<?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 Anjali Tiwari on Medium]]></title>
        <description><![CDATA[Stories by Anjali Tiwari on Medium]]></description>
        <link>https://medium.com/@anjalitiwari02199?source=rss-4a17cf6d89f4------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*wNVskfl0kE2n33WAyKXisg.jpeg</url>
            <title>Stories by Anjali Tiwari on Medium</title>
            <link>https://medium.com/@anjalitiwari02199?source=rss-4a17cf6d89f4------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Wed, 18 Nov 2026 08:05:56 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@anjalitiwari02199/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[Essential Data Visualization to know!]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://towardsdev.com/essential-data-visualization-to-know-9623dc7dcb16?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/2600/0*X8I0cpNqvVbM3T_s" width="5472"></a></p><p class="medium-feed-snippet">Starting a career as a data analyst necessitates the development of numerous skills. Almost everyone has emphasized the importance of SQL&#x2026;</p><p class="medium-feed-link"><a href="https://towardsdev.com/essential-data-visualization-to-know-9623dc7dcb16?source=rss-4a17cf6d89f4------2">Continue reading on Towards Dev »</a></p></div>]]></description>
            <link>https://towardsdev.com/essential-data-visualization-to-know-9623dc7dcb16?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/9623dc7dcb16</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analyst]]></category>
            <category><![CDATA[data]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Tue, 14 Jun 2022 00:09:28 GMT</pubDate>
            <atom:updated>2022-08-05T10:59:55.701Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Work on your happiness and wellbeing]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@anjalitiwari02199/work-on-your-happiness-and-wellbeing-f45edef3f8e8?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/2600/0*ZxrmT094LpPiBofL" width="5343"></a></p><p class="medium-feed-snippet">Does scrolling digital media actually gives you happiness?</p><p class="medium-feed-link"><a href="https://medium.com/@anjalitiwari02199/work-on-your-happiness-and-wellbeing-f45edef3f8e8?source=rss-4a17cf6d89f4------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@anjalitiwari02199/work-on-your-happiness-and-wellbeing-f45edef3f8e8?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/f45edef3f8e8</guid>
            <category><![CDATA[wellbeing]]></category>
            <category><![CDATA[social-media]]></category>
            <category><![CDATA[mental-health]]></category>
            <category><![CDATA[productivity]]></category>
            <category><![CDATA[happiness]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Fri, 16 Oct 2020 18:51:07 GMT</pubDate>
            <atom:updated>2022-06-22T23:32:43.907Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Women in Data Science Dublin]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@anjalitiwari02199/women-in-data-science-dublin-cba36d280a56?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/800/0*-112Ldf0f2zxUw1m" width="800"></a></p><p class="medium-feed-snippet">WiDS Dublin a digital conference took place on 9th June in association with Letterkenny Institute of Technology, Ireland. Being an&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/@anjalitiwari02199/women-in-data-science-dublin-cba36d280a56?source=rss-4a17cf6d89f4------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@anjalitiwari02199/women-in-data-science-dublin-cba36d280a56?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/cba36d280a56</guid>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[ireland]]></category>
            <category><![CDATA[women]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[women-in-tech]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Fri, 10 Jul 2020 16:29:21 GMT</pubDate>
            <atom:updated>2022-06-22T23:35:53.788Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Solving a Data Science Problem]]></title>
            <link>https://medium.com/@anjalitiwari02199/solving-a-data-science-problem-5daf7b2a25ee?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/5daf7b2a25ee</guid>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Fri, 13 Mar 2020 15:32:35 GMT</pubDate>
            <atom:updated>2020-03-14T04:22:45.276Z</atom:updated>
            <content:encoded><![CDATA[<blockquote>Can you hop on the top step of the ladder while skipping all other steps? The obvious answer is No!</blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*IUiNW2fn8kqvhdc2" /><figcaption>Photo by <a href="https://unsplash.com/@taylor08n?utm_source=medium&amp;utm_medium=referral">Taylor</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>Similarly, it is impossible to apply machine learning algorithms on a problem statement without performing the basic necessary steps on it.</p><p>If you do not follow a procedure while working on a data science problem chances are either you won’t get a result or you will get a result but it might not be giving you significant results.</p><p>This article, explains the necessary steps that should be taken while solving a data science problem.</p><h4>1. Understanding the problem:</h4><p>Look at the features and understand how do they help in your particular problem. It is important to understand what features to use and what features to miss out. Having the right data is the first step for a data science problem.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*-zGiKvNFw6tQsAiX" /><figcaption>Photo by <a href="https://unsplash.com/@stanleydai?utm_source=medium&amp;utm_medium=referral">Stanley Dai</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><h4>2. Hypothesis Generation:</h4><p>We need to formulate the hypothesis to understand how features are influencing the target variable having a confidence interval i.e. 95% or 0.05. Here, we state a Null Hypothesis (Ho) and Alternate Hypothesis (Ha) where Ho means there is no impact of independent variable on response variable and Ha states that there exist a direct impact of independent variable on response variable. The value of p decides whether to reject the null hypothesis or fail to reject the hypothesis.</p><ol><li>Reject the null hypothesis (Accept the Ha): If p value &lt; 0.05</li><li>Fail to reject the null hypothesis ( Accept the Ho): If p &gt; 0.05</li></ol><h4>3. Data Cleaning:</h4><p>Data Cleaning is an important aspect of data science projects. It is important to have a relevant dataset which is free of errors and doesn’t contain duplicates. The features in a dataset can be categorical and numerical variables. Hence, it is not advisable to use the same techniques on the different types of data. Also, get rid of variables which are of no use.</p><h4>4. Data Exploration:</h4><p>Data exploration helps in understanding each variable and how are they distributed which is done using the different visualisation plots. Many problems that are resolved here are the skewness, outliers, multicollinearity and more.</p><h4>5. Feature Engineering:</h4><p>This stage is used for adding new features in the dataset. This step is usually based on hypothesis generation where we actually understand what features can be added. Based on categorical variables, we use encoding which suits our data ( Label Encoder, Dummy Encoder and more) . While in numerical variables we deal with the missing values. These missing values can either be ignored or filled using proper ways for better predictions. This technique makes data ready for machine learning models.</p><h4>6. Model Training:</h4><p>Here we use machine learning models to train our data based on its distribution by using a particular model for a particular target variable.</p><p>Every machine learning algorithm can not be used here because of the data distribution( Normal distribution, binomial distribution, poisson etc).</p><h4>7. Model Evaluation and Testing:</h4><p>Based on our model we choose the performance metric to evaluate the performance of our model on our problem. These metics gives us a value which explains the significance of the variables in prediction of future target variable.</p><ol><li>Regression models have different set of performance metrics such as Rsquare, adjusted Rsquare, Mean Squared Error and more.</li><li>Classification models uses performance metrics such as AIC, Confusion Matrix, AUC.</li></ol><p>Later, we train our model again for much better accuracy and then once finding the variables useful for our target variable we apply the same model on our test data.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5daf7b2a25ee" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Science and Docker]]></title>
            <link>https://medium.com/@anjalitiwari02199/data-science-and-docker-7979aa3dc68e?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/7979aa3dc68e</guid>
            <category><![CDATA[docker]]></category>
            <category><![CDATA[kubernetes]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[containers]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Wed, 01 Jan 2020 23:58:55 GMT</pubDate>
            <atom:updated>2020-01-01T23:58:55.407Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*d6BFMyQVkvIvgKw9" /><figcaption>Photo by <a href="https://unsplash.com/@frankiefoto?utm_source=medium&amp;utm_medium=referral">frank mckenna</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>As a data scientist, you would be needed to work on various tools. To install these tools one would require a humongous space. Having the easiest option in the market right now i.e. Docker, why one would be installing these tools?</p><p>In more simple words, Docker allows us to setup a development environment in the easiest way. Docker makes it easy to run various applications in a single operating system with the ability of doing it quickly. Having the docker engine on your system is the only requirement to build multiple applications.</p><blockquote><strong>Let’s understand the terminologies used to work on a Docker.</strong></blockquote><h4><strong>Docker Container</strong></h4><p>Docker allows us to build, package, and deploy applications by using the docker containers. These containers are lightweight, stand-alone packages that are enough to run your applications. <strong>These containers consist of code, libraries and other dependencies that is required to run an application</strong>. Every application has its own container and since the containers are light weight we can run as many applications as compared to virtual machine without taking up kernel space. To understand the differences between docker and VMs, head to this article by <a href="https://devopscon.io/blog/docker/docker-vs-virtual-machine-where-are-the-differences/">Devops Con</a>.</p><p>If you delete a Container the data related to it is deleted. To store the data generated from a container even if the container is deleted, one could use Volumes (<strong>data volumes</strong> and<strong> bind mounts). </strong>To get a better understanding of Volumes you can get a look on <a href="https://dzone.com/articles/demystifying-the-data-volume-storage-in-docker">Data Volume storage in Docker</a>.</p><p>For example: <a href="https://neo4j.com/sandbox-v2/">Neo4j Sandboxes</a> is an example of docker containers. Every sandbox is a Neo4j instance of a container. Every sandbox is different from other and have specific configurations,datasets and plugins.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/480/1*x3O0xlOntR2xQ1HJ3ucTAA.png" /><figcaption><a href="https://www.docker.com/">Image Source</a></figcaption></figure><blockquote><strong>Installation:</strong> To work on such containers, the only requirement is to install the Docker tool . Install the Docker from the <a href="https://docs.docker.com/install/">docker website</a>.</blockquote><h4>Docker Image</h4><p>Docker Image is the basis for a docker container, which means to build a container it is important to have a docker image. Docker image has its own file system and can easily be downloaded and installed from the <a href="https://hub.docker.com/">Docker hub</a>. A single image can create numerous containers.</p><blockquote><strong>A single Docker image can be linked to multiple containers.</strong></blockquote><h4>Docker Files</h4><p>For the docker Image to be used, which when run leads to creation of docker container we need code.This code which creates a docker Image is stored in a file called as Docker file.</p><p>This Docker file contains all the dependencies and then uses it to build the docker Image.</p><blockquote>To build once anywhere and run anywhere. — Docker</blockquote><blockquote>Extra Note: In a clustered environment, the orchestration of various containerized application can be done using any of these applications: Kubernetes, Docker swarm, Amazon ECS and others. Although today in the market, Kubernetes and Docker swarm use is more.</blockquote><blockquote>For your own learning have a check on this article <a href="https://hackernoon.com/kubernetes-vs-docker-swarm-a-comprehensive-comparison-73058543771e">Kubernetes and Docker swarm</a> . Let’s compare and then use!</blockquote><h3>Conclusion</h3><p>Docker is fast and easy to implement. Docker provides Linux containers to easily build and deploy the application. The docker Images encapsulates all the file needed to run an Image. The docker Images can easily be installed from the Docker hub, where all the images resides for the various softwares and tools.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7979aa3dc68e" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Connect to Neo4j graph database]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@anjalitiwari02199/connect-to-neo4j-graph-database-49e4977b596b?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/1366/1*bLnmwMdcyKfnriFepCwDPg.png" width="1366"></a></p><p class="medium-feed-snippet">The Neo4j database is a graph database and is used to represent the data in the form of graphs. Since the data is huge and is networked&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/@anjalitiwari02199/connect-to-neo4j-graph-database-49e4977b596b?source=rss-4a17cf6d89f4------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@anjalitiwari02199/connect-to-neo4j-graph-database-49e4977b596b?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/49e4977b596b</guid>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Sun, 29 Dec 2019 16:05:07 GMT</pubDate>
            <atom:updated>2022-06-22T23:53:42.535Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Git — Version Control System]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/git-version-control-system-666a1ffd85d3?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/932/1*odxtilqfN40uE5hfGAJWPQ.png" width="932"></a></p><p class="medium-feed-snippet">Why you need a Version control software &#x200A;&#x2014;&#x200A; You worked on something and now you want to save it somewhere before it gets disrupted or&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/data-science/git-version-control-system-666a1ffd85d3?source=rss-4a17cf6d89f4------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/git-version-control-system-666a1ffd85d3?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/666a1ffd85d3</guid>
            <category><![CDATA[git]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[github]]></category>
            <category><![CDATA[cloud]]></category>
            <category><![CDATA[web-development]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Sat, 07 Dec 2019 20:04:59 GMT</pubDate>
            <atom:updated>2022-06-22T23:48:59.986Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A/B Testing : A Python Approach (Part 2)]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/analytics-vidhya/a-b-testing-a-python-approach-part-2-9958ed870a6f?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/2600/0*myvVIHkhjwgZ58vb" width="5853"></a></p><p class="medium-feed-snippet">We already performed EDA on our dataset which is taken from the Kaggle challenge. The dataset is based on a game called cookie cats. To&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/analytics-vidhya/a-b-testing-a-python-approach-part-2-9958ed870a6f?source=rss-4a17cf6d89f4------2">Continue reading on Analytics Vidhya »</a></p></div>]]></description>
            <link>https://medium.com/analytics-vidhya/a-b-testing-a-python-approach-part-2-9958ed870a6f?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/9958ed870a6f</guid>
            <category><![CDATA[data-engineering]]></category>
            <category><![CDATA[hypothesis-testing]]></category>
            <category><![CDATA[statistics]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Thu, 28 Nov 2019 01:39:30 GMT</pubDate>
            <atom:updated>2022-06-26T00:51:15.148Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A/B Testing : A Python Approach (Part 1)]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/analytics-vidhya/a-b-testing-a-python-approach-part-1-75fdb904f271?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/2600/0*QsbwJhj4RF6mTi65" width="5853"></a></p><p class="medium-feed-snippet">This article is for people who wants to learn how to implement A/B testing. If you want to get a recap on A/B testing, please check my&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/analytics-vidhya/a-b-testing-a-python-approach-part-1-75fdb904f271?source=rss-4a17cf6d89f4------2">Continue reading on Analytics Vidhya »</a></p></div>]]></description>
            <link>https://medium.com/analytics-vidhya/a-b-testing-a-python-approach-part-1-75fdb904f271?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/75fdb904f271</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[hypothesis-testing]]></category>
            <category><![CDATA[statistics]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Thu, 28 Nov 2019 01:31:41 GMT</pubDate>
            <atom:updated>2022-06-22T23:43:18.571Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A/B Testing for Data Science]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/analytics-vidhya/a-b-testing-for-data-science-f1203e9503b6?source=rss-4a17cf6d89f4------2"><img src="https://cdn-images-1.medium.com/max/2600/0*MDhU8xbkfFm18WiD" width="5184"></a></p><p class="medium-feed-snippet">Let me tell you a story!</p><p class="medium-feed-link"><a href="https://medium.com/analytics-vidhya/a-b-testing-for-data-science-f1203e9503b6?source=rss-4a17cf6d89f4------2">Continue reading on Analytics Vidhya »</a></p></div>]]></description>
            <link>https://medium.com/analytics-vidhya/a-b-testing-for-data-science-f1203e9503b6?source=rss-4a17cf6d89f4------2</link>
            <guid isPermaLink="false">https://medium.com/p/f1203e9503b6</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[hypothesis-testing]]></category>
            <category><![CDATA[a-b-testing]]></category>
            <category><![CDATA[statistics]]></category>
            <category><![CDATA[startup]]></category>
            <dc:creator><![CDATA[Anjali Tiwari]]></dc:creator>
            <pubDate>Tue, 19 Nov 2019 19:08:28 GMT</pubDate>
            <atom:updated>2022-06-26T00:47:42.254Z</atom:updated>
        </item>
    </channel>
</rss>