<?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 Aykut Azazi on Medium]]></title>
        <description><![CDATA[Stories by Aykut Azazi on Medium]]></description>
        <link>https://medium.com/@aykutazazi?source=rss-c1bbe3753da------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*uQcE0rUeekfONgaMKgQmjQ.png</url>
            <title>Stories by Aykut Azazi on Medium</title>
            <link>https://medium.com/@aykutazazi?source=rss-c1bbe3753da------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 01:01:43 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@aykutazazi/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[We Can See Future with This Sales Visualization Dashboards(with Tableau and PowerBI)]]></title>
            <link>https://aykutazazi.medium.com/we-can-see-future-with-this-sales-visualization-dashboards-with-tableau-and-powerbi-81545348b964?source=rss-c1bbe3753da------2</link>
            <guid isPermaLink="false">https://medium.com/p/81545348b964</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[python]]></category>
            <dc:creator><![CDATA[Aykut Azazi]]></dc:creator>
            <pubDate>Mon, 01 Feb 2021 12:20:05 GMT</pubDate>
            <atom:updated>2021-02-01T12:20:05.785Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/798/1*6D2GX7vL7rca6GoFvkRt3Q.png" /></figure><p>Data visualization is a general term that describes any effort to help people understand the significance of data by placing it in a visual context. Patterns, trends and correlations that might go undetected in text-based data can be exposed and recognized easier with data visualization software. It enables decision makers to see analytics presented visually, so they can grasp difficult concepts or identify new patterns.</p><h3>Why is Data Visualization Important?</h3><p>Using charts or graphs to visualize large amounts of complex data is easier than poring over spreadsheets or reports because human brain perceives, understands and grasps visuals better and faster than numbers or alphabets. Data visualization is a quick, easy way to convey concepts in a universal manner and we can experiment with different scenarios by making slight adjustments.<br>Data visualization can:<br>- Identify areas that need attention or improvement.<br>- Clarify which factors influence customer behavior.<br>- Help you understand which products to place where.<br>- Predict sales volumes.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/560/1*27s78GC15vOGvKCUzK3DKg.png" /></figure><h3>The Scenario of Project</h3><p>The objective of this project is to understand sales trends for one of the leading pharmaceutical company. Let’s imagine this client would like to come see a dynamic dashboard with different KPI’s at different levels (National, Region &amp; Territory etc). We can create the different sales charts as these would help us explore the past data in a better manner and give a good picture of the progress and failures. This in turn would catalyse the decision-making process, making it easier, simpler and accurate.</p><h3>About Data</h3><p>The data attached is a two-year sales data of a pharma company which talks about sales in 2015 and 2016 across various regions and time frames.</p><ul><li>Account Id : Customer ID</li><li>Account Name : Customer Name</li><li>Tier : Customer Segment</li><li>Sales 2015 : Sales for the year 2015</li><li>Sales 2016 : Sales for the year 2015</li><li>Units 2015 : NO of Units sold for 2015</li><li>Units 2016 : NO of Units sold for 2016</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/699/1*2jLiagCjkX9I_kf-Ih6Faw.png" /><figcaption>Random Datas From the Dataset</figcaption></figure><p>To detail my project results and visualizations more, I created a new column named ‘Qtr’ and wrote a code assigning quarters for each row based on quarters(like Q1, Q2, Q3 and Q4) of ‘Month’ values;</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/883/1*xWJh7OMtMy1AcpA8c_jDoA.png" /><figcaption>View of the Dataset After Append Qtr Column</figcaption></figure><p>And I’ve wanted to see the sales numbers by the quarter with the groupby transaction. After that I can move on to the data visualization side.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/407/1*YUdGicJUJvGDuuG3nZJY-Q.png" /></figure><h3>Data Visualization and Results</h3><p>In my opinion, different visualization programs should be used except Pyhton libraries for a more professional point of view. I’m using “PowerBI” and “Tableau”</p><p>Tableau is a data analytics and visualization tool used widely in the industry today. Many businesses even consider it indispensable for data-science-related work. Tableau’s ease of use comes from the fact that it has a drag and drop interface. This feature helps to perform tasks like sorting, comparing and analyzing, very easily and fast. Tableau is also compatible with multiple sources, including Excel, SQL Server, and cloud-based data repositories which makes it an excellent choice for Data Scientists.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mABUidQ5YlP_ecYwC9FepA.png" /><figcaption>All results in One Dashboard</figcaption></figure><p>That’s all we need to create a good visualization in Tableau although, one might find doing a lot more revising in each stage than we did here. So with experimentation and practise, tableau becomes a lot more familiar and will unleash amazing features to help us analyze and present data.</p><p>Thus, this dashboard can be detailed according to the desired results and the size of the dataset.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=81545348b964" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Save Your Costs with Price Prediction Project]]></title>
            <link>https://aykutazazi.medium.com/save-your-costs-with-price-prediction-project-d6ab4dd5c991?source=rss-c1bbe3753da------2</link>
            <guid isPermaLink="false">https://medium.com/p/d6ab4dd5c991</guid>
            <category><![CDATA[price-prediction]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[linear-regression]]></category>
            <dc:creator><![CDATA[Aykut Azazi]]></dc:creator>
            <pubDate>Mon, 18 Jan 2021 19:31:59 GMT</pubDate>
            <atom:updated>2021-01-18T19:31:59.835Z</atom:updated>
            <content:encoded><![CDATA[<p>When we buy most things in our lives, we need comparison. Because there are many brands and alternative models. Doing this manually sometimes takes a lot of effort. In these cases, what would it be like if there was a system that calculates the average price of the product whose features we give? That would make our job a lot easier, wouldn’t it? Most big marketing and other sector companies have already started to focus and use this system. We can use this system even when buying a home, car or small computer items. That’s why I wanted to make a project about that.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*JHxvZ0QTDsLBw40GljtUKQ.png" /></figure><h3>The Scenario of Project</h3><p>Let’s say I’m working for a company that produces ram, and my boss asked me for help about pricing for a new model that we will produce soon. He wants me to create a model using the price data of RAMs with similar features in our competitors. He expects this model algorithm to give correct prices.</p><p>Or I want to use a nice computer that I will buy the parts one by one. For this I wanted to know the average prices of the parts. Firstly I want to buy my RAM’s. For this i will build a model with machine learning algorithms and formulate it. Thus, i will have information about the average price of the ram I want.</p><h3>Web Scraping For Dataset</h3><p>I need to detailed dataset and a realistic price list for this project. If I researched on web for this dataset, it would be difficult and inadequate. So I found a shopping site with detailed features and prices about RAMs. I’ve chosed the required pages and started web scraping for it.(I don’t have special api for this website so i scraped manually.)</p><p>I’ve used the BeautifulSoap library for this and edited the datas to create a strong and useful dataframe.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/778/1*PG0dwz92kj8deAKByNiORg.png" /><figcaption>Some of the Web Scraping Codes</figcaption></figure><h3>Data Wrangling</h3><p>After finishing web scraping I’ve looked up dataset , I was curious about the shape and columns properties of dataset. Then I could edit, change and clean index,columns and other things that important for me.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/501/1*ya5TjKYhJc77Uj_7N3kZww.png" /><figcaption>Some of the Data Wrangling</figcaption></figure><p>My data had a categorical column (Memory_Type). It consisted of this category and I’ve done “One Hot Encoding” with dummies codes to use it in machine learning.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*0EGxGCCu2LASj9oncBJ5oQ.png" /><figcaption>One Hot Encoding with Dummies Codes</figcaption></figure><p>My dataset had empty values in the Price_TL columns. At the same time, prices have so many different valuse because of different GB and speed values. So it wouldn’t make sense to mean() or drop() them directly. That’s why I used the K-nearest Neighbors Algorithm(KNN) for these null values.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/587/1*akdMECu7ZHutKl5xHzOTFw.png" /></figure><p>When I checked several rows, the code was okey. In this way, My dataset was ready for machine learning models and algorithms. After I analyzed my dataset, I wanted to check if there is any outliers.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/830/1*rd_H3gsO1IMSYUp3HtN3cw.png" /><figcaption>Outliers for “Memory_GB” and “Speed_MHz” Colums</figcaption></figure><p>As we can see in the graphs above, outliers was not at a problematic values. So can make our final checks and tests on the dataframe and jump into machine learning and model algorithms side.</p><h3>Model Algorithms and Test-Train Performances</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/444/1*SmYGoqAgXZxz2m6id-Bacg.png" /><figcaption>Model Overview(Check for Correlation)</figcaption></figure><p>To predict the sale prices I am using the following regression algorithms: Linear Regression, Ridge regression, Lasso regression , Polinomial Regression, PLS Regression, PCR Regression and lastly Elastic Net regression algorithm. These algorithms can be feasibly implemented in python with the use of the scikit-learn package. Finally, I will conclude which model is best suitable for the given case by evaluating each of them using the evaluation metrics provided by the scikit-learn package.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/682/1*BGFNNYAJWQIM1Ut70bAwvQ.png" /><figcaption>All Model Algorithms</figcaption></figure><h3>Cross-Validation and Model Tuning</h3><p>Cross-Validation is an essential tool in the Data Scientist toolbox. It allows us to utilize our data better. When we’re building a machine learning model using some data, we often split our data into training and validation/test sets. The training set is used to train the model, and the validation/test set is used to validate it on data it has never seen before. The classic approach is to do a simple 80%-20% split, sometimes with different values like 70%-30% or 90%-10%. In cross-validation, we do more than one split. We can do 3, 5, 10 or any K number of splits.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/709/1*bBgQ6le5BF5zO4q7K8XWSg.png" /><figcaption>Cross-Validation</figcaption></figure><p>By doing this, we’re able to use all our 100 examples both for training and for testing while evaluating our learning algorithm on examples it has never seen before.</p><p>And finally, by looking at the mean_absolute_error() values, we can see which model gave us the least error.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/553/1*n9xCeiO9gZuFfcBxw4oR-g.png" /></figure><h3>Models Testing and Training Conclusions</h3><p>When analyzing the report, it is noted that the cross validition score of the <strong>Polynomial Ridge regression</strong> model is seemed to be the highest which means, it takes the place of being the most suitable model for our dataset . It is followed by the Linear regression model.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/327/1*alaspdLvWRXD7hRlfU0Orw.png" /><figcaption>cross_val_score() values</figcaption></figure><p>We can also see same results if we would like to see mean of absolute error values. We can conclude that <strong>Polynomial Ridge model</strong> can be used the best model for our RAMs prices prediction problem.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/330/1*F_sjDzzPhr2qqDoBdHL2yg.png" /><figcaption>mean_absolute_error() values</figcaption></figure><p>We can see that, every model while rounding the output values will result in a score of 0.84 (84%) or 0.85 (85%) which means our model performs well on our dataset and can be used to solve real-world problems. So we can get a formula using the parameters given by our model. With this formula, we can calculate the price of RAM given its properties.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d6ab4dd5c991" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Use Your Time Efficiently with My Airlines Project]]></title>
            <link>https://aykutazazi.medium.com/use-your-time-efficiently-with-my-airlines-project-10716a6c5773?source=rss-c1bbe3753da------2</link>
            <guid isPermaLink="false">https://medium.com/p/10716a6c5773</guid>
            <category><![CDATA[python]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-visualization]]></category>
            <dc:creator><![CDATA[Aykut Azazi]]></dc:creator>
            <pubDate>Sun, 03 Jan 2021 16:26:16 GMT</pubDate>
            <atom:updated>2021-01-18T13:53:26.221Z</atom:updated>
            <content:encoded><![CDATA[<p>There are many points where we can use data science and exploratory data analysis for directing our lives, saving time, increasing our profitability-incomes etc. We can do this by cleaning the data sets which have consisting of crowded and unnecessary informations. Then we can make it useful for our business. Finally we can obtain statistical informations from this cleared data sets and draw many conclusions or automate it with machine learning and artificial intelligence.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xu_NUTO3jqdjUifLRg8ASg.png" /></figure><h3>The Scenario of Project</h3><p>Let’s imagine that we are at the beginning of 2016. My employer asked me to identify the most punctual domestic airlines in the US because his travel schedule will be quite busy and he does not want to wait even a minute for delays and cancellations. Thus, airlines that I detected as the most punctual ones will be preferred to buy tickets primarily.</p><p>Or let’s assume there is a famous traveller who has at least 2 flights in a day. Traveller wants to earn more miles to reduce flight costs. At the same time, he/she wants to choose airlines with the least cancellation, because traveller wants to buy tickets much earlier with less price. So he/she will be able to get large amount of miles because of flying with same airlines mostly.</p><p>I was checking open source datas on the web and found a dataset named as “<a href="https://www.kaggle.com/usdot/flight-delays">2015 Flight Delays and Cancellations</a>”.</p><h3>Meeting with Dataset</h3><p>After reading and analyzing the data set, I’ve wanted to see which columns it has and which ones I can use. At the same time, I’ve wanted to analyze how much data these columns have, how many of them contain nulls and what is columns values like min-max, std.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/563/1*kJrxlyLGeZzI56LWKooWPQ.png" /><figcaption>Description about Dataset</figcaption></figure><h3>Data Analysis</h3><p>I’ve made the necessary arrangements on the columns that affect the flight times, cancellations and delays of the airlines. After integrating these values with the annual flight numbers, I’ve created rates for each airline company. Considering all the important datas and values, we could see a ranking table with this rates.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/471/1*nX8_LSXT3aqtvMVPdpkxqQ.png" /><figcaption>Airlines Rates</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/425/1*KrnX3rVp78MdpvImfKDbGA.png" /><figcaption>Table of Airlines Rates</figcaption></figure><p>I also wanted to use the day and month values in the dataset. In this way, evaluating the performance of airlines according to the seasons(climate conditions) category will give us a more detailed and strong results. To detail my project results more, I created a new column named ‘CLIMATE’ and wrote a code assigning climates for each row based on condition of ‘MONTH’ values;</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/454/1*hhDNj1KdVX6W3_xj5tiwJg.png" /><figcaption>Assigning Climates Codes</figcaption></figure><p>For stronger and more detailed results, I’ve used groupby tables with the climate catagories. Then with new rates I sorted airlines by seasons.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/529/1*1msvDfH2sEK8_AofBj-ndA.png" /><figcaption>Example Rating Dataframe for Spring</figcaption></figure><h3>Data Conclusions and Visual Results</h3><p>Of course the most effective way to submit a result of analysis is to make it to visual expression. Matplotlib and Seaborn libraries are quite useful to help us for that.<br>There are results of my analysis about delayed&amp;cancelled flights rates of each airlines and climates by barcharts below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/658/1*9NCvuWmL3Se4jXpxCsADtQ.png" /><figcaption>Airlines Rating Table for Autumn</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/662/1*7CachOukl4cjSsvMXDejBQ.png" /><figcaption>Airlines Rating Table for Spring</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/659/1*BTPaLNAG4o9QMXylsykXqw.png" /><figcaption>Airlines Rating Table for Winter</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/665/1*yxgqjAhlSE7oEIbg-W7gfg.png" /><figcaption>Airlines Rating Table for Summer</figcaption></figure><p>To sum up, the most three punctual airlines are same for all climates but their sort are changing.</p><p>Airlines performance of timing for all year;</p><p>1.Hawaiian Airlines</p><p>2.Alaska Airlines</p><p>3.Delta Airlines.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=10716a6c5773" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>