Python:
Complete Python
Demo:
i. WhyPython?
ii. Who Uses Pythontoday
iii. What can we do with Python
iv. How Python Developed and Supported
v. Pyth on–Technical Strengths.
vi. What next?
Python Interpreter
Program Execution–programmer’s view, Python’s view
Installation
i. Python
ii. All Related Software: PyCharm, Anaconda
iii. Setup,configure Pythonin Laptop
iv. IDLE– UI, usage, features
All Numeric types in Python, coding / Hands-on
Python Variables, objects, References, Shared References, coding/Hands-on
Garbage Collection of objects
All builtin types in python: Strings, Lists, Dictionaries, Tuples, sets, Files
Python Statements-coding / Hands-on
Assignments, Expressions and Prints
i. if-else,if-elif-else,if-elseternary expression
ii. whileand for loops
iii. Comprehensions vs regular
iv. ParallelTraversals: mapand zip functions
v. Otherimportant functions: range, len, enumerate
Iterations and Comprehensions-coding/Hands-on
Python online Documentation
Python Functions–def, nested functions
Variable Scopes –basics, LEG Brules,global, nonlocal
Function Arguments-coding/Hands-on
i. Arguments and shared references
ii. Arguments passing basics
iii. Arguments matching basics
iv. Arguments matching syntax
v. Multiple Results
Python Modules
i. Definition, whymodules?
ii. Typical Python program architecture
iii. Import statement-coding/Hands-on
iv. How Import works: Findit, Compileit, Runit
v. Standard library modules
vi. Pycache folder for byte codefiles
vii. Module search path
Module coding Basics
i. Module creation
ii. import statement, from statement, from*statement
iii. Module Name spaces, Name space dictionaries: dict
iv. Reloading modules
Module Packages
i. Package import basics
ii. Why Package imports?
iii. Relative import basics
iv. Why relative imports?
v. Package Name spaces
Advanced ModuleTopics
i. Data hiding in modules -coding/Hands-on
ii. Mixed usage modes: name and main -coding/Hands-on
iii. Theas extension for import and from-coding/Hands-on
Introduction to Python Classes-coding/Hands-on
i. Why Classes?
ii. Classes, constructors and Instances
iii. Method calls
iv. Attribute in heritance search
v. OOPisab out codereuse
vi. Subclassing by Inheritance
vii. Polymorphism in Action
viii. Class vs instance attributes
ix. Storing objects in DB–Pickles & Shelves
Coding with Classes-coding/Hands-on
i. Abstract super classes
ii. Nested classes
iii. Classes vs Modules
iv. Name space dictionaries
v. LEGB scopesrule revisited
Operator Overloading-coding/Hands-on
i. Constructors: init
ii. Indexing, Slicing: getitem and setitem
iii. Attribute Access: getattr and setattr
iv. String Representation: repr andstr
v. Rightside andIn-PlaceUses: radd and iadd
vi. CallExpressions: call
vii. Comparisons: lt,gt andothers
viii. BooleanTests: bool andlen
ix. Destructors: del
Special features of Classes-coding/Hands-on
i. Inheritance:“IS-a”relationship
ii. Composition:“HAS-a”relationship
iii. Pseudo private class attributes
iv. Boundandun bound method objects
v. Class objects
vi. “Mix-In”classes
Advanced Class Topics-coding /Hands-on
i. “Newstyle”class model
ii. Diamondinheritancechange
iii. MRO: Method Resolution Order
iv. Slots: Attribute Declarations
v. Properties: Attribute Accessors
vi. Staticand Class methods
vii. The “super” built-in function
Exception Basics-coding / Hands-on
i. Why Exceptions?
ii. Default Exception handler
iii. Catching Exceptions
Coding Exceptions-coding / Hands-on
i. Thetry / except / else statement
ii. Try / finally statement
iii. Raise statement
iv. Assert statement
v. With / as context managers
vi. Nesting Exception Handlers
Exception Objects
i. Class based exceptions
ii. Why Exception hierarchies?
iii. Built-in Exception Classes
iv. Custom Exceptions
Regular Expressions with Python:
i. What are regular expressions?
ii. Regex module in python
iii. The match Function
iv. The search Function
v. Matching vs searching
vi. Search and Replace
vii. Meta characters , advanced patterns
Data Libraries:
i. Introduction to numpy
ii. Creating arrays
iii. Indexing Arrays
iv. Array Transposition
v. Universal Array Function
vi. Array Processing
vii. Array Input and Output
viii. Introduction to Pandas, Series, Data frames
ix. Data reading with Pandas
x. Data cleaning with Pandas
xi. Data wrangling with Pandas
xii. Data selection with Pandas
xiii. Data extraction with Pandas
xiv. Introduction to Mat plot lib
xv. Data Visualization with mat plot lib
Mathematics:
i. Linear Algebra
ii. Statistics:
iii. Probability:
iv. Differential Calculus:
MachineLearning:
Introduction to Machine Learning:
i. What is Machine Learning
ii. Why use Machine Learning
iii. Examples of ML applications
iv. Types of ML Systems.
v. Supervised Learning
vi. Unsupervised Learning
vii. Batch vs Online Learning
viii. Instance-based vs Model-based Learning
ix. Challenges of Machine Learning
x. Over fitting vs un derfitting training data
xi. All phases of End to End ML Project.
Classification Models
i. Binary Classifier
ii. Performance Measures
a) Accuracy
b) Confusion Matrix
c) Precisionand Recall
d) ROCCurve
iii. Multi Class Classification
iv. Error Analysis
v. Multi Label Classification
vi. Multi Output Classification
Regression Models
i. Linear Regression
ii. Gradient Descent
a) Batch Gradient Descent
b) Stochastic Gradient Descent
c) Mini-batch Gradient Descent
iii. Polynomial Regression
iv. Regularized Linear Models
a) Ridge Regression
b) Lasso Regression
c) Early Stopping
v. Logistic Regression
Support Vector Machines:
I. Linear SVM Classification
II. Soft Margin vs Hard Margin Classification
III. Nonlinear SVM Classification
IV. SVM Regression Models
Decision Trees:
i. Introduction to Decision Tree
ii. Training Decision Tree
iii. Visualizing Decision Tree
iv. Estimating Class Probabilities
v. The CART Training Algorithm
vi. Computational Complexity
vii. Gini Impurity vs Entropy
viii. Regularization of Hyper parameters
ix. Regression, Instability
Random Forests:
i. Ensemble Learning
ii. Voting Classifiers
iii. Bagging and Pasting
iv. Bagging & Pasting insci-kit Learn
v. Out of bage valuation
vi. Random Patches and Random Subspaces
vii. Random Forests
viii. Extra Tree and Feature importance
ix. Introduction to Boosting
x. Ada Boost and Gradient Boost
xi. Stacking
Dimensionality Reduction:
i. The Curse of dimensionality
ii. Approaches for dimensionality reduction
iii. Projection and Manifold Learningiv. PCA
Unsupervised Learning Techniques
i. Clustering
ii. K-Means Algorithm and Limit sofK-Means
iii. Image segmentation using Clustering
iv. Preprocessingusing Clustering
v. Semi-supervised Learnin gusing Clustering
vi. DBSCAN
vii. Gaussian Mixtures
Deep Learning:
Introduction to Artificial Neural Networks with Keras
i. Biological Neuron
ii. The Perceptron
iii. Multilayer Perceptron and Back propagation
iv. Regression MLPs
v. Classification MLPs
vi. Implementing MLPs with Keras
vii. Buildingan Image classifierusing Sequential API
Building Regression ML Pusingsequential API
i. Building complex Modelsusing Functional API
ii. Saving and Restoring Model
iii. Using Callbacks
iv. Finetuning neural network hyper parameters
v. Number of Hidden layers
vi. Number of neuronsperhiddenlayer
vii. Learning rate, Batch size and other hyper parameters
Training Deep Neural networks
i. Vanishing / Exploding Gradients problems.
a. Glorot and He initialization
b. Non saturating Activation Functions
c. Batch Normalization
d. Gradient Clipping
ii. Reusing Pretrained Layers
a) Transfer Learning
b) Unsupervised Pretraining
iii. Faster optimizers
iv. Avoiding over fitting through Regularization
1. I1 &l2 regularization
2. Drop out
3. MC(Monte Carlo)Dropout
4. Max-Norm Regularization
Loading and Preprocessing Data with Tensor flow
I. Quickt our of Tensorflow
II. Tensors and Operations
III. Tensors vs numpy
IV. The Data API
1. Chaining Transformations
2. Shuffling Data
3. Preprocessing Data
4. Prefetching Data
V. Preprocessing Input features
1. Encoding categorical Features using one hot vectors
2. Encoding categorical features using Embeddings
3. Keras Preprocessing Layers
VI. TF Transform
VII. TFDS Project
