English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 41 Hours | 17.1 GB

Learn Python, Tensorflow, Deep Learning, Regression, Classification, Neural Networks, Artificial Intelligence & more!

Welcome to the Complete Data Science and Machine Learning Bootcamp, the only course you need to learn Python and get into data science.

At over 35+ hours, this Python course is without a doubt the most comprehensive data science and machine learning course available online. Even if you have zero programming experience, this course will take you from beginner to mastery. Here’s why:

The course is a taught by the lead instructor at the App Brewery, London’s leading in-person programming bootcamp.

In the course, you’ll be learning the latest tools and technologies that are used by data scientists at Google, Amazon, or Netflix.

This course doesn’t cut any corners, there are beautiful animated explanation videos and real-world projects to build.

The curriculum was developed over a period of three years together with industry professionals, researchers and student testing and feedback.

To date, we’ve taught over 200,000 students how to code and many have gone on to change their lives by getting jobs in the industry or starting their own tech startup.

You’ll save yourself over $12,000 by enrolling, but get access to the same teaching materials and learn from the same instructor and curriculum as our in-person programming bootcamp.

We’ll take you step-by-step through video tutorials and teach you everything you need to know to succeed as a data scientist and machine learning professional.

The course includes over 35 hours of HD video tutorials and builds your programming knowledge while solving real-world problems.

- In the curriculum, we cover a large number of important data science and machine learning topics, such as:
- Data Cleaning and Pre-Processing
- Data Exploration and Visualisation
- Linear Regression
- Multivariable Regression
- Optimisation Algorithms and Gradient Descent
- Naive Bayes Classification
- Descriptive Statistics and Probability Theory
- Neural Networks and Deep Learning
- Model Evaluation and Analysis
- Serving a Tensorflow Model

Throughout the course, we cover all the tools used by data scientists and machine learning experts, including:

- Python 3
- Tensorflow
- Pandas
- Numpy
- Scikit Learn
- Keras
- Matplotlib
- Seaborn
- SciPy
- SymPy

By the end of this course, you will be fluently programming in Python and be ready to tackle any data science project. We’ll be covering all of these Python programming concepts:

- Data Types and Variables
- String Manipulation
- Functions
- Objects
- Lists, Tuples and Dictionaries
- Loops and Iterators
- Conditionals and Control Flow
- Generator Functions
- Context Managers and Name Scoping
- Error Handling

By working through real-world projects you get to understand the entire workflow of a data scientist which is incredibly valuable to a potential employer.

What you’ll learn

- You will learn how to program using Python through practical projects
- Use data science algorithms to analyse data in real life projects such as spam classification and image
- recognition
- Build a portfolio of data science projects to apply for jobs in the industry
- Understand how to use the latest tools in data science, including Tensorflow, Matplotlib, Numpy and many
- more
- Create your own neural networks and understand how to use them to perform deep learning
- Understand and apply data visualisation techniques to explore large datasets

**+ Table of Contents**

**Introduction to the Course**

1 What is Machine Learning

2 What is Data Science

3 Download the Syllabus

4 Top Tips for Succeeding on this Course

5 Course Resources List

**Predict Movie Box Office Revenue with Linear Regression**

6 Introduction to Linear Regression & Specifying the Problem

7 Gather & Clean the Data

8 Explore & Visualise the Data with Python

9 The Intuition behind the Linear Regression Model

10 Analyse and Evaluate the Results

11 Download the Complete Notebook Here

12 Join the Student Community

13 Any Feedback on this Section

**Python Programming for Data Science and Machine Learning**

14 Windows Users – Install Anaconda

15 Mac Users – Install Anaconda

16 Does LSD Make You Better at Maths

17 Download the 12 Rules to Learn to Code

18 [Python] – Variables and Types

19 [Python] – Lists and Arrays

20 [Python & Pandas] – Dataframes and Series

21 [Python] – Module Imports

22 [Python] – Functions – Part 1 Defining and Calling Functions

23 [Python] – Functions – Part 2 Arguments & Parameters

24 [Python] – Functions – Part 3 Results & Return Values

25 [Python] – Objects – Understanding Attributes and Methods

26 How to Make Sense of Python Documentation for Data Visualisation

27 Working with Python Objects to Analyse Data

28 [Python] – Tips, Code Style and Naming Conventions

29 Download the Complete Notebook Here

30 Any Feedback on this Section

**Introduction to Optimisation and the Gradient Descent Algorithm**

31 What’s Coming Up

32 How a Machine Learns

33 Introduction to Cost Functions

34 LaTeX Markdown and Generating Data with Numpy

35 Understanding the Power Rule & Creating Charts with Subplots

36 [Python] – Loops and the Gradient Descent Algorithm

37 [Python] – Advanced Functions and the Pitfalls of Optimisation (Part 1)

38 [Python] – Tuples and the Pitfalls of Optimisation (Part 2)

39 Understanding the Learning Rate

40 How to Create 3-Dimensional Charts

41 Understanding Partial Derivatives and How to use SymPy

42 Implementing Batch Gradient Descent with SymPy

43 [Python] – Loops and Performance Considerations

44 Reshaping and Slicing N-Dimensional Arrays

45 Concatenating Numpy Arrays

46 Introduction to the Mean Squared Error (MSE)

47 Transposing and Reshaping Arrays

48 Implementing a MSE Cost Function

49 Understanding Nested Loops and Plotting the MSE Function (Part 1)

50 Plotting the Mean Squared Error (MSE) on a Surface (Part 2)

51 Running Gradient Descent with a MSE Cost Function

52 Visualising the Optimisation on a 3D Surface

53 Download the Complete Notebook Here

54 Any Feedback on this Section

**Predict House Prices with Multivariable Linear Regression**

55 Defining the Problem

56 Gathering the Boston House Price Data

57 Clean and Explore the Data (Part 1) Understand the Nature of the Dataset

58 Clean and Explore the Data (Part 2) Find Missing Values

59 Visualising Data (Part 1) Historams, Distributions & Outliers

60 Visualising Data (Part 2) Seaborn and Probability Density Functions

61 Working with Index Data, Pandas Series, and Dummy Variables

62 Understanding Descriptive Statistics the Mean vs the Median

63 Introduction to Correlation Understanding Strength & Direction

64 Calculating Correlations and the Problem posed by Multicollinearity

65 Visualising Correlations with a Heatmap

66 Techniques to Style Scatter Plots

67 A Note for the Next Lesson

68 Working with Seaborn Pairplots & Jupyter Microbenchmarking Techniques

69 Understanding Multivariable Regression

70 How to Shuffle and Split Training & Testing Data

71 Running a Multivariable Regression

72 How to Calculate the Model Fit with R-Squared

73 Introduction to Model Evaluation

74 Improving the Model by Transforming the Data

75 How to Interpret Coefficients using p-Values and Statistical Significance

76 Understanding VIF & Testing for Multicollinearity

77 Model Simplification & Baysian Information Criterion

78 How to Analyse and Plot Regression Residuals

79 Residual Analysis (Part 1) Predicted vs Actual Values

80 Residual Analysis (Part 2) Graphing and Comparing Regression Residuals

81 Making Predictions (Part 1) MSE & R-Squared

82 Making Predictions (Part 2) Standard Deviation, RMSE, and Prediction Intervals

83 Build a Valuation Tool (Part 1) Working with Pandas Series & Numpy ndarrays

84 [Python] – Conditional Statements – Build a Valuation Tool (Part 2)

85 Build a Valuation Tool (Part 3) Docstrings & Creating your own Python Module

86 Download the Complete Notebook Here

87 Any Feedback on this Section

**Pre-Process Text Data for a Naive Bayes Classifier to Filter Spam Emails Part 1**

88 How to Translate a Business Problem into a Machine Learning Problem

89 Gathering Email Data and Working with Archives & Text Editors

90 How to Add the Lesson Resources to the Project

91 The Naive Bayes Algorithm and the Decision Boundary for a Classifier

92 Basic Probability

93 Joint & Conditional Probability

94 Bayes Theorem

95 Reading Files (Part 1) Absolute Paths and Relative Paths

96 Reading Files (Part 2) Stream Objects and Email Structure

97 Extracting the Text in the Email Body

98 [Python] – Generator Functions & the yield Keyword

99 Create a Pandas DataFrame of Email Bodies

100 Cleaning Data (Part 1) Check for Empty Emails & Null Entries

101 Cleaning Data (Part 2) Working with a DataFrame Index

102 Saving a JSON File with Pandas

103 Data Visualisation (Part 1) Pie Charts

104 Data Visualisation (Part 2) Donut Charts

105 Introduction to Natural Language Processing (NLP)

106 Tokenizing, Removing Stop Words and the Python Set Data Structure

107 Word Stemming & Removing Punctuation

108 Removing HTML tags with BeautifulSoup

109 Creating a Function for Text Processing

110 A Note for the Next Lesson

111 Advanced Subsetting on DataFrames the apply() Function

112 [Python] – Logical Operators to Create Subsets and Indices

113 Word Clouds & How to install Additional Python Packages

114 Creating your First Word Cloud

115 Styling the Word Cloud with a Mask

116 Solving the Hamlet Challenge

117 Styling Word Clouds with Custom Fonts

118 Create the Vocabulary for the Spam Classifier

119 Coding Challenge Check for Membership in a Collection

120 Coding Challenge Find the Longest Email

121 Sparse Matrix (Part 1) Split the Training and Testing Data

122 Sparse Matrix (Part 2) Data Munging with Nested Loops

123 Sparse Matrix (Part 3) Using groupby() and Saving .txt Files

124 Coding Challenge Solution Preparing the Test Data

125 Checkpoint Understanding the Data

126 Download the Complete Notebook Here

127 Any Feedback on this Section

**Train a Naive Bayes Classifier to Create a Spam Filter Part 2**

128 Setting up the Notebook and Understanding Delimiters in a Dataset

129 Create a Full Matrix

130 Count the Tokens to Train the Naive Bayes Model

131 Sum the Tokens across the Spam and Ham Subsets

132 Calculate the Token Probabilities and Save the Trained Model

133 Coding Challenge Prepare the Test Data

134 Download the Complete Notebook Here

135 Any Feedback on this Section

**Test and Evaluate a Naive Bayes Classifier Part 3**

136 Set up the Testing Notebook

137 Joint Conditional Probability (Part 1) Dot Product

138 Joint Conditional Probablity (Part 2) Priors

139 Making Predictions Comparing Joint Probabilities

140 The Accuracy Metric

141 Visualising the Decision Boundary

142 False Positive vs False Negatives

143 The Recall Metric

144 The Precision Metric

145 The F-score or F1 Metric

146 A Naive Bayes Implementation using SciKit Learn

147 Download the Complete Notebook Here

148 Any Feedback on this Section

**Introduction to Neural Networks and How to Use Pre-Trained Models**

149 The Human Brain and the Inspiration for Artificial Neural Networks

150 Layers, Feature Generation and Learning

151 Costs and Disadvantages of Neural Networks

152 Preprocessing Image Data and How RGB Works

153 Importing Keras Models and the Tensorflow Graph

154 Making Predictions using InceptionResNet

155 Coding Challenge Solution Using other Keras Models

156 Download the Complete Notebook Here

157 Any Feedback on this Section

**Build an Artificial Neural Network to Recognise Images using Keras & Tensorflow**

158 Solving a Business Problem with Image Classification

159 Installing Tensorflow and Keras for Jupyter

160 Gathering the CIFAR 10 Dataset

161 Exploring the CIFAR Data

162 Pre-processing Scaling Inputs and Creating a Validation Dataset

163 Compiling a Keras Model and Understanding the Cross Entropy Loss Function

164 Interacting with the Operating System and the Python Try-Catch Block

165 Fit a Keras Model and Use Tensorboard to Visualise Learning and Spot Problems

166 Use Regularisation to Prevent Overfitting Early Stopping & Dropout Techniques

167 Use the Model to Make Predictions

168 Model Evaluation and the Confusion Matrix

169 Model Evaluation and the Confusion Matrix

170 Download the Complete Notebook Here

171 Any Feedback on this Section

**Use Tensorflow to Classify Handwritten Digits**

172 What’s coming up

173 Getting the Data and Loading it into Numpy Arrays

174 Data Exploration and Understanding the Structure of the Input Data

175 Data Preprocessing One-Hot Encoding and Creating the Validation Dataset

176 What is a Tensor

177 Creating Tensors and Setting up the Neural Network Architecture

178 Defining the Cross Entropy Loss Function, the Optimizer and the Metrics

179 TensorFlow Sessions and Batching Data

180 Tensorboard Summaries and the Filewriter

181 Understanding the Tensorflow Graph Nodes and Edges

182 Name Scoping and Image Visualisation in Tensorboard

183 Different Model Architectures Experimenting with Dropout

184 Prediction and Model Evaluation

185 Download the Complete Notebook Here

186 Any Feedback on this Section

**Serving a Tensorflow Model through a Website**

187 What you’ll make

188 Saving Tensorflow Models

189 Loading a SavedModel

190 Converting a Model to Tensorflow.js

191 Introducing the Website Project and Tooling

192 HTML and CSS Styling

193 Loading a Tensorflow.js Model and Starting your own Server

194 Adding a Favicon

195 Styling an HTML Canvas

196 Drawing on an HTML Canvas

197 Data Pre-Processing for Tensorflow.js

198 Introduction to OpenCV

199 Resizing and Adding Padding to Images

200 Calculating the Centre of Mass and Shifting the Image

201 Making a Prediction from a Digit drawn on the HTML Canvas

202 Adding the Game Logic

203 Publish and Share your Website!

204 Any Feedback on this Section

**Next Steps**

205 Where next

206 What Modules Do You Want to See

207 Stay in Touch!

Resolve the captcha to access the links!