<?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 Tenicka Terell Norwood on Medium]]></title>
        <description><![CDATA[Stories by Tenicka Terell Norwood on Medium]]></description>
        <link>https://medium.com/@tenicka.norwood?source=rss-57368ac155bf------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*QqvedSgxgbj1f6uGFMIKAw.jpeg</url>
            <title>Stories by Tenicka Terell Norwood on Medium</title>
            <link>https://medium.com/@tenicka.norwood?source=rss-57368ac155bf------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Wed, 18 Nov 2026 08:56:37 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@tenicka.norwood/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[Your AI Product Has an Expiration Date!]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@tenicka.norwood/your-ai-product-has-an-expiration-date-b74a265df27e?source=rss-57368ac155bf------2"><img src="https://cdn-images-1.medium.com/max/2600/0*jwiPU0m-frYOQTIb" width="3080"></a></p><p class="medium-feed-snippet">Can we reliably ask users who they are, agree on secrets and talk privately?</p><p class="medium-feed-link"><a href="https://medium.com/@tenicka.norwood/your-ai-product-has-an-expiration-date-b74a265df27e?source=rss-57368ac155bf------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@tenicka.norwood/your-ai-product-has-an-expiration-date-b74a265df27e?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/b74a265df27e</guid>
            <category><![CDATA[post-quantum-cryptography]]></category>
            <category><![CDATA[generative-ai-tools]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[tennessee]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Wed, 08 Apr 2026 20:35:48 GMT</pubDate>
            <atom:updated>2026-04-08T20:35:48.669Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A Breath of Innovation: CNNs for Pneumonia Detection]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@tenicka.norwood/a-breath-of-innovation-cnns-for-pneumonia-detection-bcf716cc249c?source=rss-57368ac155bf------2"><img src="https://cdn-images-1.medium.com/max/2600/0*lB5h-I6BB9ea_I6N" width="3576"></a></p><p class="medium-feed-snippet">Breathing new life into my data skillset in the most convoluted way&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/@tenicka.norwood/a-breath-of-innovation-cnns-for-pneumonia-detection-bcf716cc249c?source=rss-57368ac155bf------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@tenicka.norwood/a-breath-of-innovation-cnns-for-pneumonia-detection-bcf716cc249c?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/bcf716cc249c</guid>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Wed, 20 Sep 2023 15:02:59 GMT</pubDate>
            <atom:updated>2023-09-20T15:02:59.072Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Fueling Student Success]]></title>
            <link>https://medium.com/@tenicka.norwood/fueling-student-success-1723abd2991b?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/1723abd2991b</guid>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[ml-so-good]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Mon, 24 Jul 2023 16:19:15 GMT</pubDate>
            <atom:updated>2023-07-24T18:22:02.679Z</atom:updated>
            <content:encoded><![CDATA[<p>The Power of Machine Learning Pipelines</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*Kf7QmowceuRrZCj8" /><figcaption>Photo by <a href="https://unsplash.com/pt-br/@chris_dion?utm_source=medium&amp;utm_medium=referral">Christophe Dion</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><blockquote>An average person with only a high school diploma or GED would earn an estimated <strong>1.6 million dollars in their lifetime</strong>, compared to a person with a bachelor’s degree who potentially can make <strong>~2.8 million dollars in their lifetime</strong>. — Carnevale et al. (2021) Georgetown University <a href="https://cew.georgetown.edu/cew-reports/the-college-payoff/">The College Payoff</a></blockquote><p>This profound disparity in earning potential underscores the transformative power of higher education and highlights the significance of timely graduation in enhancing students’ long-term financial security.</p><p>· <a href="#65a1">Choosing a meaningful project</a><br>· <a href="#f6bc">Leveraging the OSEMN Pipeline</a><br>· <a href="#dbb2">Attempting to stay DRY</a><br>· <a href="#7ed1">Pay attention to your AUDIENCE</a><br> ∘ <a href="#0dfe">Insight 1: Curricular Units in 2nd Semester Matter</a><br> ∘ <a href="#c40a">Insight 2: Monitoring Tuition Fee Payments is Pivotal</a><br> ∘ <a href="#85d5">Insight 3: Evaluations and Grades are Crucial</a><br>· <a href="#4157">What are my next steps?</a><br>· <a href="#d897">Contact Me</a></p><h3>Choosing a meaningful project</h3><p>As I progress in my data journey, one of the things that I have learned is that domain knowledge and genuine interest MATTER. Continuously reworking projects that a multitude of folks have completed simply will not help you build your skillset. Along these lines, here are some of the practices that I have collected along the way:</p><ul><li><strong>Simple</strong> is best. I am a true believer. Whichever language you are using determines the style, function, and skills in the industry that make coding in that language readable. Currently, for my Python users out there, I am using <a href="https://peps.python.org/pep-0008/">PEP8</a> which is a style guide that gives users a heads-up on the conventions that will enhance readability and collaboration.</li><li>Stay<strong> DRY. </strong>The <strong>D</strong>on’t <strong>R</strong>epeat <strong>Y</strong>ourself principle helps me from the exhausting practice of rewriting large code blocks that NO ONE will read, use or adapt.</li><li>Pay Attention to Your <strong>Audience</strong>. Figure out <strong>what</strong> matters to your audience. Then find a way to show them things they care about (<strong>so what)</strong>, and what to do with the insights you shared (<strong>now what)</strong>.</li></ul><p>I have often leaned into my education domain knowledge. So when I started a project on using machine learning for classification, I chose a dataset that was related to something near and dear to my heart, academic success. The University of California at Irvine has lots of datasets <a href="https://archive.ics.uci.edu/">here </a>that you can use to hone your machine learning knowledge(a bit squeaky clean, and yet rather useful) that I highly recommend.</p><p>i<strong>N</strong>terpret → Identify insights and create visualizations of findings.</p><p>For this project:</p><ul><li><strong>Stakeholder</strong>: Instituto Politecnico de Portalegre</li><li><strong>Business Case</strong>: Researchers at the Instituto Politecnico de Portalegre want to reduce the rate of student academic failure in higher education.</li><li>Recall was valued over precision as I was trying to minimize false negatives. (I postulated that minimizing the number of false negatives will help to ensure that fewer students who need educational assistance slip through the cracks and are not appropriately identified and supported).</li></ul><h3>Leveraging the OSEMN Pipeline</h3><p>I wanted to tackle this data in a logical way that aligns with steps that folks in the industry would implement when tackling projects that matter to their stakeholders. So I used the OSEMN pipeline:</p><p><strong>O</strong>btain → Import the data.</p><p><strong>S</strong>crub → Manage the datatypes, and resolve missing data or duplicates.</p><p><strong>E</strong>xplore → Identify patterns within the relationships between variables in the data.</p><p><strong>M</strong>odel → Create a set of predictive models.</p><p>i<strong>N</strong>terpret → Identify insights and create visualizations of findings.</p><h3>Attempting to stay DRY</h3><p>In my latest iteration of attempting to stay DRY, I began writing classes so that I can in essence stop trying to reinvent the wheel. Classes help with organization, the reusability of code, making objects interchangeable, and making the overall implementation feel a bit more polished.</p><p>Here are two classes I used in this project that helped me explore concepts like constructors (initialize attributes), inheritance (properties can be shared between a class and subclass(es)), and polymorphism (multiple objects can be called if they share a common method).</p><p>The ObtainData class helped me load data I stored in a .csv file with semicolons as the separator in a specific data path.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/5f284e646b0fef6eec8a46a1c7c6cd26/href">https://medium.com/media/5f284e646b0fef6eec8a46a1c7c6cd26/href</a></iframe><p>After creating the ObtainData class, I created an instance of that class to get the data to pass it through the pipeline. While this data is pretty clean, I still crafted classes to Scrub, explore and analyze the data.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/4e95fda6c80c66230d9a2504723dc6a2/href">https://medium.com/media/4e95fda6c80c66230d9a2504723dc6a2/href</a></iframe><p>Here are some of the plots from my exploration:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*JK-CrSVzg0rNrDEApKb5Jw.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1015/1*DuB8Mq_254U0OeSIjzcpyg.png" /><figcaption>Image by author/Influence on Curricular units 1st semester (credited), 2nd semester (approved) on Graduation status</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/952/1*XdznewShhpNhcSnnUZwPDg.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/967/1*j_BAOEj-z2TFSLC5PoMA3g.png" /><figcaption>Image by author/Influence of Tuition Fees and Age at enrollment on Graduation status</figcaption></figure><p>Check out my entire repo <a href="https://github.com/dataeducator/student_academic_success/">here</a>.</p><h3>Pay attention to your AUDIENCE</h3><p>For this project my audience was a set of researchers trying identify students at risk of not graduating on time. The general idea is that if you can predict the features of groups who are at risk and provide them timely interventions you can put them back on the path to graduation. So I provided them with two main pieces of evidence:</p><ul><li>feature importances / coefficients of machine learning models I trained on the data using an 80(train) 20(test) split and evaluated using a recall score.</li><li>Insights from the exploration that related to key features that the models identified as important.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*E4zJbyjgS-ZfJYWaAKtgDA.png" /><figcaption>Image by author/ Evaluation of Machine Learning Models on Ternary Classification of Student Data</figcaption></figure><h4>Insight 1: Curricular Units in 2nd Semester Matter</h4><ul><li>Students with more approved units in the 2nd semester have a higher chance of academic success.</li><li>The number of enrolled units in the 2nd semester also positively impacts academic outcomes.</li><li>Encouraging students to pass more units in the 2nd semester can lead to a reduced rate of academic failure.</li></ul><h4>Insight 2: Monitoring Tuition Fee Payments is Pivotal</h4><p>Being up-to-date with tuition fees is crucial for predicting academic success. Timely tuition fee payments correlate with better student outcomes. Implementing strategies to ensure prompt tuition fee payments can positively impact academic performance and reduce failure rates.</p><h4>Insight 3: Evaluations and Grades are Crucial</h4><p>Academic performance in the 1st and 2nd-semester evaluations significantly influences students’ likelihood of success. Students who achieve higher grades tend to have better academic outcomes overall. Early identification and intervention for students struggling with evaluations or grades can lead to improved academic performance and decreased failure rates.</p><p>Generally, I want to improve my craft and design projects that are insightful and clear to the audience. I will continue to keep pushing myself to build more skills and improve my implementation of data analysis tools.</p><h3>What are my next steps?</h3><p>I want to gain a better understanding of the following:</p><ul><li>How can NLP techniques be applied to projects related to the education domain?</li></ul><p>I am currently working on creating visualizations for all of the elementary schools of Sumner County in Tennessee using tools from my ever-growing toolkit.</p><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood">LinkedIn</a> or email me at tenicka.norwood@gmail.com.</p><h4><a href="https://mlearning.substack.com/about">WRITER at MLearning.ai</a> //<a href="https://open.substack.com/pub/mlearning/p/machine-learning-eeg-ear-emotion-prediction-ai?r=z7zu8&amp;utm_campaign=post&amp;utm_medium=web"> EEG AI Prediction</a> // <a href="https://open.substack.com/pub/mlearning/p/learn-how-to-animate-midjourney-images-tutorial?r=z7zu8&amp;utm_campaign=post&amp;utm_medium=web">Animate Midjourney</a></h4><p><a href="https://medium.com/mlearning-ai/mlearning-ai-submission-suggestions-b51e2b130bfb">Mlearning.ai Submission Suggestions</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1723abd2991b" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Designing projects with heart]]></title>
            <link>https://medium.com/@tenicka.norwood/designing-projects-with-heart-d2365180c01b?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/d2365180c01b</guid>
            <category><![CDATA[perseverance]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[design]]></category>
            <category><![CDATA[grief]]></category>
            <category><![CDATA[python-programming]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Thu, 23 Mar 2023 22:04:49 GMT</pubDate>
            <atom:updated>2023-03-23T22:34:44.225Z</atom:updated>
            <content:encoded><![CDATA[<p>Finding inspiration after loss</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*R09gqAfE9hiNYHY7qkrjbg@2x.jpeg" /><figcaption>Photo by Luigi Boccardo on Unsplash</figcaption></figure><h3>Coding hits a roadblock</h3><p>The world of coding and machine learning is often characterized by its relentless pursuit of progress and fast-paced nature. Recently, a devastating loss threw me off course and left me feeling unmoored. Despite my overwhelming grief and frustration, I am finding my way through each day by grabbing onto the joy that comes each morning.</p><p>When my dad passed away, I was in the midst of a deep dive into articles, tutorials, and coding exercises. Suddenly, everything stopped as I struggled to process my emotions and support my family through this difficult time. Yet even through the turmoil and pain of this loss, I find myself turning to the tools and skills that I have been cultivating, seeking solace and a sense of purpose.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*W8m6CnJqR1BQIEZI" /><figcaption>Photo by <a href="https://unsplash.com/@riku?utm_source=medium&amp;utm_medium=referral">Riku Lu</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><h3>Losing motivation</h3><p>These past few weeks have been a blur of activity and numbness. I couldn’t tell you one thing that I ate wrote about or learned to do. I just kept going while pouring my energy into designing stationery booklets that captured my dad’s essence while trying to meet my commitments at work and at home. Despite my best efforts, I continued to find it hard to stay motivated and engaged in projects. The spark that previously drove me to succeed in the past seems to have dimmed.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*Ii0PFLC-aG0R-Pi7" /><figcaption>Photo by <a href="https://unsplash.com/@cristofer?utm_source=medium&amp;utm_medium=referral">Cristofer Maximilian</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><h3>Finding joy in small wins</h3><p>I felt a bit ungrateful, as a little bit of me cringed and got a bit greyer each time someone told me to reach out if I needed anything. My daughter, who, like me, takes after my grandmother but shares my sister’s height, is creative and flexible, whereas I am logical and a bit clumsy; she is where I find the strength to stay positive and take joy in small wins. Through it all, I kept moving forward, one small win at a time. Whether it was meeting a budget deadline, planning a party, or learning a new coding skill, I celebrated after each accomplishment. After each win, I clawed a bit of my soul back.</p><h3>Being ok, with not being ok</h3><p>I have discovered that being okay doesn’t always mean being strong or in control. Emotionally, I feel as though I have the structural integrity of the 7–5–5–7, which is where flawed carbon nanotubes (purportedly one of the strongest materials in existence) fail when compressed. I am not ok, and each day I am learning to be ok with that. Currently, I am allowing myself moments of vulnerability and grief, talking with my family, listening to music, and simply being present in my grief. All to remind me of who I am, who I want to be, and who my dad raised me to be; and who I am even while feeling this broken is, as my dad would say: “always enough!”</p><h3>What‘s my next step?</h3><p>I want to build a project using machine learning that is connected to something my dad and I both loved:</p><ul><li>Bahamian flora and fauna</li></ul><h3>Contact me</h3><p>If you want to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood"><strong>LinkedIn</strong></a><strong> </strong>or email me at <strong>tenicka.norwood@gmail.com.</strong></p><h3>Continue the conversation</h3><p>What about you, fellow data nerds? How do you push forward with your projects when a sudden loss occurs? Let me know in the comments.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d2365180c01b" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Designing Engaging Python Lesson Plans with the Help of AI]]></title>
            <link>https://medium.com/@tenicka.norwood/building-better-python-lessons-b60b6b4d3cdf?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/b60b6b4d3cdf</guid>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[education]]></category>
            <category><![CDATA[programming]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Mon, 06 Feb 2023 03:36:16 GMT</pubDate>
            <atom:updated>2023-02-08T23:39:29.372Z</atom:updated>
            <content:encoded><![CDATA[<p>Utilizing ChatGPT to improve instructional design</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*cKwkvbfUc66UQ0tr" /><figcaption>Photo by <a href="https://unsplash.com/@hiteshchoudhary?utm_source=medium&amp;utm_medium=referral">Hitesh Choudhary</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>The <a href="https://ldaamerica.org/lda_today/the-state-of-learning-disabilities-today/">National Center for Learning Disabilities</a> reports that 1 in 5 people in the United States experience learning differences, including dyslexia and ADHD. With this in mind, we often build lessons with multiple means of engagement to provide multiple access points to content within a single lesson. <a href="https://www.cast.org/impact/universal-design-for-learning-udl">Universal Design for Learning</a> is a popular methodology for ensuring learners are given multiple pathways across a standards-aligned lesson.</p><p>Recently, I began testing, and tuning prompts to leverage ChatGPT as a pseudo-coding partner to improve my Python programming knowledge. After building prompts to identify and build a reproducible protocol for wrangling data in python, I decided to attempt to craft a UDL Lesson for an introduction to Python programming leveraging the output from ChatGPT. Mostly, because experience has taught me that teaching concepts to others is one of the best ways to solidify your own knowledge base.</p><h3>Python Datatypes</h3><p>So I wanted to create a guided Jupyter notebook as an introduction to standard datatypes in Python. Check out my entire repo <a href="https://github.com/dataeducator/UDLfromChatGPT">here</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*KHqS11P9vPzb3X-Y7c1C4Q.png" /><figcaption>Image by author/Lesson Objective, Assessment, and Standards</figcaption></figure><p>Some of the datatypes I introduced in the lesson include:</p><p>int: An integer data type used to represent whole numbers. For example, 1, 2, 3, etc.<br>float: A floating-point data type used to represent real numbers. For example, 1.0, 2.5, 3.14, etc.<br>str: A string or object data type used to represent text data. For example, &quot;Hello, World!&quot;, &quot;python&quot;, etc.<br>bool: A Boolean data type used to represent truth values (True or False).<br>list: A collection data type used to store an ordered sequence of elements. For example, [1, 2, 3], [&quot;apple&quot;, &quot;banana&quot;, &quot;cherry&quot;], etc.<br>tuple: An immutable collection data type used to store an ordered sequence of elements. For example, (1, 2, 3), (&quot;apple&quot;, &quot;banana&quot;, &quot;cherry&quot;), etc.<br>dict: A dictionary data type used to store key-value pairs. For example, {&quot;name&quot;: &quot;John Doe&quot;, &quot;age&quot;: 30}, etc.</p><h3>Guided Practice</h3><p>Within the notebook, a set of prompts are modified from the output from ChatGPT shown here. Some of the cells ask students to replace characters. For example, when introducing strings, I asked students to replace the empty strings with their first name and assign their first name to a variable called first_name, that is, type string(object).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*V7HR3aHrt_kmeJwR1ZXuxQ.png" /><figcaption>Image by author/Create a string in python</figcaption></figure><p>While guiding students through Booleans and variables, I included cells that students could run without making changes. I wanted students to predict the code&#39;s evaluation and test their predictions.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tHx3QwdjTIJV84kwnJbnIA.png" /><figcaption>Image by author/Guided Practice on Booleans in Python</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*L1vJa57Pa3776kihE2ySQw.png" /><figcaption>Image by author/Variables in Python</figcaption></figure><p>After the guided practice, I added sections for understanding checks and reflection, incorporating choice and voice.</p><h3>Multiple Means of Engagement</h3><p>To check for understanding, a set of 10 questions is provided, and participants must choose at least 7 to either craft a modified README.md file or create a sketch note offline and complete a reflection on what they learned as they traversed the lesson.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*igFD0xqK8O98oOM3g443qQ.png" /><figcaption>Image by Author/ Checks for understanding based on ChatGPT prompt responses</figcaption></figure><h3>Reflection</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*06fjBp56RGy9WOqZ9SEThQ.png" /><figcaption>Image by Author/Reflection on Python guided practice based on ChatGPT prompts</figcaption></figure><p>While I still have serious questions about assessing the output of ChatGPT prompts, I can readily see how it can be combined with research-based instructional design to build something beautiful (sans soup).</p><h3>What‘s my next step?</h3><p>I want to build a more robust analysis of prompt construction for ChatGPT:</p><ul><li>I want to create a set of SQL-guided practices based on the feedback from ChatGPT.</li></ul><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood"><strong>LinkedIn</strong></a><strong> </strong>or email me at <strong>tenicka.norwood@gmail.com.</strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b60b6b4d3cdf" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Building your <Python> Knowledge]]></title>
            <link>https://medium.com/@tenicka.norwood/building-your-python-knowledge-3348a7556737?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/3348a7556737</guid>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[chatbots]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[education]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Sat, 04 Feb 2023 01:09:49 GMT</pubDate>
            <atom:updated>2023-02-05T07:56:12.210Z</atom:updated>
            <content:encoded><![CDATA[<p>With assistance from chatGPT</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*I8p6-KqFuNcUUWJp" /><figcaption>Photo by <a href="https://unsplash.com/@hiteshchoudhary?utm_source=medium&amp;utm_medium=referral">Hitesh Choudhary</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>Since the launch of chatGPT, it has been celebrated and denigrated for its ability to generate human-like responses. The speed of responses, the ability to regenerate responses, and the unchecked confidence in the answers generated by this system engendered much fear among several folks in academia. The bans came swiftly, from small liberal arts colleges to large pre-K — 12 school districts, with leading voices shouting to the rafters that education must be shielded from the dangers posed by this new tool that could seemingly create solutions that teachers could not assess as non-student-generated.</p><p>My mind did not go off in that direction. Instead, I began to wonder what I could use chatGPT to learn. I started building prompts. My first prompts were about poetry; I wanted to see if chatGPT could write about specific content in a style of my choice. Naturally, I chose to poke fun at one of my favorite people who prefers R to Python and chose a poem that counters his favorite argument.</p><h4>Prompt 1: Write a poem with three stanzas in iambic pentameter about the benefits of Python compared to R:</h4><h3><strong>Prompt 1 Result:</strong></h3><blockquote>In data science, choices must be made,<br>Two languages stand out, well refined,<br>Python and R both with strengths displayed.</blockquote><blockquote>Python is versatile, strong and nimble, With vast libraries, easy to handle,<br>For any task, it is the symbol. R is a master at statistics, <br>With packages that make data analysis,<br>So much easier and truly fantastic.</blockquote><blockquote>So when it comes to data science work,<br>Consider Python, for it will never shirk,<br>And your projects, it will always perk!</blockquote><p>-ChatGPT generated poem</p><p>I was hooked but wanted to build content-specific knowledge, so I tried a more python-centered prompt next.</p><h4>Prompt 2: Craft the solution to 5 intermediate data science problems using PEP8 compliant python code:</h4><h3>Prompt 2 Result:</h3><p>ChatGPT warns that the following code is simply a starting point, and how the dataset is related to the problem of interest affects the actual implementation of each stage of this protocol:</p><h3>Load and Explore a Dataset</h3><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/f1f4204de7b2242ad7537bf3b780d704/href">https://medium.com/media/f1f4204de7b2242ad7537bf3b780d704/href</a></iframe><h3>Clean and pre-process data</h3><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/0c403c0482a47d77a21f2be2ed792cef/href">https://medium.com/media/0c403c0482a47d77a21f2be2ed792cef/href</a></iframe><h3>Visualize data</h3><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/8d010f65fb7ad852fcde1dfbfc71f0aa/href">https://medium.com/media/8d010f65fb7ad852fcde1dfbfc71f0aa/href</a></iframe><h3>Splitting the Data into Training and Testing Sets</h3><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/323360f373143204438ad61d2ab13281/href">https://medium.com/media/323360f373143204438ad61d2ab13281/href</a></iframe><h3>Building a Machine Learning Model</h3><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/647896ff9c145ceca414dfd6117c7ee4/href">https://medium.com/media/647896ff9c145ceca414dfd6117c7ee4/href</a></iframe><p>While this output seemed clear and concise, I wanted to push the prompts further to see how ChatGPT could be used to extend my python knowledge. So I created a prompt to build a 2-hour course to develop my python knowledge.</p><h4>Prompt 3: Write a short 2-hour course with guided lessons to familiarize me with basic data types and variables in Python, including sample code snippets that are pep8 compliant and follow the DRY principle.</h4><h3>Prompt 3: Result</h3><p><em>2 Hour Course: </em><strong><em>Getting Familiar with Basic Data Types and Variables in Python</em></strong></p><p><strong><em>Introduction</em></strong><em><br>This course aims to provide a comprehensive overview of basic data types and variables in Python and equip participants with the skills to write clean, PEP8-compliant, and DRY code.</em></p><p><em>Session 1: Basic Data Types (1 Hour)</em></p><ul><li><em>Overview of basic data types in Python, including integers, floating-point numbers, strings, and booleans.</em></li><li><em>Participants will learn how to define and manipulate variables in Python, as well as how to convert between different data types.</em></li><li><em>Guided practice exercises will be provided to reinforce learning and ensure participants understand the concepts.</em></li></ul><p><em>Session 2: Variables and Data Types in Practice (1 Hour)</em></p><ul><li><em>Participants will work with real-world data sets and apply the concepts learned in the previous session to solve practical problems.</em></li><li><em>They will be introduced to the importance of writing clean, PEP8-compliant, and DRY code and using best practices to avoid common coding errors.</em></li><li><em>A review of the concepts learned in the course will be provided, along with a question and answer session to address any remaining questions or concerns.</em></li></ul><p><em>Conclusion:</em></p><ul><li><em>At the end of this course, participants will have a solid understanding of basic data types and variables in Python and be able to write clean and practical code.</em></li><li><em>The guided practice exercises and real-world examples will help them gain practical experience, and the review and question and answer session will provide a comprehensive overview of the key concepts learned in the course.</em></li></ul><p>I asked for a follow-up to this lesson to illustrate the guided practice.</p><h4>Prompt 4: Give me an example using python code for the Guided Practice Exercises in session 1.</h4><h3>Prompt 4: Result</h3><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/27beddd3fe63b80e63586818c78fd50d/href">https://medium.com/media/27beddd3fe63b80e63586818c78fd50d/href</a></iframe><p>For completeness, I rounded off my questions to include a prompt to determine what ChatGPT thought I should learn in session 2.</p><h4>Prompt 5: Give me an example using Python code of the Guided Practice Exercises in session two.</h4><p>Sure, here’s an example of guided practice exercises for the basic data structures in Python:</p><ol><li>Lists:</li></ol><ul><li>Create a list of 5 numbers and perform the following operations:</li><li>Sort the list in ascending order</li><li>Reverse the list</li><li>Remove the last element from the list</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/5b12e62ab3169440e1c9c2c53206f196/href">https://medium.com/media/5b12e62ab3169440e1c9c2c53206f196/href</a></iframe><p>2. Tuples:</p><ul><li>Create a tuple of 5 numbers and perform the following operations:</li><li>Retrieve the second element from the tuple</li><li>Check if a number exists in the tuple</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/ab47507bd21d057cc540f128aa772bc2/href">https://medium.com/media/ab47507bd21d057cc540f128aa772bc2/href</a></iframe><p>3. Dictionaries:</p><ul><li>Create a dictionary with keys as numbers and values as their squares and perform the following operations:</li><li>Retrieve the value for a given key</li><li>Update the value for a given key</li><li>Remove a key-value pair from the dictionary</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/4d1e5d997fb7de454b3a7b86e89e7420/href">https://medium.com/media/4d1e5d997fb7de454b3a7b86e89e7420/href</a></iframe><p>4. Sets:</p><ul><li>Create two sets of numbers and perform the following operations:</li><li>Union of the two sets</li><li>The intersection of the two sets</li><li>The difference of the two sets</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/3d95b325fbe344efa9a08882fbc4ea90/href">https://medium.com/media/3d95b325fbe344efa9a08882fbc4ea90/href</a></iframe><p>The ChatGPT-generated lessons and guided exercises with code snippets seem like reasonable responses, but I am still learning and trying to determine ways to assess the output.</p><h3>What‘s my next step?</h3><p>I want to build a more robust analysis of prompt construction for ChatGPT:</p><ul><li>I want to create a set of Jupyter notebooks to create a set of guided practices based on the feedback from ChatGPT.</li></ul><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood"><strong>LinkedIn</strong></a><strong> </strong>or email me at <strong>tenicka.norwood@gmail.com.</strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3348a7556737" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Sip, Explore, Analyze...]]></title>
            <link>https://medium.com/@tenicka.norwood/heres-the-tea-3222918b582c?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/3222918b582c</guid>
            <category><![CDATA[seaborn]]></category>
            <category><![CDATA[teamwork]]></category>
            <category><![CDATA[plotly]]></category>
            <category><![CDATA[design-thinking]]></category>
            <category><![CDATA[visualization]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Wed, 25 Jan 2023 04:27:27 GMT</pubDate>
            <atom:updated>2023-02-03T01:23:27.670Z</atom:updated>
            <content:encoded><![CDATA[<p>My Favorite Teas for Visualization work</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*3f1X5EXZQ0sXToHw" /><figcaption>Photo by <a href="https://unsplash.com/@kellysikkema?utm_source=medium&amp;utm_medium=referral">Kelly Sikkema</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><blockquote><a href="#0a46"><strong>What are the essential tools for building compelling visualizations?</strong></a></blockquote><blockquote><a href="#fda0"><strong>What are my go to teas when wrangling data?</strong></a></blockquote><blockquote><a href="#9a72"><strong>What are some caffeine free options for visualization work?</strong></a></blockquote><h3>What are the essential tools for building compelling visualizations?</h3><p>There are a few things that are essential when crafting compelling visuals from what is often rather messy data:</p><ul><li>A good dataset that is complex enough to gain insights from, engaging enough for you to spend time cleaning and digging deeper into, and novel enough that you are not wasting time and energy reinventing the wheel.</li><li>The right tools to explore data and build visualizations that meet your target audience’s needs, add value and help tell a data story.</li><li>A clear understanding of what story you want to tell</li><li>And finally, a good cup of tea helps me clear my mind boosts my mood, and soothes my soul as the level of requests keeps rising minute by minute until the end of January.</li></ul><h3><strong>What is my go-to tea when wrangling data?</strong></h3><p>This time of year is when I spend a lot of time trying to build a better programming engine, keep students on a path to graduation and identify interventions for my most challenging to serve students. While I love coffee enough to consume pounds of chocolate-covered espresso beans each month, it is not my beverage of choice when I need to focus and be creative. With that said, I have difficulty keeping up with the changing demands of my stakeholders and often lean into a collection of tea and the <a href="https://todoist.com/productivity-methods/eisenhower-matrix">Eisenhower matrix</a> to get through the next few weeks.</p><p>My go-to tea is Earl grey. I am in good company as this classic black tea is savored by writers, designers, thinkers, and tinkerers. Whether it’s the bergamot oil, memories of my grandmother, or the crisp flavor of the whole-leaf brand, I tend to favor Earl grey. It has never let me down when I am wrangling a complex dataset. Recently, I was trying my hand at multivariate linear regression on the King County dataset and found myself out of my depth. Thankfully, I had my favorite brands of loose-leaf teas on hand and was able to, with judicious use of online sns documentation was able to create a set of visuals, including the following:</p><ul><li>An Earl Grey-fueled interactive map.</li><li>A Camomile-driven scatter plot with a trendline</li><li>A Jasmine-infused barplot</li><li>A scatterplot built while sipping Rooibos</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*SKdzGsRGVa6TO3hdSVf_gA.gif" /><figcaption>Image by Author/Visualization of King County Housing Dataset built while sipping Earl Grey.</figcaption></figure><p>Check out my entire repo <a href="https://github.com/dataeducator/real_estate_linear_regression">here.</a></p><h3><strong>What are some caffeine-free options for visualization work?</strong></h3><p>My favorite caffeine-free options are camomile, jasmine, and rooibos. Let’s start with camomile, which is made from dried flowers that are in the daisy family. Sometimes, you hit a groove and want to keep exploring the data but look up, and it’s 3:38 am. This is when I tip into my stash of camomile, which is soothing enough to help me wind down my day but just energetic enough to push my final commits to my repo before finally heading to sleep.</p><figure><img alt="Image by Author/Visualization of King County Housing Dataset built while sipping Camomile" src="https://cdn-images-1.medium.com/max/826/1*RGVi6xB4-9ZLybF3pMZFug.png" /><figcaption>Image by Author/Visualization of King County Housing Dataset built while sipping camomile tea.</figcaption></figure><p>Jasmine tea is a fragrant green tea that relaxes me and helps me focus on complex tasks. I often sip on Jasmine tea when I have to switch gears from one complex task to another. For example, I started sipping on Jasmine tea after I had spent a while generating report cards with narratives so that when I switched to auditing schedules to see if they matched counselor request files, I could focus on the details and not get caught in the weeds. This gave me the energy I needed to generate, distribute and analyze sale price trends in the King County dataset.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*v0afuNCpVvtjs10cputdUg.png" /><figcaption>Image by Author/Visualization of King County Housing Dataset built while sipping Jasmine Tea.</figcaption></figure><p>Sometimes, I can be a night owl, which is where Rooibos comes in. This sweet, caffeine-free, and delicious tea has helped me burn that midnight oil when water just wouldn’t cut it since I eventually want to sleep and find myself in the awkward position that if I drink a caffeinated beverage after 2 pm, sleep will elude me.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*p-i2e8nEE1kfSSPfJeqXDA.png" /><figcaption>Image by Author/Visualization of King County Housing Dataset built while sipping Rooibos tea.</figcaption></figure><p>While these are my favorite pairings, everyone’s tastes are different, and the teas that work for me might not work for you. But I hope this article has given you a sense of the teas that I find most helpful for visualization work and that it’s inspired you to try them out for yourself.</p><h3>What are my next steps?</h3><p>I want to gain a better understanding of the following:</p><ul><li>To what extent do academic interventions affect progress toward graduation in 9–12 settings?</li></ul><p>I am currently working on creating visualizations for all of the member schools of the Internationals network using plotly express and dash .</p><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood">LinkedIn</a> or email me at tenicka.norwood@gmail.com.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3222918b582c" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The meaning of life, the universe, and everything…]]></title>
            <link>https://medium.com/@tenicka.norwood/the-meaning-of-life-the-universe-and-everything-9423dcb79c06?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/9423dcb79c06</guid>
            <category><![CDATA[education-reform]]></category>
            <category><![CDATA[education]]></category>
            <category><![CDATA[gpt-3]]></category>
            <category><![CDATA[disruption]]></category>
            <category><![CDATA[chatbots]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Thu, 12 Jan 2023 00:57:21 GMT</pubDate>
            <atom:updated>2023-01-12T00:58:58.167Z</atom:updated>
            <content:encoded><![CDATA[<h3>42 and other answers that need better defined questions</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*FOcxffX6Zp_jaEkb" /><figcaption>Photo by <a href="https://unsplash.com/ja/@juniorferreir_?utm_source=medium&amp;utm_medium=referral">Júnior Ferreira</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><blockquote>Artificial Intelligence (AI) is supposed to complement human intelligence not compete with nor replace it.</blockquote><p>-David De Cremer and Garry Kasparov</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*F6TTm-YEfmHJ-zmv" /><figcaption>Photo by <a href="https://unsplash.com/es/@tetrakiss?utm_source=medium&amp;utm_medium=referral">Arseny Togulev</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>One of the key benefits of AI is that it has the potential to process content, complete repetitive tasks or make predictions at a pace that is not currently possible for humans. Banning a technology or limiting access to it hardly ever yields the results that drive those concerned with safety, trauma or harm related to that technology often pontificate about.</p><h3>The end of education as we know it</h3><p>Calculators, PCs, cellphones, search engines, simulators, emulators, Oh my, the list goes on and on of the inventions that would be t<a href="https://www.forbes.com/sites/petergreene/2022/12/11/no-chatgpt-is-not-the-end-of-high-school-english-but-heres-the-useful-tool-it-offers-teachers/?sh=4893ebc11437">he end of education as we know it</a>. The idea that technology will be the end of education as we know it, is often bandied about each time there is an iteration in the capability of technology.</p><p>It is curious to me that instead of creating novel tasks that are grounded in critical analysis connected to authentic experiences and require synthesis of disparate sources, the tasks that students are tasked with creating are ones that are easily automated and monotonously churned out with single pathways to demonstrate competence ad nauseum.</p><p>In my experience, students are resilient, for every way you attempt to block their access to a system, they will find a way to access, manipulate and gain from it. School aged children are digital natives, who were born into a reality where technology is ubiquitous and practically integrated into every facet of their daily lives. Excluding access to tools can limit students’ ability to learn how to ethically and responsibly use tools which is the opposite of what we want. The data nerd in me, wonders how models with a knowledge base limited in time to the year 2021 could possibly be considered dangerous.</p><h3>Why is trying to use technology responsibly so difficult?</h3><p>With that said, exposing children to tools that may proliferate incorrect information, reinforce biases or blur the lines between research and plagiarism seems like too high a risk without a larger knowledge base on the effects of AI on educational outcomes in school aged children.</p><p>In one of my favorite stories, the main characters spend an inordinate amount of time and effort searching for the meaning of life, the universe and the ultimate <strong>answer. </strong>However, each of the protagonists eventually realize they indeed have <em>the answer</em>, but do not understand nor can they articulate the answer.</p><p>This reminds me of the recent debates and eventual bans on cutting-edge technology across academia. It leaves me feeling frustrated and powerless, which is eerily similar to how I felt watching the character in my story struggle. I may understand and even empathize everyone’s perspectives, arguments and opinions, but have no power to change the outcome. It’s a thought-provoking reminder of the complex nature of progress and the nuances of technology governance, leadership, and decision making that impacts society at large.</p><h3>What‘s my next step?</h3><p>I would like to build a playbook on how to write effective queries to yield impactful responses from Chat-GPT:</p><ul><li>How do I use data science to create a better playbook for creating effective Natural Language Processing queries?</li></ul><p>I was thinking of leveraging the an API, but am still thinking about this, so for right now, I just keep reading journal articles on how text based algorithms work, and am testing out queries on my own.</p><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood"><strong>LinkedIn</strong></a><strong> </strong>or email me at <strong>tenicka.norwood@gmail.com.</strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9423dcb79c06" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Keeping Your Data So Fresh and So Clean]]></title>
            <link>https://medium.com/@tenicka.norwood/keeping-your-data-so-fresh-and-so-clean-3acf41271146?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/3acf41271146</guid>
            <category><![CDATA[python]]></category>
            <category><![CDATA[music]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[joy]]></category>
            <category><![CDATA[data-visualization]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Tue, 29 Nov 2022 04:30:12 GMT</pubDate>
            <atom:updated>2022-11-30T21:31:45.337Z</atom:updated>
            <content:encoded><![CDATA[<p>A Playlist for Squeaky Clean Data</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*F2iPiiKX0cyRjZjs" /><figcaption>Photo by <a href="https://unsplash.com/@trommelkopf?utm_source=medium&amp;utm_medium=referral">Steve Harvey</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>I have been consuming lots of data science and analysis content, and one of the major takeaways I have found is that there is no model you can build that will yield actionable insights if you feed it garbage data. One of my instructors holds that the first thing that newbies need to learn is the GIGO principle. Well, he would put it more succinctly and say that it would be better to spend 80% of your time cleaning your data instead of building a shiny model that you feed Garbage.</p><blockquote>The GIGO (Garbage In = Garbage Out) Principle holds that models are akin to humans and are what they consume. Moreover, if you feed your model unrefined data, you can expect your metrics to be dampened by the inaccuracies that compound along your data pipeline.</blockquote><p>With this in mind, I created a playlist to keep my mind focused while cleaning data and thought that you might find it helpful if you are new to digging into data like I am.</p><p>Let’s start with data that is in the .csv file format, and we have also imported all of the libraries and visualization packages necessary to build a model.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/e0ce3bd29a2721bf0099def37603cd9e/href">https://medium.com/media/e0ce3bd29a2721bf0099def37603cd9e/href</a></iframe><p>So my typical first step is to create a data frame called df that I use pd.read_csv to create.</p><p>df = pd.read_csv(&#39;myfile.csv&#39;, index_col = 0)</p><p>After I have an initial data frame, I clean the data. The initial song on my list that I am typically listening to while reading the .csv file and creating my initial data frame is :</p><p>Jill Scott’s Golden</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2F4QCXr79Rkcw%3Ffeature%3Doembed&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D4QCXr79Rkcw&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2F4QCXr79Rkcw%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="640" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/1c6d7cfc08871f66b099427fbc74efed/href">https://medium.com/media/1c6d7cfc08871f66b099427fbc74efed/href</a></iframe><h3>Cleaning Data</h3><p>To clean data, I often spend lots of time:</p><ul><li>Removing Duplicates — duplicates take up space, can slow the implementation of models, and may lead to erroneous insights.</li><li>Replacing Missing Values — while there is no optimal way to deal with missing values, learning how to handle missing values is a skill that budding data nerds should work on building up.</li><li>Replacing Placeholder values — placeholders like: ‘—,’ NANs,‘ ?’, and ‘#’ consistently gum up the works and lead to errors both seen and unseen in analysis. If you are lucky, error messages abound; if you are supremely unlucky, you notice after trying to visualize the correlation between dependent and independent variables and get noticeably improbable graphs.</li><li>Casting datatypes to more appropriate datatypes —Often, this shows up when I have naively been treating a categorical variable (think something with a fixed number of values) as though it was continuous (something that can have any value between a minimum and a maximum).</li></ul><h3>Where do I begin?</h3><p>I look at the shape of the data frame, pretty much I need to know how many rows and columns I am working with and need to wrangle into submission. As I jam to the legendary vocalist from Philadelphia, Pennsylvania, I use the following:</p><ul><li><a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.shape.html">df.shape</a> — Review the dimensions of the data</li><li><a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.info.html">df.info()</a> — Review a concise summary of the data</li><li><a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.head.html">df.head()</a> — Review the first five rows of the data (you can increase this number by adding a number n inside of the parentheses exdf.head(10) will yield the first ten rows of the data.</li></ul><h3>Onto the Next</h3><p>After I have learned the basic features of the data, I check for the entire data frame for placeholders, often with something that looks like the following:</p><p>df.isin[&#39;?&#39;, &#39;#&#39;, &#39;NaN&#39;, &#39;null&#39;, &#39;N/A&#39;, &#39;-&#39;]).any()</p><p>This is typically when I start listening to old-school Reggae Artists like Baby Cham, Capleton, and Sean Paul, which bring back the nostalgia of my high school projects in the physics lab with Mr. Green, who had the best rhythmic reggae soundtrack in the late 90s on the East Side of New Providence bar none.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2FloPRsrqrDXc&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DloPRsrqrDXc&amp;image=http%3A%2F%2Fi.ytimg.com%2Fvi%2FloPRsrqrDXc%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/f5bb49d54fcc5b7bfe402695fd2032f5/href">https://medium.com/media/f5bb49d54fcc5b7bfe402695fd2032f5/href</a></iframe><h3>Reviewing the Changes</h3><p>After identifying placeholders, I use steps like this while jamming to old-school Reggae:</p><p>df[&#39;column_with_placeholder&#39;] = pd.to_numeric(df[&#39;column_with_placeholder&#39;], errors = &quot;coerce&quot;)</p><h3>Keeping the Groove Going</h3><p>I typically transition to dirty South jams while removing duplicates and deciding whether I will drop rows from the data frame with null values or replace them with the median or mode. My favorite artists in that genre are from the Dungeon Family.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2F4sKNKoQcRSo%3Ffeature%3Doembed&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D4sKNKoQcRSo&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2F4sKNKoQcRSo%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="640" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/6c2064074d248e1c3967ce97218c8edb/href">https://medium.com/media/6c2064074d248e1c3967ce97218c8edb/href</a></iframe><p>My playlist typically looks like this:</p><ol><li>Jill Scott — <a href="https://www.youtube.com/watch?v=4QCXr79Rkcw&amp;ab_channel=JillScottVEVO">Golden</a></li><li>Baby Cham featuring Alicia Keys — <a href="https://www.youtube.com/watch?v=loPRsrqrDXc&amp;ab_channel=AtlanticRecords">Ghetto Story</a></li><li>Wayne Wonder — <a href="https://www.youtube.com/watch?v=pT1XhnfMT5c&amp;ab_channel=MarkSzymanski">No Letting Go</a></li><li>Sean Paul — <a href="https://www.youtube.com/watch?v=dW2MmuA1nI4&amp;ab_channel=AtlanticRecords">Temperature</a></li><li>Beenie Man— <a href="https://www.youtube.com/watch?v=u1nzPKgWcmI&amp;ab_channel=BeenieMan-Topic">Romie</a></li><li>Dungeon Family — <a href="https://www.youtube.com/watch?v=4sKNKoQcRSo&amp;ab_channel=DungeonFamily-Topic">Excalibur</a></li><li>Erykah Badu —<a href="https://www.youtube.com/watch?v=TW28iWV7nxE&amp;ab_channel=ErykahBadu-Topic"> On and On</a></li><li>Outkast —<a href="https://www.youtube.com/watch?v=PWgvGjAhvIw&amp;ab_channel=OutkastVEVO"> Hey Ya!</a></li><li>Outkast — <a href="https://www.youtube.com/watch?v=drsQLEU0N1Y&amp;ab_channel=OutkastVEVO">Rosa Parks</a></li><li>Lauryn Hill —<a href="https://www.youtube.com/watch?v=cE-bnWqLqxE&amp;ab_channel=laurynhillvevo"> Ex Factor</a></li></ol><h3>What‘s my next step?</h3><p>I would like to build in more flexibility in and variety of my playlist:</p><ul><li>How do I use data science to create a better playlist?</li></ul><p>I was thinking of leveraging the youtube API, but am still thinking about this, so for right now, I just add songs based on my mood.</p><ul><li>I am currently working on creating a trip planning tool to help with my upcoming trip to the Bahamas to help celebrate our 50th year of Independence.</li></ul><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood"><strong>LinkedIn</strong></a><strong> </strong>or email me at <strong>tenicka.norwood@gmail.com.</strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3acf41271146" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Crafting Effective Visuals]]></title>
            <link>https://medium.com/design-bootcamp/crafting-effective-visuals-18569648619f?source=rss-57368ac155bf------2</link>
            <guid isPermaLink="false">https://medium.com/p/18569648619f</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[education]]></category>
            <category><![CDATA[design]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analysis]]></category>
            <dc:creator><![CDATA[Tenicka Terell Norwood]]></dc:creator>
            <pubDate>Mon, 21 Nov 2022 02:23:38 GMT</pubDate>
            <atom:updated>2022-11-22T09:17:37.041Z</atom:updated>
            <content:encoded><![CDATA[<p>Impact vs. Intention</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*hG9vp7GfPOCLDY7X" /><figcaption>Photo by <a href="https://unsplash.com/@lukechesser?utm_source=medium&amp;utm_medium=referral">Luke Chesser</a> on <a href="https://unsplash.com/?utm_source=medium&amp;utm_medium=referral">Unsplash</a></figcaption></figure><p>One of the ways that Data Science connects to the field of Education is that in both domains, it is often your impact instead of your intention that matters. As I begin to dive deeper into my journey with data, some of the lessons that I have learned are:</p><ul><li>Simple is best. There are accepted norms for programming languages that make programs reproducible and scalable. Currently, this means I spend a lot of time practicing ideas covered in the <a href="https://peps.python.org/pep-0008/">PEP8 style guide </a>for Python.</li><li><strong>D</strong>on’t <strong>R</strong>epeat <strong>Y</strong>ourself. Who has the time to keep rewriting code? Build functions or leverage existing code by importing libraries. Reinventing the wheel is exhausting and bad form, so please <strong>STOP</strong> doing it already.</li><li>You are paying attention to your audience matters. Ensuring that you add value and understand the needs of stakeholders is more important than the accuracy of your model. No one cares that your p-value is less than an alpha value of 0.05 if you miss the point of the business case that you are supposed to be exploring and do not craft actionable insights.</li></ul><h3>Simple is Best</h3><p>One of the first visuals I ever made was this top-ten fitness youtube channel bar chart while trying to create a better workout playlist from one of my favorite fitness creators Pamela Reif. I thought it was gorgeous, eye-catching, and colorful. It was far from straightforward; the colors conveyed no additional information to the viewer and did not meet my need for a better workout playlist.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/946/1*Z54r1v2-nfg_wbC9-qgcLg.png" /><figcaption>Image by Author/Best Performing Videos by Pamela Reif</figcaption></figure><p>A better answer was to conduct EDA on my ten favorite fitness YouTubers and create a playlist instead of making colorful bar graphs and boxplots. Check out my entire repo <a href="https://github.com/dataeducator/Better_workout_playlist">here</a>.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/f74549d1240cf791ec051801f9e2d727/href">https://medium.com/media/f74549d1240cf791ec051801f9e2d727/href</a></iframe><p>While creating a better workout list weighed heavy on my mind during the pandemic, once I headed back into the office, I turned my focus onto creating visuals for educators who were not that into spreadsheets and pivot tables.</p><h3>Don’t Repeat Yourself</h3><p>Making code that you can reuse is helpful for you as a practitioner and as a collaborator. Python documentation and community-created resources are plentiful. This means that you can import libraries and packages to craft impactful visualizations like pandas, matplotlib and plotly. Sometimes, it is beneficial to build functions yourself.</p><p>One of my functions that I found helpful while exploring state-level data is called: retention_plot.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/a8c8d3e12ebe800725f1a7e146976978/href">https://medium.com/media/a8c8d3e12ebe800725f1a7e146976978/href</a></iframe><h3>Paying attention to your audience matters</h3><p>I started to upgrade how I presented bar graphs and made a few functions, so I was no longer making notebooks that were impossible to navigate.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/c5b7cf3794efd0649039fc4705b41a33/href">https://medium.com/media/c5b7cf3794efd0649039fc4705b41a33/href</a></iframe><figure><img alt="" src="https://cdn-images-1.medium.com/max/984/1*1l-lH4cUbKtLqFbCdpyK_A.png" /><figcaption>Image by Author/Bar Chart showing Subgroups with Graduation Rate above the Citywide Mean</figcaption></figure><p>Currently, I am working on creating interactive maps for my postsecondary readiness team. This team’s focus is on student enrollment in college after high school. We started with state-level data on the percentage of students who return to the same institution during their sophomore year in college as the one students enrolled in immediately after high school. Our internal data consistently showed that our alums who maintain enrollment for their first two years of college have a greater likelihood of graduating college within four years.</p><p>My team asked for a way to visualize how outcomes compare across the country, our state, city, and district. Below is my first stab at creating an interactive map that shows the retention rate trends for cohorts 2009 to 2019.</p><ul><li>First, I imported plotly.express as px.</li><li>Next, I used pandas as pdto read in an excel file generated from the National Student Clearinghouse <a href="https://nscresearchcenter.org/persistence-retention/">persistence and retention report</a>.</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/b0cb913713a1732f71b6dacb235e26fe/href">https://medium.com/media/b0cb913713a1732f71b6dacb235e26fe/href</a></iframe><ul><li>Then I called a function I made earlier called retention_plot</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*9wZCqFpvvPO8chVFWxsqhg.gif" /><figcaption>GIF by Author/ State-Level-Retention-Rate-Data</figcaption></figure><h3>What are my next steps?</h3><p>I want to gain a better understanding of the following:</p><ul><li>How do the graduation rates of students at member schools of the Performance Standards Consortium compare to the mean city and state graduation, retention, and persistence rates for each subgroup?</li></ul><p>I am currently working on creating visualizations for all of the member schools of the New York Performance Standards Consortium using plotly express and dash .</p><h3>Contact Me</h3><p>If you would like to be updated with my latest articles, follow me on <a href="https://medium.com/@tenicka.norwood">Medium</a>. You can also connect with me on <a href="http://www.linkedin.com/in/tenicka-norwood"><strong>LinkedIn</strong></a><strong> </strong>or email me at <strong>tenicka.norwood@gmail.com.</strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=18569648619f" width="1" height="1" alt=""><hr><p><a href="https://medium.com/design-bootcamp/crafting-effective-visuals-18569648619f">Crafting Effective Visuals</a> was originally published in <a href="https://medium.com/design-bootcamp">Bootcamp</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>