Machine Learning using Python: A Comprehensive Course

Learn the basics of Python for machine learning, including its open source, object oriented, high level design, and essential libraries like NumPy, SciPy, and scikit-learn.

Discover popular Python libraries for machine learning, including sci fi for optimization and linear algebra, pandas for data analysis, and matplotlib for data visualization.

Explore Python data types from integers and floats to strings, lists, tuples, dictionaries, and sets, with Python's object-oriented, dynamic typing, and inbuilt type checks.

Explore Python operators across arithmetic, logical, relational, membership, identity, and bitwise categories. Learn division types, exponentiation, modulus, and examples that demonstrate these operators in code.

Explore advanced data types in Biton, including bitwise operators on binary numbers and the behavior of lists, tuples, dictionaries, and sets with indexing, slicing, immutability, and common list methods.

Learn to run Python in Jupiter notebook, create and save notebooks, and write simple programs performing input, type conversion, and basic arithmetic for data science and machine learning projects.

Explore Python condition statements and selective execution using if, elif, and else. See how grading logic uses marks and input validation to demonstrate these concepts.

Learn how Python loops use for and while statements to iterate over lists, strings, dictionaries, and tuples, and apply linear search with break and a flag.

Learn how to use break and continue in Python loops to control execution, with examples on prime number checks and skipping numbers divisible by three.

Learn how Python functions enable modular, reusable code through built-in and user-defined functions, with definition and calling steps, arguments, and examples like finding the largest list element.

Explore how functions receive arguments in Python, using strings and lists, with return values and user input, and how call by value or by reference affects mutable vs immutable objects.

Explore Python function signatures by comparing required arguments with keyword, default, and variable length arguments, and learn how to call functions with correct parameter types.

Explore default and keyword arguments in Python functions by defining a function with a default location, and calling it with or without that parameter to see Sydney as the default.

Explore default arguments, variable length arguments, and keyword arguments in Python functions, enabling default values, flexible input counts, and named-parameter calls.

Explore built-in Python functions like sum for lists, then learn bubble sort with passes, comparisons, and swapping to sort a list in ascending or descending order.

Explore the scope of variables in programming by comparing local and global scope, illustrating how local variables vanish outside functions while global variables remain accessible.

Explore the Python math module, using inbuilt functions for logarithms, exponentiation, and numeric operations, and learn constants pi and e, with floor, ceil, factorial, and modf examples.

Explore Python function arguments, including string and numeric inputs, using return for sums, input for values, and compare calling by value versus by reference with lists and strings.

Learn to create simple plots with matplotlib and build line and scatter plots, customize axes, labels, titles, legends, and subplots.

Design and implement a loan calculator GUI in Python that uses labels, entry widgets, and a compute button to output monthly EMI and total payable.

Create a basic gui loan calculator that computes monthly payment and total payment using the emi formula, with inputs loan amount, annual rate, and years.

Master numpy basics in Python by importing numpy as np, creating ndarrays, handling multi-dimensional arrays, and using data types such as float, complex, boolean, plus ndmin for minimum dimensions.

Explore numpy basics by examining shape and dimensions, reshaping arrays, and the range function. Learn about item size and array creation with empty, zeros, and ones.

Explore numpy basics by building a two-dimensional array, performing advanced slicing, indexing by rows and columns, and applying boolean filters to select elements.

Explore numpy basics in a hands-on Jupyter notebook tutorial, covering arange, linspace, and logspace with start, stop, step, and endpoint options.

Learn to compute weighted averages using numpy's average function, with and without weights. Explore axis handling for one-dimensional and two-dimensional arrays and see how weights influence the result.

Explore Python's random and string modules to generate random strings and passwords of varied lengths, including lowercase, uppercase, digits, and special characters, for secure applications.

Learn to generate random strings in Python using uppercase letters, specific letter sets, and alphanumeric options, with and without repeated characters, via random and string modules.

Master numpy's unique function: it returns the array of unique elements and can provide indices, inverse mappings, or counts. Flatten inputs, track first occurrences, and use counts to read repetitions.

Explore numpy's delete function to remove rows or columns by index, reshape arrays, and flatten to a one-dimensional array with practical examples.

Master how numpy's insert function adds values before a given index along a specified axis, returning a new array (not in place) and flattening input when the axis is omitted.

Discover NumPy basics by flattening arrays with an order option, comparing flattening along column or row major orders, and practicing axis swaps and transpose-like operations on two- and three-dimensional arrays.

Master NumPy basics by computing per-column and per-row minimums and maximums, using axis to select rows or columns, and viewing the corresponding indices in a beginner-friendly tutorial.

Learn numpy basics by applying rounding functions, including the round function, floor function, and the seen function, to control decimals and convert values to the nearest integers.

Learn how numpy append adds values to an array without in-place modification, and how axis and shape rules govern append behavior, while resize demonstrates repeated entries when enlarging.

Learn NumPy basics by applying the nonzero function to locate indices of nonzero elements in a 2d array and using where to select and print values greater than a threshold.

Explore numpy basics by creating matrices with empty, zeros, ones, and identity, learn shape and data type options, and generate random matrices with the random function.

Master numpy basics through element-wise and in-place operations on arrays, using shorthand operators like += and *= to modify data, including squaring elements and transposing two-dimensional arrays.

Master numpy basics by using boolean indexing to filter arrays and create boolean lists. Apply conditions to keep values higher than 50 or even numbers, illustrating filtering with boolean lists.

Explore numpy basics by mastering manipulation functions such as reshape, flatten, transpose, broadcast, and dimension changes like expand dimensions and squeeze. Also learn concatenation, stacking, splitting, inserting, and deleting elements.

Explore three numpy functions, broadcasting, array shapes, and techniques to remove NaN and complex numbers, with hands-on examples of one-dimensional and two-dimensional arrays.

Explore NumPy basics by learning indexing and slicing in one- and two-dimensional arrays, using slice objects with start, stop, and step values to access and modify data.

Master numpy basics by studying append and resize operations, axis selection, and whether changes occur in place, with attention to input shapes and how new values are added.

Master NumPy basics by converting with item, building diagonal zeros and ones, creating identity and bordered 10x10 matrices, filling a 3x4 array 10–21, and using linspace to generate 10 values.

Explore numpy basics by finding the maximum and minimum of a flattened array with max and min, compute axis-wise peak-to-peak differences, debug with a search keyword, and apply weighted average.

Generate random strings and binary sequences using Python's random module, exploring random choices, random.choice, and random.sample, and compute sums with list comprehensions for practical tasks like passwords.

Explore numpy basics by learning simple array operations: replace elements by condition without altering the original array, find common items with intersect1d, and compute set differences with setdiff1d.

Learn how to split numpy arrays with the split function using indices and axis, create parts of sizes, and stack them along a new axis for 2D and 3D arrays.

Explore NumPy's split function, including normal, horizontal, and vertical splits. See how to divide arrays along an axis using index or selections, with examples of equal parts.

Explore numpy basics by using boolean indexing to filter arrays, selecting elements with masks, and applying conditions to extract values such as even numbers and those greater than 50.

Explore Python file handling and filesystem basics, opening text and binary files with modes r, w, a, x and binary variants, and performing read, write, or append operations.

Learn to manage files in Python using the open function, read and write modes, and the with statement for safe automatic closing.

Explore Python file system operations by opening files in append and write modes, reading content with read, readline, and readlines, and managing file pointers with tell and seek.

Import the random module and generate random numbers in Python, including random integers within a range and random floats between zero and one, plus one- and two-dimensional arrays.

Explore the random module basics in Python, generating float values from 0 to 1, creating one- and two-dimensional arrays, and using the choice function to select values from arrays.

Explore the random module basics by generating random numbers, standard normal samples, and integers, with shape and size outputs and the random sample function.

Learn the basics of the random module, including simple random data, samples from the standard normal distribution, random integers, and random sampling across shapes.

Master random module basics by selecting multiple items from a list with random.choices and random.sample. Understand that random.choices may repeat items, while random.sample returns unique selections.

Learn to use Python's random.choice on sets by converting the set to a tuple for indexing, then combine range with random.choice to pick numbers within a range.

Learn the random module basics in Python, including using choice for booleans, lists, and dictionaries, and using seed to reproduce results.

Explore the pandas library for data science, learning to create series and data frames from a dictionary, clean and transform data, and analyze statistics and relationships with indexing and selection.

Learn pandas basics for data cleaning, transformation, and analysis in Python, including loading the IMDb dataset, creating data frames, computing statistics, handling missing values, and visualizing with graphs.

Master pandas basics by loading a movie dataset with read_csv, setting the title as index, and using head, tail, info, shape, and drop_duplicates with in_place.

Discover pandas basics by cleaning and renaming columns, using the columns attribute to check names, and applying in-place updates, lowercase conversions, and underscores for robust data handling.

Learn to handle missing values in pandas by dropping nulls or imputing with the mean, using isnull and fillna for in-place data cleaning.

Master pandas basics by imputing missing values with the mean, performing group-wise imputation by donor categories, and using describe to summarize both continuous and categorical data.

Explore pandas basics by using value_counts and head to inspect frequencies, then analyze relationships among continuous variables with correlation and scatterplots for data insight.

Learn to slice, select, and extract data in pandas by using square brackets, lists of column names, and indexers like loc and iloc, including slicing rows and selecting multiple columns.

Explore matplotlib basics, including plotting types such as line, box plot, histogram, and scatter, and learn to use axis labeling, figure management, and the show function for visual analysis.

Explore matplotlib basics with simple plotting of X and Y values, power operations, and the show function, plus colors and symbols for overlays.

Explore Matplotlib basics with the object oriented interface, creating figures and axes, labeling plots, using axis plus, and adding legends for clear plots.

Discover matplotlib basics by learning plot location names and their codes from zero to ten. See examples of center, left, lower left, and other positions.

Explore Matplotlib basics by building and customizing line plots that compare advertising expenses to TV and smartphone sales, using solid and dashed lines, colors, markers, axes, and a legend.

Explore matplotlib basics by creating a 2x2 grid of subplots, plotting x, x^2, sqrt(x), exp(x), and log(x) with titles to demonstrate reusable layouts.

Master matplotlib basics by creating subplots, toggling grid visibility, customizing line styles and colors, and applying tight layout plus axis limits with auto or explicit x and y limits.

Learn to customize matplotlib charts by setting x and y ticks and their labels on the axes, using explicit positions and corresponding labels.

Master Matplotlib basics by plotting bar charts with the bar function, using x, height, bottom, and width, and create multiple series with offsets and thickness.

Master Matplotlib basics by building a stacked bar chart that stacks groups by gender, using the bottom parameter to start values, and adding a legend and labels.

Master matplotlib basics: enable grids, customize line styles, and create subplots in multi-column layouts. Control axis limits and use tight_layout to simplify figure layouts.

Explore matplotlib basics, including the interface to the object-oriented plotting level, simple plots with custom colors and symbols, labeled axes, and overlaying multiple plots with a show function.

Develop a Python age calculator app that uses labeled entry fields for birth date and current date, validates inputs, clears data, and computes exact age in years, months, and days.

Build an age calculator app that computes day, month, and year differences from a birth date by adjusting when the birth day exceeds the given day, then displays results.

Design the GeoEye age calculator GUI with a green background and blue labels for date of birth and current date, entries and two buttons to calculate age and clear.

Build a grid-based age calculator app with labels and entry widgets for date of birth, day, month, and year, plus a calculate age function and input validation.

Learn the basics of machine learning, from data-driven supervised, unsupervised, and reinforcement learning to applications like spam filtering, recommendations, and image classification.

Explore why Python is the preferred language for machine learning, and how Python’s rich libraries and tooling enable quick, flexible development of ML applications.

Explore the three types of machine learning—supervised, unsupervised, and reinforcement—along with how supervised learning uses features, labels, training, and testing to predict outputs like house prices or spam filters.

Explore supervised learning with classification and regulation, using features and labels to predict outcomes, and contrast unsupervised clustering and association, plus reinforcement learning in games.

Identify the prerequisite foundations for machine learning, including probability, linear algebra, calculus, and Python, and explore core applications like image recognition, speech recognition, natural language processing, recommendations, and self-driving cars.

Explore key machine learning applications like self-driving cars, spam filtering, virtual assistants, fraud detection, stock trading, medical diagnosis, and language translation, and learn seven-step lifecycle from data gathering to deployment.

Explore the machine learning lifecycle from data gathering and wrangling to data analysis and training, and learn how data preparation and cleaning affect deployment.

Explore the machine learning lifecycle, from training and testing to deployment, in supervised learning contexts; emphasize data separation, validation, cross-validation, and avoiding overfitting; learn diverse data sources and dataset types.

Learn essential data preprocessing for machine learning, including acquiring, importing, cleaning, and structuring datasets, handling missing values, encoding categorical data, and splitting into training and test sets with feature scaling.

Learn the basics of machine learning, including supervised learning with labeled data and common algorithms such as linear and logistic regression, SVM, and trees, plus unsupervised clustering and association.

Master the basics of machine learning by exploring supervised, unsupervised, and reinforcement learning. Learn how features and labels map inputs to outputs with examples like spam filtering.

Explore the difference between supervised and unsupervised learning, highlighting labeled input-output pairs, feedback signals, and the goal of predicting new data versus discovering hidden patterns.

Explore the basics of supervised, unsupervised, and reinforcement learning, the machine learning lifecycle, and key algorithms like regression, classification, logistic regression, decision trees, and SVM.

Explore supervised learning with regression analysis, modeling the relationship between dependent and independent variables to predict outputs. Learn linear, logistic, polynomial, SVR, decision tree, and random forest regression.

Explore linear regression, the simplest method modeling the linear relation between continuous variables, with simple and multiple forms, and introduce logistic regression with a sigmoid function for binary classification.

Explore supervised learning with logistic regression for binary, multiclass, and ordinal classification using the sigmoid. Explore polynomial regression for nonlinear data; use support vector machines and decision trees.

Explore types of machine learning with decision trees, entropy and information gain, and compare logistic regression, polynomial regression, and support vector machines through practical weather-based examples.

Explore classification in machine learning, a supervised task that maps data to discrete target labels, covering binary, multiclass, and multilabel goals, and basics of k-nearest neighbors.

Fit a regression line with the least squares method from a scatter plot of hours studied vs. marks. Predict outcomes and evaluate with the coefficient of determination.

Learn to implement simple linear regression in Python from scratch, compute B0 and B1, predict Y, and plot the regression line with a scatter plot using hours studied vs marks.

Fix the return function to correctly compute regression coefficients b1 and b0 from x and y using the mean and SS.

Explore types of machine learning through a negative relationship example that models how daily exercise minutes affect heart attack risk, including plotting data and debugging a simple linear regression.

we revisited a simple linear regression example, fixed the return to compute b1 and b0, and plotted x against y to show the negative relationship.

Explore simple linear regression with one input, learn to estimate the intercept and slope by minimizing squared errors, and assess fit with R-squared.

Explore simple linear regression with numpy and a popular python library, training on X and y, and predict new values while interpreting intercept, slope, and the coefficient of determination (R^2).

Explore multiple linear regression, an extension of simple regression using several explanatory variables to predict a dependent variable, via Y = Xb + epsilon and X'X inverse X'Y.

Explore multiple linear regression with two independent variables, derive A, B1, B2 via matrix algebra, and apply to predict job performance from aptitude and conscientiousness.

Learn to implement multiple linear regression using the psychic loan package, prepare two-input X and one-output Y, fit the model, obtain intercept, coefficients, and r-squared, and predict on new data.

Use multiple regression to predict the stock index price from the interest rate and unemployment rate, building a dataset and validating linearity before modeling.

Learn how to perform multiple regression in Python by modeling the stock index price with interest rate and unemployment rate, using scikit-learn and statsmodels, and interpret coefficients and predictions.

Build a Python graphical user interface to perform multiple linear regression by letting users enter independent variables and display the intercept and regression coefficients, and prep for supervised learning topics.

Explore applying multiple regression to stock index using new interest rate and new unemployment rate, display coefficients and intercept, and render dual scatter plots with legends.

Perform multiple regression on the Boston housing dataset to predict median home value using lower status and rooms; split into training and testing sets, and evaluate with RMSE and R-squared.

Knn is a simple, non parametric, lazy learning algorithm that uses Euclidean distance to classify data by the label among the k nearest neighbors, and can be used for regression.

Implement the k-nearest neighbors algorithm in Python using scikit-learn with the Iris dataset. Split data into 80% training, 20% testing, apply feature scaling, fit a 5-nearest-neighbor model, and predict.

Assess the knn algorithm with confusion metrics, classification reports, precision, recall, and f1 score on a test dataset, showing a confusion matrix and accuracy above 95 percent.

Learn how to read a confusion matrix for binary classification, dissecting true/false positives and negatives, and compute accuracy, misclassification rate, recall, false positive rate, and prevalence.

Split a dataset into training and testing sets using train_test_split to train models and evaluate performance. Adjust train_size, test_size, and random_state, and consider overfitting, underfitting, and cross-validation.

learn how the k-nearest neighbors algorithm classifies data using a weather and temperature dataset, encoding categorical features, and predicting play outcomes.

Explore the k-nearest neighbors classifier on a wine dataset from the cyclone library, using 13 features across three cultivars, with a training and testing split, accuracy from 61% to 80%.

Introduce the decision tree classifier, explaining entropy and information gain to select the root node and split data into leaf outcomes.

Explore entropy and information gain as tools to build a decision tree, using contingency tables and features like credit rating and balance to determine the best split.

Implement a decision tree classifier in Python using the Cyclone Library, using information gain to select the root node and predict bank note authenticity from four attributes.

Build and evaluate a decision tree classifier in Python using the confusion matrix, precision, recall, and accuracy, and generate a classification report showing about 97% accuracy.

Explains the decision tree algorithm for regression and classification, guiding data preparation, training and testing splits, and evaluation with mean absolute error, mean squared error, and root mean square error.

Explore unsupervised learning through clustering, which groups unlabeled data by similar features and patterns. Understand hard versus soft clustering and various methods—partitioning, density-based, distribution model based, hierarchical, and fuzzy clustering.

Explore partition clustering and k-means, focusing on centroid-based grouping and predefined cluster counts. Examine density-based methods like dbscan, gaussian mixture models with em, and hierarchical agglomerative approaches for flexible shapes.

Explore unsupervised learning through hierarchical clustering and agglomerative methods with tree-like representations. Learn single, complete, centroid, and average linkage and applications in cancer, search engines, customer segmentation, biology, land use.

this lecture demonstrates python-based agglomerated hierarchical clustering on mall customers, comparing with k means, and covers data preprocessing, determining cluster count, training, and visualizing clusters using age and annual income.

Apply the AHC algorithm to perform agglomerative clustering with five clusters using euclidean distance and linkage, train and predict on the model, and visualize the results.

Explore k-means clustering, an unsupervised learning method that partitions data into clusters using centroids. Apply the elbow method to determine the optimal number of clusters and assess within-cluster distances.

Explore k-means clustering on a two-subject dataset of seven individuals. Initialize two clusters with far-apart points, iteratively assign by Euclidean distance and update centroids until stable.

Implement k-means clustering in Python, using the elbow method to select the number of clusters based on within-cluster sum of squares, for a customer dataset with income and spending score.