Machine Learning & Data Science Masterclass in Python and R

Install essential tools for the course by downloading R and RStudio, configuring defaults, adjusting display zoom, and linking the course materials folder for future work.

Explore the RStudio workflow: create and run R scripts, manage the environment, print vectors, learn indexing from 1, install and load packages, and use source versus echo.

Install and configure R and RStudio for the course, guiding setup on Windows, macOS, and Linux. Learn to adjust zoom, set defaults, and connect to your course materials folder.

Explore the basics of r and rstudio, create and run r scripts, manage variables and vectors, install packages, and use source, echo, and environment tools for data science workflows.

Learn to create and print vectors in R using c, see how vectors hold a single data type, observe type coercion to character, and compute min, max, and mean.

Install and load the data table package to create a data table, access columns with the $ operator, and compute min, max, and mean or median.

Discover how data and models enable predictions in machine learning, using diabetes examples and features like fatigue, weight, and blood pressure, and explore classification, linear regression, and clustering.

Explore how regression, classification, clustering, and natural language processing apply to real problems, from predicting turnover and car prices to spam detection and customer segmentation.

Explore linear regression by drawing a line through data points to predict price from size, using y equals a times x plus b and interpreting slope and intercept.

Build a linear regression model that predicts apartment value from size by minimizing the sum of squared distances to the model line, using Python and R.

Load the flat prices csv into a pandas data frame in a Jupyter notebook, display the first rows, and plot a scatter of square meters versus price.

Apply a linear regression model to predict prices from square metres using fit with x and y, interpreting intercept and coefficient to estimate a 40 square metres flat.

Fit a linear regression model to predict apartment prices from square meters, then predict multiple values using double brackets and plot the model line from min to max square meters.

Apply linear regression in R to a CSV of square meters and prices. Read data, install and load data.table and ggplot2, plot the relationship, format axes with scales.

Apply linear regression in R with the stats library using lm and a price ~ square meters formula, using data to reveal intercept and slope and plot the regression line.

apply linear regression by drawing the model line with genome dot smooth and lm, se = false. predict apartment prices from square meters, e.g., 95 m².

Predict apartment prices from square meters with R regression. Use predict to estimate prices for 35 and 95 m2 and store results in a data table with a price column.

Explore why quadratic error drives linear regression by minimizing squared distances between real values and predictions, demonstrating why this approach outperforms plain distance in practice.

Apply linear regression to predict used car prices from kilometers driven using real data, while cleaning out anomalous entries to prevent distortion.

Apply a practical Python workflow using pandas to create a data frame, visualize kilometers vs. price with a scatter plot, and run linear regression to predict car value.

Learn an R-based sample solution predicting used car prices from kilometers, using data read from autos prepared, scatter plots, and a linear model for prediction.

Split data into training and testing sets to estimate model performance, using roughly 75/25 or 80/20 distributions, and randomize to ensure even coverage before testing unseen points.

Learn to split data into train and test sets with train_test_split, prepare X and y (square meters and prices), and explore multiple features improving predictions.

Train the model on x_train and y_train with linear regression, then predict on x_test and plot the line to compare it with the test data.

Apply the train-test concept by replacing flat prices with the autos prepared CSV and rebuild the code to model price based on kilometers.

Split apartment price data into train and test sets with a train index using caret, setting price as the target y for model evaluation.

Showcases train and test data visualization using a cue plot with square meters on the x-axis and price on the y-axis, plus a reproducible linear regression line with seed-based consistency.

Engage in a hands-on R exercise using a train/test split to predict a car price from its kilometers, reinforcing understanding of the code and keeping you motivated.

Explore multidimensional linear regression by modeling hotel prices with features like rooms and last year's profit, forming a plane in three dimensions with Python and R.

Explore linear regression with multiple variables, emphasize data independence, avoid redundant features, and handle correlated columns to improve price prediction.

Apply multiple-variable linear regression to predict hotel price using profit and million square meters, training a model with a machine learning library, inspecting intercept and coefficients, and computing price.

Evaluate the linear regression model with multiple variables by predicting y for the test data and comparing results to actual values.

Use multiple-variable linear regression with square meters and profit to predict price in million, perform train/test split, extract coefficients, and add a price prediction column for model comparison.

Explore the coefficient of determination, or r squared, as a measure of model quality by comparing your model to a baseline that ignores inputs and uses the Y average.

Explore how r squared, the coefficient of determination, evaluates model fit by comparing the model line to the mean baseline and showing how smaller residual distances yield higher values.

Learn to compute R² with linear regression in Python using scikit-learn, including train-test split, fitting with X and y, predicting on test data, and using the score method.

this lecture demonstrates comparing models by R² in Python using linear regression on hotel data, showing how random state and feature choices affect the average score across 100 iterations.

Calculate the R² for a linear regression predicting price in million from square meters and profit, using train data, and compare with test data to assess performance.

Compare models by R² to determine whether including profit improves hotel price predictions; train with and without profit, compute coefficient of determination, and interpret the results.

Compare regression models using the coefficient of determination on a used car dataset, building one model with kilometers alone and another with horsepower, and evaluate R squared on test data.

Apply linear regression to predict price from km and horsepower, training and testing the model and printing its score. See how horsepower improves the score and squared reflects prediction quality.

learn how to split data into train and test sets, build price prediction models using kilometers and horsepower (PS), and evaluate with r squared.