Data Journey¶

Introduction to Data Science

Who should take it? Everyone! If you wish to become a Data Scientist or if just want to get a more comprehensive overview of this field this should be your starting point.

Effort Required: Minimal, plan to attend a 2 hours workshop.

By the end of this track you will be able to:

1. Understand what is Data Science and how you can derive value from it in your business;
2. Have a basic intuition on how is a Data Science process conducted;
3. Get familiar with Braskem's initiatives and other market benchmarks.

Content

1. What is Data Science
2. Braskem's Initiaves & Market outlook
3. Effort
4. Workshop

Business Analyst

Who should take it? Analysts, Coordinator or Managers in business areas that wish to get familiar with development of solutions. Professionals seeking tools to enhance productivity or to help them develop business solutions with data.

Effort Required Duration: TBD

By the end of this track you will be able to: - Have a practical knowledge of the tools for development of business solutions; - Ingest and process data in Python; - Know the concepts of different databases and cloud solutions, such as Data lake and data pipelines; - Get a basic concept of the process involved in developing and deploying a digital product;

Content

1. Developing Tools
2. Anaconda Navigator
3. Jupyter Notebook
4. Spyder / Sublime / Visual Studio
5. Introduction to Python
6. Objects & Structure
7. Logic Operators & Loops
8. Classes, Methods & Functions
9. Libraries (Pandas, Numpy & Matplotlib)
10. Data Wrangling
11. Importing Data
12. Data Structure
13. Tidying Data
14. Combining Data
15. Cleaning Data
16. Software & Data Engineering | Azure
17. Microsoft Azure Introduction
18. SQL & NoSQL Databases
19. Data Pipeline
20. Standard Tables Architecture
21. DevOps & Continuous Deployment
22. Big Data with PySpark & Databricks (optional)

Data Analyst

Who should take it? Professionals seeking a technical approach to Data driven decisions. Business units undergoing digital transformation where more data driven reports and analysis are required.

Effort Required: Duration: TBD

By the end of this track you will be able to: How to derive insights from data; Perform basic statistical analysis with available data; Build graphs and reports in Python; Know how to transform and choose the best features to enhance the analysis of data; Be equipped to provide your team with more data driven insights.

Content

1. Exploratory Data Analysis I
2. Types of Variables
3. Variable Summary | Statiscal Moments
4. Correlation Matrix & ANOVA
5. Feature Engineering
6. Feature Selection
7. Feature Creation & Transformation
8. Data Normalization & Balance
9. Data Interpolation
10. Data Visualization
11. Matplotlib & Seaborn
12. Graph & Figure Types

Data Scientist

Who should take it? Any professional aspiring to specialize in Data Science with development of Machine Learning algorithms and scientific data analysis.

Effort Required: Duration: TBD

By the end of this track you will be able to: Conduct scientific processes for data analysis; Develop Machine Learning algorithms; Deploy and deliver Data Science based digital products; Provide the business with huge data driven insights and strategies; Fully understand the intuition, math and code behind the main Machine Learning algorithms; Conduct explanatory data analysis to extract causation to enhance business decisions; Develop, deploy and maintain any Data Science project. Understand what are the best approaches and algorithms for each business problem;

Content

1. Linear Algebra
2. Matrices & Vectors with Numpy
3. Alternate Corrdinate Systems
4. Probability Theory
5. Probability Models & Axioms
6. Conditioning & Independence
7. Counting
8. Discrete & Continuous Variables Distributions
9. Bayesian Inference
10. The Monte Carlo Simulation with Scipy
11. Statistical Inference
12. Sample Means & Central Limit Theorem
13. Confidence Intervals & Hypothesis Testing
14. Causality Analysis
15. Linear Modeling & Experimental Design
16. Exploratory Data Analysis II
17. Hypothesis Creation & Testing
18. Endogenous Variables Transformation
19. Time Series Analysis
20. Calculus (optional)
21. Limits & Continuity
22. Differentials & Derivatives
23. Univariate Integration
24. Multivariate Calculus
25. Learning Techniques
26. Supervised & Unsupervised Learning
27. Regressions, Classifications & Clusterings
28. Train & Test Sets | Dimensionality
29. Model Scoring
30. Regression Metrics
31. Classification Metrics
32. Clustering Metrics
33. Cross Validation
34. Back Propagation & Hyper Parameters
35. Parameters vs Hyper Parameters
36. Grid Search & Hyper Parameters Settings
37. Back Propagation
38. Main Algorithms Intuition
39. Linear Regression (Regression)
40. SVM (Regression & Classification)
41. Random Forest (Regression & Classification)
42. Logistic Regression (Classification)
43. K-Means (Clustering)
44. Special Models
45. Boosting
46. Neural Networks (Deep Learning)
47. Reinforcement Learning
48. Natural Language Processing (NLP)
49. Computer Vision