<?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 AHMET KARAOGLAN on Medium]]></title>
        <description><![CDATA[Stories by AHMET KARAOGLAN on Medium]]></description>
        <link>https://medium.com/@karaoglanahmet?source=rss-3cf445372ae8------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*8qzEsPFyNzsmxIGNXFRGSA@2x.jpeg</url>
            <title>Stories by AHMET KARAOGLAN on Medium</title>
            <link>https://medium.com/@karaoglanahmet?source=rss-3cf445372ae8------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 19:07:24 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@karaoglanahmet/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[Statistical concepts that every Data Scientist should know‍‍‍]]></title>
            <link>https://medium.com/@karaoglanahmet/statistical-concepts-that-every-data-scientist-should-know-da33c1cf8084?source=rss-3cf445372ae8------2</link>
            <guid isPermaLink="false">https://medium.com/p/da33c1cf8084</guid>
            <dc:creator><![CDATA[AHMET KARAOGLAN]]></dc:creator>
            <pubDate>Wed, 27 Sep 2023 05:04:03 GMT</pubDate>
            <atom:updated>2023-09-27T05:04:03.223Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6pEJ1doIEIpqnlzm84LRNQ.jpeg" /><figcaption>Source: Pixels images</figcaption></figure><p>Data science relies heavily on statistical concepts to extract meaningful insights from data and make data-driven decisions. Here are some essential statistical concepts that every data scientist should know:</p><h4><strong><em>1. Descriptive Statistics:</em></strong></h4><p>— Mean (Average): The sum of all values divided by the number of values.<br> — Median: The middle value in a dataset when it is sorted.<br> — Mode: The most frequently occurring value in a dataset.</p><h4>2. Variability and Spread:</h4><p>— Variance: Measures how data points deviate from the mean.<br> — Standard Deviation: A common measure of the spread or dispersion of data.<br> — Range: The difference between the maximum and minimum values in a dataset.<br> — Interquartile Range (IQR): The range between the first quartile (25th percentile) and the third quartile (75th percentile) in a dataset.</p><h4><strong>3. Probability:</strong></h4><p>— Probability Distribution: Describes the likelihood of each possible outcome in a random experiment.<br> — Normal Distribution: A bell-shaped probability distribution frequently encountered in nature.<br> — Binomial Distribution: Models the number of successes in a fixed number of independent Bernoulli trials.<br> — Poisson Distribution: Models the number of events occurring in a fixed interval of time or space.</p><h4>4. Sampling and Sampling Distributions:</h4><p>— Population vs. Sample: The entire group of interest vs. a subset used for analysis.<br> — Sampling Bias: Systematic errors introduced by selecting a non-representative sample.<br> — Central Limit Theorem: States that the sampling distribution of the sample mean approaches a normal distribution as sample size increases.</p><h4>5. Hypothesis Testing:</h4><p>— Null Hypothesis (H0) and Alternative Hypothesis (H1): Statements to be tested using data.<br> — p-value: The probability of observing data as extreme as, or more extreme than, what was observed, assuming the null hypothesis is true.<br> — Type I and Type II Errors: Errors in hypothesis testing, where Type I is a false positive, and Type II is a false negative.</p><h4>6. Confidence Intervals:</h4><p>— A range of values that likely contains the true population parameter at a specified confidence level.</p><p>7. Correlation and Regression:<br> — Correlation Coefficient (e.g., Pearson, Spearman): Measures the strength and direction of a linear relationship between two variables.<br> — Linear Regression: Models the relationship between a dependent variable and one or more independent variables.</p><h4>8. Bayesian Statistics:</h4><p>— Bayes’ Theorem: A mathematical formula for updating probabilities based on new evidence.<br> — Prior and Posterior Probability: The probability distribution before and after observing data.</p><h4>9. Machine Learning Concepts:</h4><p>— Overfitting and Underfitting: Issues related to model complexity and performance.<br> — Cross-Validation: Technique to assess a model’s performance on unseen data.</p><h4>10. A/B Testing:</h4><p>— Experimental design and statistical analysis to compare the performance of two or more groups.</p><h4>11. Resampling Techniques:</h4><p>— Bootstrapping: Sampling with replacement to estimate population parameters.<br> — Monte Carlo Simulation: Using random sampling to estimate complex probabilities.</p><h4>12. Time Series Analysis:</h4><p>— Autocorrelation: Correlation of a time series with a lagged version of itself.<br> — Seasonality and Trends: Patterns in time series data over time.</p><p>These are fundamental statistical concepts that provide a solid foundation for data scientists to analyze data, build models, and draw meaningful insights from data. Depending on the specific field or domain, data scientists may need to delve deeper into specialized statistical techniques and tools.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=da33c1cf8084" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Certainly! Here’s a roadmap for learning Python for data analysis]]></title>
            <link>https://medium.com/@karaoglanahmet/certainly-heres-a-roadmap-for-learning-python-for-data-analysis-159137b76df9?source=rss-3cf445372ae8------2</link>
            <guid isPermaLink="false">https://medium.com/p/159137b76df9</guid>
            <dc:creator><![CDATA[AHMET KARAOGLAN]]></dc:creator>
            <pubDate>Tue, 21 Feb 2023 03:04:43 GMT</pubDate>
            <atom:updated>2023-02-21T03:04:43.835Z</atom:updated>
            <content:encoded><![CDATA[<p>Week 1–2: Python Basics</p><ul><li>Introduction to Python: Familiarize yourself with the basic syntax of Python and the structure of the language.</li><li>Resources: Codecademy Learn Python course</li><li>Control flow: Learn how to use control flow statements like loops and conditionals.</li><li>Resources: W3Schools’ Python Loops and Python Conditions tutorials</li><li>Functions: Understand how to define and call functions.</li><li>Resources: DataCamp’s Python Functions tutorial</li><li>Numpy: Start exploring Numpy, a library used for numerical computing with Python.</li><li>Resources: Numpy User Guide</li></ul><p>Week 3–4: Data Manipulation</p><ul><li>Pandas: Learn how to use Pandas, a popular Python library for data manipulation and analysis.</li><li>Resources: Pandas documentation and tutorials on Kaggle</li><li>CSV and JSON files: Understand how to read and write data from CSV and JSON files.</li><li>Resources: DataCamp’s Importing Data in Python course</li><li>Data cleaning: Learn how to identify and clean missing or inconsistent data in your datasets.</li><li>Resources: DataCamp’s Cleaning Data in Python course</li></ul><p>Week 5–6: Data Visualization</p><ul><li>Matplotlib: Start exploring Matplotlib, a library for creating visualizations with Python.</li><li>Resources: Matplotlib documentation and tutorials on Kaggle</li><li>Seaborn: Understand how to use Seaborn, a library built on top of Matplotlib for creating more complex visualizations.</li><li>Resources: Seaborn documentation and tutorials on Kaggle</li><li>Plotly: Start exploring Plotly, a library for creating interactive and dynamic visualizations.</li><li>Resources: Plotly documentation and tutorials on Kaggle</li></ul><p>Week 7–8: Machine Learning</p><ul><li>Scikit-learn: Learn how to use Scikit-learn, a popular library for machine learning with Python.</li><li>Resources: Scikit-learn documentation and tutorials on Kaggle</li><li>Supervised learning: Understand the basics of supervised learning algorithms like linear regression and decision trees.</li><li>Resources: DataCamp’s Supervised Learning with Scikit-learn course</li><li>Unsupervised learning: Learn about unsupervised learning algorithms like clustering and dimensionality reduction.</li><li>Resources: DataCamp’s Unsupervised Learning in Python course</li></ul><p>Week 9–10: Advanced Topics</p><ul><li>Big data: Learn how to use Python for big data processing and storage with tools like Hadoop and Spark.</li><li>Resources: Apache Hadoop and Apache Spark documentation</li><li>Web scraping: Understand how to use Python to scrape data from websites.</li><li>Resources: DataCamp’s Web Scraping with Python course</li><li>Database integration: Learn how to connect Python to databases like MySQL and PostgreSQL.</li><li>Resources: DataCamp’s Python SQL tutorial</li></ul><p>Week 11–12: Capstone Project</p><ul><li>Apply your Python skills to a data analysis project of your own choosing.</li><li>Use the libraries and techniques you’ve learned to explore a dataset, perform analysis, and create visualizations.</li><li>Share your results and code with the community or on a platform like GitHub.</li></ul><p>By following this roadmap, you can gain a strong understanding of Python for data analysis in just 3 months. Keep in mind that learning any programming language is a continuous process, so don’t be afraid to continue exploring and practicing beyond this roadmap. Good luck on your learning journey!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=159137b76df9" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Word Vectorization]]></title>
            <link>https://medium.com/@karaoglanahmet/word-vectorization-b779c08de8a3?source=rss-3cf445372ae8------2</link>
            <guid isPermaLink="false">https://medium.com/p/b779c08de8a3</guid>
            <dc:creator><![CDATA[AHMET KARAOGLAN]]></dc:creator>
            <pubDate>Wed, 12 Oct 2022 12:16:13 GMT</pubDate>
            <atom:updated>2022-10-12T12:16:13.650Z</atom:updated>
            <content:encoded><![CDATA[<p>Create and use a bag of words, and identify words unique to individual documents.</p><ul><li>Implement tokenization and count vectorization from scratch</li><li>Use dimensionality reduction on vectorized text data to create and interpret visualizations</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/224b831df2392707cb19c337296501bd/href">https://medium.com/media/224b831df2392707cb19c337296501bd/href</a></iframe><p>To make it easy to read in all of the documents, use a list comprehension to create a list containing the name of every single song file in the cell below.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/a6d6bd703f687d5f979eca5c7c595092/href">https://medium.com/media/a6d6bd703f687d5f979eca5c7c595092/href</a></iframe><pre>[&#39;song1.txt&#39;,<br> &#39;song2.txt&#39;,<br> &#39;song3.txt&#39;,<br> &#39;song4.txt&#39;,<br> &#39;song5.txt&#39;,<br> &#39;song6.txt&#39;,<br> &#39;song7.txt&#39;,<br> &#39;song8.txt&#39;,<br> &#39;song9.txt&#39;,<br> &#39;song10.txt&#39;,<br> &#39;song11.txt&#39;,<br> &#39;song12.txt&#39;,<br> &#39;song13.txt&#39;,<br> &#39;song14.txt&#39;,<br> &#39;song15.txt&#39;,<br> &#39;song16.txt&#39;,<br> &#39;song17.txt&#39;,<br> &#39;song18.txt&#39;,<br> &#39;song19.txt&#39;,<br> &#39;song20.txt&#39;]</pre><p>Next, let’s import a single song to see what our text looks like so that we can make sure we clean and tokenize it correctly.</p><p>Use the code in the cell below to read in the lyrics from song18.txt as a list of lines, just using vanilla Python:</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/9c72690415243caf3bd58eb25c923ae9/href">https://medium.com/media/9c72690415243caf3bd58eb25c923ae9/href</a></iframe><pre>[&#39;[Kendrick Lamar:]\n&#39;,<br> &quot;Two wrongs don&#39;t make us right away\n&quot;,<br> &quot;Tell me something&#39;s wrong\n&quot;,<br> &#39;Party all of our lives away\n&#39;,<br> &#39;To take you on\n&#39;,<br> &#39;[Zacari:]\n&#39;,<br> &#39;Oh, baby I want you\n&#39;,<br> &#39;Baby I need you\n&#39;,<br> &#39;I wanna see you\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I want you\n&#39;,<br> &#39;Baby I need you\n&#39;,<br> &#39;I wanna see you\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;All night (all night, all night)\n&#39;,<br> &#39;All night\n&#39;,<br> &quot;Your body&#39;s on fire\n&quot;,<br> &#39;And your drinks on ice\n&#39;,<br> &#39;All night (all night, all night)\n&#39;,<br> &#39;All night\n&#39;,<br> &quot;Your body&#39;s on fire\n&quot;,<br> &#39;And your drinks on ice\n&#39;,<br> &#39;[Babes Wodumo:]\n&#39;,<br> &#39;Oh my word oh my gosh oh my word (Oh my gosh)\n&#39;,<br> &#39;Oh my word oh my gosh oh my word (Oh my gosh)\n&#39;,<br> &#39;Oh my word oh my gosh oh my word (Oh my gosh)\n&#39;,<br> &#39;Oh my word oh my gosh oh my word (Oh my gosh)\n&#39;,<br> &#39;Everybody say kikiritikiki (kikiritikiki)\n&#39;,<br> &#39;Everybody say kikiritikiki (kikiritikiki)\n&#39;,<br> &#39;Everybody say kikiritikiki (kikiritikiki)\n&#39;,<br> &#39;Everybody say kikiritikiki (kikiritikiki)\n&#39;,<br> &quot;Ung&#39;bambe, ung&#39;dedele. Ung&#39;bhasobhe, ung&#39;gudluke\n&quot;,<br> &quot;Ung&#39;bambe, ung&#39;dedele. Ung&#39;bhasobhe, ung&#39;gudluke\n&quot;,<br> &quot;Ung&#39;bambe, ung&#39;dedele. Ung&#39;bhasobhe, ung&#39;gudluke\n&quot;,<br> &quot;Ung&#39;bambe, ung&#39;dedele. Ung&#39;bhasobhe, ung&#39;gudluke\n&quot;,<br> &#39;[Zacari:]\n&#39;,<br> &#39;Baby I want you\n&#39;,<br> &#39;Baby I need you\n&#39;,<br> &#39;I wanna see you\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I want you\n&#39;,<br> &#39;Baby I need you\n&#39;,<br> &#39;I wanna see you\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;All night (all night all night)\n&#39;,<br> &#39;All night\n&#39;,<br> &quot;Your body&#39;s on fire\n&quot;,<br> &#39;And your drinks on ice\n&#39;,<br> &#39;All night (all night all night)\n&#39;,<br> &#39;All night\n&#39;,<br> &quot;Your body&#39;s on fire\n&quot;,<br> &#39;And your drinks on ice\n&#39;,<br> &#39;[Kendrick Lamar:]\n&#39;,<br> &#39;(We go)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;High up (High up)\n&#39;,<br> &#39;[?]\n&#39;,<br> &#39;[Zacari:]\n&#39;,<br> &#39;Baby I want you\n&#39;,<br> &#39;Baby I need you\n&#39;,<br> &#39;I wanna see you\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I want you\n&#39;,<br> &#39;Baby I need you\n&#39;,<br> &#39;I wanna see you\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;Baby I wanna go out yeah\n&#39;,<br> &#39;All night (all night all night)\n&#39;,<br> &#39;All night\n&#39;,<br> &quot;Your body&#39;s on fire\n&quot;,<br> &#39;And your drinks on ice\n&#39;,<br> &#39;All night (all night all night)\n&#39;,<br> &#39;All night\n&#39;,<br> &quot;Your body&#39;s on fire\n&quot;,<br> &#39;And your drinks on ice\n&#39;]</pre><p>Before we can create a bag of words or vectorize each document, we need to clean it up and split each song into an array of individual words. Our goal is to tken</p><p>Consider the following sentences from the example above:</p><p>&quot;Two wrongs don&#39;t make us right away\n&quot;, &quot;Tell me something&#39;s wrong\n&quot;</p><p>After tokenization, this should look like:</p><p>[&#39;two&#39;, &#39;wrongs&#39;, &#39;dont&#39;, &#39;make&#39;, &#39;us&#39;, &#39;right&#39;, &#39;away&#39;, &#39;tell&#39;, &#39;me&#39;, &#39;somethings&#39;, &#39;wrong&#39;]</p><p>We need to remove punctuation and capitalization, so that all words will be counted correctly.</p><p>Before we tokenize our songs, we’ll do only a small manual bit of cleaning.</p><p>In the cell below, write a function to:</p><ul><li>remove lines that just contain [&#39;artist names&#39;]</li><li>join the list of strings into one big string for the entire song</li><li>remove newline characters \n</li><li>remove the following punctuation marks: &quot;,.&#39;?!()&quot;</li><li>make every word lowercase</li></ul><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/8d2f0ea74f6336f4d3df3e0b06ffc5d3/href">https://medium.com/media/8d2f0ea74f6336f4d3df3e0b06ffc5d3/href</a></iframe><pre>two wrongs dont make us right away  tell me somethings wrong  party all of our lives away  to take you on  oh baby i want you  baby i need you  i wanna see you  baby i wanna go out yeah  baby i wanna go out yeah  baby i want you  baby i need you  i wanna see you  baby i wanna go out yeah  baby i wanna go out yeah  all night all night all night  all night  your bodys on fire  and your drinks on ice  all night all night all night  all night  your bodys on fire  and your drinks on ice  oh my word oh my gosh oh my word oh my gosh  oh my word oh my gosh oh my word oh my gosh  oh my word oh my gosh oh my word oh my gosh  oh my word oh my gosh oh my word oh my gosh  everybody say kikiritikiki kikiritikiki  everybody say kikiritikiki kikiritikiki  everybody say kikiritikiki kikiritikiki  everybody say kikiritikiki kikiritikiki  ungbambe ungdedele ungbhasobhe unggudluke  ungbambe ungdedele ungbhasobhe unggudluke  ungbambe ungdedele ungbhasobhe unggudluke  ungbambe ungdedele ungbhasobhe unggudluke  baby i want you  baby i need you  i wanna see you  baby i wanna go out yeah  baby i wanna go out yeah  baby i want you  baby i need you  i wanna see you  baby i wanna go out yeah  baby i wanna go out yeah  all night all night all night  all night  your bodys on fire  and your drinks on ice  all night all night all night  all night  your bodys on fire  and your drinks on ice  we go  high up high up  high up high up  high up high up  high up high up  high up high up  high up high up  high up high up  high up high up  baby i want you  baby i need you  i wanna see you  baby i wanna go out yeah  baby i wanna go out yeah  baby i want you  baby i need you  i wanna see you  baby i wanna go out yeah  baby i wanna go out yeah  all night all night all night  all night  your bodys on fire  and your drinks on ice  all night all night all night  all night  your bodys on fire  and your drinks on ice</pre><p>Test this function on clean_test_song to ensure that the function works.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/2643f59bcdfc8bb5150a7f9254b3fc33/href">https://medium.com/media/2643f59bcdfc8bb5150a7f9254b3fc33/href</a></iframe><pre>[&#39;two&#39;,<br> &#39;wrongs&#39;,<br> &#39;dont&#39;,<br> &#39;make&#39;,<br> &#39;us&#39;,<br> &#39;right&#39;,<br> &#39;away&#39;,<br> &#39;tell&#39;,<br> &#39;me&#39;,<br> &#39;somethings&#39;]</pre><p>Great! Now that we can tokenize our songs, we can move onto vectorization. Count Vectorization</p><p>Machine Learning algorithms don’t understand strings. However, they do understand math, which means they understand vectors and matrices. By <strong><em>Vectorizing</em></strong> the text, we just convert the entire text into a vector, where each element in the vector represents a different word. The vector is the length of the entire vocabulary — usually, every word that occurs in the English language, or at least every word that appears in our corpus. Any given sentence can then be represented as a vector where all the vector is 1 (or some other value) for each time that word appears in the sentence.</p><p>Both of these are examples of <strong><em>Count Vectorization</em></strong>. They allow us to represent a sentence as a vector, with each element in the vector corresponding to how many times that word is used.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/5faba4f99764432475b68b7309c9c92b/href">https://medium.com/media/5faba4f99764432475b68b7309c9c92b/href</a></iframe><pre>{&#39;high&#39;: 16, &#39;ice&#39;: 6, &#39;drinks&#39;: 6, &#39;me&#39;: 1, &#39;somethings&#39;: 1, &#39;of&#39;: 1, &#39;gosh&#39;: 8, &#39;see&#39;: 6, &#39;everybody&#39;: 4, &#39;na&#39;: 18, &#39;lives&#39;: 1, &#39;tell&#39;: 1, &#39;dont&#39;: 1, &#39;wrong&#39;: 1, &#39;your&#39;: 12, &#39;need&#39;: 6, &#39;ungbhasobhe&#39;: 4, &#39;party&#39;: 1, &#39;ungbambe&#39;: 4, &#39;word&#39;: 8, &#39;you&#39;: 19, &#39;kikiritikiki&#39;: 8, &#39;all&#39;: 25, &#39;ungdedele&#39;: 4, &#39;on&#39;: 13, &#39;to&#39;: 1, &#39;yeah&#39;: 12, &#39;baby&#39;: 24, &#39;up&#39;: 16, &#39;wrongs&#39;: 1, &#39;go&#39;: 13, &#39;my&#39;: 16, &#39;right&#39;: 1, &#39;away&#39;: 2, &#39;take&#39;: 1, &#39;oh&#39;: 17, &#39;i&#39;: 30, &#39;unggudluke&#39;: 4, &#39;bodys&#39;: 6, &#39;say&#39;: 4, &#39;our&#39;: 1, &#39;want&#39;: 6, &#39;we&#39;: 1, &#39;and&#39;: 6, &#39;fire&#39;: 6, &#39;two&#39;: 1, &#39;us&#39;: 1, &#39;night&#39;: 24, &#39;make&#39;: 1, &#39;wan&#39;: 18, &#39;out&#39;: 12}</pre><p>Great! You’ve just successfully vectorized your first text document !</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b779c08de8a3" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How to do One hot encoding Tanzania Wells]]></title>
            <link>https://medium.com/@karaoglanahmet/how-to-do-one-hot-encoding-tanzania-wells-98efce9267dd?source=rss-3cf445372ae8------2</link>
            <guid isPermaLink="false">https://medium.com/p/98efce9267dd</guid>
            <dc:creator><![CDATA[AHMET KARAOGLAN]]></dc:creator>
            <pubDate>Sun, 21 Aug 2022 15:44:37 GMT</pubDate>
            <atom:updated>2022-08-21T15:44:37.810Z</atom:updated>
            <content:encoded><![CDATA[<h4>Data Understanding</h4><p>1- Import Standard packages</p><p>2- Merge datasets</p><p>3- Check data types</p><ul><li>df.info()</li></ul><p>4- Check for duplicates</p><ul><li>sum(df.duplicated())</li></ul><h4>Missing Values</h4><p>Clean datasets by removing similar and unnecessary columns and trim the dataset of remaining null values.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/84d6765540ee99bad5865bde7bc3b685/href">https://medium.com/media/84d6765540ee99bad5865bde7bc3b685/href</a></iframe><h4>Well Function map</h4><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/e33fc311e7f9e01a257ae8f8253b4766/href">https://medium.com/media/e33fc311e7f9e01a257ae8f8253b4766/href</a></iframe><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_8pXvuSkdZc6fpLqGpJS7A.png" /></figure><h3>Modeling</h3><h4>One Hot Encoding</h4><p>Encoding is useful to quantify categorical or otherwise qualitative data.We will be using one hot encoding for low cardinality features and ordinal encoding for our high cardinality features. We also use null value <a href="https://scikit-learn.org/stable/modules/generated/sklearn.impute.SimpleImputer.html">imputing</a> and <a href="https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.RobustScaler.html">standard scaling</a> on our data in order to clean it before we feed it to our model.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/d8d79677d79e63297bf028da2860b3a3/href">https://medium.com/media/d8d79677d79e63297bf028da2860b3a3/href</a></iframe><p>after target and perform train test split</p><ul><li>logistic Regression</li><li>K Nearest Neighbors</li><li>Decision Tree Model</li><li>Random Forests</li><li>XG Boost</li></ul><h4>Conclusion</h4><p>You can easily make models by converting categorical values to numeric variables.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=98efce9267dd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[What is Linear Regression ?]]></title>
            <link>https://medium.com/@karaoglanahmet/what-is-linear-regression-204935d029c9?source=rss-3cf445372ae8------2</link>
            <guid isPermaLink="false">https://medium.com/p/204935d029c9</guid>
            <dc:creator><![CDATA[AHMET KARAOGLAN]]></dc:creator>
            <pubDate>Tue, 22 Mar 2022 20:47:54 GMT</pubDate>
            <atom:updated>2022-03-22T20:50:42.520Z</atom:updated>
            <content:encoded><![CDATA[<h3>What is Linear Regression ?</h3><p>Linear regression quantifies the relationship between one or more predictor variable(s) and one outcome variable. Linear regression is common used for predictive analysis and modeling. For example, it can be used to quantify the relative impacts of age, gender, and diet(the predictor variables) on height (the outcome variables). Linear regression is also known as multiple regression, multivariate regression, ordinary least squares(OLS), and regression.</p><h3>Calculating Regression Coefficients: Slope and intercepts</h3><p>A straight line can be written as :</p><p>y = mx+c</p><p>or, alternatively</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*SJsDQIKiafr3QOCFQfCP2Q.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DG3z7vp7eJTd8D-k4-Oclw.png" /></figure><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/42d8aa5135f5b53f575812afc4d4d444/href">https://medium.com/media/42d8aa5135f5b53f575812afc4d4d444/href</a></iframe><figure><img alt="" src="https://cdn-images-1.medium.com/max/807/1*a2uUPF-2I3OnrE7Y_l0sMw.png" /></figure><p><strong>Write a Function cals_slope()</strong></p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/f20393c3c5a2a4d7386da2c3e6bae85d/href">https://medium.com/media/f20393c3c5a2a4d7386da2c3e6bae85d/href</a></iframe><p><strong>Write a function best_fit()</strong></p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/6b50df24fcf49eb895de816e727b7ca2/href">https://medium.com/media/6b50df24fcf49eb895de816e727b7ca2/href</a></iframe><p>We now have a working model with m and c as model parameters.</p><p><strong>Write a function reg_line()</strong></p><p>Write a function reg_line() that takes in slope, intercept and X vector and calculates the regression line using 𝑦=𝑚𝑥+𝑐 for each point in X</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/d1e33d8023c2a239fd17179f0210c669/href">https://medium.com/media/d1e33d8023c2a239fd17179f0210c669/href</a></iframe><p>Plot the (x, y) data points and draw the calculated regression line for visual inspector</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/a47204f9645a2a2784f76fa7c12ff5a2/href">https://medium.com/media/a47204f9645a2a2784f76fa7c12ff5a2/href</a></iframe><figure><img alt="" src="https://cdn-images-1.medium.com/max/776/1*I4KXGZ5BQupKVQKN9_7cXA.png" /></figure><p><strong>Summary</strong></p><p>You learned how to perform linear regression for data that are linearly related. you first calculated the slope and intercept parameters of the regression lie that best fit the data.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=204935d029c9" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Artificial Intelligence]]></title>
            <link>https://medium.com/@karaoglanahmet/artificial-intelligence-5b3e36038f36?source=rss-3cf445372ae8------2</link>
            <guid isPermaLink="false">https://medium.com/p/5b3e36038f36</guid>
            <dc:creator><![CDATA[AHMET KARAOGLAN]]></dc:creator>
            <pubDate>Thu, 23 Dec 2021 02:21:54 GMT</pubDate>
            <atom:updated>2021-12-23T02:21:54.452Z</atom:updated>
            <content:encoded><![CDATA[<p>Can we ever hope to understand the nature of intelligence in the same sense that we understand, say, the<br>nature of flight? Will our understanding of intelligence ever be. sufficient to help us build working<br>models — machines that think and perceive — in the same<br>way that our understanding of aerodynamics helps us<br>build airplanes? Intelligence seems so varied. We<br>see it when a chemist discovers the structure of a<br>complex molecule, when a computer plays chess, when<br>a mathematician finds a proof, and even when a child<br>walks home from school. Are there basic mechanisms<br>or processes that are common to all, of these activities and to all others commonly thought to require<br>intelligence?</p><blockquote>The structure of the field</blockquote><p>Basic mechanisms of intelligence and implementational techniques that are common to several applications, I call core topics. It seems to me that there are four major parts to this central core:</p><ul><li>Techniques for modeling and representation of knowledge.</li><li>Techniques for common sense reasoning, deduction, and problem solving.</li><li>Techniques for heuristic search.</li><li>AI systems and languages.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Owly4e05qqUunbVzhtQx6A.png" /></figure><p>ROBOTS</p><p>Every now and then, man gathers up whatever technology happens to be around and attempts to build robots. During the late 1960s, research on robots provided a central focus for integrating much of the AI technology. To build an intelligent robot is to build a model of man. Such a robot should have general reasoning ability, locomotive and manipulative skills, perceptual (especially visual) abilities, and facility with natural language. Thus, robot research is closely linked with several other applications areas.</p><p>Machine Vision</p><p>The ability to interpret visual images of the world is adequate enough even in some insects to guide many complex behavior patterns. Yet the analysis of everyday visual scenes by machine still remains a largely unconquered challenge to AI researchers. Early work concentrated almost exclusively on designing systems that could classify two-dimensional images into a small number of categories — alphanumeric character recognition, for example. In fact, much of the AI work during the 1950s was concerned with pattern recognition. Researchers, such as Frank Rosenblatt and Oliver Selfridge, were influential in shaping this early period. Pattern classification (or recognition) continues as a separate active research interest, but since about 1965, AI interest in vision has centered on the more difficult problem of interpreting and describing complex three-dimensional scenes. Both aspects, classification and description, are thoroughly and clearly treated in an excellent textbook by Duda and Hart (1973).</p><p>Natural language systems</p><p>The system demonstrates its understanding of the last two commands by having a simulated robot arm carry out appropriate actions in a simulated blocks world. The work of Schank (1972) typifies a rather successful trend in natural language understanding. Many of the recent systems, in one way or another, attempt to match a section of input text or utterance against semantically likely stored structures (that are more or less complex.) These structures are themselves schemas or scenario families having variables that are bound to constants in the input during matching. The instantiated scenarios serve as a sort of deep structure that represent the meaning of the utterance. [See also Minsky (1974).</p><p>CONCLUSIONS</p><p>In summary, we see that the AI campaign is being waged on several different fronts, and that the victories, as well” as the setbacks, contribute to a growing common core of ideas that aspires to be a science of Intelligence. Against this background, it is worth mentioning some of the popular criticisms of A</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5b3e36038f36" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>