Introduction to Machine Learning - From DBA's to Data Scientists - OGBEMEA
0 likes208 views
The document discusses the evolution of database administrators (DBAs) transitioning to data scientists through the implementation of autonomous databases and machine learning. It highlights the roles, tasks, and innovations in data management that enable organizations to leverage analytics for improved decision-making and predictive capabilities. Additionally, it outlines various machine learning methodologies, use cases, and the benefits of integrating these technologies into enterprise data workflows.
Introduction to Machine Learning - From DBA's to Data Scientists - OGBEMEA
- 1. VP AIOps for the Autonomous Database Sandesh Rao From DBA’s to Data Scientists Introduction to Machine Learning @sandeshr https://www.linkedin.com/in/raosandesh/ https://www.slideshare.net/SandeshRao4
- 2. Tasks Specific to Business and Innovation • Architecture, planning, data modeling • Data security and lifecycle management • Application related tuning • End-to-End service level management Maintenance Tasks • Configuration and tuning of systems, network, storage • Database provisioning, patching • Database backups, H/A, disaster recovery • Database optimization Traditionally DBAs are Responsible for: Value Scale Innovation Maintenance
- 3. Tasks Specific to Business and Innovation • Architecture, planning, data modeling • Data security and lifecycle management • Application related tuning • End-to-End service level management Maintenance Tasks • Configuration and tuning of systems, network, storage • Database provisioning, patching • Database backups, H/A, disaster recovery • Database optimization Freedom from Drudgery for DBA: More Time to Innovate and Improve the Business Autonomous Database Removes Generic Tasks Value Scale Innovation Maintenance
- 4. Machine Learning Solving data-driven problems Discovering insights Making predictions Data Security Data classification, Data life-cycle mgmt Application Tuning SQL tuning, connection mgmt The Evolution of the DBA/Database Developer Role Data Engineer Architecture, “data wrangler”
- 5. Data extraction Data wrangling Deriving new attributes (“feature engineering”) … … … Import predictions & insights Translate and deploy ML models Automate You Are Probably Already Doing Most of This Work! Database Developer to Data Scientist Journey 1 - https://www.infoworld.com/article/3228245/data-science/the-80-20-data-science-dilemma.html Typically 80% of the work Most data scientists spend only 20 percent of their time on actual data analysis and 80 percent of their time finding, cleaning, and reorganizing huge amounts of data, which is an inefficient data strategy1 Eliminated or minimized with Oracle Data Management platform becomes combine/hybrid DM + machine learning platform
- 6. Albert Einstein “If I had an hour to solve a problem I'd spend 55 minutes thinking about the problem and 5 minutes thinking about solutions.”
- 7. Lots of Data needs to be crunched • No time to manually sift through the data Machine Learning has become accessible • Software and algorithms are available • Frameworks allow for massive training with no coding • CI/CD available for MLOps • It’s not the algorithm you need to know about !! Business use cases - Find the use cases for maximum impact Why Machine Learning is important
- 8. Analytics Value vs. Maturity Reports & Dashboards Data Information Predictions & Insights Appls with ML Analytical Maturity ValueofAnalytics Diagnostic Analysis & Reports Predictive / Machine Learning “ML Enabled” Applications What Happened? Why it Happened? What WILL happen? Automated ML Appls
- 9. Database Developer to Data Scientist Journey
- 10. ML Project Workflow Set the business objectives Gather compare and clean data Identify and extract features (important columns) from imported data This helps us identify the efficiency of the algorithm Take the input data which is also called the training data and apply the algorithm to it For the algorithm to function efficiently, it is important to pick the right value for hyper parameters (algorithm input parameters to the algorithm) Once the training data in the algorithm are combined we get a model 1 2 3 4 5
- 11. Types of Machine Learning Supervised Learning Predict future outcomes with the help of training data provided by human experts Semi-Supervised Learning Discover patterns within raw data and make predictions, which are then reviewed by human experts, who provide feedback which is used to improve the model accuracy Unsupervised Learning Find patterns without any external input other than the raw data Reinforcement Learning Take decisions based on past rewards for this type of action
- 12. TIME SERIES Temporal Aspect Hitting a threshold Forecasting energy use Seasonality of data
- 13. Algorithms automatically sift through large amounts of data to discover hidden patterns, new insights and make predictions What is Machine Learning? Identify most important factor (Attribute Importance) Predict customer behavior (Classification) Find profiles of targeted people or items (Classification Predict or estimate a value (Regression) Segment a population (Clustering) Find fraudulent or “rare events” (Anomaly Detection) Determine co-occurring items in a “basket” (Associations)X1 X2 A1A2A3A4 A5A6 A7 SupervisedLearningUnsupervisedLearning Copyright © 2020 Oracle and/or its affiliates.
- 14. Machine Learning Algorithms • Multiple Regression, Support Vector Machine, Linear Model, LASSO, Random Forest, Ridge Regression, Generalized Linear Model, Stepwise Linear Regression Regression Association & Collaborative Filtering Reinforcement Learning - brute force, Monte Carlo, temporal difference.... • Many different use cases Neural network & deep Learning with Deep Neural Network • Hierarchical k-means, Orthogonal Partitioning Clustering, Expectation- Maximization Clustering Feature Extraction/Attribute Importance / Component Analysis • Decision Tree, Naive Bayes, Random Forest, Logistic Regression, Support Vector Machine Classification
- 15. What is Workload Automatically check workload for past x mins Decide if workload is abnormally high Highlight any abnormal workload issues Optionally run on demand Optionally snooze checking of a component Calculated via machine learning
- 16. Prediction (Every 5 minutes) 5 X 1 min metrics captured for each dimension & ASH report captured for later analysis Metrics evaluated by the primary model to determine if there are anomalies If there is no primary model (i.e. <7 days of data or <=95% model confidence) then SME rules are used for anomaly detection Each anomaly is compared against the SME rules to determine which dimension it applies to Any anomalies are raised along with recently captured ASH report
- 17. Resource usage prediction Configurable threshold boundary – notify Admin of forecasts above here Actual values (Black) Forecast values (Blue line) Upper & lower forecast range (light blue area) Unusual values (anomalies) Future forecast values
- 18. Oracle Machine Learning Key Features: • Collaborative UI for data scientist and analysts • Packaged with Autonomous Databases • Quick start Example notebooks • Easy access to shared notebooks, templates, permissions, scheduler, etc. • OML4SQL • OML4Py coming soon • Supports deployment of OML models Machine Learning Notebooks included in Autonomous Databases Copyright © 2020 Oracle and/or its affiliates.
- 19. Simple SQL Syntax—Statistical Comparisons (t-tests) Compare AVE Purchase Amounts Men vs. Women Grouped_By INCOME_LEVEL Statistical Functions SELECT SUBSTR(cust_income_level, 1, 22) income_level, AVG(DECODE(cust_gender, 'M', amount_sold, null)) sold_to_men, AVG(DECODE(cust_gender, 'F', amount_sold, null)) sold_to_women, STATS_T_TEST_INDEPU(cust_gender, amount_sold, 'STATISTIC', 'F') t_observed, STATS_T_TEST_INDEPU(cust_gender, amount_sold) two_sided_p_value FROM customers c, sales s WHERE c.cust_id = s.cust_id GROUP BY ROLLUP(cust_income_level) ORDER BY income_level, sold_to_men, sold_to_women, t_observed; STATS_T_TEST_INDEPU (SQL) Example; P_Values < 05 show statistically significantly differences in the amounts purchased by men vs. women
- 20. Simple SQL Syntax—Attribute Importance - ML Model Build (PL/SQL) Model Build and Real-time SQL Apply Prediction BEGIN DBMS_DATA_MINING.CREATE_MODEL( model_name => 'BUY_INSURANCE_AI', mining_function => DBMS_DATA_MINING.ATTRIBUTE_IMPORTANCE, data_table_name => 'CUST_INSUR_LTV', case_id_column_name => 'cust_id', target_column_name => 'BUY_INSURANCE', settings_table_name => 'Att_Import_Mode_Settings'); END; / SELECT attribute_name, rank , attribute_value FROM BUY_INSURANCE_AI ORDER BY rank, attribute_name; Model Results (SQL query) ATTRIBUTE_NAME RANK ATTRIBUTE_VALUE BANK_FUNDS 1 0.2161 MONEY_MONTLY_OVERDRAWN 2 0.1489 N_TRANS_ATM 3 0.1463 N_TRANS_TELLER 4 0.1156 T_AMOUNT_AUTOM_PAYMENTS 5 0.1095 A1A2A3A4 A5A6 A7
- 21. Multiple Languages UIs Supported for End Users & Apps Development Oracle Machine Leaning Application DevelopersDBAs R & Python Data Scientists “Citizen” Data ScientistsNotebook Users & DS Teams New! New!
- 22. Create New Derived Attributes or “Engineered Features” Feature Engineering - examples Source Attribute New Attribute/”Engineered Feature” Date of Birth AGE Address DISTANCE_TO_DESTINATION COMMUTE_TIME Call detail records (CDRs) #_DROPPED_CALLS PERCENT_iNTERNATIONAL Salary PERCENT_VS_PEERS Purchases TOTALS_PER_CATEGORY (e.g. Food, Clothing)
- 23. First, Identify the Key Attributes That Most Influence the Target Attribute Modeling and Machine Learning Attribute Importance Model
- 24. Next, Build Predictive Models to Predict Customers who are Likely to Have Good_Credit Modeling and Machine Learning Split Data into Train and Test Build and Test Classification Model
- 25. Test the ML model’s accuracy • Randomly selected “hold out” sample of data that was used to train the ML model • Compute Cumulative Gains, Lift, Accuracy, etc. • Review the attributes used in the model and model coefficients • Make sure the model makes sense Next, Build Predictive Models to Predict Customers who are Likely to Have Good_Credit Model Evaluation (Machine Learning) Model Evaluation
- 26. Simple SQL Apply scripts run 100% inside the Database for immediate ML model deployment Apply the Models to Predict “Best Customers” Deployment Model Apply/”Scoring”
- 27. Coming Soon! | AutoML – new with OML4Py Auto Feature Selection – Reduce # of features by identifying most predictive – Improve performance and accuracy Increase data scientist productivity – reduce overall compute time Auto Algorithm Selection Much faster than exhaustive search Auto Feature Selection De-noise data and reduce # of features AutoTune Significant accuracy improvement Auto Algorithm Selection – Identify in-database algorithm that achieves highest model quality – Find best algorithm faster than with exhaustive search Auto Tune Hyperparameters – Significantly improve model accuracy – Avoid manual or exhaustive search techniques Copyright © 2020 Oracle and/or its affiliates. Enables non-expert users to leverage Machine Learning Data Table ML Model
- 28. Coming Soon! | OML AutoML User Interface Automate production and deployment of ML models • Enhance Data Scientist productivity and user-experience • Enable non-expert users to leverage ML • Unify model deployment and monitoring • Support model management Features • Minimal user input: data, target • Model leaderboard • Model deployment via REST “Code-free” user interface supporting automated end-to-end machine learning Copyright © 2020 Oracle and/or its affiliates.
- 29. Coming Soon! | Algorithms for Database 20c Gradient Boosted Trees (XGBoost) • Highly popular and powerful algorithm – Kaggle winners • Classification, regression, ranking, survival analysis MSET-SPRT • Multivariate State Estimation Technique - Sequential Probability Ratio Test (MSET-SPRT) • Nonlinear, nonparametric anomaly detection algorithm designed to monitor critical processes. • Detects subtle anomalies while also producing minimal false alarms. Two major new ML algorithms Copyright © 2020 Oracle and/or its affiliates.
- 30. Oracle Data Miner UI Easy to use to define analytical methodologies that can be shared SQL Developer Extension Workflow API and generates SQL code for immediate deployment Drag and Drop, Workflows, Easy to Use UI for “Citizen Data Scientist” Copyright © 2020 Oracle and/or its affiliates.
- 31. Congratulations! Almost there J Data Scientist
- 32. • Oracle Cloud Infrastructure Data Science • AutoML - Automated algorithm selection and tuning - Automates the process of running tests against multiple algorithms and hyperparameter configurations - Checks results for accuracy and confirms that the optimal model and configuration are selected for use. - This saves significant time for data scientists • Feature Selection - Automated predictive feature selection simplifies feature engineering by automatically identifying key predictive features from larger datasets. • Model Evaluation - Measure model performance against new data, - Rank models over time to enable optimal behavior in production • Model Explanation - Explanation of the relative weighting and importance of the factors that go into generating a prediction Oracle Cloud Data Science Platform
- 33. • Oracle Cloud Infrastructure Data Science • Notebook Sessions - Built-in cloud-hosted JupyterLab notebook sessions enable teams to build and train models using Python. • Visualization Tools - Use popular open source visualization tools like plotly, matplotlib, and bokeh to visualize and explore data. • Open Source Machine Learning Frameworks - Launch notebook sessions with popular machine learning frameworks like TensorFlow, Jupyter, Dask, Keras, XGboost, and scikit-learn, or bring your own packages. Oracle Cloud Data Science Platform
- 34. Algorithms Operate on Data ML and AI are just “Algorithms” Move the Algorithms; Not the Data!; It Changes Everything!
- 35. Thank You Any Questions ? Sandesh Rao VP AIOps for the Autonomous Database @sandeshr https://www.linkedin.com/in/raosandesh/ https://www.slideshare.net/SandeshRao4