Marta Bralic Kerns’ Post

Dear data connections, 👋 Have you ever wondered what to include in your CV? 🤔 Are you seeking insights into valuable projects to enhance your resume? 📊 Look no further! I recommend reading the article titled “Four Data Engineering Projects That Look Great on your CV” by Mike Shakhomirov. 👇 #dataengineer #dataanalyst #datascientist #hiring #analytics #haysrecruitment #haysmalaysia

What are the challenges of working with geospatial data in data science? Working with geospatial data in data science presents several challenges that data scientists need to address: 1. Data volume and complexity: Geospatial data can be vast and complex, consisting of multiple layers, attributes, and formats. Managing and processing such large-scale data requires specialized tools, algorithms, and infrastructure to handle the volume and complexity effectively. 2. Spatial and temporal dependencies: Geospatial data often exhibits spatial and temporal dependencies, where observations in proximity or over time are correlated. Accounting for these dependencies is crucial to avoid biased analysis and ensure accurate modeling. 3. Data integration and interoperability: Geospatial data comes from diverse sources and formats, making data integration and interoperability challenging. Harmonizing and integrating data from different providers or formats requires careful consideration of spatial reference systems, data resolution, and attribute matching. 4. Spatial analysis techniques: Geospatial data requires the use of specialized spatial analysis techniques such as spatial interpolation, geostatistics, spatial clustering, and network analysis. Data scientists need to have a strong understanding of these techniques and their appropriate application in geospatial analysis. 5. Visualization and interpretation: Geospatial data visualization is crucial to understand patterns, trends, and relationships. However, effectively visualizing and interpreting geospatial data can be challenging due to the intrinsic spatial nature of the data. Choosing appropriate visualization techniques and effectively communicating the insights to non-technical stakeholders is essential. 6. Privacy and security: Geospatial data often contains sensitive information related to location or individuals. Ensuring privacy and security while working with geospatial data requires careful consideration of data anonymization, access controls, and compliance with relevant regulations. Addressing these challenges requires a combination of domain knowledge, expertise in geospatial analysis techniques, and the use of specialized tools and technologies that support geospatial data processing, analysis, and visualization. Do you need help writing your resume/CV, cover letter or optimizing your LinkedIn profile? Contact me now. Let us do this! Visit my website: www.yourresumeexpert.com #resume #resumewriting #resumewritingservices #cv #cvwriting #cvwritingservices #linkedinprofile #linkedinprofileoptimization #jobsearch #jobopportunity #jobvacancy #jobinterview #jobsearching #careergrowth #careerdevelopment #careeropportunities #interview #softwareengineerresume #datascience #dataanalyst #computerscience #executiveresumes

🚀 Day 2 of 30-day Challenge 🚀 Today's task: Finding Facebook pages with zero likes. This challenge is all about mastering joins and nested queries to extract meaningful insights. 💻Title: Page with no likes 💻 Company: Facebook 💻Level: Easy Link to the question: https://lnkd.in/da-4MvE6 Join me on this journey and share your favorite SQL tips or questions! #30daysSQLChallenge #SQL #DataScience #CareerGrowth #JobInterviews #TechSkills #upskilling #job #opentowork #DataAnalyst #analyst #skills #linkedin #linkedindaily #linkedinpost #linkedinforcontentcreators #softwaredeveloper #engineering

#SAS Interview Question Problem Statement : Your code has run time of 20 hours, state how will you optimise this code to reduce its run time with explanation for each step. Solution : Here’s the list of steps with explanation : 1. Efficient Data Management Filter Early: Use WHERE statements to filter data early in the process to reduce the number of observations processed. Keep Only Needed Variables: Use KEEP= or DROP= to limit the number of variables being processed. Sort Only When Necessary: Avoid unnecessary sorting; use indexed datasets instead. Indexing: Create indexes on variables used in frequent WHERE clauses or joins. 2. Optimize I/O Operations Minimize Data Reads/Writes: Use DATA _NULL_ if you don’t need to create datasets. Compress Datasets: Use COMPRESS=YES for large datasets to reduce disk I/O. Temporary Libraries: Use WORK library for intermediate datasets to avoid writing to disk. 3. Efficient Code Structure Avoid Loops on Large Datasets: Use vectorized operations or SQL instead of data step loops. Use SQL Smartly: For large joins, ensure proper indexing and avoid Cartesian joins. Combine Steps: Combine multiple DATA steps if possible. 4. Parallel Processing Multithreading: Use the THREADS option with procedures like PROC SORT or PROC SQL. Distribute Work: Split datasets into chunks and process them in parallel. 5. Use Efficient Procedures Use procedures designed for large datasets, e.g., PROC MEANS instead of DATA step for summarizations. 6. Review and Debug Code Eliminate Redundancies: Remove unnecessary joins, merges, or calculations. 7. External Tools and Techniques Database Processing: Push processing to the database using PROC SQL with CONNECT TO database. Use Hash Tables: For in-memory lookups instead of merges. ** Remember these are not all the steps and need not be used in every code. It all depends on the business requirements. Do share how you optimize your code in the comment section. #analytics #dataanalyst #datascience #opentowork #dataanalytics

What are the challenges of working with geospatial data in data science? Working with geospatial data in data science presents several challenges: - Data Volume: Geospatial data can be vast and high-resolution, requiring efficient storage, processing, and analysis techniques. - Data Integration: Geospatial data often comes from diverse sources and formats, requiring appropriate data integration and alignment for meaningful analysis. - Spatial Heterogeneity: Geospatial data exhibits spatial variability and heterogeneity, necessitating spatial statistics and modeling techniques to capture meaningful patterns. - Spatial Autocorrelation: Geospatial data often exhibits spatial autocorrelation, where nearby locations are more similar than distant ones, requiring specialized statistical methods. - Data Quality: Geospatial data may suffer from inaccuracies, errors, and missing values due to collection methods, sensor limitations, or data transformations. - Coordinate Systems: Dealing with different coordinate systems and projections requires careful handling and conversion to ensure accurate geospatial analysis and integration. - Scale and Resolution: Geospatial data may have varying scales and resolutions, requiring appropriate spatial aggregation or disaggregation techniques for analysis. - Spatial Interpolation: Estimating values at unobserved locations poses challenges, necessitating spatial interpolation methods to fill data gaps. - Computational Complexity: Geospatial analysis involves complex algorithms and calculations, demanding computational resources and efficient algorithms for scalability. - Interpretation and Visualization: Geospatial data visualization and interpretation require specialized techniques to effectively communicate spatial patterns and insights to stakeholders. Do you need help writing your resume/CV, cover letter or optimizing your LinkedIn profile? Contact me now. Let us do this! Visit my website: www.yourresumeexpert.com #resume #resumewriting #resumewritingservices #cv #cvwriting #cvwritingservices #linkedinprofile #linkedinprofileoptimization #jobsearch #jobopportunity #jobvacancy #jobinterview #jobsearching #careergrowth #careerdevelopment #careeropportunities #interview #softwareengineerresume #datascience #dataanalyst #computerscience #executiveresumes

Interviewer: What are your day-to-day activities as a Data Engineer in your current role? Candidate:  - Check-in with the team for 15-30 minutes to review progress and issues. - Review work completed by other team members to ensure it meets best practices and functions correctly. - Meet ad-hoc with individuals to address any bugs or blockers. - Write, test, and run code and algorithms on the data to ensure they run correctly. - Plan tasks for the team for the upcoming days and weeks and review decisions with management. Reality: "I've retriggered this pipeline, and it's now working fine. I'm currently working on this and will provide an update by EOD." Other: "Hello, can you hear me? Am I audible?" 🤣😂 #dataengineer #dataengineering #pun #interview #AzureDataEngineer

How can data scientists handle data imputation in missing data scenarios? Data scientists employ various techniques to handle data imputation in missing data scenarios. Here are some commonly used approaches: 1. Mean/median imputation: Missing values are replaced with the mean or median of the available data for that variable. This method is simple but may distort the distribution of the variable. 2. Regression imputation: A regression model is built using other variables as predictors to estimate missing values. The predicted values are then used to impute the missing data. 3. Multiple imputation: This approach involves creating multiple plausible imputed datasets based on the observed data and their relationships. Statistical techniques are used to combine the results and obtain a final imputed dataset. 4. K-nearest neighbors (KNN) imputation: Missing values are imputed by taking the average of the nearest neighbors based on other variables. This method uses similarity measures to identify the most similar records. 5. Expectation-Maximization (EM) algorithm: This iterative algorithm estimates missing values by maximizing the likelihood of the observed data. It iteratively imputes missing values based on initial estimates. It's important for data scientists to carefully consider the characteristics of the data and choose an appropriate imputation method based on the nature of the missingness and the specific requirements of the analysis. Do you need help writing your resume/CV, cover letter or optimizing your LinkedIn profile? Contact me now. Let us do this! Visit my website: www.yourresumeexpert.com #resume #resumewriting #resumewritingservices #cv #cvwriting #cvwritingservices #linkedinprofile #linkedinprofileoptimization #jobsearch #jobopportunity #jobvacancy #jobinterview #jobsearching #careergrowth #careerdevelopment #careeropportunities #interview #softwareengineerresume #datascience #dataanalyst #computerscience #executiveresumes

📢Recruiters and candidates in DATA, we need your help! - DATA Job Project👥   "Alone we go faster, together we go further." As part of our new #data project within the Wild Code School, my team, consisting of Anissa KACEM, Quentin Loumeau, Terry Cornelusse, and myself, is conducting a study on the recruitment sector in data. To assist us, all you need to do is complete the questionnaire below. 📝 Recruiters ➡️ https://lnkd.in/eYshsCcY Candidates ➡️ https://lnkd.in/eQwkEFzY This will enable us to carry out a detailed analysis of the market and create a powerful and robust machine learning model that will allow our future application to recommend jobs that best match your profile or the ideal candidate for your job offer. If you wish, we can also send you the results of this study later on. Please don't hesitate to like👍, share 🗣️ , and tag anyone who might be able to help us in the comments📝. Thank you and see you soon! #Data #Job #DataJob #DataRecruitment #Recruitment #DataAnalyst #DataScientist #DataEngineer #ProductOwnerData #TalentAcquisition #HeadOfData #LeadData #HM #HumanRessource

Interview Questions Recently Faced by One of My Connections at an MNC for a Data Analyst Role:- Question :- Differences between 'ALL' and 'ALLSELECTED' in DAX ? Explanation:- ALL:- 1.Ignores Filters: Removes all filters from the specified columns or tables. 2. Global Scope: Affects the entire data set, regardless of any filters applied in the current context. 3.Use Case: Useful when you want to perform calculations on the entire dataset without considering any filters. ALLSELECTED 1.Respects Initial Filters: Removes filters, but only those applied within the current query context, keeping the initial context filters. 2.Partial Scope: Affects the data set within the current visual or context, considering the initial selection. 3.Use Case: Useful when you want to perform calculations considering the user's initial filter selections but ignoring any additional filters applied later. Please share any interview questions you have encountered in the comments section so we can help each other prepare better! Hope everyone understood 🤞! 👉𝐑𝐞𝐟𝐞𝐫𝐫𝐚𝐥𝐬/𝐑𝐞𝐬𝐨𝐮𝐫𝐜𝐞𝐬:: : https://lnkd.in/gcw-ziZm MADHU THANGELLA connect with me for more updates !

📢Recruiters and candidates in DATA, we need your help! - DATA Job Project👥 "Alone we go faster, together we go further." As part of our new #data project within the Wild Code School, my team, consisting of Anissa KACEM, Loïc Copin, Terry Cornelusse, and myself, is conducting a study on the recruitment sector in data. To assist us, all you need to do is complete the questionnaire below. 📝 Recruiters ➡️ https://lnkd.in/eYshsCcY Candidates ➡️ https://lnkd.in/eQwkEFzY This will enable us to carry out a detailed analysis of the market and create a powerful and robust machine learning model that will allow our future application to recommend jobs that best match your profile or the ideal candidate for your job offer. If you wish, we can also send you the results of this study later on. Please don't hesitate to like👍, share 🗣️ , and tag anyone who might be able to help us in the comments📝. Thank you and see you soon! hashtag #Data #Job #DataJob #DataRecruitment #Recruitment #DataAnalyst #DataScientist #DataEngineer #ProductOwnerData #TalentAcquisition #HeadOfData #LeadData #HM #HumanRessource