Machine Learning Cookbook with Python: Create ML and Data Analytics Projects Using Some Amazing Open Datasets

Cover Page
Title Page
Copyright Page
Dedication Page
About the Author
Acknowledgement
Preface
Errata
Table of Contents
1. Boston Crime
    Introduction
    Structure
    Objective
    What is Data?
        Types of Data
    Let’s talk about the Boston dataset
        Data Dictionary
    O.S.E.M.N. framework
        What is Data Obtaining?
        What is Data Scrubbing?
        Finding Data Types
        How to Handle Missing Data?
        What to Do with Duplicate Values?
        What is Data Exploring?
        Univariate Feature Analysis
            What is Statistical Distribution?
        Multivariate Feature Analysis
    Further reading
    Conclusion
2. World Happiness Report
    Introduction
    Structure
    Objective
    Let’s Talk about the Dataset
    Pre-requisites
    Data Exploration
    Different Types of Data
        Data represented on Nominal (Categorical) Scale
        Data represented on Ordinal Scale
    Measurement of Data
        Discrete Variables
        Continuous Variables
        Interval Scale
        Circular Scale
        Ratio Scale
    Distributions
    Normal Distribution
        Distribution Plot
        Kernel Density Estimation
        Box Plot
    Skewed Distribution
        Left Skewed (Negative Skewness)
            Distribution Plot
            Kernel Density Estimation
            Box Plot
        Right Skewed (Positive Skewness)
            Distribution Plot
            Kernel Density Estimation
            Box Plot
        Other Distributions
    Further Reading
    Conclusion
3. Iris Species
    Introduction
    Structure
    Objective
    Introduction to Machine Learning
    What is Machine Learning?
        Types of Machine Learning
            Supervised Learning
            Unsupervised Learning
            Reinforcement Learning
        Machine Learning Pipeline
    Understanding the dataset
    Exploratory Data Analysis
        Load Dataset
            Scikit-learn
            Seaborn
        Data Analysis
            Pair Plot
            Correlation
    How to Choose ML Algorithms?
    Classification
        K - nearest Neighbors (K-nn)
            How Does It Work?
            Model Training
            Evaluation
            Model Tuning
    Clustering
        K-means
            How Does It Work?
            Model Training
            Evaluation & Model Tuning
    Regression
        Linear Regression
            How Does It Work?
            Model Training
            Evaluation
    Further reading
    Conclusion
4. Credit Card Fraud Detection
    Introduction
    Structure
    Objective
    Let’s Understand the Data
        What is an Imbalanced Dataset?
        Knowing the Features
    Prerequisites
        Normalization/Feature Scaling
            Min-max Feature Scaling (Rescaling)
            Mean Normalization
            Standardization (Z-score Normalization)
        Principal Component Analysis
        Cross-validation
    Data Analysis
        Scaling
            Standard Scaler
            Robust Scaling
            Power Transformer
            Quantile Transformer
        Splitting Dataset
        Handling Imbalance
            Random Undersampling
            Random Oversampling
            Tomek’s Links for Undersampling
            Synthetic Minority Oversampling Technique
        Data Reanalysis
        Positive Feature (V1..., V28)
            Negative Feature (V1.. ., V28)
        Scaled Features
    Modeling
        Machine Learning Algorithms
            Logistic Regression
            Decision Tree
            Support Vector Machine (SVM)
        Model Training
            Data Preparation
            Metric Trap
        Training & Evaluation
    Further reading
    Conclusion
5. Heart Disease UCI
    Introduction
    Structure
    Objective
    Prerequisites
        Why is ML in Medicine So Critical?
        What is Explainable AI?
        Regularization
        Hypothesis Testing
        Ensemble Learning
            Bagging
            Boosting
    Let’s Understand the Data
        Data Analysis
            Correlation
            “ca”
            “oldpeak”
            “thalach”
            “cp”
        Splitting Dataset
    Machine Learning Modeling
        Machine Learning Algorithms
            Naive Bayes Classifier
            Random Forest
        Model Training
        Training & Basic Evaluation
            Naive Bayes
            Ensemble Method (Bagging)
            Ensemble Method (Boosting)
            Random Forest
        Feature Selection & Grid Searching
            Feature Selection
            Pipeline
            Grid Searching
    Explainable AI
        Feature Importance
        Model Visualization
        Partial Dependence Plot
        SHAP (SHapley Additive exPlanations)
    Further reading
    Conclusion