<?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 Maryam Suleiman on Medium]]></title>
        <description><![CDATA[Stories by Maryam Suleiman on Medium]]></description>
        <link>https://medium.com/@Mamuu_03?source=rss-026126a211ed------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*OgimCcgf2c-o1NB1.jpg</url>
            <title>Stories by Maryam Suleiman on Medium</title>
            <link>https://medium.com/@Mamuu_03?source=rss-026126a211ed------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 18:59:24 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@Mamuu_03/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[Pizza Sales Analysis with Power BI]]></title>
            <link>https://medium.com/@Mamuu_03/pizza-sales-analysis-with-power-bi-4c788d9b8c10?source=rss-026126a211ed------2</link>
            <guid isPermaLink="false">https://medium.com/p/4c788d9b8c10</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[datagirls]]></category>
            <category><![CDATA[power-bi]]></category>
            <dc:creator><![CDATA[Maryam Suleiman]]></dc:creator>
            <pubDate>Fri, 09 Aug 2024 08:37:54 GMT</pubDate>
            <atom:updated>2024-08-09T09:36:53.734Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/736/1*aPU_Z8nejr8bNWak57alvg.jpeg" /><figcaption>Pizza</figcaption></figure><p>Power BI is among of the tools used in performing data analysis. And today I will be using it in performing my analysis on pizza sales🍕; using this tool I will guide you on how I started off from cleaning my dataset, modelling, analysis to creating interactive visuals.</p><p>This is a final project on my training using Power BI which was conducted by <a href="https://medium.com/u/61a3fa6ce26c">DataGirls Tanzania</a> . And thanks to <a href="https://medium.com/u/f9f792defbba">Maven Analytics</a> for providing this dataset.</p><p>The pizza sales dataset is a CSV file which provides data of a pizza place for the year 2015. It has four tables namely; order_details, orders, pizza_types and pizzas where these tables contains details like name, size, category, order_id, quantity and price.</p><p><strong>Data Cleaning 🧹</strong></p><p>Among of the crucial step in data analysis is data cleaning and this is the first step I started with after successfully loading my dataset into Power BI. The following are the processes I used in cleaning my dataset</p><ul><li><strong>Remove Errors:</strong> I removed all incorrect values from the tables to ensure that data is consistency.</li><li><strong>Remove Duplicates</strong>: I ensure that there are no repeated rows/entities in the table.</li><li><strong>Use First Row as Headers:</strong> In the table named “pizza_types” I promoted the first row as header.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*PtEy1abYMzmySJnObbYscQ.png" /><figcaption>Using First Row as Headers</figcaption></figure><p><strong>Data Modelling 🗂</strong></p><p>After ensuring my data is clean, then I performed data modelling where I established relationships between tables and created calculated columns and measures which I will later on use in creating dashboards.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/820/1*TLKfJEBMQqxFZcniSsCTWA.png" /><figcaption>One-to-Many Relationship</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/693/1*ZygmqVhy9yr_3hcBD_nUIA.png" /><figcaption>Calculated column of month, day, day_of_week, month_of_a_year and hour</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/478/1*XNmv6PxlzTTKsOG5VvDJEQ.png" /><figcaption>Calculated measures of TotalSales</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/380/1*H1SJrjPnmVA-54hUsERVPA.png" /><figcaption>Calculated measures of TotalPizzasSoldPerDay</figcaption></figure><p><strong>Data Analysis and Visualization📈</strong></p><p>From the data modelling, I calculated different measures depending on the problems I was going to solve from the pizza sales analysis. The following are some of the questions that guided me in the data modelling process:</p><ol><li>What is the total sales of pizza per year.</li><li>What are the most ordered pizza and the least ordered ones.</li><li>What are the most busy hours and days.</li><li>What is the total sales by size and category of pizzas.</li></ol><p>By formulating these questions, I was able to perform analysis of the dataset using the calculated measures and columns from data modelling by creating charts like bar, line and pie charts, which resulted to an interactive dashboard that summarizes the dataset.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1012/1*Rysq5CIpaaBUgXKobRu3UQ.png" /><figcaption>Pizza Sales Dashboard</figcaption></figure><p>From the dashboard, I was able to answer the above questions and uncovered the following insights</p><ol><li><strong>Annual Sales:</strong> The total sales for the whole year 2015 of the pizza place was $817,860. Where July had the highest sales followed by May, March and November while September and October had the least sales.</li><li><strong>Ordered Pizzas by Category and Size:</strong> The most ordered pizza is the Thai Chicken Pizza where Classic and Supreme are the most ordered category and the large sized pizza is the most preferred one.</li><li><strong>Pizza Trends:</strong> In terms of daily trend Friday is the busiest day during the week and the hourly trend 12.00 and 13.00 are the busiest hours of the day.</li></ol><p><strong>Recommendations📌</strong></p><p>To increase the figures on the annual sales of the pizza place the following are the recommendation I provide:</p><ul><li>Increasing and promoting the large and classic pizza as they are more preferred that the rest of the size and category.</li><li>Marketing the least preferred pizza like “The Brie Carre Pizza, Mediterranean Pizza and The Spinach Pesto Pizza” by providing discounts and offers, also considering renewing the recipes of these pizzas.</li><li>Increasing staffs on the most busiest hours and days to cater all customers efficiently, also considering adjustment in operational hours specifically on the slower periods by ensuring resources are allocated during peak hours.</li></ul><p><strong>Conclusion🚀</strong></p><p>Through this analysis, I have been able to uncover powerful insights on the trends of pizza sales across the year which will help to improve the performance of the pizza place and increasing the annual sales.</p><p>Lastly, I enjoyed using Power BI in performing this analysis and recommend it for data analysis as it is easy to use and great to work with. Hope you find this article impactful to you. And I would love to hear your thoughts and insight regarding my analysis, as it will help me improve in my data analysis journey.</p><p>Here is the link to my LinkedIn post <a href="https://www.linkedin.com/posts/maryam-suleiman-5b06392b4_datagirlstz-dataanalysis-powerbi-activity-7227607043132567553-3Mrw?utm_source=share&amp;utm_medium=member_android">https://www.linkedin.com/posts/maryam-suleiman-5b06392b4_datagirlstz-dataanalysis-powerbi-activity-7227607043132567553-3Mrw?utm_source=share&amp;utm_medium=member_android</a> let’s connect.</p><p>Thank you!😊</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4c788d9b8c10" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Cleaning with Power BI]]></title>
            <link>https://medium.com/@Mamuu_03/data-cleaning-with-power-bi-797d4c3ddff5?source=rss-026126a211ed------2</link>
            <guid isPermaLink="false">https://medium.com/p/797d4c3ddff5</guid>
            <category><![CDATA[power-query-editor]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-cleaning]]></category>
            <category><![CDATA[power-bi]]></category>
            <dc:creator><![CDATA[Maryam Suleiman]]></dc:creator>
            <pubDate>Mon, 22 Jul 2024 19:13:59 GMT</pubDate>
            <atom:updated>2024-07-22T19:13:59.061Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>Data Cleaning with Power BI</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/735/1*lwgpv4rPcsK4N9gSpkgzrA.jpeg" /></figure><p>Cleaning…</p><p>We all know how cleaning is important to us, well it’s very important too when it’s come to data. You can’t get good results with unclean data thus, it’s very crucial to perform data cleaning. In fact it is the first step in data analysis.</p><p>Data Cleaning is an essential step in data analysis, it involves checking the data for errors and inconsistences, and correcting or removing them.</p><p>In this article, I will guide you on how to perform data cleaning with Power bi using power query. I used “<a href="https://docs.google.com/spreadsheets/d/1Gq-acPg4sJJ-TueU7rLYeNUuR7HZ-M8Q/edit?usp=sharing&amp;ouid=117178077226169901442&amp;rtpof=true&amp;sd=true">US_Regional_Sales_Data</a>” which is an excel file to perform data cleaning. It has six columns which are: Customers Sheet, Products Sheet, Regions Sheet, Sales Orders Sheet, Sales Team Sheet and Store Locations Sheet.</p><h4>Load Data:</h4><p>First thing in performing data cleaning with PowerBI is loading the data into power bi. This can be performed by opening PowerBI, go to “home tab” then click the<strong> <em>Get data</em></strong> icon to open a drop down list and choose excel workbook from the list, then navigate to where the excel file is stored and select the dataset to import it into PowerBI.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*eXdcasQMrh_hVEIac9h1UA.png" /><figcaption>Get data</figcaption></figure><p>After selecting the dataset, choose the columns you want to load and preview them before loading into power bi.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*P69yvrL_sWY9ZKMjd6uUgA.png" /><figcaption>Preview the data</figcaption></figure><p>Load the dataset by clicking on the load button which will load the data into the table view of the PowerBI.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tb71H_6_yVCAY1gJpsK8gQ.png" /><figcaption>Data in power bi</figcaption></figure><h4>Transform Data:</h4><p>The next step after loading the data is to transform it to power query where the cleaning process is performed. There are two approaches in this step:</p><ol><li>The first approach: Opening PowerBI, go to “home tab” then click the<strong> <em>Get data</em></strong> icon to open a drop down list and choose excel workbook from the list, then navigate to where the excel file is stored and select the dataset to import it into PowerBI. A new dialog will open where you choose the columns you want to import, then click the button “Transform Data” to transform the dataset to Power Query.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*P69yvrL_sWY9ZKMjd6uUgA.png" /><figcaption>Transform data</figcaption></figure><p>2. The second approach: After loading the dataset to PowerBI go to “home tab” then select “Transform data” and transform it to Power Query.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tbEPl161VMDxxJhod4xMeQ.png" /><figcaption>Load data then transform</figcaption></figure><p>Both approaches leads to the same results, where it will open a new window of Power Query Editor.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*JVGJEjlwYC_kJxLtBGvFKA.png" /><figcaption>Power Query Editor</figcaption></figure><h4>Performing data cleaning:</h4><p>In Power Query Editor is where you can perform data cleaning. But before starting cleaning, make sure to change the column profiling to “Column profiling based on entire data set” which is found at the bottom left side of the power query editor. By changing it, then it will perform data cleaning on the entire dataset since by default power query is set to perform cleaning based on the top 1000 rows.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*750hB2UXFcJ3kGGDkAplGw.png" /><figcaption>Column profiling based on entire data set</figcaption></figure><p><strong>1. Remove Errors: </strong>The dataset had errors on the Sales Orders Sheet, to remove errors I hovered to the column(Order Date) with error and click the remove errors dialog that appeared.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*MzLEbObQyUYIGKS_Hi_O9g.png" /><figcaption>Remove Errors</figcaption></figure><p><strong>2. Remove Empty:</strong> To remove an empty cell on a selected column, hover to the column(Order Date) with empty cell and click on the remove empty dialog that appears over it.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*4zPkh9p7vFB5bZFV4w7heQ.png" /><figcaption>Remove Empty</figcaption></figure><p><strong>3. Remove Duplicates:</strong> On the left side of the columns before the first column select the table icon at the top and from the drop down list choose “Remove Duplicates” to remove duplicates from the table.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/644/1*lbPkk58vC1Ao4-DR-U6kvw.jpeg" /><figcaption>Remove Duplicates</figcaption></figure><p><strong>4. Change data type: </strong>Select the column(columns) that you want to change the datatype, here I changed the Discount Applied, Unit Price and Unit Cost columns in Sales Orders Sheet from decimal number to fixed decimal number. On “Transform” tab go to “Any Column” then select data type and change it to fixed decimal number.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*SOKYpvwq-ovD1r2OQYANLQ.jpeg" /><figcaption>Change data type(From Decimal Number)</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6M0lUrkWgHkF54KjA9nw-Q.jpeg" /><figcaption>Changed (To Fixed Decimal Number)</figcaption></figure><p><strong>5. Split column:</strong> Splitting column by delimiter, on the “City Name” column in “Store Locations Sheet”, I used the split column to split the column using open bracket “ ( ” as a delimiter. On “Transform” tab got to “Text Column” then select split column choose by delimiter from the drop down list another dialog will open and select “( ”as a delimiter then click ok to perform the changes.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*uATIJLNj8KswQmRuBT3aOw.jpeg" /><figcaption>Before Splitting(Split Aurora and Township)</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*GuqpsI1mpYFg5OsHwhqi_Q.jpeg" /><figcaption>Split by delimiter</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/830/1*4UcOIOE1p_ppIYZ8zHZ3Ew.png" /><figcaption>Split column by delimiter (</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*D5PJHJ_aV7J5LMBhlu4UWg.png" /><figcaption>After Splitting(Aurora and Township are in different column)</figcaption></figure><p><strong>6. Remove column:</strong> After splitting the column another column will be created with the values after the delimiter to delete this column, select the column then go to “home” tab on “manage columns” then select remove columns to remove the selected column.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Yc5guKYNKo7I7Vd0vvzqnw.jpeg" /><figcaption>Remove Columns</figcaption></figure><p><strong>7. Use first row as header:</strong> While loading data in power bi, some headers can be defined as data instead of headers, hence I used the “use first row as header” to transform the first row in “Regions Sheet” to header. By selecting “Transform” in home tab then select “use first row as header”</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*pAaW-1X933UHZsFt4N9_lw.jpeg" /><figcaption>Using first row as headers</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3R4R00v7d2nlzqkPnm_8ww.png" /><figcaption>First row as header</figcaption></figure><p><strong>8. Replace Values:</strong> On “Sales Orders Sheet” in the column “Sales Channel”. I replaced Dis _tributor with Distributor, On line with Online, In__Store with In-Store and Whole#_sale with Wholesale since both had the same meaning but were written differently. Select the column then go to “Transform” tab then in “Any Column” tab select “Replace Values” and another dialog will open and type the value to find and the value you want to replace with then click OK to perform the changes.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/433/1*hgsJvQwlJobSw_1m2bB5oQ.png" /><figcaption>Before replacing values</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/836/1*JTHin0ehovvpJD7dKKo5mQ.jpeg" /><figcaption>Replace Values</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/804/1*XxOY_n8cl8xJ020F4Fv13A.png" /><figcaption>Replace Dis_tributor with Distributor</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/468/1*JkYDGLtrW6F6OYa773X6Rw.png" /><figcaption>After replacing values</figcaption></figure><p><strong>9. Close and apply:</strong> After performing data cleaning, you need to apply the changes you have modified in the data set, by selecting the close and apply icon on the “home tab” this will close the Power Query Editor and loads the applied changes to PowerBI desktop.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/749/1*lQnHCjn6NW6ifkt1PXt-mQ.jpeg" /><figcaption>Close and Apply</figcaption></figure><p>Data cleaning in PowerBI is made easy, since it is easy to find missing values, errors and duplicates. It can be done in Power Query Editor on the selected table underneath the column name there is a thin line with <strong><em>green</em></strong>, <strong><em>red</em></strong> or <strong><em>grey</em></strong> that indicate the validity of data, when you hover on these lines from a selected column it will pop a dialog that will show whether the column has errors or missing values or is clean.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*T2Ps22rypkA8ypIQ4GUaJQ.png" /><figcaption>Valid indicated by green color</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*n-IRt7_BqfKE76fpw1Ua-g.png" /><figcaption>Error indicated by red color</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*PfiyU67XbFwxTSQz4v-3GQ.png" /><figcaption>Empty indicated by grey color</figcaption></figure><p>Alternative way, on the “view” tab in the “Data Preview” section check the “column quality” this will display the validity of each column in the selected table, it will indicate the percentage of valid, error and empty values in the column. Hence, these approach makes it easier to perform data cleaning.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nl4uKTVWL2FIPs0pbNNqiQ.png" /><figcaption>Column quality</figcaption></figure><p>Also, when performing data cleaning, each step of cleaning is recorded on the right hand side panel which makes it easier to undo changes and return to the default dataset whenever you wish to.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/389/1*FSvPEBBQJ_5G34xWiPkpDA.png" /><figcaption>Applied Steps</figcaption></figure><p>After cleaning my dataset, I can now perform data analysis and attain good results since my data is free from inconsistencies, errors and missing values. And through the analysis we can create dashboards and attain valuable insights from it.</p><p>Thanks for reading this article, hope you found it helpful. I would love your valuable and constructive feedback on this article. Happy Cleaning…</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=797d4c3ddff5" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[My First Excel Dashboard: Coffee Shop Sales Analysis]]></title>
            <link>https://medium.com/@Mamuu_03/my-first-excel-dashboard-coffee-shop-sales-analysis-0ba6db870b60?source=rss-026126a211ed------2</link>
            <guid isPermaLink="false">https://medium.com/p/0ba6db870b60</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-cleaning-with-excel]]></category>
            <category><![CDATA[data-visualisation]]></category>
            <dc:creator><![CDATA[Maryam Suleiman]]></dc:creator>
            <pubDate>Thu, 04 Apr 2024 22:06:26 GMT</pubDate>
            <atom:updated>2024-04-04T22:06:26.314Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>My First Excel Dashboard: Coffee Shop Sales Analysis</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NzvhJyEsoIqA8fUbuIEnWQ.jpeg" /><figcaption>A cup of coffee</figcaption></figure><p>Hello, it’s me once again. And today I would love to show you how I went by in preparing my dataset from the earliest stage of data cleaning to data visualization.</p><p>Before starting, I want to express my gratitude for the opportunity to participate in the <a href="https://t.co/Ydkywc8qwb">@datagirlsTz</a> . As a newcomer to the world of data analysis, this project represents a significant milestone in my learning journey at Datagirls Tanzania Initiative, and I am excited to apply the skills and knowledge gained throughout the training.</p><p>Now, let’s delve into the heart of our project. Sourced from <a href="https://mavenanalytics.io/data-playground?pageSize=10&amp;search=coffee%20shop%20sales">Maven Analytics</a>, this guided project provides us with a rich dataset ripe for exploration. The dataset contains one excel sheet with transaction records for Maven Roasters, a fictitious coffee shop operating out of three NYC locations namely Astoria, Lower Manhattan and Hell’s Kitchen. Dataset includes the transaction date, timestamp and location, along with product-level details.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tl0jvtElaPeQmyhVRwPmMg.png" /><figcaption>Coffee Shop Sales</figcaption></figure><p>After downloading the dataset, I performed the following steps which are:</p><ol><li>Data Cleaning</li><li>Data Analysis</li><li>Data visualization</li></ol><p><strong>Data Cleaning</strong></p><p>Before immersing ourselves into data cleaning, I conducted an initial visual inspection of the dataset, I surveyed the dataset to understand its structure, noting the number of fields and their corresponding meanings. With 149,116 records in total, this preliminary overview set the stage for a systematic approach to data analysis. Then I went into cleaning, the first thing I did was to remove duplicates. In the excel I navigated to the data tab then to the data tools a tool named “Remove Duplicates” where I found no duplicates.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Lp1JcO_zykWtJpJfF86jFg.png" /><figcaption>Remove Duplicates</figcaption></figure><p>Then I highlighted cells with errors using “Conditional Formatting” found in the home tab-&gt;Styles section. I selected “New Rules” which opened a formatting dialog and selected “format only cells that contain” and from the dropdown list, I selected “Errors” then formatted it to highlight with red color and clicked OK. And there were no errors found so far.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*EiUplqQEMJrIiycd35VKYg.png" /><figcaption>Highlight Errors</figcaption></figure><p>Afterwards, I went to check on missing values using the same approach I did on highlighting errors the only difference is on the dropdown list, where I selected “Blanks” then formatted it to highlight with yellow color and clicked OK. Also I found no missing values.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*XnzgAKpP9ags7Rl1s30rwg.png" /><figcaption>Missing Values</figcaption></figure><p>Then, I formatted the “unit_price” column. By converting it to currency($dollar) with two decimal places.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*duhyAisBR40JZ6ytKitD-Q.png" /><figcaption>Formatting “unit_price” column</figcaption></figure><p>I also added some new columns which would help me in the analysis process. The columns I added were:</p><ul><li>Revenue column; Revenue=(price*quantity)</li><li>Month and Day of the week; from “transaction_date” column</li><li>Hour; from “transaction_time” column</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/744/1*tNuTS1EnZs6bmYqPvT--ZA.png" /><figcaption>Adding new columns</figcaption></figure><p>With minimal cleaning required due to largely clean records, the dataset now stands primed for advanced analysis. We’re set to extract valuable insights and drive meaningful conclusions in the next phase of analysis.</p><p><strong>Data Analysis</strong></p><p>In this step of data analysis, I used pivot tables to generated some useful insights. Through the new columns I added, I created pivot tables from them. I had a total of five pivot tables which show the following insights:</p><ul><li><strong><em>Revenue</em></strong> by <strong><em>month</em></strong></li><li><strong><em>Number of transactions</em> </strong>by <strong><em>day of the week</em></strong></li><li><strong><em>Number of transactions</em></strong> by <strong><em>hour of the day</em></strong></li><li><strong><em>Number of transactions</em></strong> by <strong><em>product categories</em></strong></li><li><strong><em>Number of transactions</em></strong> and <strong><em>revenue</em></strong> by<strong><em> product type</em></strong></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*i_ty7SZw3Mhlrh_9bSICMg.png" /><figcaption>Pivot tables</figcaption></figure><p>From the pivot table, I crafted compelling charts and integrated slicers for enhanced dashboard navigation. Now, as we approach the final step — visualization — the stage is set for presenting our findings in a visually captivating and easily digestible format. Get ready to witness the power of data visualization come to life!</p><p><strong>Data Visualization</strong></p><p>From the analysis, I uncovered some interesting insights, where I presented my finding in a visual format which makes it easier to analyze pattern, trends and relationships.</p><p>By analysis one location at a time, using the slicer. I came up with the following patterns:</p><p>In Astoria, sales peak on Monday, Wednesday, Thursday, and Friday. From 7:00 to 10:00 in the morning being the busiest hour, while maintaining consistency from 11:00 to 19:00 during the evening.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*7wmtGCrjhBdzF9PGPelUWw.png" /><figcaption>Coffee Shop Sales Dashboard filtering Astoria</figcaption></figure><p>In Hell’s Kitchen, Tuesdays, Fridays, and Sundays are the busiest days for transactions. Sales peak from 8:00 to 10:00 in the morning, dropping significantly from 19:00 to 20:00 during the evening.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NgwlMDpV_XCvCbeARpDShw.png" /><figcaption>Coffee Shop Sales Dashboard filtering Hell’s Kitchen</figcaption></figure><p>In Lower Manhattan, Mondays see high transaction volumes, while the remaining days maintain consistency. Sales peak from 7:00 to 10:00, with a decrease in the late evening from 19:00 to 20:00.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*geZWSFJYuKX8SwevjzUQmw.png" /><figcaption>Coffee Shop Sales Dashboard filtering Lower Manhattan</figcaption></figure><p>In general, from the overall dashboard of coffee shop sales. I analyzed the following:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*hCICl545TpsdKa5JJIaozw.png" /><figcaption>Coffee Shop Sales Dashboard</figcaption></figure><p>The total revenue by month started at $80,000 in January, experienced a slight decrease in February, and then increased steadily from March to June, ranging from $100,000 to $180,000.</p><p>Transactions by day of the week in the area show high sales on Monday, Wednesday, Thursday, and Friday, with consistent sales observed on Tuesday, Saturday, and Sunday.</p><p>Transactions by hour of the day reveal a significant spike during the morning hours, while sales decrease towards the evening, with fewer products being sold.</p><p>Transactions by product category indicates that coffee, tea, and bakery items are the top-selling categories. Among the top 15 products across all locations, Barista Espresso generates the highest revenue, while Sugar-Free Syrup ranks lowest in terms of revenue.</p><p><strong>Recommendations</strong></p><p>To optimize operational efficiency and maximize revenue, it’s wise to consider adjusting operating hours, particularly during slower periods. Upon analysis, it’s evident that sales decrease significantly from 19:00 to 20:00. Therefore, commencing operations at 6:00 in the morning to 18:00 in the evening presents a promising solution. This adjustment aligns with consumer demand patterns, ensuring resources are allocated efficiently during peak hours while mitigating unnecessary costs associated with extended evening operations.</p><p>Implementing a proactive approach to inventory management and production scheduling ensuring that coffee, tea, and bakery items remain adequately stocked throughout operating hours. By closely monitoring sales trends and adjusting production levels accordingly, we can guarantee a seamless supply of these popular items to meet customer expectations.</p><p><strong>Conclusion</strong></p><p>In conclusion, the journey through our coffee shop sales analysis has been enlightening and productive. Embracing the power of visualization has undoubtedly enhanced our understanding of the data, making complex insights more accessible and actionable.</p><p>Reflecting on this analysis, it’s evident that visualization serves as a powerful tool for communication and comprehension. By transforming raw data into intuitive charts and graphs, we’ve unlocked valuable insights that may have otherwise remained obscured amidst a sea of numbers and text.</p><p>As we draw the curtain on this analysis, I invite constructive feedback and suggestions for improvement. Your insights are invaluable in refining our analytical processes and driving continuous improvement.</p><p>Until next time, let’s continue to innovate, adapt, and strive for excellence in all our endeavors. Here’s to the future and the exciting opportunities it holds for us. Cheers to making every decision count and every analysis impactful.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=0ba6db870b60" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[MASTERING THE ART OF DATA CLEANING: A BEGINNER’S GUIDE TO DATA CLEANING TOOLS]]></title>
            <link>https://medium.com/@Mamuu_03/mastering-the-art-of-data-cleaning-a-beginners-guide-to-data-cleaning-tools-b5a3fe3600ab?source=rss-026126a211ed------2</link>
            <guid isPermaLink="false">https://medium.com/p/b5a3fe3600ab</guid>
            <category><![CDATA[data-cleaning-tool]]></category>
            <dc:creator><![CDATA[Maryam Suleiman]]></dc:creator>
            <pubDate>Thu, 28 Mar 2024 22:26:38 GMT</pubDate>
            <atom:updated>2024-06-23T20:55:55.202Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>MASTERING THE ART OF DATA CLEANING: A BEGINNER’S GUIDE TO DATA CLEANING TOOLS</strong></p><p>Ever tried to find something on a messy room? It feels like a treasure hunt, things scuttered everywhere. Well, welcome to the world of data. Just like a messy room, raw data often comes with chaos like missing values, inconsistency and errors.</p><p>Then fear not! For data cleaning is here to save the day. In this beginner’s guide, we’ll embark on a journey to unravel the mysteries of data cleaning in a simple way.</p><p>By the end of this article, you’ll be equipped with the tools to turn your messy data into sparkling insights. Ready to uncover hidden treasures within your data? Then, let’s get started!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gowHy_qdhGozBPRBLxirfw.jpeg" /><figcaption>Data Cleaning Tools</figcaption></figure><p><strong>What is Data Cleaning and Data Cleaning Tools</strong></p><p>Data cleaning is an essential and crucial step in data preprocessing, ensuring the dataset is accurate, consistent and ready for analysis.</p><p>Data cleaning tools refer to software programs or libraries specifically designed to assist in the process of cleaning and preparing data for analysis.</p><p>There are several tools available for data cleaning, ranging from general-purpose programming languages to specialized software designed specifically for data cleaning tasks. Here are some commonly used tools:</p><p><strong>Tools used for Data Cleaning</strong></p><p><strong>1.Excel</strong></p><p>It is a commonly used data cleaning tool due to its widespread availability and ease of use, especially for individuals who are not proficient in programming or specialized data cleaning software.</p><p><strong>Features:</strong></p><p>Excel provides a wide range of features used in data cleaning these includes removing duplicates, find and replace, conditional formatting and sorting and filtering.</p><p><strong>Pros:</strong></p><p><strong><em>User-friendly interface</em></strong> which makes it more accessible to a wide range of users, including those with minimal technical expertise.</p><p><strong><em>Data visualization</em></strong> which can aid in identifying patterns, trends and anomalies in the data during the cleaning process.</p><p><strong><em>Basic data cleaning functions</em></strong> such as sorting, filtering and conditional formatting which can help identify and fix errors or inconsistencies in data.</p><p><strong>Cons:</strong></p><p><strong><em>Manual process</em></strong> such as identifying and correcting errors, which can be time-consuming and error-prone especially for large datasets.</p><p><strong><em>Limited data size</em></strong> in terms of the size of data that it can handle, which can be a significant drawback for users dealing with large datasets.</p><p><strong><em>Data security</em></strong> due to its inadequate encryption features for protecting sensitive business information which can lead to vulnerability to the dataset.</p><p><strong>2. Microsoft Power BI</strong></p><p>Is a cloud-based business intelligence tool that offers data cleaning and preparation features as part of its data modelling capabilities.</p><p><strong>Features:</strong></p><p>It includes functionalities for data shaping, cleansing and profiling to identify data types, missing values and data anomalies also transformation of data such as data type conversion, text parsing and date parsing, allowing users to prepare data for visualization and analysis.</p><p><strong>Pros:</strong></p><p><strong><em>Reusability</em></strong> enabling users to create reusable data cleaning templates and automate repetitive cleaning tasks saving time and effort.</p><p><strong><em>Custom visualization</em></strong> i.e. visualization made by developers for specific use, which can be used in reports and dashboards. These visualizations includes maps, charts, KPIs etc.</p><p><strong><em>Data modeling</em></strong> allow users to create relationships between tables and create calculated columns and measures which helps to structures the data while ensuring data integrity and consistency.</p><p><strong>Cons:</strong></p><p><strong><em>Learning curve</em></strong> for beginners new to the platform it may require some time and training to become familiar with data cleaning features and mastering advanced capabilities like DAX expressions.</p><p><strong><em>Version control issues</em></strong> as it becomes a challenge managing multiple versions of files containing data cleaning steps especially in collaborative environments.</p><p><strong><em>Performance issues</em></strong> users often experience slow performance, especially when handling large datasets.</p><p><strong>3. Python</strong></p><p>Is a general-purpose programming language used as a data cleaning tool due to its rich ecosystem of libraries and tools including Pandas, a powerful library for data manipulation an analysis as well as NumPy, often used along with Pandas for numerical computing tasks.</p><p><strong>Features:</strong></p><p>With its wide range of libraries python has multiple features for data cleaning such as outlier detection, missing values and handling duplicate records.</p><p><strong>Pros:</strong></p><p><strong><em>Beginner friendly </em></strong>it has a simple syntax which makes it easier for beginners to write and debug code.</p><p><strong><em>Flexibility </em></strong>due to its extensive library of modules and packages which provide pre-written code that can be easily integrated into a project.</p><p><strong><em>Scalability</em></strong> as it an handle a large amount of data and support distributed computing, which makes it a good choice for big data processing and machine learning applications.</p><p><strong>Cons:</strong></p><p><strong><em>Less secure</em></strong> in terms of security it is considered to be less secure that other programming languages this is because it is a dynamically typed language.</p><p><strong><em>Memory usage</em></strong><em> its </em>memory management can sometimes be inefficient, particularly when working with large datasets.</p><p><strong><em>Error handling</em></strong> due to its dynamic typing can sometimes lead to errors that are only discovered at runtime, rather than during compilation.</p><p><strong>Data Cleaning Tools Recommendation</strong></p><p>Having knowing the tools used in data cleaning as well as their features, pros and cons. Then, I bet you are wondering which one should I use when wanting to clean my dataset.</p><p>Well, worry not and let me walk you through each tool mentioned and when you can effectively use it based on a specific use cases and scenarios.</p><p><strong>Quick Data Exploration and Visualization</strong></p><p><strong><em>Use:</em></strong> Excel</p><p><strong><em>Reason: </em></strong>It provides a user-friendly interface for data manipulation, analysis and visualization.</p><p><strong>Interactive and Dynamic Data Dashboards</strong></p><p><strong><em>Use:</em></strong> Power BI</p><p><strong><em>Reason:</em></strong> It offers advanced data visualization capabilities and interactive features like filters and slicers, ideal for creating dynamic and visually appealing dashboards for business intelligence purposes.</p><p><strong>Large-scale Data Cleaning and Transformation</strong></p><p><strong><em>Use:</em></strong> Python</p><p><strong><em>Reason: </em></strong>Its libraries like Pandas, NumPy and SciPy provides a powerful tools for data manipulation, cleaning and analysis.</p><p>In summary, effective data cleaning is essential for ensuring the accuracy and reliability of analysis and decision-making. While there are various tools available for this task, choosing the right one depends on factors such as the size and complexity of the dataset, the specific requirement of the project and the skills level of the users.</p><p>By harnessing the power of tools like Python, Excel and Power BI, we empower to navigate the twists and turns of data cleaning with confidence and clarity. With each click, each command, we inch closer to unravelling the mysteries hidden within our datasets and uncover the insights that lie beneath which brings us closer to enlightenment. Happy cleaning!🧹</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b5a3fe3600ab" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>