Module 1: Introduction to Machine Learning and Python

• What is Machine learning
• Types of machine learning
• Supervised, unsupervised
• Use of python is this domain
• Feature of python
• Software installation
• If else loops in python
• Function and module
• Class, object in python
• String manipulation
• Data structures in python(list, tuple, dictionary)
• List and dictionary comprehension

Module 2: ML libraries of Python

• Understanding the uses of various open source libraries
• Importing various modules with different methods
• Working with Numpy
• Numerical operations on numpy array
• Exploring various use cases of numpy
• Fundamental of Pandas
• Series and DataFrame
• Different functions on dataframe
• Pandas plotting functions
• Read external dataset using Pandas

Module 3: Data Pre-processing and Visualization

• Need of pre-processing of data
• What is Data Wrangling and feature engineering
• Introduction to sklearn module of python
• Handling different pre processing technique like missing value impute, explore data, convert from string to number etc
• Concepts of normalization and standardisation
• Standardize the dataset using StandardScalar(), MaxMinScalar()
• Fundamental of Matplotlib and Seaborn
• Various 2D and 3D graphs
• Data visualization in different types of graphs

Module 4: Supervised Machine learning – Regression

• Explain supervised machine learning
• Difference between classification and regression
• Concepts of train data and test data
• K fold cross validation vs train test split
• Types of regression problem, linear regression , polynomial regression
• Simple Linear Regression and it uses
• Apply polynomial regression for non linear dataset
• What is r2score and RMSE score

Module 5: Gradient Descent and Multivariate Regression

• Multiple linear regression
• Condition for multivariate linear regression
• Gradient descend algorithm
• How gradient descend works
• Use gradient descend to optimize linear regression parameter

Module 6: Supervised Machine learning – Classification

• Different types of classifier
• LogisticRegression to solve classification problem
• Check for accuracy metrics for classification
• Confusion matrix, classification report
• Understanding the mathematics and working of KNN
• Implement KNN algorithm on your dataset
• Application of KNN
• Handling imbalanced classification problem
• approaches to handle imbalanced data

Module 7: Tree Based Algorithm

• concept of tree based algorithm
• decision tree algorithm
• maths behind decision tree
• standard deviation reduction for regression
• entropy and gini index for classification problem
• pruning of tree
• overfiting in decision and its solution

Module 8: Ensemble learning and Boosting

• concepts of ensemble learning
• what is bagging and boosting
• random forest for bagging
• advantage and disadvantage of random forest
• random forest for both regression and classification
• adaboost and gradient boost
• use case for both boosting technique

Module 9: Naive Bayes algorithm for text classification

• what is naïve bayes
• bayes theorem and conditional probability
• types of naïve bayes
• Countvectorizer and tfidfvectorizer for text

Module 10: SVM and Kernel trick

• Support vector machine and its uses
• Concepts of decision boundary, linear SVM
• SVM for non linear problem
• Kernel trick, poly, linear, rdf Affect of gamma and C in SVM

Module 11: Unsupervised learning and Dimensionality Reduction

• What is unsupervised learning
• Clustering problem
• K means clustering
• Concept of dimensionality reduction
• Feature extraction and feature elimination
• PCA and its uses

Module 12: Natural Language Processing

• Lexical Processing
• Syntactic Processing
• Semantic Processing

Module 13: Project Work & Documentation