<?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 Karthiga Prabhakaran on Medium]]></title>
        <description><![CDATA[Stories by Karthiga Prabhakaran on Medium]]></description>
        <link>https://medium.com/@karthigaprabhakaran?source=rss-2a7b0e4b6aa8------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Stories by Karthiga Prabhakaran on Medium</title>
            <link>https://medium.com/@karthigaprabhakaran?source=rss-2a7b0e4b6aa8------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 17:24:55 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@karthigaprabhakaran/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[From Raw Transactions to Insights: My E-commerce Analysis Using SQL]]></title>
            <link>https://karthigaprabhakaran.medium.com/from-raw-transactions-to-insights-my-e-commerce-analysis-using-sql-df832f0fb407?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/df832f0fb407</guid>
            <category><![CDATA[sql]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[business-intelligence]]></category>
            <category><![CDATA[database]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Wed, 25 Mar 2026 03:13:30 GMT</pubDate>
            <atom:updated>2026-03-25T03:13:30.609Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*uf8A0YPV-Of4kr29" /><figcaption>Photo by <a href="https://unsplash.com/@austindistel?utm_source=medium&amp;utm_medium=referral">Austin Distel</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>After working on Power BI dashboards, I wanted to strengthen my core data skills especially SQL, which is a must-have for any data analyst role. Instead of just practicing queries, I decided to work on a dataset that reflects real-world business scenarios. I chose an <a href="https://www.kaggle.com/datasets/carrie1/ecommerce-data?resource=download">e-commerce</a> transactional dataset containing thousands of records, including product details, customer information, and purchase history. At first glance, it looked like a simple dataset. But as I started exploring, I realized it had all the characteristics of real-world data — missing values, returns, and inconsistencies. That’s when the real analysis began. In any e-commerce business, understanding sales performance and customer behavior is critical.</p><p>However, raw transactional data alone doesn’t provide clear answers. Key questions such as:</p><ul><li>Who are the most valuable customers?</li><li>Which products drive the most sales?</li><li>How does revenue change over time?</li><li>Which regions contribute the most revenue? require proper data cleaning and structured analysis.</li></ul><h3><strong><em>Data Preparation in SQL</em></strong></h3><p>Before jumping into analysis, I focused on cleaning the data — an essential step that often gets overlooked. Using SQL, I</p><p><strong><em>Removed records with missing customer IDs</em></strong></p><p>DELETE FROM online_retail<br>WHERE CustomerID IS NULL;</p><p><strong><em>Filtered out negative quantities</em></strong></p><p>DELETE FROM online_retail<br>WHERE Quantity &lt;= 0;</p><p><strong><em>Eliminated invalid or zero-priced transactions</em></strong></p><p>DELETE FROM online_retail<br>WHERE UnitPrice &lt;= 0;</p><p>These steps ensured that the analysis was based only on meaningful and reliable data. This process also gave me a deeper appreciation for how messy real-world data can be.Once the data was cleaned, I started analysing it using SQL queries. Some of the key techniques I used:</p><ul><li>Aggregations (SUM, COUNT) to calculate revenue and sales</li><li>GROUP BY to analyze performance across products and countries</li><li>ORDER BY to identify top performers</li><li>Window functions (RANK) to rank customers based on revenue</li></ul><p>Instead of running random queries, I focused on answering business-driven questions.</p><h3><strong><em>Exploratory Analysis</em></strong></h3><p><strong><em>— Total number of records</em></strong><br> SELECT COUNT(*) FROM online_retail;<br> <br><strong><em> — Unique customers</em></strong><br> SELECT COUNT(DISTINCT CustomerID) AS total_customers<br> FROM online_retail;<br> <br><strong><em> — Unique products</em></strong><br> SELECT COUNT(DISTINCT Description) AS total_products<br> FROM online_retail;</p><h3><strong><em>Business Question Queries</em></strong></h3><p><strong><em>— Total Revenue</em></strong><br> SELECT ROUND(SUM(Quantity * UnitPrice), 2) AS total_revenue<br> FROM online_retail;<br> <br><strong><em> — Revenue by Country</em></strong><br> SELECT Country,<br> ROUND(SUM(Quantity * UnitPrice), 2) AS revenue<br> FROM online_retail<br> GROUP BY Country<br> ORDER BY revenue DESC;<br> <br><strong><em> — Top 10 Products</em></strong><br> SELECT Description,<br> SUM(Quantity) AS total_sold<br> FROM online_retail<br> GROUP BY Description<br> ORDER BY total_sold DESC<br> LIMIT 10;<br> <br><strong><em> — Top Customers</em></strong><br> SELECT CustomerID,<br> ROUND(SUM(Quantity * UnitPrice), 2) AS revenue<br> FROM online_retail<br> GROUP BY CustomerID<br> ORDER BY revenue DESC<br> LIMIT 10;<br> <br><strong><em> — Monthly Revenue Trend</em></strong><br> SELECT strftime(‘%Y-%m’, InvoiceDate) AS month,<br> ROUND(SUM(Quantity * UnitPrice), 2) AS revenue<br> FROM online_retail<br> GROUP BY month<br> ORDER BY month;<br> <br><strong><em> — Customer Ranking</em></strong><br> SELECT CustomerID,<br> ROUND(SUM(Quantity * UnitPrice), 2) AS revenue,<br> RANK() OVER (ORDER BY SUM(Quantity * UnitPrice) DESC) AS rank<br> FROM online_retail<br> GROUP BY CustomerID;</p><p>Here are some of the insights I discovered during the analysis:</p><p>· A significant portion of total revenue comes from a small group of customers. This highlights the importance of retaining high-value customers.</p><p>· A few products consistently dominate sales, indicating clear best-sellers that drive revenue.</p><p>· Certain countries contribute more to overall revenue, showing strong regional demand differences.</p><p>· Monthly revenue trends show fluctuations, suggesting potential seasonality in purchasing behavior.</p><p>This analysis shows how SQL can be used not just to retrieve data, but to uncover meaningful business insights. For an e-commerce business, these findings can help:</p><ul><li>Focus on high-value customers</li><li>Promote top-performing products</li><li>Understand regional demand</li><li>Plan for seasonal trends</li></ul><p>This project reinforced an important lesson. SQL is not just about writing queries, it’s about thinking analytically. Cleaning the data, asking the right questions, and interpreting the results made a big difference in the outcome. It also helped me realize that even a simple transactional dataset can reveal powerful insights when explored properly. If you’re learning SQL, don’t stop at basic queries. Try working on a real dataset, ask meaningful questions, and explore it deeply. You’ll not only improve your SQL skills, but also your ability to think like a data analyst.</p><p><em>Thanks for reading!</em> 😊</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=df832f0fb407" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[From Operational Data to Insights: Building an Art Program Dashboard in Power BI]]></title>
            <link>https://karthigaprabhakaran.medium.com/from-operational-data-to-insights-building-an-art-program-dashboard-in-power-bi-6981b7981333?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/6981b7981333</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[business-intelligence]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[dashboard-design]]></category>
            <category><![CDATA[power-bi]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Tue, 24 Mar 2026 08:26:50 GMT</pubDate>
            <atom:updated>2026-03-24T08:26:50.692Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ntq_Dl75kHHcIdyG4m2nLA.jpeg" /></figure><p>Sometimes, the most meaningful data projects don’t come from large public datasets, they come from scenarios that closely reflect real-world work environments. In this project, I worked with a dataset that simulates a real-time operational setup, containing class registration details such as schedules, participation, and fees. At first glance, it looked like routine transactional data. But I saw an opportunity to turn it into something more valuable — insights that could support better planning and decision-making. So, I built a Power BI dashboard to explore participation patterns, class popularity, and revenue trends</p><p>The art program offers a variety of classes across different terms, days, and times. However, there was no clear visibility into:</p><ul><li>Which classes are most popular</li><li>When students prefer to attend</li><li>How participation and revenue change over time</li><li>The difference between members and non-members</li></ul><p>Without this, it becomes difficult to plan schedules, allocate resources, or make informed decisions about future programs. I started by preparing the dataset. The data included:</p><ul><li>Year and term</li><li>Class type and class name</li><li>Day and time of the class</li><li>Fees</li><li>Membership status (member / non-member)</li></ul><p>I then used Power BI to clean and transform the data. This included:</p><ul><li>Standardizing column names and data types</li><li>Handling missing values</li><li>Creating a combined Term-Year field to analyze trends over time</li></ul><p>The goal was to design a dashboard that tells a clear story, starting from a high-level overview and gradually moving into detailed insights.</p><p>The dashboard includes:</p><ul><li><strong>KPI cards</strong> showing total students, total revenue, and average fee</li><li><strong>Trend charts</strong> to track participation and revenue over time</li><li><strong>Class popularity analysis</strong> to identify the most in-demand classes</li><li><strong>Attendance patterns</strong> by time of day</li><li><strong>Membership distribution</strong> to understand customer segments</li></ul><p><strong>Key Insights</strong></p><p>As I explored the data, a few interesting patterns stood out.</p><p><strong>a)</strong> <strong>Participation Trends</strong></p><p>Student participation remained fairly stable over time, with some noticeable peaks and dips across terms. This suggests that demand is consistent but may be influenced by seasonal factors.</p><p><strong>b)</strong> <strong>When Do Students Prefer Classes?</strong></p><p>Evening classes clearly have the highest participation compared to morning and afternoon sessions. This makes sense, as many people are likely attending after work or school.</p><p><strong>c) Which Classes Are Most Popular?</strong></p><p>ceramic emerged as the most popular class, followed by watercolor clay modelling. These classes consistently attracted more students, indicating strong interest.</p><p><strong>d) Revenue Patterns</strong></p><p>Revenue trends closely follow participation, with higher student numbers directly contributing to increased revenue. This highlights the importance of maintaining high-demand classes.</p><p><strong>e)</strong> <strong>Membership Insights</strong></p><p>A significant portion of participants are non-members, suggesting an opportunity to encourage memberships and improve retention.</p><p>This analysis shows that small operational datasets can provide powerful insights when explored properly. For the art program, these insights can help:</p><ul><li>Schedule more evening classes to meet demand</li><li>Focus on high-performing classes like ceramics</li><li>Plan resources better across terms</li><li>Explore strategies to convert non-members into members</li></ul><p>This project was a great reminder that data analysis is not just about tools — it’s about asking the right questions. Using Power BI, I was able to transform simple data into meaningful insights that can support better decisions. If you’re working with any kind of data — even something small — try exploring it. You might be surprised by the insights hidden within it.</p><p><em>Thanks for reading!</em> 😊</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6981b7981333" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Global Brain Tumor Data Analysis Using Excel: Exploring Demographic Patterns and Survival Trends]]></title>
            <link>https://karthigaprabhakaran.medium.com/global-brain-tumor-data-analysis-using-excel-exploring-demographic-patterns-and-survival-trends-631afa8fb0bd?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/631afa8fb0bd</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[excel]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-visualization]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Wed, 11 Mar 2026 07:11:40 GMT</pubDate>
            <atom:updated>2026-03-11T07:16:33.746Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ncBuMk2eKlhGhREufb-wDg.png" /></figure><p><em>In this project, I worked with a large clinical dataset to explore patterns in brain tumor cases and identify factors that may influence survival outcomes. The goal of this project was to understand how tumor cases vary across demographics and treatments, and whether certain lifestyle or medical factors influence tumor occurrence. Healthcare datasets often contain complex information across demographics, medical conditions, and treatment outcomes. By applying structured data analysis techniques, we can transform raw data into insights that support medical research and public health planning.</em></p><p><em>In this project, I analyzed a global brain tumor dataset containing 250,000 patient records using Microsoft Excel to explore patterns in tumor occurrence, survival rates, and risk factors.</em></p><h4><em>Understanding the Business Problem</em></h4><p><em>Brain tumors represent a serious global health challenge. Understanding patterns in tumor cases can help healthcare researchers and policy planners identify risk factors and improve treatment strategies. The analysis was designed around four key questions:</em></p><ol><li><em>How do brain tumor cases vary across countries, genders, and age groups?</em></li><li><em>How do treatment choices influence survival rates?</em></li><li><em>Are malignant tumor cases disproportionately higher in certain countries?</em></li><li><em>Which lifestyle, medical, or genetic factors are associated with tumor presence?</em></li></ol><p><em>These questions guided the analytical approach throughout the project. As a first step, download the </em><a href="https://www.kaggle.com/datasets/ankushpanday1/brain-tumor-prediction-dataset?select=Brain_Tumor_Prediction_Dataset.csv"><em>dataset </em></a><em>from Kaggle.</em></p><h4><strong>Dataset Overview</strong></h4><p><em>The dataset included 250,000 patient records from multiple countries and contained both demographic and clinical attributes. Some of the key variables included:</em></p><ul><li><em>Country</em></li><li><em>Age</em></li><li><em>Gender</em></li><li><em>Tumour Type (Benign or Malignant)</em></li><li><em>Treatment Type</em></li><li><em>Survival Rate</em></li><li><em>Lifestyle and medical risk factors such as smoking, alcohol use, diabetes, and family history.</em></li></ul><p><em>Working with a dataset of this size required careful data preparation and exploration before meaningful analysis could begin.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/944/1*1BVSS2lu4pKkC30wN1h68w.png" /></figure><h4><strong><em>Data Cleaning and Preparation</em></strong></h4><p><em>Before starting the analysis, several preparation steps were performed to ensure the dataset was ready for exploration. The main data preparation tasks included:</em></p><ul><li><em>Converting multiple Yes/No variables into binary values (1 and 0) for statistical analysis.</em></li><li><em>Creating age group categories to make demographic comparisons easier.</em></li><li><em>Standardizing tumor types into benign and malignant categories.</em></li><li><em>Removing unnecessary columns after transformation.</em></li></ul><p><em>These steps helped make the dataset easier to analyze using Excel.</em></p><p><strong>Exploratory Data Analysis</strong></p><p><em>The first step in the analysis was to understand how tumor cases were distributed across different demographic groups. Using pivot tables and descriptive statistics, I explored patterns across age, gender, and country.</em></p><p><strong>Age Distribution — </strong><em>The dataset showed that the average age of patients was around 47 years, with tumor cases spread across a wide age range. However, most tumor cases occurred between the ages of 21 and 80, while the youngest and oldest groups had significantly fewer cases. This suggests that age is an important demographic factor influencing tumor occurrence.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/736/1*1a7fymygL1quZVsVtExZmQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/458/1*2tw97MbuDtrOBRb4eV8i4A.png" /></figure><p><strong>Country Distribution — </strong><em>Tumor counts were also fairly consistent across countries, with most countries showing similar case numbers. No region showed an unusually high number of malignant tumors.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/830/1*iyMiASBnsgg_DP7Si49U2Q.png" /></figure><p><strong>Gender Distribution — </strong><em>When comparing cases across gender, the data showed almost identical counts for male and female patients, indicating no major gender imbalance in tumor occurrence.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/821/1*4MzT-nDdohOJFCNXbEIj4Q.png" /></figure><p><em>These initial observations helped identify where deeper analysis might be needed.</em></p><p><strong>Analyzing Treatment and Survival Outcomes</strong></p><p><em>The next step was to analyze whether different treatments affected survival outcomes. The dataset included four treatment categories:</em></p><ul><li><em>Chemotherapy</em></li><li><em>Radiation</em></li><li><em>Surgery</em></li><li><em>No treatment</em></li></ul><p><em>When comparing survival rates across treatments, an interesting pattern emerged. Survival rates remained very consistent across all treatments, staying around 54–55%. Although surgery showed slightly higher survival rates, the difference was small and not statistically meaningful. Similarly, survival rates for benign and malignant tumors were almost identical, suggesting that tumor type alone does not strongly influence survival outcomes within this dataset.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mopzsj2IVeALfpAP0keY2A.png" /></figure><p><strong>Diagnostic Analysis Using Statistical Tests</strong></p><p><em>To explore these patterns more deeply, several statistical techniques were applied.</em></p><p><strong><em>ANOVA: Do Treatments Influence Survival? — </em></strong><em>ANOVA was used to test whether survival rates differed significantly across treatment types.</em></p><p><em>The result showed a </em><strong><em>p-value greater than 0.05</em></strong><em>,</em> ind<em>icating that treatment type </em><strong><em>does not significantly influence survival outcomes</em></strong><em> in this dataset. However, when analyzing </em><strong><em>age groups</em></strong><em> alongside treatments, </em><strong><em>age showed a statistically significant impact</em></strong><em>. This confirms that age plays a stronger role in survival outcomes than treatment type.</em></p><p><strong><em>Chi-Square Test: Tumor Severity Across Countries? — </em></strong><em>A chi-square test was performed to examine whether malignant tumor rates varied significantly across countries. </em><strong><em>The test produced a p-value of 0.478</em></strong><em>, which indicates </em><strong><em>no statistically significant differences between countries</em></strong><em>. In other words, malignant tumor rates appear to be evenly distributed globally within this dataset.</em></p><p><strong>Risk Factor Analysis</strong></p><p><em>Finally, lifestyle and medical risk factors were analyzed to determine whether they were associated with tumor presence. Several factors were tested, including:</em></p><ul><li><em>Smoking</em></li><li><em>Alcohol use</em></li><li><em>Family history</em></li><li><em>Diabetes</em></li><li><em>Chronic illness</em></li><li><em>Head injury</em></li><li><em>Genetic risk</em></li></ul><p><em>Among all these variables, </em><strong><em>diabetes was the only factor showing a statistically significant relationship with tumor presence</em></strong><em>. All other factors showed weak or no meaningful associations.</em></p><p><strong><em>Key Insights from the Analysis</em></strong></p><p><em>This analysis revealed several important patterns within the dataset.</em></p><ol><li><strong><em>Age is the strongest demographic factor — </em></strong><em>Most tumor cases occur between ages </em><strong><em>21 and 80</em></strong><em>, indicating age plays a key role in tumor occurrence.</em></li></ol><p><strong><em>2. Treatment type shows minimal influence on survival — </em></strong><em>Survival rates remained similar across different treatment options.</em></p><p><strong><em>3. Tumor severity is globally consistent — </em></strong><em>No country showed significantly higher malignant tumor rates.</em></p><p><strong><em>4. Diabetes appears as a significant risk factor — </em></strong><em>Among the variables analyzed, diabetes showed the strongest statistical relationship with tumor presence.</em></p><p><strong><em>Conclusion</em></strong></p><p><em>This project demonstrates how data analytics can transform complex healthcare datasets into meaningful insights. By combining </em><strong><em>exploratory data analysis, statistical testing, and visual exploration</em></strong><em>, it was possible to uncover patterns related to demographics, treatments, and risk factors.</em></p><p><em>While the dataset showed that treatment type had limited impact on survival outcomes, age and certain medical conditions emerged as more influential factors. Projects like this highlight how </em><strong><em>data analytics can support evidence-based decision making in healthcare and public policy</em></strong><em>.</em></p><p><em>For me, this project was also an important step in strengthening my skills in </em><strong><em>data preparation, exploratory analysis, and statistical reasoning using Excel</em></strong><em>.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=631afa8fb0bd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Power BI For Beginners — Series — 03]]></title>
            <link>https://karthigaprabhakaran.medium.com/power-bi-for-beginners-series-03-04b852a071cd?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/04b852a071cd</guid>
            <category><![CDATA[data-cleaning]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[power-bi-tutorials]]></category>
            <category><![CDATA[power-bi]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Tue, 18 Feb 2025 22:57:32 GMT</pubDate>
            <atom:updated>2025-02-18T22:58:30.170Z</atom:updated>
            <content:encoded><![CDATA[<h3>Power BI For Beginners — Series — 03</h3><p>“Simplifying Power BI: A Beginner’s Journey into Data Visualization”</p><p><a href="https://karthigaprabhakaran.medium.com/power-bi-for-beginners-series-02-fadf1ddfe78a">Power BI For Beginners — Series — 02</a></p><p>Recollecting the <strong>Data analytics Steps</strong></p><p>· Identify business questions</p><p>· Collect and store data</p><p>· Clean and prepare data (Power query)</p><p>· Analyse data (Data Model)</p><p>· Visualize and communicate data (Report View)</p><p>Consider the you identify the business questions and collected the data.</p><p>The data sources could be any type file like Excel, CSV, JSON or database etc. Now we step into the cleaning the data where power query helps us in various ways to streamline the data.</p><p><strong>1.</strong> <strong>Power Query Editor</strong></p><p>It is a data transformation tool which helps us to clean and prepare the data before loading in the PowerBI. Here the place where you do the ETL (Extract,Transform,Load) Process. It uses “M” language internally for transformations. For complex transformation we can write custom M code.</p><p>Features of Power Query Editor</p><p>· <strong>Query Pane (Left Side) — </strong>Lists all the tables or queries. Allows selecting different queries for transformation.</p><p>· <strong>Data Preview (Center) — </strong>Displays the dataset. Shows a preview of applied transformations but does not change the original data source.</p><p>· <strong>Applied Steps (Right Side) — </strong>Tracks each transformation step, allowing easy modification or removal. Every action (removing columns, filtering data, changing types) is recorded.</p><p>· <strong>Ribbon (Top Menu) — </strong>Provides various tools for data transformation.</p><p><strong><em>Installing Power BI:</em></strong></p><p>Use the below link to download based on your windows (32 or 64bit) and install with default settings.</p><p><a href="https://www.microsoft.com/en-us/download/details.aspx?id=58494">https://www.microsoft.com/en-us/download/details.aspx?id=58494</a></p><p>I have used a dirty dataset from Kaggle to perform step by step cleaning process in power query Editor. This Data has 8 columns with 10k records.</p><p><a href="https://www.kaggle.com/datasets/ahmedmohamed2003/cafe-sales-dirty-data-for-cleaning-training">Cafe Sales — Dirty Data for Cleaning Training</a></p><p>Open the PowerBi &gt; Get data &gt; Select Excel &gt; choose the input data &gt;</p><p>By Default, the power query editor will open and ask with 3 options</p><p>Load, transform data, cancel. &gt; Choose Transform data. Now you are in Power Query Editor.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*V5BF1erwEmtnK0oqfg4T8g.png" /></figure><p>Data Transformation:</p><ol><li>Check the <strong><em>Column Quality, distribution, profile </em></strong>in view tab. For detailed information, refer this link <a href="https://powerbidocs.com/2021/03/02/column-quality-column-distribution-column-profile/">https://powerbidocs.com/2021/03/02/column-quality-column-distribution-column-profile/</a></li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1018/1*oVnxZUPhOFRwdcYxLylZ2g.png" /></figure><p>2. Use <strong><em>First row as a headers</em></strong> Option to promote the header.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*XPGIgLkhjpA1RehOFU9bQA.png" /></figure><p>3. Check the <strong><em>datatype</em></strong> of each column. Before changing the data type handle the errors/missing values to avoid the datatype errors. To change the datatype right click on the left corner(123) and you can see the drop down like this and change the datatype.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/237/1*mXyj0kPkFBQXKX9SBAZamA.png" /></figure><p>4. Handle the <strong><em>Null/Invalid values</em></strong>. You can replace the data with N/A or any nearby value based on your analysis.</p><p>5. In Transaction date, there were some dates are error and the datatype is text. If you are not sure about the data to be fill in, you can use filter options and unselect the blank/error and use the remaining datas’s.</p><p>6. After the data cleaning process, the column quality will be in 100% on each column.</p><p>7. I have duplicated the date column and extracted the month.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*0jNt3JFlwiTzVttXi5wi9g.png" /></figure><p>I have used the necessary data cleaning steps for this project. There were more data cleaning steps which are mentioned below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/705/1*9cqvzOSVok1ax2MQsnqksQ.png" /></figure><p><em>— — — — — — — — — — — — — — — — — — — — — — — — — — to be continued</em></p><p><a href="https://karthigaprabhakaran.medium.com/power-bi-for-beginners-series-01-6ec16c5f8889">Power BI For Beginners — Series — 01</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=04b852a071cd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Power BI For Beginners — Series — 02]]></title>
            <link>https://karthigaprabhakaran.medium.com/power-bi-for-beginners-series-02-fadf1ddfe78a?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/fadf1ddfe78a</guid>
            <category><![CDATA[power-bi-step-by-step]]></category>
            <category><![CDATA[data-analytics-tools]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[power-bi-beginners]]></category>
            <category><![CDATA[power-bi-tutorials]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Tue, 04 Feb 2025 00:57:25 GMT</pubDate>
            <atom:updated>2025-02-04T01:06:10.738Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>Power BI For Beginners — Series</strong> — <strong>02</strong></h3><p>“Simplifying Power BI: A Beginner’s Journey into Data Visualization”</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*-oY7q3jXn7yg89lX" /><figcaption>Photo by <a href="https://unsplash.com/@headwayio?utm_source=medium&amp;utm_medium=referral">Headway</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p><a href="https://karthigaprabhakaran.medium.com/power-bi-for-beginners-series-01-6ec16c5f8889">Power BI For Beginners — Series — 01</a></p><p><em>There are 3 major sections</em></p><p><em>1.</em> <em>Query Editor (Power Query)</em></p><p>2. <em>Data Model</em></p><p>3. <em>Report View</em></p><p>I just used basic simple words to make you understand and remember easily. We will see every step in detail in the upcoming blogs.</p><p><strong>1.</strong> <strong>Power Query Editor</strong></p><p>· helps to connect data from multiple resources.</p><p>· Transform the data</p><p>· ETL Process</p><p>Ie. Extract the data from multiple sources (like excel, text), then clean the data and then load the data into data model for the next section.</p><p><strong>2.</strong> <strong>Data Model (Power Pivot)</strong></p><p>· Organize the data</p><p>· Create relationship between Tables</p><p>· Analyse the data</p><p>Ie. The clean data is organized and created relationship, then you can perform the analysis and create measures (DAX) and do calculations.</p><p><strong>3.</strong> <strong>Report View</strong></p><p>· Create a report with the charts/graphs</p><p>· Story telling with Insights.</p><p>Now, we will see how the data analytics Process can be achieved in the Power BI Desktop.</p><p>Recollecting the <strong>Data analytics Steps</strong></p><p>· Identify business questions</p><p>· Collect and store data</p><p>· Clean and prepare data (Power query)</p><p>· Analyse data(Data Model)</p><p>· Visualize and communicate data(Report View)</p><p><em>— — — — — — — — — — — — — — — — — — — — — — — — — — — — — to be continued</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fadf1ddfe78a" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Power BI For Beginners — Series — 01]]></title>
            <link>https://karthigaprabhakaran.medium.com/power-bi-for-beginners-series-01-6ec16c5f8889?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/6ec16c5f8889</guid>
            <category><![CDATA[data-analytics-tools]]></category>
            <category><![CDATA[power-bi-tutorials]]></category>
            <category><![CDATA[power-bi-training]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[power-bi-step-by-step]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Sun, 26 Jan 2025 05:51:09 GMT</pubDate>
            <atom:updated>2025-06-18T22:52:20.817Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>Power BI For Beginners — Series — 01</strong></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*1ZhyJ02omvuQLqfi" /><figcaption>Photo by <a href="https://unsplash.com/@markusspiske?utm_source=medium&amp;utm_medium=referral">Markus Spiske</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p><em>In analytics journey, Power BI plays a major role to find insights and creating interactive dashboards. I would like to share the knowledge in this blog as a beginner. So that it will be easy for everyone who has gone through this page.</em></p><p><em>When I start to learn Power BI, the first question that pops up in my mind is</em></p><p><em>Why Power BI over Excel??????</em></p><p><em>The best term to describe the relationship in one word is “SIBLINGS.”.</em></p><p><em>Excel is the elder one; Power BI is the younger one from the parent of MICROSOFT. In fact, as everyone knows how, the two siblings in a family of the same gender used to react. The elder one can’t tolerate the serious/more scoldings from the mother, whether the younger ones handle that in an easy way. Another best example is that the creativity and curious knowledge will be more for the younger one compared to the elder one. (In my personal experience).</em></p><p><em>With the above examples, you can easily compare why Power BI is better than Excel.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/791/1*FWEMOF2vdhtTblbfmzr50g.png" /></figure><p><em>Generally, everyone thinks Power BI is a just a colorful reporting tool. Creating a dashboard is not a big deal, just a drag and drop. Right!!!! However, the real challenge comes here.</em></p><p><em>How much messy data have you handled so far?</em></p><p><em>How many records are you used to creating a report?</em></p><p><em>What insights are you going to provide to your clients to solve their problems?</em></p><p><em>How are your reports helping the client?</em></p><p><em>Do the reports satisfy the business needs?</em></p><p><em>You can put it in any terms to understand, but the real challenge comes when you work on the real data, rather than the sample data, which is less than 1k.</em></p><p><em>I am sharing my knowledge and the understandings in this Power BI Series blog, which may help you if you are a beginner. If some experienced analyst read my blog, your reviews and comments are most welcome, which really helps me to improve my skills.</em></p><p><em>Let’s Start Simple!!!!</em></p><p>Major 3 sections to discover in Power BI.</p><p><em>1.</em> <em>Query Editor</em></p><p><em>2.</em> <em>Data Model</em></p><p><em>3.</em> <em>Report View</em></p><p><em>— — — — — — — — — — -to be continued</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6ec16c5f8889" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[My New Journey Begins!!!!!!!]]></title>
            <link>https://karthigaprabhakaran.medium.com/my-new-journey-begins-d05170925a84?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/d05170925a84</guid>
            <category><![CDATA[life]]></category>
            <category><![CDATA[new-zealand]]></category>
            <category><![CDATA[new-life]]></category>
            <category><![CDATA[immigration]]></category>
            <category><![CDATA[new-journey]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Wed, 10 Jul 2024 03:16:27 GMT</pubDate>
            <atom:updated>2024-07-10T03:16:27.461Z</atom:updated>
            <content:encoded><![CDATA[<p>Leaving Comfort Behind: Embracing Fear and Excitement</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*zJO9C6E28ZFai81v" /><figcaption>Photo by <a href="https://unsplash.com/@sophie_turner?utm_source=medium&amp;utm_medium=referral">Sophie Turner</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>Its been more than two months, i didn&#39;t write any stories in medium. You know why??</p><p>I made a big decision in my life. Yes we moved from India to new Country. Yes !!!! its New New New to New Zealand……………</p><p>I am really excited and happy, but at the same time moving from your mother country to new country is not an easy one.</p><p>Of course, there are lot more things to learn in each and everything to get to know about it. But its worth to do. If is not now!!!! then When to!!!!!!</p><blockquote>Life is full of Surprise!!!</blockquote><p>Sometimes you like the surprise, few times you may not.. But that will give you a great experience….</p><p>Wish me for my Happy Beginnings !!!!!!</p><p>Thank you if you read it till now…………………….</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d05170925a84" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Rethinking Success: Moving Beyond Materialism for True Happiness]]></title>
            <link>https://karthigaprabhakaran.medium.com/rethinking-success-moving-beyond-materialism-for-true-happiness-8cdc777af7a7?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/8cdc777af7a7</guid>
            <category><![CDATA[successful]]></category>
            <category><![CDATA[happiness-in-life]]></category>
            <category><![CDATA[balanced-life]]></category>
            <category><![CDATA[planning]]></category>
            <category><![CDATA[life-lessons]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Sat, 23 Mar 2024 14:29:36 GMT</pubDate>
            <atom:updated>2025-04-12T20:48:58.777Z</atom:updated>
            <content:encoded><![CDATA[<p>Exploring the Illusion of Material Success and Finding Fulfillment in Life’s Balance</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*7u-irsnoqNMuylr6" /><figcaption>Photo by <a href="https://unsplash.com/@photoholgic?utm_source=medium&amp;utm_medium=referral">Photoholgic</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p><em>Over the past decade, there has been a fervent pursuit among people to achieve success and happiness in both their professional and personal lives. However, one must question whether these endeavors are truly yielding the desired outcomes. From my perspective, the answer is a resounding no.</em></p><p><em>What constitutes success and happiness varies from person to person. Is it owning a lavish home, driving a fancy car, or possessing an abundance of material possessions that define success? While these things may contribute to a sense of accomplishment, they do not necessarily equate to genuine happiness. It’s crucial to strike a balance.</em></p><p><em>When one fixates solely on acquiring material possessions beyond their threshold of need, it can gradually erode their happiness. Instead of relishing in their work, cherishing time with loved ones, and enjoying personal pursuits, individuals find themselves trapped in a cycle of debt and responsibility, which weighs heavily on their minds, sapping away their daily joy..</em></p><p><em>Constantly being burdened by financial obligations creates a persistent pressure that overshadows any fleeting moments of happiness. It’s essential to adopt a more strategic approach to life planning. By making thoughtful decisions and prioritizing fulfillment over mere acquisition, one can lead a more gratifying existence.</em></p><p><em>Therefore, it is imperative to plan wisely, derive satisfaction from what you do, and find contentment in your daily achievements rather than relentlessly pursuing material luxuries.</em></p><p><strong><em>Happiness lies not in the accumulation of possessions, but in the fulfillment derived from living a purposeful and balanced life.</em></strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=8cdc777af7a7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[“How Many Friends Do You Have?”]]></title>
            <link>https://short.sweet.pub/how-many-friends-do-you-have-7dbf84b8aa92?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/7dbf84b8aa92</guid>
            <category><![CDATA[happiness-in-life]]></category>
            <category><![CDATA[life]]></category>
            <category><![CDATA[friendship]]></category>
            <category><![CDATA[values]]></category>
            <category><![CDATA[relationships]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Thu, 29 Feb 2024 09:14:14 GMT</pubDate>
            <atom:updated>2024-02-29T21:28:08.554Z</atom:updated>
            <content:encoded><![CDATA[<p>“Navigating the Depths of Social Bonds: Assessing Your Circle of Connections”</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*JWdSeFGxcbBZ5qYM" /><figcaption>Photo by <a href="https://unsplash.com/@miinyuii?utm_source=medium&amp;utm_medium=referral">Duy Pham</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>In these 2020 ERA, Technology gives more advance knowledge and exposure to everyone.</p><p>The ability to connect with anyone, anywhere in the world is now a reality.</p><p>Can we consider these connections or followers as true friends?</p><p>I can see, people always do such crazy things to get followers in social media.</p><p>In real life, do they have a friend, to share everything???</p><p>Whoever who are, how strong your mindset will be?</p><p>At some point of time, we need someone to share our stress, hear your voice especially when you are completely down.</p><p>The Best relationship which God created are <strong>“Friends”</strong>. I don’t mean the other relationship are not fair. But friends are the one who value your feelings and thoughts.</p><p>I found 3 Gems in my life, one from schooling, next from college and the life of friend from career. These 3 peoples are my stress relievers always.</p><p>Despite the number of followers on platforms like Instagram or Facebook, it is essential to strive for at least one genuine, lasting friendship in real life. The number of followers on social media may be substantial, but the depth of connection with a true friend is incomparable.</p><p>True friendships that endure for more than two decades are a evidence to the strength of character involved. Cultivating such relationships adds an enriching dimension to life, surpassing the transient nature of online connections.</p><p>Try to get one friend for your life…………………….</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7dbf84b8aa92" width="1" height="1" alt=""><hr><p><a href="https://short.sweet.pub/how-many-friends-do-you-have-7dbf84b8aa92">“How Many Friends Do You Have?”</a> was originally published in <a href="https://short.sweet.pub/">Short. Sweet. Valuable.</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[First Day at School — As a Mother]]></title>
            <link>https://medium.com/modern-women/first-day-at-school-as-a-mother-4f9c45f9ce8b?source=rss-2a7b0e4b6aa8------2</link>
            <guid isPermaLink="false">https://medium.com/p/4f9c45f9ce8b</guid>
            <category><![CDATA[parenting]]></category>
            <category><![CDATA[women]]></category>
            <category><![CDATA[motherhood]]></category>
            <category><![CDATA[parenting-advice]]></category>
            <category><![CDATA[relationships]]></category>
            <dc:creator><![CDATA[Karthiga Prabhakaran]]></dc:creator>
            <pubDate>Thu, 23 Nov 2023 08:43:11 GMT</pubDate>
            <atom:updated>2023-11-23T08:43:11.526Z</atom:updated>
            <content:encoded><![CDATA[<h3>First Day at School — As a Mother</h3><h4>Embarking on the Educational Journey: A Mother’s Perspective on the First Day of School</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*VQnAsB1F7Q0wIfe7" /><figcaption>Photo by <a href="https://unsplash.com/@daen_2chinda?utm_source=medium&amp;utm_medium=referral">Tanaphong Toochinda</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>Every mother has to face this day and it’s not as easy as it was in our childhood. We don’t even remember what the experience was on our first day at school. But this is the milestone of every mother and if you cross this stage successfully, your mission is accomplished.</p><p>Even a decade back, parenting was quite easy and I felt personally it’s not this tough to handle kids. The reason behind this is, currently we have tons of options gadgets, lifestyle behaviour which makes the kids addicted and it sucks their brain which leads tantrums and anxiety in worst case.</p><p>By the way, I am a mother of a 5-year-old kid right now. Due to the pandemic, I was at work from home, so it really helped me to stay and connect with my kid. Time has flown away. Finally, the day came for her to go to school. More than her, I was so nervous about how she would handle it without me.</p><p>She got up happily and refreshed and wore her uniform and shoes in those cutie legs and had breakfast and took her school bag and moved out of our home and waited for the school bus.</p><p>Yes, I opted for the school bus, so we were waiting at the stop. The bus came then she got onto the bus and waved her hand to me. I was holding tears in my eyes, but she got in happily and sat on the seat.</p><p>That time she was just 3.7 years old. Thousands of thoughts are going through my mind before I reach home. Then I got a mobile notification. When I opened, I got a picture of her teacher. She sent a picture taken on the bus along with my kid and sent a note.</p><p>“Your kid will be happy and safer with us, don’t worry “.</p><p>The good thing is my kid had a nice smile in that picture. Then at mid-morning , almost a break time for her at school, I got a call from my child-friend’s mother. Yeah, we got connected at the time of admission and exchanged contacts.</p><p>I was literally tense about picking her call and she asked how up your kid is sitting nicely and enjoying schooling, where the entire class is full of crying sounds and tantrums. She sent a picture of my kid. In the background of the picture can see kids crying, some parents were inside the classrooms, but my kid is sitting nicely and posing picture the picture.</p><p>So, <strong>how this magic has happened??????</strong></p><p>Before 4 months from starting school, every day I had a conversation with my children. It’s not going to be hourly conversation. It is just a 5 to 10 mins’ conversation about schooling. I really didn’t expect that 5 mins daily effort will give this much results to her behaviour.</p><p>Our daily conversation will have one question each day.</p><p>What is schooling?</p><p>Who will be there?</p><p>What is the use of going to school?</p><p>What relationship will you have in school?</p><p>What will you learn there?</p><p>How will you go to school?</p><p>You might think 3-years old understand all this.</p><h4>Absolutely Yes!!!!!!!!!</h4><p>It’s all how creatively you narrate the story and make it interesting to feel like going to school with full of happiness. It’s all in mother’s hands.</p><p>My mantra is ….</p><p>What we put in is what we get…</p><p>Then by noon I was waiting at the stop to pick her up. She was so happy and got down from the bus and gave me a big hug and said,</p><h4><em>Mama, school was superb.</em></h4><p>After hearing those words, my mission was successfully completed. Later, I received continuous feedback from her school, how she is so perfect and about being happy in school and it’s been a couple of years and she is going to complete her kindergarten in 4 months. Till now she has never hesitated or refused to go to school. She will scold me if I would her to take leave during her day sickness also. That great bond has been created between her and school…</p><p>Happy Parenting!!!! :)</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4f9c45f9ce8b" width="1" height="1" alt=""><hr><p><a href="https://medium.com/modern-women/first-day-at-school-as-a-mother-4f9c45f9ce8b">First Day at School — As a Mother</a> was originally published in <a href="https://medium.com/modern-women">Modern Women</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>