Data Science skills

data_science.md

1. Data Pipelines: Airflow
2. MS Excel
3. Programming/Tools: Python, PySpark, SQL
4. Version Control: Github/Bitbucket
5. Data Wrangling and Feature Engineering
6. ML
   • Regression
   • Logistic regression (in Python)
   • NLP
   • Decision trees
   • Classification
   • Clustering
   • Data preparation techniques
   • Boosted algorithms
   • Hyperparameter tuning
   • Model evaluation metrics
7. Presentation & Storytelling/Communication: Tableu, PowerBI, Python libraries
8. Analytics and Modeling: analyze data, run tests, and create explanatory models to gather new insights and predict possible outcomes.
9. A/B Testing
10. Statistics
    • To help make recommendations and decisions: maximum likelihood estimators, distributors, and statistical tests
    • Tied to ML Algorithms: Calculus and linear algebra
    • Descriptive statistics (using Python): mean, median, mode, variance, standard deviation.
    • Probability distributions, sample and population, CLT, skewness and kurtosis
    • Inferential statistics: hypothesis testing, confidence intervals
11. Data Visualization
    1. Break down complex data into smaller, digestible pieces as well as using a variety of visual aids (charts, graphs, etc.)
       Bar Chart
    2. Effectively communicate key messaging and get buy in for proposed solutions
12. Big Data: Hadoop, Apache Spark / PySpark
13. Deep Learning: CNN, RNN