book

Data Science with Python

Name: Data Science with Python
ISBN: 9781838552862

by Rohan Chopra, Aaron England, Mohamed Noordeen Alaudeen

July 2019

Beginner to intermediate

426 pages

7h 36m

English

Packt Publishing

Read now

Unlock full access

Preface
About the BookAbout the Authors Learning ObjectivesAudienceApproachMinimum Hardware RequirementsSoftware Requirements Installation and SetupUsing Kaggle for Faster ExperimentationConventionsInstalling the Code Bundle
Chapter 1
Introduction to Data Science and Data Pre-ProcessingIntroductionPython LibrariesRoadmap for Building Machine Learning ModelsData RepresentationIndependent and Target VariablesExercise 1: Loading a Sample Dataset and Creating the Feature Matrix and Target MatrixData Cleaning Exercise 2: Removing Missing DataExercise 3: Imputing Missing DataExercise 4: Finding and Removing Outliers in DataData IntegrationExercise 5: Integrating DataData TransformationHandling Categorical DataExercise 6: Simple Replacement of Categorical Data with a NumberExercise 7: Converting Categorical Data to Numerical Data Using Label EncodingExercise 8: Converting Categorical Data to Numerical Data Using One-Hot EncodingData in Different ScalesExercise 9: Implementing Scaling Using the Standard Scaler MethodExercise 10: Implementing Scaling Using the MinMax Scaler MethodData DiscretizationExercise 11: Discretization of Continuous Data Train and Test DataExercise 12: Splitting Data into Train and Test SetsActivity 1: Pre-Processing Using the Bank Marketing Subscription DatasetSupervised LearningUnsupervised Learning Reinforcement LearningPerformance MetricsSummary
Chapter 2
Data VisualizationIntroductionFunctional ApproachExercise 13: Functional Approach – Line PlotExercise 14: Functional Approach – Add a Second Line to the Line PlotActivity 2: Line PlotExercise 15: Creating a Bar PlotActivity 3: Bar PlotExercise 16: Functional Approach – HistogramExercise 17: Functional Approach – Box-and-Whisker plotExercise 18: ScatterplotObject-Oriented Approach Using SubplotsExercise 19: Single Line Plot using SubplotsExercise 20: Multiple Line Plots Using SubplotsActivity 4: Multiple Plot Types Using SubplotsSummary
Chapter 3
Introduction to Machine Learning via Scikit-LearnIntroductionIntroduction to Linear and Logistic RegressionSimple Linear RegressionExercise 21: Preparing Data for a Linear Regression ModelExercise 22: Fitting a Simple Linear Regression Model and Determining the Intercept and CoefficientExercise 23: Generating Predictions and Evaluating the Performance of a Simple Linear Regression ModelMultiple Linear RegressionExercise 24: Fitting a Multiple Linear Regression Model and Determining the Intercept and CoefficientsActivity 5: Generating Predictions and Evaluating the Performance of a Multiple Linear Regression ModelLogistic RegressionExercise 25: Fitting a Logistic Regression Model and Determining the Intercept and CoefficientsExercise 26: Generating Predictions and Evaluating the Performance of a Logistic Regression ModelExercise 27: Tuning the Hyperparameters of a Multiple Logistic Regression ModelActivity 6: Generating Predictions and Evaluating Performance of a Tuned Logistic Regression ModelMax Margin Classification Using SVMsExercise 28: Preparing Data for the Support Vector Classifier (SVC) ModelExercise 29: Tuning the SVC Model Using Grid SearchActivity 7: Generating Predictions and Evaluating the Performance of the SVC Grid Search ModelDecision TreesActivity 8: Preparing Data for a Decision Tree ClassifierExercise 30: Tuning a Decision Tree Classifier Using Grid SearchExercise 31: Programmatically Extracting Tuned Hyperparameters from a Decision Tree Classifier Grid Search ModelActivity 9: Generating Predictions and Evaluating the Performance of a Decision Tree Classifier ModelRandom ForestsExercise 32: Preparing Data for a Random Forest RegressorActivity 10: Tuning a Random Forest RegressorExercise 33: Programmatically Extracting Tuned Hyperparameters and Determining Feature Importance from a Random Forest Regressor Grid Search ModelActivity 11: Generating Predictions and Evaluating the Performance of a Tuned Random Forest Regressor ModelSummary
Chapter 4
Dimensionality Reduction and Unsupervised LearningIntroductionHierarchical Cluster Analysis (HCA)Exercise 34: Building an HCA ModelExercise 35: Plotting an HCA Model and Assigning PredictionsK-means ClusteringExercise 36: Fitting k-means Model and Assigning PredictionsActivity 12: Ensemble k-means Clustering and Calculating PredictionsExercise 37: Calculating Mean Inertia by n_clustersExercise 38: Plotting Mean Inertia by n_clustersPrincipal Component Analysis (PCA)Exercise 39: Fitting a PCA ModelExercise 40: Choosing n_components using Threshold of Explained VarianceActivity 13: Evaluating Mean Inertia by Cluster after PCA TransformationExercise 41: Visual Comparison of Inertia by n_clustersSupervised Data Compression using Linear Discriminant Analysis (LDA)Exercise 42: Fitting LDA ModelExercise 43: Using LDA Transformed Components in Classification ModelSummary
Chapter 5
Mastering Structured DataIntroductionBoosting AlgorithmsGradient Boosting Machine (GBM)XGBoost (Extreme Gradient Boosting)Exercise 44: Using the XGBoost library to Perform ClassificationXGBoost LibraryControlling Model OverfittingHandling Imbalanced DatasetsActivity 14: Training and Predicting the Income of a PersonExternal Memory UsageCross-validationExercise 45: Using Cross-validation to Find the Best HyperparametersSaving and Loading a ModelExercise 46: Creating a Python Pcript that Predicts Based on Real-time InputActivity 15: Predicting the Loss of CustomersNeural NetworksWhat Is a Neural Network?Optimization AlgorithmsHyperparametersKerasExercise 47: Installing the Keras library for Python and Using it to Perform ClassificationKeras LibraryExercise 48: Predicting Avocado Price Using Neural NetworksCategorical VariablesOne-hot EncodingEntity EmbeddingExercise 49: Predicting Avocado Price Using Entity EmbeddingActivity 16: Predicting a Customer's Purchase AmountSummary
Chapter 6
Decoding ImagesIntroductionImagesExercise 50: Classify MNIST Using a Fully Connected Neural NetworkConvolutional Neural NetworksConvolutional LayerPooling LayerAdam OptimizerCross-entropy LossExercise 51: Classify MNIST Using a CNNRegularizationDropout LayerL1 and L2 RegularizationBatch NormalizationExercise 52: Improving Image Classification Using Regularization Using CIFAR-10 images Image Data PreprocessingNormalizationConverting to GrayscaleGetting All Images to the Same SizeOther Useful Image OperationsActivity 17: Predict if an Image Is of a Cat or a DogData AugmentationGeneratorsExercise 53: Classify CIFAR-10 Images with Image AugmentationActivity 18: Identifying and Augmenting an ImageSummary
Chapter 7
Processing Human LanguageIntroductionText Data Processing Regular ExpressionsExercise 54: Using RegEx for String Cleaning Basic Feature ExtractionText PreprocessingExercise 55: Preprocessing the IMDB Movie Review DatasetText ProcessingExercise 56: Creating Word Embeddings Using GensimActivity 19: Predicting Sentiments of Movie ReviewsRecurrent Neural Networks (RNNs)LSTMsExercise 57: Performing Sentiment Analysis Using LSTM Activity 20: Predicting Sentiments from TweetsSummary
Chapter 8
Tips and Tricks of the TradeIntroductionTransfer LearningTransfer Learning for Image DataExercise 58: Using InceptionV3 to Compare and Classify ImagesActivity 21: Classifying Images using InceptionV3Useful Tools and TipsTrain, Development, and Test DatasetsWorking with Unprocessed Datasetspandas ProfilingTensorBoardAutoMLExercise 59: Get a Well-Performing Network Using Auto-KerasModel Visualization Using KerasActivity 22: Using Transfer Learning to Predict ImagesSummary
Appendix
Chapter 1: Introduction to Data Science and Data PreprocessingActivity 1: Pre-Processing Using the Bank Marketing Subscription DatasetChapter 2: Data VisualizationActivity 2: Line PlotActivity 3: Bar PlotActivity 4: Multiple Plot Types Using SubplotsChapter 3: Introduction to Machine Learning via Scikit-LearnActivity 5: Generating Predictions and Evaluating the Performance of a Multiple Linear Regression ModelActivity 6: Generating Predictions and Evaluating Performance of a Tuned Logistic Regression ModelActivity 7: Generating Predictions and Evaluating the Performance of the SVC Grid Search ModelActivity 8: Preparing Data for a Decision Tree ClassifierActivity 9: Generating Predictions and Evaluating the Performance of a Decision Tree Classifier ModelActivity 10: Tuning a Random Forest RegressorActivity 11: Generating Predictions and Evaluating the Performance of a Tuned Random Forest Regressor ModelChapter 4: Dimensionality Reduction and Unsupervised LearningActivity 12: Ensemble k-means Clustering and Calculating PredictionsActivity 13: Evaluating Mean Inertia by Cluster after PCA TransformationChapter 5: Mastering Structured DataActivity 14: Training and Predicting the Income of a PersonActivity 15: Predicting the Loss of CustomersActivity 16: Predicting a Customer's Purchase AmountChapter 6: Decoding ImagesActivity 17: Predict if an Image Is of a Cat or a DogActivity 18: Identifying and Augmenting an ImageChapter 7: Processing Human LanguageActivity 19: Predicting Sentiments of Movie ReviewsActivity 20: Predicting Sentiments from TweetsChapter 8: Tips and Tricks of the TradeActivity 21: Classifying Images using InceptionV3Activity 22: Using Transfer Learning to Predict Images

Content preview from Data Science with Python

Chapter 5 Mastering Structured Data

Learning Objectives

By the end of this chapter, you will be able to:

Work with structured data to create highly accurate models
Use the XGBoost library to train boosting models
Use the Keras library to train neural network models
Fine-tune model parameters to get the best accuracy
Use cross-validation
Save and load your trained models

This chapter will cover the basics on how to create highly accurate structured data models.

Introduction

There are two main types of data, structured and unstructured. Structured data refers to data that has a defined format and is usually shaped as a table, such as data stored in an Excel sheet or a relational database. Unstructured data does not have a predefined schema. ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781838552862

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Data Science with Python

by Rohan Chopra, Aaron England, Mohamed Noordeen Alaudeen

Chapter 5

Mastering Structured Data

Learning Objectives

Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.