<?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 Adetunji Muhammed on Medium]]></title>
        <description><![CDATA[Stories by Adetunji Muhammed on Medium]]></description>
        <link>https://medium.com/@adetunjimuhammed26?source=rss-4a68c6e8dc5a------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*9qoKXme-HKvshVkx</url>
            <title>Stories by Adetunji Muhammed on Medium</title>
            <link>https://medium.com/@adetunjimuhammed26?source=rss-4a68c6e8dc5a------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 09:21:12 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@adetunjimuhammed26/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[Cycling Through the Storm: Unraveling Weather’s Impact on London Bike Sharing (2015–2017)]]></title>
            <link>https://medium.com/@adetunjimuhammed26/cycling-through-the-storm-unraveling-weathers-impact-on-london-bike-sharing-2015-2017-df73aa78f3c0?source=rss-4a68c6e8dc5a------2</link>
            <guid isPermaLink="false">https://medium.com/p/df73aa78f3c0</guid>
            <category><![CDATA[analysis]]></category>
            <category><![CDATA[analytics]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Adetunji Muhammed]]></dc:creator>
            <pubDate>Mon, 02 Oct 2023 03:00:28 GMT</pubDate>
            <atom:updated>2023-10-02T03:24:22.797Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>Introduction</strong></h3><figure><img alt="https://www.islabikes.co.uk/products/kids-lightweight-multi-purpose-bike-beinn-24-age-7" src="https://cdn-images-1.medium.com/max/1024/1*Lzs3uC05CkaIx7WMXzA5Bg.jpeg" /></figure><p>The concept of bike sharing has revolutionized urban mobility, offering an eco-friendly and convenient mode of transportation for city dwellers. London, with its bustling streets, historic landmarks, and diverse neighborhoods, has enthusiastically embraced bike sharing as a means to reduce traffic congestion, lower emissions, and promote healthier urban living. However, the success and utility of bike-sharing systems are intricately tied to a multitude of factors, with one of the most influential being the capricious nature of weather conditions. In a city known for its meteorological unpredictability, understanding how weather impacts bike sharing in London becomes paramount. This exploration delves into the dynamic relationship between London’s ever-changing weather patterns and the utilization, accessibility, and user preferences of its bike-sharing programs. It unravels the subtle yet profound ways in which wind, rain, temperature, and seasonal variations can shape the adoption and effectiveness of bike sharing, shedding light on a vital dimension of sustainable urban mobility in the British capital.</p><p>The dataset was sourced from Kaggle, and you can access it through this provided <a href="https://www.kaggle.com/datasets/hmavrodiev/london-bike-sharing-dataset"><strong><em>link</em></strong></a>.</p><h4>Key Milestones Achieved Throughout the Entire Project</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*v6A2RcK2uYplCb01W1aNgg.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*fE1YxMhOELP5i4bp3zpu-Q.png" /><figcaption>Here are previews of the dataset in power query.</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*EwmZx4CDBGnTZ6opqcstUQ.png" /><figcaption>Data dictionary as gotten from Kaggle.</figcaption></figure><p>Upon careful examination of the dataset, it became evident that while the data was generally clean, certain transformations were necessary. Guided by the data dictionary sourced from Kaggle, I proceeded to implement these essential transformations, as outlined below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1XfGdb2xv5ilTZDauA2xwA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*rN15_yvvS5wwMHkZBxLNrQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*j7im0EHR9lM16_t4K9fdRQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*GMkUBcav7iIv1bFFvJGcCg.png" /><figcaption>Transforming some of the columns in the dataset using the conditional column in Power query.</figcaption></figure><p>The results after the data transformation can be seen below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*GooDdUj0EIbsnNLUWkzX3w.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Ev2YeOs3HGpr7ctwRHR2mw.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*LEl4GtKxyktDnySzp_4DTw.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*LhbZBKPAFXL6JjiNl5wWqA.png" /><figcaption>Images showing the columns before transformation and after transformation.</figcaption></figure><p>After completing the data transformations, I eliminated the prior columns. Subsequently, I divided the timestamp column into separate date and time columns.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*X0J1m2FUfekT_Ul7r7dfcg.png" /><figcaption>Splitting the timestamp column into date and time columns.</figcaption></figure><p>You can catch a glimpse of the transformed dataset in the image below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*W9BpE2v56YHmpefhqzaPjw.png" /><figcaption>Transformed dataset.</figcaption></figure><p>Following Data Transformations, the Information Was Imported into Power BI for an Insightful Visual Experience, Showcased in the Dashboard Below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YdJ0vJY41ok2zKDvWS8bOA.jpeg" /><figcaption>Data visualization result using Power BI.</figcaption></figure><p>You can explore and interact with the dashboard by following this provided <a href="https://app.powerbi.com/links/J-yt0hPXvf?ctid=a29037ad-c24c-47f1-b52f-ec3218d5c4e9&amp;pbi_source=linkShare"><strong><em>link</em></strong></a>.</p><h4>Insights</h4><p><strong>(1)</strong> Clear Clouds, Scattered Clouds, and Broken Clouds are the WeatherCodes responsible for the highest bike sharing numbers, with 7.15 million, 6.04 million, and 4.24 million bikes shared, respectively. Conversely, Rain with Thunderstorms and Snowfall represent the WeatherCodes with the lowest bike-sharing figures, at 0.01 million and 0.02 million bikes shared, respectively. The former three WeatherCodes are considered ideal for bike cycling because they provide good visibility, low chances of precipitation, and comfortable riding conditions. Cyclists can enjoy clear skies and mild temperatures, making it a favorable time for biking, and these make them the primary contributors to the highest bike<br>sharing statistics, while the latter two WeatherCodes are unfavorable for bike cycling and account for the lowest bike sharing numbers.</p><p><strong>(2) </strong>The seasons with the highest bike sharing numbers are Summer, Fall, and Spring, with 6.4 million, 5.1 million, and 4.9 million bikes shared, respectively. Conversely, Winter yielded the lowest bike-sharing figures, with 3.6 million bikes shared. Additionally, it is notable that Clear Clouds, Scattered Clouds, and Broken Clouds are most prevalent in London during Summer, Spring, and early Fall, whereas Rain with Thunderstorms and Snowfall occur predominantly during Winter. This weather pattern correlation can serve as a supplementary explanation for the previously mentioned trend. Spring, Summer, and Fall predominantly span from March to July, coinciding with a significant surge in bike-sharing numbers. In contrast, Winter extends from late October to February, coinciding with a sharp decline in bike-sharing activity.</p><p><strong>(3)</strong> Average humidity levels begin to rise from August to February, reaching values between 67.29% and 81.03%. These conditions are less than ideal for bike cycling due to the following reasons:</p><p>a). Comfort Level: High humidity can make the air feel muggy and uncomfortable, which may discourage some cyclists from riding. Cyclists may find it less enjoyable to bike in very humid conditions.</p><p>b). Thermal Comfort: Humidity affects how efficiently the body can cool itself through sweat evaporation. In extremely humid conditions, sweat doesn’t evaporate as effectively, making it harder for the body to cool down. This can lead to an increased perception of heat and discomfort.</p><p>c). Dehydration: In high humidity, cyclists may sweat more to try to cool down, leading to a higher risk of dehydration. It’s important for cyclists to stay well-hydrated in humid conditions to avoid heat-related issues.</p><p>d). Performance: Humid conditions can lead to decreased cycling performance. When the body struggles to dissipate heat due to high humidity, cyclists may fatigue more quickly and find it harder to maintain their usual pace and endurance.</p><p>e). Breathing Comfort: High humidity can make it feel more difficult to breathe, especially for cyclists with respiratory conditions. The moist air may feel heavier and less comfortable to inhale.</p><p>f). Maintenance: High humidity can also affect the maintenance of a bike. It may lead to increased corrosion of metal components and require more frequent maintenance to prevent rust.</p><p>This combination of factors culminates in a decrease in the number of shared bikes during this timeframe. Conversely, average humidity levels start to decrease from late February to July, ranging<br>from 74.91% to 64.38%. This marks the ideal period for bike cycling and explains the increase in the number of bikes being shared.</p><p><strong>(4)</strong> Bike sharing experiences its peak during the months of late April to August, when the average temperature ranges from 10.21°C to 19.22°C, coinciding with lower<br>humidity levels. Conversely, as temperatures drop and humidity rises during November to February, with average temperatures ranging from 9.15°C to 6.19°C, bike<br>sharing sees a decrease in activity.</p><p><strong>(5)</strong> During non-holiday periods, there is a substantial bike sharing activity, amounting to 19.6 million bikes, which accounts for a significant portion, approximately 98.2%,<br>of the total bikes shared. In contrast, the holiday season contributes a smaller share, constituting only 1.48% of the total bikes shared.</p><p><strong>(6)</strong> The majority of bike sharing takes place on non-weekend days, representing approximately 75.6% of the total bikes shared, with the remaining 24.4% being shared<br>during the weekend.</p><p>As I conclude this project, I want to express my heartfelt gratitude for taking the time to read this article. Your engagement and interest are truly appreciated.</p><h4>About the writer</h4><p>Greetings, I’m Muhammed — a dedicated data enthusiast skilled in transforming raw numbers into valuable insights. Proficient in both MS Excel and Power BI, I’m committed to utilizing the potential of data to empower informed decision-making. Join me in embarking on data-driven adventures!</p><p>You can reach me via these links. <a href="http://Adetunjimuhammed26@gmail.com/"><strong><em>Email</em></strong></a> and <a href="https://www.linkedin.com/in/muhammed-adetunji-abiodun/"><strong><em>LinkedIn</em></strong></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=df73aa78f3c0" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Sprocket Central Pty Ltd (a bike sales company) Analysis]]></title>
            <link>https://medium.com/@adetunjimuhammed26/sprocket-central-pty-ltd-a-bike-sales-company-analysis-fd868e0634fd?source=rss-4a68c6e8dc5a------2</link>
            <guid isPermaLink="false">https://medium.com/p/fd868e0634fd</guid>
            <category><![CDATA[analytics]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[internships]]></category>
            <dc:creator><![CDATA[Adetunji Muhammed]]></dc:creator>
            <pubDate>Wed, 19 Jul 2023 03:43:01 GMT</pubDate>
            <atom:updated>2023-07-20T23:46:15.955Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>Introduction</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/325/1*q9Ily-3amBLO9GhgCYB12A.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/658/1*okcStE6DUw11R_i5khhAPQ.png" /></figure><p>“Sprocket Central Pty Ltd, a medium size bikes &amp; cycling accessories organization, has approached Tony Smith (Partner) in KPMG’s Lighthouse &amp; Innovation Team. Sprocket Central Pty Ltd is keen to learn more about KPMG’s expertise in its Analytics, Information &amp; Modelling team.</p><p>Primarily, Sprocket Central Pty Ltd needs help with its customer and transaction data. The organization has a large dataset relating to its customers, but its team is unsure how to effectively analyze it to help optimize its marketing strategy.</p><p>However, to support the analysis, you speak to the Associate Director for some ideas and she advised that “<em>the importance of optimizing the quality of customer datasets cannot be underestimated. The better the quality of the dataset, the better chance you will be able to use it to drive company growth</em>.”</p><p>The client provided KPMG with 3 datasets:</p><ul><li>Customer Demographic</li><li>Customer Addresses</li><li>Transactions data in the past 3 months.”</li></ul><p>There are three tasks to be done during the virtual internship, they are:</p><ul><li>Data Quality Assessment</li><li>Model Development</li><li>Data Visualization</li></ul><p><strong>Task 1 (Data Quality Assessment)</strong></p><p>The initial step of the exercise is to compose an email to the client. The email should focus on identifying any concerns regarding the quality of the provided datasets and suggesting potential solutions to rectify those issues. Please find below a draft email to the client, highlighting the data quality issues present in the datasets provided and suggesting ways to address these issues:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ajIEVMOn7L4hJSYm8fUFjQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*oYJRDbpu_TqnQKrs6llQQw.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-5FJ4bPQrJQhtHeHrnMwHw.png" /><figcaption>Email Draft</figcaption></figure><p><strong>Task 2 (Model Development)</strong></p><p>The second task entails the development of a PowerPoint presentation that comprehensively outlines the strategic approach that will be adopted. The client has agreed to a 3-week project scope, which will be divided into three phases: Data Exploration, Model Development, and Interpretation. Prepare a detailed approach for completing the analysis including activities — i.e. understanding the data distributions, feature engineering, data transformations, modeling, results interpretation, and reporting. This detailed plan needs to be presented to the client to get a sign-off. Please advise what steps you would take.</p><ul><li>The primary goal of this analysis is to leverage the available labeled dataset, comprising customer demographic, customer address, and transaction data, in order to provide a recommendation on which of the 1000 new customers should be targeted in order to maximize organizational value.</li></ul><p>I will be presenting my slides which include the processes of data exploration, model development, and interpretation. I have used the PowerPoint template provided in the exercise for this purpose.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/895/1*VqwXJg_KQ5zJfpiewDUcGg.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/868/1*qhCy89lwbeSlGJjFwV4dgA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/865/1*ZOC2WUJQnFhqMUTsaYyQfQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/874/1*I913WCtks4x-Wl7jep86Dg.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/876/1*RVz2bIS4IcCr0zS_PtLHWA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/860/1*B-srtNUhQCDUEGZNI___PQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/849/1*U85FtXWtTLM50LmL9RcsFg.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/856/1*b0OwnjOTeZwIsKVGRpg0uA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/859/1*sMSlk15ZGavSpOWENthNlg.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/855/1*-IGW2_Jj6jyCjxGWTJtdJQ.png" /></figure><p><strong>Task 3 (Data Visualization)</strong></p><p>The third task involves creating a captivating dashboard that utilizes data visualization tools to showcase valuable insights to the client. Please refer to the dashboard presented below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*8gNR7OV6c9IMT2nBbPNe9g.jpeg" /></figure><p><strong>Insights and Recommendations</strong></p><ol><li>WeareA2B is the brand with the highest profit, indicating its popularity and potential for increased sales. Stakeholders can focus on marketing strategies to maintain and enhance the brand’s position.</li></ol><p>2. The “Medium” category has the highest number of online orders and accounts for the majority of both profit and online orders. Stakeholders can allocate more marketing resources to target customers in the “Medium” category to further boost sales.</p><p>3. The “Mass Customer” segment has the highest number of orders, making them an important customer base to target. Stakeholders can develop targeted marketing campaigns to attract and retain these customers.</p><p>4. Female customers account for a significant portion of the total orders. Stakeholders can tailor marketing efforts to specifically target and engage female customers, recognizing their importance in driving sales.</p><p>5. The “70–80” age group shows a high level of engagement in terms of bike-related purchases and profit. Stakeholders can create marketing campaigns and product offerings that cater to the needs and preferences of this age group to capitalize on their spending potential.</p><p>6. October has the highest count of online orders, indicating a potential opportunity for stakeholders to focus marketing efforts during this month to drive sales.</p><p>7. Understanding the car ownership patterns across different states can help stakeholders tailor their marketing strategies and product offerings to meet the specific needs and preferences of customers in each region.</p><p>You can interact with the dashboard using this<strong> </strong><a href="https://app.powerbi.com/links/8qyNwt04ne?ctid=a29037ad-c24c-47f1-b52f-ec3218d5c4e9&amp;pbi_source=linkShare"><strong>link</strong></a></p><p>As we reach the conclusion of this virtual internship process, I want to express my sincere gratitude for your presence and engagement. Thank you for staying with me and taking the time to read through this journey.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fd868e0634fd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[FIFA21 Data Cleaning Challenge]]></title>
            <link>https://medium.com/@adetunjimuhammed26/fifa21-data-cleaning-challenge-99a925146aab?source=rss-4a68c6e8dc5a------2</link>
            <guid isPermaLink="false">https://medium.com/p/99a925146aab</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[excel]]></category>
            <category><![CDATA[data-cleaning]]></category>
            <dc:creator><![CDATA[Adetunji Muhammed]]></dc:creator>
            <pubDate>Mon, 20 Mar 2023 01:19:33 GMT</pubDate>
            <atom:updated>2023-03-20T01:19:33.175Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>FIFA21 Data Cleaning Challenge.</strong></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nRxotuNJXT_864CmzT01ww.jpeg" /><figcaption>Source: <a href="https://th.bing.com/th/id/OIP.nRxotuNJXT_864CmzT01wwHaEK?pid=ImgDet&amp;rs=1">https://th.bing.com/th/id/OIP.nRxotuNJXT_864CmzT01wwHaEK?pid=ImgDet&amp;rs=1</a></figcaption></figure><h4><strong>Background</strong></h4><p>The #DataCleaningChallenge was organized by <a href="https://medium.com/u/abe7d3b593f">Promise Chinonso</a> to challenge Data Analysts (Beginners, Intermediates, and Advanced Data Analysts) to test their cleaning skills.</p><p>Data cleaning is an essential step in data analysis that ensures the integrity of the data can’t be questioned. Additionally, to eliminate data inconsistencies, errors, and dirtiness.</p><h4><strong>Goals of the data cleaning</strong></h4><p>I outlined some goals to be met after the data cleaning was completed before starting the data cleaning.</p><ol><li>Ensure the special characters from the name column are removed.</li><li>Ensure that the columns are in their correct data types.</li></ol><h4>Information on the Dataset</h4><p>The FIFA21 dataset used for the data cleaning challenge was obtained from Kaggle and can be found <a href="https://www.kaggle.com/datasets/yagunnersya/fifa-21-messy-raw-dataset-for-cleaning-exploring">here</a>. Data on football players and their performance in 2021 are included in the dataset. There are 18979 columns and 77 rows in the dataset.</p><h4>Cleaning Steps</h4><p>The tool I used for the data cleaning was Microsoft Excel. The dataset was imported into Excel Power Query for cleaning and transformation.</p><p>There are many problems associated with the dataset, or to put it nicely, the dataset is very dirty! From the players&#39; names having special characters to the wages etc.</p><p>To ensure that the special characters in the ‘Name’ and ‘Long Name’ columns are gone, I changed the file origin to Unicode (UTF-8) while importing the CSV file into Excel Power Query, and boom! the special characters were gone!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/864/1*2FufBAz9RbgzoMQIX_2vQw.png" /><figcaption>The special characters are gone.</figcaption></figure><p>To start with the ‘ID’ column, which is the unique number assigned to individual player, going through column, there’s no problem associated with it.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/97/1*h8Vhtt3caCFwCH485zz-eQ.png" /></figure><p>The ‘Name’, ‘LongName’, and ‘PlayerURL’ contain all the necessary information about individual player. Since I’ve already dealt with the special characters in the ‘Name’ and ‘LongName’ columns, I moved on to the next column.</p><p>The ‘Nationality’, ‘Age’, and ‘Club’ columns have no problems and they’re deemed okay.</p><p>‘OVA’ and ‘POT’ are expected to be in percentages; therefore, I divided each cell of the columns by <strong>100 </strong>changed the datatype to percentage. Below is the final result.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/132/1*TIdocPwripjqdxLPL0jfKw.png" /></figure><p>‘Positions’, ‘Preferred foot’ and ‘Best position’ columns are free from inconsistencies, so I moved on to the next column.</p><p>The ‘W/F’, ‘SM’ and ‘IR’ are rated over 5, but somehow, there are stars Infront of those numbers.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/801/1*erjh1qYpnnwf1hM8CSYzzg.png" /></figure><p>To get rid of the stars, I split the columns by delimiter, and I have the ratings and the stars on separate columns.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/783/1*nShs0d0OAT_wGvZ3Jms2jg.png" /></figure><p>‘Attacking’, ‘Crossing’, ‘Finishing’, ‘Heading_accuracy’, ‘Short_passing’, ‘Volleys’, ‘Skill’, ‘Dribbling’, ‘Curve’, ‘FK_accuracy’, ‘Long_passing’, ‘Ball_control’, ‘Movement’, ‘Acceleration’, ‘Spring_speed’, ‘Agility’, ‘Reactions’, ‘Balance’, ‘Power’, ‘Shot_power’, ‘Jumping’, ‘Stamina’, ‘Strength’, ‘Long_shot’, ‘Mentality’, ‘Aggression’, ‘Interception’, ‘Positioning’, ‘Vision’, ‘Penalties’, ‘Composure’, ‘Defending’, ‘Marking’, ‘Standing_tackle’, ‘Sliding_tackle’, ‘Goalkeeping’, ‘GK_handling’, ‘GK_diving’, ‘Gk_kicking’, ‘Gk_positioning’, ‘Gk_reflexes’, ‘Total_stats’, ‘Base_stats’, ‘Pace’, ‘Shooting’, ‘Passing’, ‘DRI’, ‘DEF’, ‘Physical’, ‘Best_position’, ‘Preferred_foot’, ‘Attacking_workrate’, and ‘Defensive_workrate’ were all carefully checked and are all free from inconsistencies.</p><p>Going back to the ‘Height’ column, from the data dictionary given, the heights are supposed to be in <strong>cm, </strong>but some are in<strong> </strong><em>feet and inches. </em>Then I filtered the column to show me those that are not in <strong>cm</strong> and split them into feet and inches column, then using the formulae in the picture below, I converted the heights in feet and inches to cm.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/448/1*x-kW6sB2iqMPnJSZl4d04w.png" /></figure><p>And below is the height column in cm.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/113/1*PczIRhu_jr5W9jzZFm8uUQ.png" /></figure><p>A number of the cells in the ‘weight’ column have inconsistencies, some with kilograms and others with pounds.<em> </em>According to the data dictionary, the weight should be in pounds.<em> </em>To achieve this, I used the <em>if conditional statement in Excel </em>to convert the weights from kilograms to pounds.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/976/1*Hwf7qKmD_HUrhk3WP0skgA.jpeg" /></figure><p>The players ‘value’, ‘wage’ and ‘release clause’ all have issues with some cells having suffix ‘M’ while some with ‘K’ and the rest without either of them. To get rid of the issues, I used the same method as that of the height column.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*eJu1jPeSDMdwmRH7YobMZw.jpeg" /><figcaption>Converting the weight column using if conditional statement</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*qycU6X3_qPaVb7ZdRaWrYw.jpeg" /><figcaption>Release clause conversion</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/528/1*T8HHmtrS_d-Fdigj1h6oFg.jpeg" /><figcaption>wage conversion</figcaption></figure><p>And below is the cleaned ‘value’, ‘wage’, and ‘release clause’ columns and changing the datatype.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/332/1*qSleATCObRcySTFO_sbklg.png" /></figure><p>‘Hits’ column also has the same problem as that of the ‘height’ column and with its datatype in text format. Using the if conditional statement to get rid of the issue and changing the datatype, below is our final ‘Hits’ column.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*c9clDpNm5papygyABrwawg.png" /><figcaption>Hits column after using the if conditional statement.</figcaption></figure><p>After all of these, I checked for duplicate entries in the dataset, and fortunately there was none. After this, I changed the datatype of each column to how they should be.</p><h4>Conclusion</h4><p>This DataCleaningChallenge was a really big test for my Excel skills because the dataset was very challenging. But all the same, the messy data was cleaned!</p><p>You can reach to me on my <a href="http://adetunjimuhammed26@gmail.com/"><strong>Gmail</strong></a><strong> </strong>and<strong> </strong><a href="https://www.linkedin.com/in/adetunji-muhammed-1872881a9/"><strong>LinkedIn</strong></a><strong> </strong>accounts. Thanks for staying all through reading the article.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=99a925146aab" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>