**Python Fundamentals LiveLessons Part V: Machine Learning with Classification, Regression & Clustering; Deep Learning with Convolutional & Recurrent Neural Networks; Big Data with Hadoop®, Spark , NoSQL & IoT**

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 12h 54m | 4.52 GB

The professional programmer’s Deitel® video guide to Python development with the powerful IPython and Jupyter Notebooks platforms. Part V focuses on machine-learning, deep learning and big-data case studies, using popular AI and big-data tools in Python.

Python Fundamentals LiveLessons with Paul Deitel is a code-oriented presentation of Python—one of the world’s most popular and fastest growing languages. In the context of scores of real-world code examples ranging from individual snippets to complete scripts, Paul will demonstrate coding with the interactive IPython interpreter and Jupyter Notebooks. You’ll quickly become familiar with the Python language, its popular programming idioms, key Python Standard Library modules and several popular open-source libraries. In the Intro to Data Science videos, Paul lays the groundwork for later lessons in which he’ll introduce some of today’s most compelling, leading-edge computing technologies, including natural language processing, data mining Twitter® for sentiment analysis, cognitive computing with IBM® Watson™, supervised machine learning with classification and regression, unsupervised machine learning with clustering, computer vision through deep learning and convolutional neural networks, sentiment analysis through deep learning with recurrent neural networks, big data with Hadoop®, Spark™ streaming, NoSQL databases and the Internet of Things.

What you will learn in Part V’s case studies:

- Lesson 14–Machine Learning: Classification, Regression and Clustering–Use scikit-learn with popular datasets to perform machine learning studies; Use Seaborn and Matplotlib to visualize and explore data; Perform supervised machine learning with k-nearest neighbors classification and linear regression; Perform multi-classification with Digits dataset; Divide a dataset into training, testing and validation sets; Tune hyperparameters with k-fold cross-validation; Measure model performance; Display a confusion matrix showing classification prediction hits and misses; Perform multiple linear regression with the California Housing dataset; Perform dimensionality reduction with PCA and t-SNE on the Iris and Digits datasets to prepare them for two-dimensional visualizations. Perform unsupervised machine learning with k-means clustering and the Iris dataset.
- Lesson 15–Deep Learning–What a neural network is and how it enables deep learning; Create Keras neural networks;Keras layers, activation functions, loss functions and optimizers; Use a Keras convolutional neural network (CNN) trained on the MNIST dataset to build a computer vision application that recognizes handwritten digits; Use a Keras recurrent neural network (RNN) trained on the IMDb dataset to create a sentiment analysis application that performs binary classification of positive and negative movie reviews.
- Lesson 16–Big Data: Hadoop, Spark, 17–Manipulate a SQLite relational database using SQL; Understand the four major types of NoSQL databases; Store tweets in a MongoDB NoSQL JSON document database and visualize them on a Folium map; Apache Hadoop and how it’s used in big-data batch-processing applications; Build a Hadoop MapReduce application on Microsoft’s Azure HDInsight cloud service; Apache Spark and how it’s used in high-performance, real-time big-data applications; Process mini-batches of data with Spark streaming; Internet of Things (IoT) and the publish/subscribe model; Publish messages from a simulated Internet-connected device and visualize messages in a dashboard; Subscribe to PubNub’s sample live streams and visualize the data.

**Table of Contents**

1 Lesson overview

2 Introduction to Machine Learning

3 Case Study – Classification with k-Nearest Neighbors and the Digits Dataset, Part 1

4 k-Nearest Neighbors Algorithm

5 k-Nearest Neighbors Algorithm – Hyperparameters and Hyperparameter Tuning

6 Loading the Dataset

7 Loading the Dataset – Displaying the Description

8 Loading the Dataset – Checking the Sample and Target Sizes

9 Loading the Dataset – A Sample Digit Image

10 Loading the Dataset – Preparing the Data for Use with Scikit-Learn

11 Visualizing the Data

12 Splitting the Data for Training and Testing

13 Creating the Model

14 Training the Model

15 Predicting Digit Classes

16 Case Study – Classification with k-Nearest Neighbors and the Digits Dataset, Part 2

17 Metrics for Model Accuracy – Estimator Method score

18 Metrics for Model Accuracy – Confusion Matrix

19 Metrics for Model Accuracy – Classification Report

20 Metrics for Model Accuracy – Visualizing the Confusion Matrix

21 K-Fold Cross-Validation

22 Running Multiple Models to Find the Best One

23 Hyperparameter Tuning

24 Case Study – Time Series and Simple Linear Regression

25 Loading the Average High Temperatures into a DataFrame

26 Splitting the Data for Training and Testing

27 Training the Model

28 Testing the Model

29 Predicting Future Temperatures and Estimating Past Temperatures

30 Visualizing the Dataset with the Regression Line

31 Overfitting_Underfitting

32 Case Study – Multiple Linear Regression with the California Housing Dataset

33 Loading the Dataset

34 Exploring the Data with Pandas

35 Visualizing the Features

36 Splitting the Data for Training and Testing

37 Training the Model

38 Testing the Model

39 Visualizing the Expected vs. Predicted Prices

40 Regression Model Metrics

41 Choosing the Best Model

42 Case Study – Unsupervised Machine Learning, Part 1–Dimensionality Reduction

43 Loading the Digits Dataset

44 Creating a TSNE Estimator for Dimensionality Reduction

45 Transforming the Digits Dataset’s Features into Two Dimensions

46 Visualizing the Reduced Data

47 Visualizing the Reduced Data with Different Colors for Each Digit

48 Visualizing the Reduced Data in 3D

49 Case Study – Unsupervised Machine Learning, Part 2–k-Means Clustering

50 Loading the Iris Dataset

51 Exploring the Iris Dataset – Descriptive Statistics with Pandas

52 Visualizing the Dataset with a Seaborn pairplot

53 Using a KMeans Estimator

54 Dimensionality Reduction with Principal Component Analysis

55 Choosing the Best Clustering Estimator

56 Lesson overview

57 Introduction

58 Deep Learning Applications

59 Deep Learning Demos

60 Keras Resources

61 Keras Built-In Datasets

62 Custom Anaconda Environments

63 Neural Networks

64 Tensors

65 Convolutional Neural Networks for Vision; Multi-Classification with the MNIST Dataset

66 Reproducibility in Keras and Deep Learning

67 Basic Keras Neural Network

68 Loading the MNIST Dataset

69 Data Exploration

70 Visualizing Digits

71 Reshaping the Image Data

72 Normalizing the Image Data

73 One-Hot Encoding – Converting the Labels From Integers to Categorical Data

74 Creating the Neural Network

75 Adding Layers to the Network

76 Convolution

77 Adding a Conv2D Convolution Layer to Our Model

78 Dimensionality of the First Convolution Layer‚Äôs Output

79 Overfitting

80 Adding a Pooling Layer

81 Adding Another Convolutional Layer and Pooling Layer

82 Flattening the Results to One Dimension with a Keras Flatten Layer

83 Adding a Dense Layer to Reduce the Number of Features

84 Adding Another Dense Layer to Produce the Final Output

85 Printing the Model’s Summary

86 Visualizing a Model‚Äôs Structure

87 Compiling the Model

88 Training and Evaluating the Model

89 Evaluating the Model on Unseen Data

90 Making Predictions

91 Locating the Incorrect Predictions

92 Visualizing Incorrect Predictions

93 Displaying the Probabilities for Several Incorrect Predictions

94 Saving and Loading a Model

95 Visualizing Neural Network Training with TensorBoard

96 ConvnetJS – Browser-Based Deep-Learning Training and Visualization

97 Recurrent Neural Networks for Sequences; Sentiment Analysis with the IMDb Dataset

98 Loading the IMDb Movie Reviews Dataset

99 Data Exploration

100 Movie Review Encodings and Decoding a Review

101 Data Preparation

102 Creating the Neural Network

103 Adding an Embedding Layer

104 Adding an LSTM Layer

105 Adding a Dense Output Layer

106 Compiling the Model and Displaying the Summary

107 Training and Evaluating the Model (1 of 2)

108 Training and Evaluating the Model (2 of 2)

109 Tuning Deep Learning Models

110 Lesson overview

111 Introduction–Databases

112 Introduction–Apache Hadoop and Apache Spark

113 Introduction–Internet of Things

114 Introduction–Experience Cloud and Desktop Big-Data Software

115 Introduction–Big Data Sources

116 Relational Databases and Structured Query Language (SQL)

117 A books Database

118 SELECT Queries

119 WHERE Clause

120 ORDER BY Clause

121 Merging Data from Multiple Tables – INNER JOIN

122 INSERT INTO Statement

123 UPDATE Statement

124 DELETE FROM Statement

125 NoSQL and NewSQL Big-Data Databases – A Brief Tour

126 NoSQL Key-Value Databases

127 NoSQL Document Databases

128 NoSQL Columnar Databases

129 NoSQL Graph Databases

130 NewSQL Databases

131 Case Study – A MongoDB JSON Document Database

132 Creating the MongoDB Atlas Cluster

133 Streaming Tweets into MongoDB

134 Hadoop

135 Hadoop Overview

136 Summarizing Word Lengths in Romeo and Juliet via MapReduce

137 Creating an Apache Hadoop Cluster in Microsoft Azure HDInsight – Part 1

138 Creating an Apache Hadoop Cluster in Microsoft Azure HDInsight – Part 2

139 Hadoop Streaming

140 Implementing the Mapper

141 Implementing the Reducer

142 Preparing to Run the MapReduce Example

143 Running the MapReduce Job

144 Spark Overview

145 Docker and the Jupyter Docker Stacks

146 Word Count with Spark

147 Spark Word Count on Microsoft Azure

148 Spark Streaming – Counting Twitter Hashtags Using the pysparknotebook Docker Stack

149 Streaming Tweets to a Socket

150 Summarizing Tweet Hashtags; Introducing Spark SQL

151 Internet of Things and Dashboards

152 Publish and Subscribe

153 Visualizing a PubNub Sample Live Stream with a Freeboard Dashboard

154 Simulating an Internet-Connected Thermostat in Python and Creating a Dashbboard in Freeboard.io

155 Creating a Python PubNub Subscriber

Resolve the captcha to access the links!