Data Analytics Projects - SQL, Excel, Tableau, Python & Power BI Interview Resources

Feature Scaling is one of the most useful and necessary transformations to perform on a training dataset, since with very few exceptions, ML algorithms do not fit well to datasets with attributes that have very different scales. Let's talk about it 🧵 There are 2 very effective techniques to transform all the attributes of a dataset to the same scale, which are: ▪️ Normalization ▪️ Standardization The 2 techniques perform the same task, but in different ways. Moreover, each one has its strengths and weaknesses. Normalization (min-max scaling) is very simple: values are shifted and rescaled to be in the range of 0 and 1. This is achieved by subtracting each value by the min value and dividing the result by the difference between the max and min value. In contrast, Standardization first subtracts the mean value (so that the values always have zero mean) and then divides the result by the standard deviation (so that the resulting distribution has unit variance). More about them: ▪️Standardization doesn't frame the data between the range 0-1, which is undesirable for some algorithms. ▪️Standardization is robust to outliers. ▪️Normalization is sensitive to outliers. A very large value may squash the other values in the range 0.0-0.2. Both algorithms are implemented in the Scikit-learn Python library and are very easy to use. Check below Google Colab code with a toy example, where you can see how each technique works. https://colab.research.google.com/drive/1DsvTezhnwfS7bPAeHHHHLHzcZTvjBzLc?usp=sharing Check below spreadsheet, where you can see another example, step by step, of how to normalize and standardize your data. https://docs.google.com/spreadsheets/d/14GsqJxrulv2CBW_XyNUGoA-f9l-6iKuZLJMcc2_5tZM/edit?usp=drivesdk Well, the real benefit of feature scaling is when you want to train a model from a dataset with many features (e.g., m > 10) and these features have very different scales (different orders of magnitude). For NN this preprocessing is key. Enable gradient descent to converge faster

I’ve heard most people today are out of ideas for their pivot data science project. You have to try these out! Save this post if you’re in a hurry! 5 data science projects that will make your portfolio explode: - Social Media Account Recommendation System Build a recommendation system using user data to suggest relevant social media accounts. This project demonstrates skills in data analysis, collaborative filtering, and machine learning techniques. - Dynamic Pricing Strategy for Airline Seat Booking Create a pricing model that adjusts airline ticket prices based on demand, time, and other factors. This project highlights dynamic pricing strategies, predictive modeling, and optimization algorithms. https://www.kaggle.com/code/abhishekmungoli/dynamic-pricing-to-fill-slots/notebook - Music Genre Classification Use audio features like tempo, rhythm, and frequency to classify songs into genres with machine learning models. This project focuses on feature extraction, data preprocessing, and supervised learning techniques. https://github.com/jsalbert/Music-Genre-Classification-with-Deep-Learning - spaCy Resume Analysis Develop a resume parser that extracts key details (skills, experience) using spaCy's NLP models. This project showcases natural language processing, text analysis, and automation of data extraction. https://deepnote.com/app/abid/spaCy-Resume-Analysis-81ba1e4b-7fa8-45fe-ac7a-0b7bf3da7826 - Personality Prediction Predict a person's personality traits based on textual data using machine learning models. This project involves NLP, data preprocessing, feature extraction, and classification techniques. https://www.kaggle.com/code/abhijitsingh001/mbti-test-your-personality Join for more: https://t.me/sqlproject

A Comprehensive Guide to Mastering Data Science 👇👇 https://datasimplifier.com/data-scientists-study-plan/

Python Top 10 Interview Questions for Freshers 👇👇 https://medium.com/@data_analyst/python-top-10-interview-questions-for-freshers-9937ed74c0a7

📌COMMON SQL INTERVIEW QUESTIONS TO PREPARE FOR: Q1. Tell me about yourself and why you want this position? Q2. What is SQL? Q3. Why do you want to work for our company in this SQL position? Q4. What is MySQL? Q5. What’s the main difference between SQL and MySQL? Q6. In SQL, what are ‘JOINS’? Q7. What is an INDEX, and why is it useful to have? Q8. What personality will you bring to the team? Q9. If a ‘constraint’ is added in SQL, what does this mean? Q10. What are the more common types of SQL constraint and what do they mean? Q11. So far, you have referred to TABLES and FIELDS in your answers. What are they? Q12. What’s your biggest weakness? Q13. Tell me what the different subsets of SQL are? Q14. It’s 5pm on a Friday and you receive a request from a stakeholder who says it’s urgent. You assess the task and it will take approximately one hour to complete. What would you do? Q15. How would you format SQL server dates? Q16. What is primary and foreign key? Q17. Why do you want to leave your current job? Q18. What is database denormalization? Q19. What is database normalization? Q20. What are your salary expectations in this SQL position? Q21. In SQL, what is a subquery? Q22. What happens to the data rows in a table when the table contains a clustered index? Q23. That’s the end of your SQL interview. Do you have any questions for the panel? Checklist for Data Analyst: https://dataanalytics.beehiiv.com/p/data I have curated best 80+ top-notch Data Analytics Resources 👇👇 https://topmate.io/analyst/861634 Like for more Interview Resources ♥️ Hope it helps :)

🎓 Difference Between IFNULL and COALESCE in SQL If you’ve worked with missing values in a database, you’ve probably come across #IFNULL and #COALESCE. At first glance, they seem to do the same thing, but let’s break down their differences. 👇 💡 IFNULL takes two arguments. If the first argument is #NULL, it returns the second. If the first argument is not NULL, it returns the first value. 📌 Example:

IFNULL(salary, 0) — returns 0 if salary is NULL, otherwise returns salary.

💡 COALESCE is more powerful. It takes multiple arguments and returns the first non-`NULL` value in the list. 📌 Example:

COALESCE(salary, bonus, 0) — returns the first non-`NULL` value starting with salary. If all are NULL, it returns 0.

🔍 Key Differences: - IFNULL only works with two arguments. - COALESCE can handle multiple arguments and returns the first non-`NULL` one. #sql #database #dataanalyst

Python Project 🔥👇 Found one of the Best Project to do in Python for Data Analytics or Data Science 👇👇👇 Sales Data Analysis Project using Pandas 👇👇

Creating a data science portfolio is a great way to showcase your skills and experience to potential employers. Here are some steps to help you create a strong data science portfolio: 1. Choose relevant projects: Select a few data science projects that demonstrate your skills and interests. These projects can be from your previous work experience, personal projects, or online competitions. 2. Clean and organize your code: Make sure your code is well-documented, organized, and easy to understand. Use comments to explain your thought process and the steps you took in your analysis. 3. Include a variety of projects: Try to include a mix of projects that showcase different aspects of data science, such as data cleaning, exploratory data analysis, machine learning, and data visualization. 4. Create visualizations: Data visualizations can help make your portfolio more engaging and easier to understand. Use tools like Matplotlib, Seaborn, or Tableau to create visually appealing charts and graphs. 5. Write project summaries: For each project, provide a brief summary of the problem you were trying to solve, the dataset you used, the methods you applied, and the results you obtained. Include any insights or recommendations that came out of your analysis. 6. Showcase your technical skills: Highlight the programming languages, libraries, and tools you used in each project. Mention any specific techniques or algorithms you implemented. 7. Link to your code and data: Provide links to your code repositories (e.g., GitHub) and any datasets you used in your projects. This allows potential employers to review your work in more detail. 8. Keep it updated: Regularly update your portfolio with new projects and skills as you gain more experience in data science. This will show that you are actively engaged in the field and continuously improving your skills. By following these steps, you can create a comprehensive and visually appealing data science portfolio that will impress potential employers and help you stand out in the competitive job market.

😂😂

Free Datasets to practice data science projects 1. Enron Email Dataset Data Link: https://www.cs.cmu.edu/~enron/ 2. Chatbot Intents Dataset Data Link: https://github.com/katanaml/katana-assistant/blob/master/mlbackend/intents.json 3. Flickr 30k Dataset Data Link: https://www.kaggle.com/hsankesara/flickr-image-dataset 4. Parkinson Dataset Data Link: https://archive.ics.uci.edu/ml/datasets/parkinsons 5. Iris Dataset Data Link: https://archive.ics.uci.edu/ml/datasets/Iris 6. ImageNet dataset Data Link: http://www.image-net.org/ 7. Mall Customers Dataset Data Link: https://www.kaggle.com/shwetabh123/mall-customers 8. Google Trends Data Portal Data Link: https://trends.google.com/trends/ 9. The Boston Housing Dataset Data Link: https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html 10. Uber Pickups Dataset Data Link: https://www.kaggle.com/fivethirtyeight/uber-pickups-in-new-york-city 11. Recommender Systems Dataset Data Link: https://cseweb.ucsd.edu/~jmcauley/datasets.html Source Code: https://bit.ly/37iBDEp 12. UCI Spambase Dataset Data Link: https://archive.ics.uci.edu/ml/datasets/Spambase 13. GTSRB (German traffic sign recognition benchmark) Dataset Data Link: http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset Source Code: https://bit.ly/39taSyH 14. Cityscapes Dataset Data Link: https://www.cityscapes-dataset.com/ 15. Kinetics Dataset Data Link: https://deepmind.com/research/open-source/kinetics 16. IMDB-Wiki dataset Data Link: https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/ 17. Color Detection Dataset Data Link: https://github.com/codebrainz/color-names/blob/master/output/colors.csv 18. Urban Sound 8K dataset Data Link: https://urbansounddataset.weebly.com/urbansound8k.html 19. Librispeech Dataset Data Link: http://www.openslr.org/12 20. Breast Histopathology Images Dataset Data Link: https://www.kaggle.com/paultimothymooney/breast-histopathology-images 21. Youtube 8M Dataset Data Link: https://research.google.com/youtube8m/

We are now on quora as well, follow for free resources related to data analytics 👇👇 https://dataanalyticsprojects.quora.com

To transition from Data Analyst ➡️ Data Scientist, you will have to focus on building relevant projects! 🎯 ✅ Predictive Analytics Project → Built a model to predict customer behaviour by analyzing past purchase patterns and used time series forecasting to predict future trends. ✅ Sentiment Analysis using NLP → Developed a sentiment analysis model that categorized customer feedback into positive, neutral, and negative sentiments to improve products. ✅ Personalized Recommendation Engine → Created a recommendation engine using collaborative and content-based filtering to give personalized suggestions based on user’s browsing history and preferences. Tailor every project to focus on business impact and user experience, which can help you stand out to recruiters. 💪🏻

Here are the top 3 projects that you may include in data portfolio 📌 Churn prediction for subscription-based services Why I chose It: Highlighted my ability to turn data into actionable business insights while improving customer retention. 📌 Predictive maintenance for manufacturing equipment Why I chose It: Showcased my skills in handling time-series data and building scalable solutions in real-time environments. 📌 Fraud detection system for E-commerce transactions Why I chose It: Highlighted my ability to solve complex, high-stakes problems with machine learning and integrate models into production systems. When creating these projects, I focused on two things: solving real business problems and showcasing my technical skills. 🧑🏻‍💻

Easy free dataset for data analysis projects: Scrape Wikipedia tables using pandas (read_html) OR Power Query (Excel/PowerBI) Get Data -> From Web. There are 58,932,188 pages to choose from. Take your pick.

How to present your data analytics project to client/hiring manager? Today, I want to walk you through the importance of effectively communicating project details to business people or hiring managers! Specifically as a freelancer data analyst. LET'S GET STARTED 👇 So, I was working on a data analytics project for a potential client to do sales analysis for their retail store! I've spent countless hours in collecting data, cleaning the data, building data models, and finally generate the insights. Is your job done? NO, HERE COMES THE MOST IMPORTANT PART It's time to present your project to the client and convince them to hire you. But, how do you effectively communicate your project's value & complexity to non-technical stakeholders? Here are the strategies to overcome 👇 ↪️ Simplify your language: - Avoid using technical jargon and focus on the project's business outcomes you extracted. ↪️ Use visualizations: - Showcase your best findings through interactive dashboards, charts, and graphs. ↪️ Highlight the benefits: - Emphasize how your project will solve the client's problems and explain how you help business grow. ↪️ Tailor a story: - Use narratives to make your project more relatable and memorable. ↪️ Showcase your expertise: - Confidently highlight your skills and experience in data analytics. CALL TO ACTION 🎬 To grab the opportunity effective communication is key to winning clients and growing your chances of freelance service's By simplifying your language in simple terms, using visualizations, highlighting benefits, telling stories, and showcasing expertise. You'll be well on your way to crafting compelling project presentations that drive results. Always remember, it's not just about showcasing your technical skills, but about demonstrating the value you can bring to clients and hiring managers! 🤝 SO, GO AHEAD AND PITCH PERFECT! 🔊 I have curated best 80+ top-notch Data Analytics Resources 👇👇 https://topmate.io/analyst/861634 Like if it helps 😄

This is a very COMMON issue that I observe in the projects of aspiring candidates They download a DATASET from Kaggle or any other website Export it to a Data Analysis TOOL And START the project with data cleaning After cleaning the data, they PLUG it into a dashboard In the dashboard, they put EVERY column into the visuals Also they APPLY the filters of top/bottom 10 Once done, they crack their KNUCKLES And put this project in a list of SUCCESSFULLY completed projects Over time, I have REVIEWED so many portfolio projects And I see this ISSUES almost every time When I go to their portfolio, for every project there is a DASHBOARD But WHAT should I do after seeing a dashboard? What is it trying to SAY? What should I do after SEEING top or bottom 10 cities, states or products? Every dashboard lacks CONTEXT And why NOT? Because they DON'T even know the business problem or problem statement So the dashboard you created is of NO use Your job is not just to create DASHBOARDS Your job would be to create DASHBOARDS to take out important INSIGHTS And from those insights, you will build RECOMMENDATIONS And these recommendations will be given to stakeholders as a SOLUTION to their business problem If they implemented your IDEAS and the problem gets solved Now you can say your work is DONE If you are SHOWING bottom 10 states, then what? You should write the INSIGHTS too For example, the sales of North India zone are FALLING The insights can be used like this Delhi that used to be in TOP 5 states is now in the BOTTOM 10 states And this might be the REASON why our North India sales are DROPPING so hard This is just a RANDOM example showing how your charts become UNDERSTANDABLE Well, everyone can EXTRACT insights from charts Even a KID can do this after looking at the tallest and smallest bar The real task is to give RECOMMENDATIONS to solve the BUSINESS problem And I have NEVER seen this in anyone's portfolio If you are doing this, then you are easily STANDING out in the crowd In my PORTFOLIO, I used to keep business problem, insights, dashboard and recommendations Even in the bullet point of projects in my resume, I included RECOMMENDATIONS Now this is what you can call a STRONG portfolio Because your analysis skills are the SAME as those used in the real life by a Data Analyst I have curated best 80+ top-notch Data Analytics Resources 👇👇 https://topmate.io/analyst/861634 Like if it helps 😄

If you are targeting your first Data Analyst job then this is why you should avoid guided projects The common thing nowadays is "Coffee Sales Analysis" and "Pizza Sales Analysis" I don't see these projects as PROJECTS But as big RED flags We are showing our SKILLS through projects, RIGHT? Then what's WRONG with these projects? Don't think from YOUR side Think from the HIRING team's side These projects have more than a MILLION views on YouTube Even if you consider 50% of this NUMBER Then just IMAGINE how many aspiring Data Analysts would have created this same project Hiring teams see hundreds of resumes and portfolios on a DAILY basis Just imagine how many times they would have seen the SAME titles of projects again and again They would know that these projects are PUBLICLY available for EVERYONE You have simply copied pasted the ENTIRE project from YouTube So now if I want to hire a Data Analyst then how would I JUDGE you or your technical skills? What is the USE of Pizza or Coffee sales analysis projects for MY company? By doing such guided projects, you are involving yourself in a big circle of COMPETITION I repeat, there were more than a MILLION views So please AVOID guided projects at all costs Guided projects are good for your personal PRACTICE and LinkedIn CONTENT But try not to involve them in your PORTFOLIO or RESUME I have curated best 80+ top-notch Data Analytics Resources 👇👇 https://topmate.io/analyst/861634 Like if it helps 😄