f8cf246be5d" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[PASSION VECTOR FELLOWSHIP: WEEK 6 — EVERY END IS A NEW BEGINNING]]></title>
            <link>https://medium.com/@Crownthirst/passion-vector-fellowship-week-6-every-end-is-a-new-beginning-a77d3ec69e38?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/a77d3ec69e38</guid>
            <category><![CDATA[education]]></category>
            <category><![CDATA[passion]]></category>
            <category><![CDATA[mentorship]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[career-advice]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Wed, 05 Aug 2020 01:01:50 GMT</pubDate>
            <atom:updated>2020-08-05T01:01:50.637Z</atom:updated>
            <content:encoded><![CDATA[<h4>PASSION VECTOR FELLOWSHIP: WEEK 6 — EVERY END IS A NEW BEGINNING</h4><p>This week happened to mark the end of many things, firstly i made sure i watched and completed the concluding part of my Linear regression analysis videos. Where we discussed Multiple regression, as regards modelling numerical response variables using multiple predictors, model diagnostic (testing your model), model selection and many more.</p><p>Secondly it was our final career session in this thrilling journey, where the <a href="http://passionvector.com/">Passion vector team</a> hosted Erioluwa Adeyinka an educator and a social change leader, who shared with us a very interesting story of a psychologist named Walter Mischel and his “Marshmallow experiment” which he used to explain the theory of “Delayed gratification,” Erioluwa also shared with us tips needed to excel in our various fields, urged us to be problem solvers and most importantly do away with fear, in his words “<strong>DO IT AFRAID.</strong>”</p><p>Lastly this week will mark the end of what has been an amazing journey with <a href="http://passionvector.com/">Passion Vector</a>, the team, and co-beneficiaries of this program, like the saying goes ”Everything that has a beginning must surely have an end,” but i want to believe learning never stops, in fact the day you stop learning is the day you stop living.</p><p>I would like to say a big thank you to everyone who contributed towards my personal development, i must confess i would miss all what we had, but this is the point where we drop our pens and pass the mantle unto the next cohort. The time for us to take on the next challenge, time for us to seek a new beginning. <strong>SEE YOU AT THE TOP</strong>.</p><p><em>Thank you, and God bless.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a77d3ec69e38" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[PASSION VECTOR FELLOWSHIP: WEEK 5 — THE BEGINNING OF THE END]]></title>
            <link>https://medium.com/@Crownthirst/passion-vector-fellowship-week-5-the-beginning-of-the-end-74a125a86b72?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/74a125a86b72</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[education]]></category>
            <category><![CDATA[passion]]></category>
            <category><![CDATA[personal-development]]></category>
            <category><![CDATA[career-advice]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Tue, 04 Aug 2020 10:34:10 GMT</pubDate>
            <atom:updated>2020-08-04T10:34:10.462Z</atom:updated>
            <content:encoded><![CDATA[<h4>PASSION VECTOR FELLOWSHIP: WEEK 5 — THE BEGINNING OF THE END</h4><p>This week marks my penultimate week with the <a href="http://passsionvector.com/">Passion Vector team</a>, and i must confess it has been nothing short of an amazing experience. After the completion of my python course on <a href="http://cognitiveclass.ai/">cognitiveclass</a>, which ran me through the basics of python, i decided to pick up a Linear regression analysis course to better my understanding about relationships between variables and how they are used to build predictive model.</p><p>I watched a 3 hour video in bits on <a href="http://khanacademy.com/">khan academy</a> on <a href="http://youtube.com/">youtube</a> where i took and understood the</p><ul><li>Introductory aspect of Linear regression</li><li>Outliers(observations in a data set) and types of outliers</li><li>Inference in Linear regression</li><li>Variability Partitioning</li></ul><p>Fortunately for me close to the end of the week my financial aid for the course “Programming for Everybody(Getting started with python)” was approved on <a href="http://coursera.org/">coursera</a>, but i set it aside so i could focus on regression analysis and take it all one step at a time.</p><p>We also had our weekly career talk with Adeshola a Machine Learning Engineer at Terragon group, it was non arguably the best session, as i enjoyed every bit of it, Adeshola took us through his journey of finding himself and self actualization, i personally had four takeaways from his chat.</p><ul><li>Overcome fear of the unknown and don’t be afraid to start, start from somewhere</li><li>Work on projects and make mistakes, it’s part of the learning process, mistakes birth experience and experience they say is the best teacher.</li><li>Know what you want and always follow the path to achieving it, stay focused.</li><li>The fourth might be funny but it was worth mentioning, “Money” make a lot of it.</li></ul><p>The chat added fuel to my burning passion and desire, thanks to Mr Adeshola. Next week i would be hoping to conclude the remaining aspects of Linear regression, while i meditate on what i have learnt over the week and how productive it has been.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=74a125a86b72" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[PASSION VECTOR FELLOWSHIP: WEEK 4 — LIFE COMES AT]]></title>
            <link>https://medium.com/@Crownthirst/passion-vector-fellowship-week-4-life-comes-at-bca06135e5cd?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/bca06135e5cd</guid>
            <category><![CDATA[career-advice]]></category>
            <category><![CDATA[life]]></category>
            <category><![CDATA[motivation]]></category>
            <category><![CDATA[education]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Mon, 03 Aug 2020 20:29:52 GMT</pubDate>
            <atom:updated>2020-08-03T20:29:52.103Z</atom:updated>
            <content:encoded><![CDATA[<h4>PASSION VECTOR FELLOWSHIP: WEEK 4 — LIFE COMES AT US IN WAVES</h4><p>This week has not really been the best week for me, due to the loss of my grandmother, which kind of disrupted my plans as i had to travel down to my hometown for burial rites and to pay my last respect.</p><p>But then a popular saying goes thus “<strong>When life gives you lemons</strong>, <strong>make lemonade</strong>” i tried to make positive what is left of my week by organizing a virtual class for few of my colleagues, running them through the introductory aspect of Microsoft Excel, helped them tackle few of their questions and the difficulties they had been encountering. For me it was an avenue to reaffirm my knowledge of the application and test how good i was, afterall in learning you will teach, and in teaching you also learn.</p><p>Another notable highlight for the week was the career and mentorship talk with Wande, organized by the <a href="http://passionvector.com/">Passion Vector team</a>, where she took us through the inspiring journey of how she switched careers from being a legal practitioner to being a business strategist. She also advised us to acquire soft skills like emotional intelligence, effective communication, develop the ability to work with teams e.t.c. She went further to emphasize the importance of learning a skill outside your field, as one could never tell where their opportunity lies.</p><p>Even though i couldn’t completely meet up with my objectives, i could say it was one hell of a eventful week, and there were absolutely no regrets.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=bca06135e5cd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[PASSION VECTOR FELLOWSHIP: WEEK 3- LEARNING NEVER EXHAUSTS THE MIND]]></title>
            <link>https://medium.com/@Crownthirst/passion-vector-fellowship-week-3-learning-never-exhausts-the-mind-12577076d8fd?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/12577076d8fd</guid>
            <category><![CDATA[career-development]]></category>
            <category><![CDATA[experience]]></category>
            <category><![CDATA[learning]]></category>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Mon, 03 Aug 2020 15:39:15 GMT</pubDate>
            <atom:updated>2020-08-03T15:39:15.712Z</atom:updated>
            <content:encoded><![CDATA[<p>This week marks the third week i started my learning journey with <a href="http://passionvector.com/">Passion Vector</a>, and so far it has been an amazing journey, I started my week on <a href="http://coursera.org/">coursera</a> where i applied for financial aid on the course “Programming for Everybody (Getting started with python),” i had to look elsewhere to achieve my learning objective for the week due to the “15days” time frame coursera takes to generate a response or approve the financial aid.</p><p>I watched few <a href="http://youtube.com/">youtube</a> videos to familiarize myself with jupyter notebooks and everything it entails, and i really satisfied my curiosity and gained full knowledge about the web based application.</p><p>i finally completed my beginners python course on <a href="http://cognitiveclass.ai/">cognitive class</a> and earned a certificate of completion for it.</p><p>The most interesting part of the week, was the career talk organized by the Passion Vector team, where the team invited Tega, a private equity analyst to share with us his knowledge and experience in his career so far.</p><p>I had two major takeaways from the session:</p><ul><li>Extra curricular activities are just as important as every other school activity, in as much as excellent grades are important don’t forget to build your network and associate with people.</li><li>Try as much as possible to prepare for the world of work ahead by building and acquiring the required skillset to thrive in any field you have chosen.</li></ul><p>Moving forward i’m hoping to draw more knowledge from people who have been there and ahead of us, because the only source of knowledge is experience.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=12577076d8fd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[PASSION VECTOR FELLOWSHIP: WEEK 2- THE JOURNEY CONTINUES]]></title>
            <link>https://medium.com/adewunmi-oluwaseun-asegun/passion-vector-fellowship-week-2-the-journey-continues-2a287b6125c7?source=rss-81d654006080------2</link>
            <guid isPermaLink="false">https://medium.com/p/2a287b6125c7</guid>
            <dc:creator><![CDATA[Adewunmi Oluwaseun Asegun]]></dc:creator>
            <pubDate>Mon, 20 Jul 2020 18:34:34 GMT</pubDate>
            <atom:updated>2020-07-20T18:34:34.140Z</atom:updated>
            <content:encoded><![CDATA[<p>Last week i started my journey into python programming and the journey so far has been exciting. This week has been quite different to be honest as i couldn’t wrap my head around some things, and it all looked ambiguous at some point, I had some assignments on hand sent to me by <a href="https://medium.com/u/85948b14972f">Wale Alashe</a> i could guess they were based on functions, equality tests and loops, but i just didn’t know how to get on with it.</p><p>I reverted to <a href="http://youtube.com/">youtube</a> where i took watched a 2hr video to further better my understanding with functions, loops and the general data structures in python, while i tried familiarizing myself with the anaconda platform, I also attended a 3hr virtual learning session on “DATA ANALYTICS WITH POWERBI” on saturday and “HR ANALYTICS WITH POWERBI” on sunday courtesy of <a href="http://dataleum.com/">dataleum</a> where i learnt the importance of analytics in my field, how data can be turned into information, information turned into insights and the insights used to answer and make strategic HR decisions. i also spent time working on a case study of a firm, where i built interactive dashboards attempted at solving the firm’s challenges and proferring solutions</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/549/1*P5pynTxW3d8HRDmjBOL2Hg.png" /></figure><p>This week, i would be looking to get more help and resources on the tasks i have at hand on python programming, and a clear understanding on how to go about it, all thanks to <a href="https://medium.com/u/85948b14972f">Wale Alashe</a> and <a href="http://passionvector.com/">Passion Vector</a>, so i can move on and take on the next challenge.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=2a287b6125c7" width="1" height="1" alt=""><hr><p><a href="https://medium.com/adewunmi-oluwaseun-asegun/passion-vector-fellowship-week-2-the-journey-continues-2a287b6125c7">PASSION VECTOR FELLOWSHIP: WEEK 2- THE JOURNEY CONTINUES</a> was originally published in <a href="https://medium.com/adewunmi-oluwaseun-asegun">Adewunmi Oluwaseun Asegun</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>