Data Science Class Room/Online
Data Science Using Python
| Course Extract | |
|---|---|
| Level | Intermediate |
| Length | 7 Weekends |
| Projects | 1 (Fully functional) |
| Pre-requisites | None |
| Batch size | 10 - 15 |
| Job preparation | Yes |
| Certificate | Yes |
| Start date | July 20th, 2019 |
Get Started
DAY 1
DAY 2
- Python the saviour for ML
- Basics of Python, Installation and setup
- Python syntax, Variable, datatypes, Keywords, Operators, Conditional statements, loops, control statements
- Functions, LAMBDA & Modules
- Exception Handling, File handling
- Data structures (List, Set, Tuples, Dictionary),
- Advanced Libraries of Python (Numpy, Pandas, Scikit-learn etc)
- Data preparation and munging using Python libraries
DAY 3
- Basic of Statistics & Probabilities for ML
- Statistical Jargons, Central tendencies
- Sample vs Population
- Exclusive Event, Independent Event, Introduction to random variables, the Joint probability
- Metric, Probability tree, Confusion Matrix
- Discrete probability distributions, Continuous probability distributions
DAY 4
- Deep dive on Linear Regression
- Understanding Linear Regression with an example
- Gradient descent and its parameters
- Formulae and maths behind this model
- Multiple Linear Regression, Polynomial Regression, Categorical Variables in Regression
- Error metrics to calibrate performance the model
- Hands-on modelling of 3 real-time problems (using Python and scikit-learn)
- Pros and cons
DAY 5
- Developing and Deploying ML models (AWS CLOUD)
- Building a simple REST application using FLASK
- Exposing the Linear Regression ML model as REST API using FLASK
- Deploying the ML model in AWS and consuming it using a sample application
DAY 6
- Deep dive on Logistic Regression
- Understanding Logistic Regression with an example
- Sigmoid function
- Formulae and maths behind this model
- Error metrics to calibrate the performance of the model
- Hands-on modelling of 3 real-time problems (using Python and scikit-learn)
- Pros and cons
Deep Dive
DAY 7
- Deep dive on SVM
- Understanding SVM with an example
- Learning about Kernal and support vector machines
- Formulae and maths behind this model
- Error metrics to calibrate the performance of the model
- Hands-on modelling of one real-time problem (using Python and sci-kit-learn)
- Pros and cons
DAY 8
- Time Series Forecasting
- Understanding Trend analysis, Cyclical and Seasonal analysis, Smoothing
- Moving averages, Auto-correlation
- ARIMA Applications of Time Series
- Hands-on modelling using FB Prophet for Time series forecasting (Python)
DAY 9
- Other Algorithms in Machine Learning
- Unsupervised Learning: Clustering techniques – K means – K means++
- Decision Tree: Real-time use case, examples, the theory of entropy. Information gain and Gini index, Hands-on
DAY 10
- Ensemble Technique
- Bagging & boosting and its impact
- Random forest, Adaboost - Gradient boosting machines
DAY 11
- Text Mining
- Understanding information retrieval, Crawling and Language modelling
- Text Indexing, Inverted Indexes
- Relevance Ranking TF and IDF
- Evaluation Metrics for Ranking
DAY 12
- Natural Language Processing
- Understanding NLP, real-life systems using NLP
- Parsing and semantic structures, Stemming, POS tagging
- Named Entity Recognition and applications of NER
- Sentiment Analysis
DAY 13
- Project Week
- Dataset will be provided
- Expected to prepare and transforms the data to be applicable for modelling
- Model using various algorithms and provide the best prediction results
- Apply Ensemble techniques to improve the prediction accuracy
DAY 14
- Project Week
- Specific business/domain use cases will be dealt with (based on the availability of the experts)
- Hackathon/contest
- Certification
Course Duration
7 WEEKS
Every Week
2 SESSIONS
Each Session
4 HOURS
Projects & Assignments
50 HOURS
Great Career
MENTOR SPOTLIGHT
Mohamed Noordeen
Senior Data Scientist
Noordeen, with 6+ years of experience in data science and has strong experience in Python and Machine Learning. He has been coaching python, data science for quite long now.