Data Science with Python

Description

Introduction

• A Practical Example: What You Will Learn in This Course
• What Does the Course Cover

 

The Field of Data Science – The Various Data Science Disciplines

• Data Science and Business Buzzwords: Why are there so Many?
• What is the difference between Analysis and Analytics
• Business Analytics, Data Analytics, and Data Science: An Introduction
• Continuing with BI, ML, and AI
• A Breakdown of our Data Science Infographic

 

The Field of Data Science – Connecting the Data Science Disciplines

• Applying Traditional Data, Big Data, BI, Traditional Data Science and ML

 

The Field of Data Science – The Benefits of Each Discipline

• The Reason Behind These Disciplines

 

The Field of Data Science – Popular Data Science Techniques

• Techniques for Working with Traditional Data
• Real Life Examples of Traditional Data
• Techniques for Working with Big Data
• Real Life Examples of Big Data
• Business Intelligence (BI) Techniques
• Real Life Examples of Business Intelligence (BI)
• Techniques for Working with Traditional Methods
• Real Life Examples of Traditional Methods
• Machine Learning (ML) Techniques
• Types of Machine Learning
• Real Life Examples of Machine Learning (ML)

 

The Field of Data Science – Popular Data Science Tools

• Necessary Programming Languages and Software Used in Data Science

 

The Field of Data Science – Careers in Data Science

• Finding the Job – What to Expect and What to Look for

 

The Field of Data Science – Debunking Common Misconceptions

• Debunking Common Misconceptions

 

                Probability

• The Basic Probability Formula
• Computing Expected Values
• Frequency
• Events and Their Complements

 

Probability – Combinatorics

• Fundamentals of Combinatorics
• Permutations and How to Use Them
• Simple Operations with Factorials
• Solving Variations with Repetition
• Solving Variations without Repetition
• Solving Combinations
• Symmetry of Combinations
• Solving Combinations with Separate Sample Spaces
• Combinatorics in Real-Life: The Lottery
• A Recap of Combinatorics
• A Practical Example of Combinatorics

 

Probability – Bayesian Inference

• Sets and Events
• Ways Sets Can Interact
• Intersection of Sets
• Union of Sets
• Mutually Exclusive Sets
• Dependence and Independence of Sets
• The Conditional Probability Formula
• The Law of Total Probability
• The Additive Rule
• The Multiplication Law
• Bayes’ Law
• A Practical Example of Bayesian Inference

 

Probability – Distributions

• Fundamentals of Probability Distributions
• Types of Probability Distributions
• Characteristics of Discrete Distributions
• Discrete Distributions: The Uniform Distribution
• Discrete Distributions: The Bernoulli Distribution
• Discrete Distributions: The Binomial Distribution
• Discrete Distributions: The Poisson Distribution
• Characteristics of Continuous Distributions
• Continuous Distributions: The Normal Distribution
• Continuous Distributions: The Standard Normal Distribution
• Continuous Distributions: The Students’ T Distribution
• Continuous Distributions: The Chi-Squared Distribution
• Continuous Distributions: The Exponential Distribution
• Continuous Distributions: The Logistic Distribution
• A Practical Example of Probability Distributions

 

Probability – Probability in Other Fields

• Probability in Finance
• Probability in Statistics
• Probability in Data Science

 

Part 3: Statistics

• Population and Sample

 

Statistics – Descriptive Statistics

• Types of Data
• Levels of Measurement
• Categorical Variables – Visualization Techniques
• Numerical Variables – Frequency Distribution Table
• The Histogram
• Histogram Exercise
• Cross Tables and Scatter Plots
• Mean, median and mode
• Skewness
• Variance
• Standard Deviation and Coefficient of Variation
• Covariance
• Correlation Coefficient

 

Statistics – Practical Example: Descriptive Statistics

• Practical Example: Descriptive Statistics

 

Statistics – Inferential Statistics Fundamentals

• Introduction
• What is a Distribution
• The Normal Distribution
• The Standard Normal Distribution
• Central Limit Theorem
• Standard error
• Estimators and Estimates

 

Statistics – Inferential Statistics: Confidence Intervals

• What are Confidence Intervals?
• Confidence Intervals; Population Variance Known; Z-score
• Confidence Interval Clarifications
• Student’s T Distribution
• Confidence Intervals; Population Variance Unknown; T-score
• Margin of Error
• Confidence intervals. Two means. Dependent samples
• Confidence intervals. Two means. Independent Samples

 

Statistics – Practical Example: Inferential Statistics

• Practical Example: Inferential Statistics

 

Statistics – Hypothesis Testing

• Null vs Alternative Hypothesis
• Rejection Region and Significance Level
• Type I Error and Type II Error
• Test for the Mean. Population Variance Known
• p-value
• Test for the Mean. Population Variance Unknown
• Test for the Mean. Dependent Samples
• Test for the mean. Independent Samples

 

Statistics – Practical Example: Hypothesis Testing

• Practical Example: Hypothesis Testing

 

Python – Introduction to Python

• Introduction to Programming
• Why Python?
• Why Jupyter?
• Installing Python and Jupyter
• Understanding Jupyter’s Interface – the Notebook Dashboard
• Prerequisites for Coding in the Jupyter Notebooks

 

Python – Variables and Data Types

• Variables
• Numbers and Boolean Values in Python
• Python Strings

 

Python – Basic Python Syntax

• Using Arithmetic Operators in Python
• The Double Equality Sign
• How to Reassign Values
• Add Comments
• Understanding Line Continuation
• Indexing Elements
• Structuring with Indentation

 

Python – Other Python Operators

• Comparison Operators
• Logical and Identity Operators

 

Python – Conditional Statements

• The IF Statement
• The ELSE Statement
• A Note on Boolean Values

 

Python – Python Functions

• Defining a Function in Python
• How to Create a Function with a Parameter
• Defining a Function in Python
• How to Use a Function within a Function
• Conditional Statements and Functions
• Functions Containing a Few Arguments
• Built-in Functions in Python

 

Python – Sequences

• Lists
• Using Methods
• List Slicing
• Tuples
• Dictionaries

 

Python – Iterations

 

• For Loops
• While Loops and Incrementing
• Lists with the range() Function
• Conditional Statements and Loops
• Conditional Statements, Functions, and Loops
• How to Iterate over Dictionaries

 

Python – Advanced Python Tools

• Object Oriented Programming
• Modules and Packages
• What is the Standard Library?
• Importing Modules in Python

 

Advanced Statistical Methods in Python

• Introduction to Regression Analysis

 

Advanced Statistical Methods – Linear Regression with StatsModels

• The Linear Regression Model
• Correlation vs Regression
• Geometrical Representation of the Linear Regression Model
• Python Packages Installation
• First Regression in Python
• Using Seaborn for Graphs
• How to Interpret the Regression Table
• Decomposition of Variability
• What is the OLS?
• R-Squared

 

Advanced Statistical Methods – Multiple Linear Regression with StatsModels

• Multiple Linear Regression
• Adjusted R-Squared
• Test for Significance of the Model (F-Test)
• OLS Assumptions
• Linearity
• No Endogeneity
• Normality and Homoscedasticity
• No autocorrelation
• Dealing with Categorical Data – Dummy Variables
• Making Predictions with the Linear Regression

 

Advanced Statistical Methods – Linear Regression with sklearn

• What is sklearn and How is it Different from Other Packages
• How are we Going to Approach this Section?
• Simple Linear Regression with sklearn
• Simple Linear Regression with sklearn – A StatsModels-like Summary Table
• Multiple Linear Regression with sklearn
• Calculating the Adjusted R-Squared in sklearn
• Feature Selection (F-regression)
• Creating a Summary Table with P-values
• Feature Scaling (Standardization)
• Feature Selection through Standardization of Weights
• Predicting with the Standardized Coefficients
• Underfitting and Overfitting
• Train – Test Split Explained

 

Advanced Statistical Methods – Practical Example: Linear Regression

• Practical Example: Linear Regression

 

Advanced Statistical Methods – Logistic Regression

• Introduction to Logistic Regression
• A Simple Example in Python
• Logistic vs Logit Function
• Building a Logistic Regression
• An Invaluable Coding Tip
• Understanding Logistic Regression Tables
• What do the Odds Actually Mean
• Binary Predictors in a Logistic Regression
• Calculating the Accuracy of the Model
• Underfitting and Overfitting
• Testing the Model

 

Advanced Statistical Methods – Cluster Analysis

• Introduction to Cluster Analysis
• Some Examples of Clusters
• Difference between Classification and Clustering
• Math Prerequisites

 

Advanced Statistical Methods – K-Means Clustering

• K-Means Clustering
• A Simple Example of Clustering
• Clustering Categorical Data
• How to Choose the Number of Clusters
• Pros and Cons of K-Means Clustering
• To Standardize or not to Standardize
• Relationship between Clustering and Regression
• Market Segmentation with Cluster Analysis
• How is Clustering Useful?

 

Advanced Statistical Methods – Other Types of Clustering

• Types of Clustering
• Dendrogram
• Heatmaps

 

Part 6: Mathematics

• What is a Matrix?
• Scalars and Vectors
• Linear Algebra and Geometry
• Arrays in Python – A Convenient Way To Represent Matrices
• What is a Tensor?
• Addition and Subtraction of Matrices
• Errors when Adding Matrices
• Transpose of a Matrix
• Dot Product
• Dot Product of Matrices
• Why is Linear Algebra Useful?

 

Part 7: Deep Learning

• What to Expect from this Part?

 

Deep Learning – Introduction to Neural Networks

• Introduction to Neural Networks
• Training the Model
• Types of Machine Learning
• The Linear Model (Linear Algebraic Version)
• The Linear Model with Multiple Inputs
• The Linear model with Multiple Inputs and Multiple Outputs
• Graphical Representation of Simple Neural Networks
• What is the Objective Function?
• Common Objective Functions: L2-norm Loss
• Common Objective Functions: Cross-Entropy Loss
• Optimization Algorithm: 1-Parameter Gradient Descent

 

Deep Learning – How to Build a Neural Network from Scratch with NumPy

• Basic NN Example

 

Deep Learning – TensorFlow 2.0: Introduction

• How to Install TensorFlow 2.0
• TensorFlow Outline and Comparison with Other Libraries
• TensorFlow 1 vs TensorFlow 2
• A Note on TensorFlow 2 Syntax
• Types of File Formats Supporting TensorFlow
• Outlining the Model with TensorFlow 2
• Interpreting the Result and Extracting the Weights and Bias
• Customizing a TensorFlow 2 Model

 

Deep Learning – Digging Deeper into NNs: Introducing Deep Neural Networks

 

• What is a Layer?
• What is a Deep Net?
• Digging into a Deep Net
• Non-Linearities and their Purpose
• Activation Functions
• Activation Functions: Softmax Activation
• Backpropagation
• Backpropagation Picture

 

Deep Learning – Overfitting

• What is Overfitting?
• Underfitting and Overfitting for Classification
• What is Validation?
• Training, Validation, and Test Datasets
• N-Fold Cross Validation
• Early Stopping or When to Stop Training

 

Deep Learning – Initialization

• What is Initialization?
• Types of Simple Initializations
• State-of-the-Art Method – (Xavier) Glorot Initialization

 

Deep Learning – Digging into Gradient Descent and Learning Rate Schedules

• Stochastic Gradient Descent
• Problems with Gradient Descent
• Momentum
• Learning Rate Schedules, or How to Choose the Optimal Learning Rate
• Learning Rate Schedules Visualized
• Adaptive Learning Rate Schedules (AdaGrad and RMSprop )
• Adam (Adaptive Moment Estimation)

 

Deep Learning – Preprocessing

• Preprocessing Introduction
• Types of Basic Preprocessing
• Standardization
• Preprocessing Categorical Data
• Binary and One-Hot Encoding

 

Deep Learning – Classifying on the MNIST Dataset

• MNIST: The Dataset
• MNIST: How to Tackle the MNIST
• MNIST: Importing the Relevant Packages and Loading the Data
• MNIST: Preprocess the Data – Create a Validation Set and Scale It
• MNIST: Preprocess the Data – Shuffle and Batch
• MNIST: Outline the Model
• MNIST: Select the Loss and the Optimizer
• MNIST: Learning
• MNIST: Testing the Model

 

Deep Learning – Business Case Example

• Business Case: Exploring the Dataset and Identifying Predictors
• Business Case: Outlining the Solution
• Business Case: Balancing the Dataset
• Business Case: Preprocessing the Data
• Business Case: Load the Preprocessed Data
• Business Case: Learning and Interpreting the Result
• Business Case: Setting an Early Stopping Mechanism
• Business Case: Testing the Model

 

Deep Learning – Conclusion

• Summary on What You’ve Learned
• What’s Further out there in terms of Machine Learning
• An overview of CNNs
• An Overview of RNNs
• An Overview of non-NN Approaches

 

Appendix: Deep Learning – TensorFlow 1: Introduction

• How to Install TensorFlow 1
• TensorFlow Intro
• Actual Introduction to TensorFlow
• Types of File Formats, supporting Tensors
• Basic NN Example with TF: Inputs, Outputs, Targets, Weights, Biases
• Basic NN Example with TF: Loss Function and Gradient Descent
• Basic NN Example with TF: Model Output

 

Appendix: Deep Learning – TensorFlow 1: Classifying on the MNIST Dataset

• MNIST: What is the MNIST Dataset?
• MNIST: How to Tackle the MNIST
• MNIST: Relevant Packages
• MNIST: Model Outline
• MNIST: Loss and Optimization Algorithm
• Calculating the Accuracy of the Model
• MNIST: Batching and Early Stopping
• MNIST: Learning
• MNIST: Results and Testing

 

Appendix: Deep Learning – TensorFlow 1: Business Case

• Business Case: Getting Acquainted with the Dataset
• Business Case: Outlining the Solution
• The Importance of Working with a Balanced Dataset
• Business Case: Preprocessing
• Creating a Data Provider
• Business Case: Model Outline
• Business Case: Optimization
• Business Case: Interpretation
• Business Case: Testing the Model
• Business Case: A Comment on the Homework

 

Software Integration

• What are Data, Servers, Clients, Requests, and Responses
• What are Data Connectivity, APIs, and Endpoints?
• Taking a Closer Look at APIs
• Communication between Software Products through Text Files
• Software Integration – Explained

 

Case Study – What’s Next in the Course?

• Game Plan for this Python, SQL, and Tableau Business Exercise
• The Business Task
• Introducing the Data Set

 

Case Study – Preprocessing the ‘Absenteeism_data’

• What to Expect from the Following Sections?
• Importing the Absenteeism Data in Python
• Checking the Content of the Data Set
• Introduction to Terms with Multiple Meanings
• Using a Statistical Approach towards the Solution to the Exercise
• Dropping a Column from a DataFrame in Python
• Analyzing the Reasons for Absence
• Obtaining Dummies from a Single Feature
• More on Dummy Variables: A Statistical Perspective
• Classifying the Various Reasons for Absence
• Using .concat() in Python
• Reordering Columns in a Pandas DataFrame in Python
• Creating Checkpoints while Coding in Jupyter
• Analyzing the Dates from the Initial Data Set
• Extracting the Month Value from the “Date” Column
• Extracting the Day of the Week from the “Date” Column
• Analyzing Several “Straightforward” Columns for this Exercise
• Working on “Education”, “Children”, and “Pets”
• Final Remarks of this Section

 

Case Study – Applying Machine Learning to Create the ‘absenteeism_module’

• Exploring the Problem with a Machine Learning Mindset
• Creating the Targets for the Logistic Regression
• Selecting the Inputs for the Logistic Regression
• Standardizing the Data
• Splitting the Data for Training and Testing
• Fitting the Model and Assessing its Accuracy
• Creating a Summary Table with the Coefficients and Intercept
• Interpreting the Coefficients for Our Problem
• Standardizing only the Numerical Variables (Creating a Custom Scaler)
• Interpreting the Coefficients of the Logistic Regression
• Backward Elimination or How to Simplify Your Model
• Testing the Model We Created
• Saving the Model and Preparing it for Deployment
• Preparing the Deployment of the Model through a Module

 

Case Study – Loading the ‘absenteeism_module’

• Deploying the ‘absenteeism_module

 

Case Study – Analyzing the Predicted Outputs in Tableau

• Analyzing Age vs Probability in Tableau
• Analyzing Reasons vs Probability in Tableau
• Analyzing Transportation Expense vs Probability in Tableau

 

Appendix – Additional Python Tools

• Using the .format() Method
• Iterating Over Range Objects
• Introduction to Nested For Loops
• Triple Nested For Loops
• List Comprehensions
• Anonymous (Lambda) Functions