Python Machine Learning Tracks road map for computer science students, which including the following main topics:
Machine Learning Tracks
| Course | Chapter | H | Videos | Exercises |
|---|---|---|---|---|
|
AI Fundamentals | Introduction to AI | 4 | 14 | 49 |
| Supervised Learning | ||||
| Unsupervised Learning | ||||
| Deep Learning & Beyond | ||||
|
Software Engineering for Data Scientists in Python | Software Engineering & Data Science | 4 | 15 | 51 |
| Writing a Python Module | ||||
| Utilizing Classes | ||||
| Maintainability | ||||
|
Preprocessing for Machine Learning in Python | Introduction to Data Preprocessing | 4 | 20 | 62 |
| Standardizing Data | ||||
| Feature Engineering | ||||
| Selecting features for modeling | ||||
| Putting it all together | ||||
|
Linear Classifiers in Python | Applying logistic regression and SVM | 4 | 13 | 44 |
| Loss functions | ||||
| Logistic regression | ||||
| Support Vector Machines | ||||
|
Unsupervised Learning in Python | Clustering for dataset exploration | 4 | 13 | 52 |
| Visualization with hierarchical clustering and t-SNE | ||||
| Decorrelating your data and dimension reduction | ||||
| Discovering interpretable features | ||||
|
Supervised Learning with scikit-learn | Classification | 4 | 17 | 54 |
| Regression | ||||
| Fine-tuning your model | ||||
| Preprocessing and pipelines | ||||
|
Machine Learning with Tree-Based Models in Python | Classification and Regression Trees | 5 | 15 | 57 |
| The Bias-Variance Tradeoff | ||||
| Bagging and Random Forests | ||||
| Boosting | ||||
| Model Tuning | ||||
|
Introduction to Predictive Analytics in Python | Building Logistic Regression Models | 4 | 14 | 52 |
| Forward stepwise variable selection for logistic regression | ||||
| Explaining model performance to business | ||||
| Interpreting and explaining models | ||||
|
Dimensionality Reduction in Python | Exploring high dimensional data | 4 | 16 | 58 |
| Feature selection I, selecting for feature information | ||||
| Feature selection II, selecting for model accuracy | ||||
| Feature extraction | ||||
|
Designing Machine Learning Workflows in Python | The Standard Workflow | 4 | 16 | 51 |
| The Human in the Loop | ||||
| Model Lifecycle Management | ||||
| Unsupervised Workflows | ||||
|
Case Study: School Budgeting with Machine Learning in Python | Exploring the raw data | 4 | 15 | 51 |
| Creating a simple first model | ||||
| Improving your model | ||||
| Learning from the experts | ||||
|
Machine Learning for Time Series Data in Python | Time Series and Machine Learning Primer | 4 | 13 | 53 |
| Time Series as Inputs to a Model | ||||
| Predicting Time Series Data | ||||
| Validating and Inspecting Time Series Models | ||||
|
Machine Learning for Marketing in Python | Machine learning for marketing basics | 4 | 16 | 53 |
| Churn prediction and drivers | ||||
| Customer Lifetime Value (CLV) prediction | ||||
| Customer segmentation | ||||
|
Human Resources Analytics: Predicting Employee Churn in Python | Introduction to HR Analytics | 4 | 14 | 44 |
| Predicting employee turnover | ||||
| Evaluating the turnover prediction model | ||||
| Choosing the best turnover prediction model | ||||
|
Machine Learning for Finance in Python | Preparing data and a linear model | 4 | 15 | 59 |
| Machine learning tree methods | ||||
| Neural networks and KNN | ||||
| Machine learning with modern portfolio theory | ||||
|
Extreme Gradient Boosting with XGBoost | Classification with XGBoost | 4 | 16 | 49 |
| Regression with XGBoost | ||||
| Fine-tuning your XGBoost model | ||||
| Using XGBoost in pipelines | ||||
|
Parallel Programming with Dask in Python | Working with Big Data | 4 | 17 | 58 |
| Working with Dask Arrays | ||||
| Working with Dask DataFrames | ||||
| Working with Dask Bags for Unstructured Data | ||||
| Case Study: Analyzing Flight Delays | ||||
|
Fraud Detection in Python | Introduction and preparing your data | 4 | 16 | 57 |
| Fraud detection using labeled data | ||||
| Fraud detection using unlabeled data | ||||
| Fraud detection using text | ||||
|
Cluster Analysis in Python | Introduction to Clustering | 4 | 14 | 46 |
| Hierarchical Clustering | ||||
| K-Means Clustering | ||||
| Clustering in Real World | ||||
|
Model Validation in Python | Basic Modeling in scikit-learn | 4 | 15 | 47 |
| Validation Basics | ||||
| Cross Validation | ||||
| Selecting the best model with Hyperparameter tuning. | ||||
|
Hyperparameter Tuning in Python | Hyperparameters and Parameters | 4 | 13 | 44 |
| Grid search | ||||
| Random Search | ||||
| Informed Search | ||||
|
Ensemble Methods in Python | Combining Multiple Models | 4 | 15 | 52 |
| Bagging | ||||
| Boosting | ||||
| Stacking | ||||
|
Practicing Machine Learning Interview Questions in Python | Data Pre-processing and Visualization | 4 | 16 | 60 |
| Supervised Learning | ||||
| Unsupervised Learning | ||||
| Model Selection and Evaluation | ||||
|
Analyzing IoT Data in Python | Accessing IoT Data | 4 | 16 | 53 |
| Processing IoT data | ||||
| Analyzing IoT data | ||||
| Machine learning for IoT |
Deep Learning Tracks
| Course | Chapter | H | Videos | Exercises |
|---|---|---|---|---|
|
Introduction to Deep Learning in Python | Basics of deep learning and neural networks | 4 | 17 | 50 |
| Optimizing a neural network with backward propagation | ||||
| Building deep learning models with keras | ||||
| Fine-tuning keras models | ||||
|
Introduction to Deep Learning with Keras | Introducing Keras | 4 | 15 | 59 |
| Going Deeper | ||||
| Improving Your Model Performance | ||||
| Advanced Model Architectures | ||||
|
Introduction to Deep Learning with PyTorch | Introduction to PyTorch | 4 | 17 | 53 |
| Artificial Neural Networks | ||||
| Convolutional Neural Networks (CNNs) | ||||
| Using Convolutional Neural Networks | ||||
|
Introduction to TensorFlow in Python | Introduction to TensorFlow | 4 | 15 | 51 |
| Linear models | ||||
| Neural Networks | ||||
| High Level APIs | ||||
|
Recurrent Neural Networks for Language Modeling in Python | Recurrent Neural Networks and Keras | 4 | 16 | 54 |
| RNN Architecture | ||||
| Multi-class classification | ||||
| Sequence to Sequence Models | ||||
|
Predicting CTR with Machine Learning in Python | Introduction to CTR and Basic Techniques | 4 | 15 | 57 |
| Exploratory CTR Data Analysis | ||||
| Model Applications and Improvements | ||||
| Deep Learning | ||||
|
Image Processing in Python | Introducing Image Processing and scikit-image | 4 | 16 | 54 |
| Filters, Contrast, Transformation and Morphology | ||||
| Image restoration, Noise, Segmentation and Contours | ||||
| Advanced Operations, Detecting Faces and Features | ||||
|
Image Processing with Keras in Python | Image Processing With Neural Networks | 4 | 13 | 45 |
| Using Convolutions | ||||
| Going Deeper | ||||
| Understanding and Improving Deep Convolutional Networks | ||||
|
Biomedical Image Analysis in Python | Exploration | 4 | 15 | 54 |
| Masks and Filters | ||||
| Measurement | ||||
| Image Comparison | ||||
|
Advanced Deep Learning with Keras | The Keras Functional API | 4 | 13 | 46 |
| Two Input Networks Using Categorical Embeddings, Shared Layers, and Merge Layers | ||||
| Multiple Inputs: 3 Inputs (and Beyond!) | ||||
| Multiple Outputs |
Natural Language Processing Tracks
| Course | Chapter | H | Videos | Exercises |
|---|---|---|---|---|
|
Introduction to Natural Language Processing in Python | Regular expressions & word tokenization | 4 | 15 | 51 |
| Simple topic identification | ||||
| Named-entity recognition | ||||
| Building a "fake news" classifier | ||||
|
Regular Expressions in Python | Basic Concepts of String Manipulation | 4 | 15 | 54 |
| Formatting Strings | ||||
| Regular Expressions for Pattern Matching | ||||
| Advanced Regular Expression Concepts | ||||
|
Sentiment Analysis in Python | Sentiment Analysis Nuts and Bolts | 4 | 16 | 60 |
| Numeric Features from Reviews | ||||
| More on Numeric Vectors: Transforming Tweets | ||||
| Let's Predict the Sentiment | ||||
|
Natural Language Generation in Python | Introduction to sequential data | 4 | 13 | 52 |
| Write like Shakespeare | ||||
| Translate words to a different language | ||||
| Autocomplete your sentences | ||||
|
Feature Engineering for NLP in Python | Basic features and readability scores | 4 | 15 | 52 |
| Text preprocessing, POS tagging and NER | ||||
| N-Gram models | ||||
| TF-IDF and similarity scores | ||||
|
Machine Translation in Python | Introduction to machine translation | 4 | 16 | 58 |
| Implementing an encoder decoder model with Keras | ||||
| Training and generating translations | ||||
| Teacher Forcing and word embeddings | ||||
|
Spoken Language Processing in Python | Introduction to Spoken Language Processing with Python | 4 | 14 | 53 |
| Using the Python SpeechRecognition library | ||||
| Manipulating Audio Files with PyDub | ||||
| Processing text transcribed from spoken language | ||||
|
Building Chatbots in Python | Chatbots 101 | 4 | 15 | 49 |
| Understanding natural language | ||||
| Building a virtual assistant | ||||
| Dialogue | ||||
|
Advanced NLP with spaCy | Finding words, phrases, names and concepts | 5 | 15 | 55 |
| Large-scale data analysis with spaCy | ||||
| Processing Pipelines | ||||
| Training a neural network model |