Julia Programming for Machine Learning

Create 4 + 2im in julia and inspect real and imaginary parts. Use constructors, compute abs and angle, and note that division or modulo is not allowed on complex numbers.

Learn to create and mutate one-dimensional arrays (vectors) in Julia, including in-place updates with replace, push!, and splice. Explore vector operations, broadcasting with dot syntax, and range-based creation via collect.

Explore 2D arrays and matrices in Julia: create, index, replace, extract submatrices, flatten and reshape, and perform element-wise and matrix multiplication, with zeros, ones, fill, identity, random matrices, and det.

Explore constructing and manipulating multi-dimensional arrays in Julia, from vectors and matrices to three- and four-dimensional tensors, using reshape, indexing, subarrays, and in-place updates with copy and fill!

Extract and transpose 2x2 submatrices from arr10. Use vcat or hcat to form a 4-by-2 matrix with rows 24 22, 12 10, 15 13, 3 1, in Julia.

Julia programming for machine learning: map digits to words using a dictionary dt, read a number, convert digits with array comprehension, and print the result in repl.

Explore if-else and elseif syntax in Julia, with a ternary operator. Determine triangle types: equilateral, isosceles, scalene; get inputs from the user and validate side lengths.

Explore a Julia program that reads three triangle side lengths, validates them with all() and a+b>c checks, and classifies the triangle as equilateral, isosceles, or scalene.

Create a Julia prime finder that reads an interval, validates bounds as natural integers, uses any() to test primality, and prints primes or a no-primes message.

Explore map, filter, and reduce in Julia using anonymous functions, the do keyword, and pipe-based function composition to transform ranges, tuples, and two- or three-variable inputs.

Explore varargs functions in Julia, defining functions with a variable number of arguments using an ellipsis and a tuple. Also handle arbitrary keyword arguments via kwargs as a NamedTuple.

Learn two Julia tasks: implement find_num for primes or squares in Int16 with typed and optional args, and create a Shapes hierarchy to compute area and perimeter via area_peri.

Explore Julia's Expr() constructor by inspecting ASTs, symbols, and :call heads, then build expressions using Polish (prefix) notation and the expression constructor to reproduce results.

Explore Julia macros such as @elapsed, @allocated, and @which to measure time, memory, and locate code origins. See @eval and @sprintf from the Printf library for formatting and evaluating expressions.

Define enumerated types with Julia's @enum macro, creating Quadrilateral and Polygon with instances like square and triangle; use instances() to view their values and define a function to print them.

Create and manipulate julia data frames with the DataFrames package, from empty frames to adding letter and index columns, constructing from vectors or dicts, and comparing df1, df2, df3.

Learn to import and read data as a DataFrame in Julia using CSV and DataFrames. Explore Occupation.csv with 153 rows and 6 columns, manipulating columns by name, index, or regex.

Learn to filter data frames in Julia by age, work experience, state, and profession with logical arrays, then sort by name, age, and profession using length and reverse options.

Apply the split-apply-combine approach to a data frame by grouping by profession (and sex and state), applying functions like nrow, mean age, and cor, and compiling aggregate statistics.

Study Julia's Dates module export list and use now, today, Date, Time, and DateTime to compute durations; create, convert, and compare Period and CompoundPeriod objects for date arithmetic.

Learn to create and access time series data in Julia with TimeArray, generating random observations, constructing from timestamps, renaming columns, plotting trends, and indexing by dates and columns.

Explores time-series manipulation with TimeArray in Julia, covering lag(), lead(), diff(), percentchange(), moving() and map() transformations, and exporting results; introduces halfofyour() and tertileofyear() functions and anonymous moving-window design.

Analyze e-commerce data with TimeArray-driven visualizations across five Brazilian cities. Compare monthly revenue and items purchased, and examine moving-window trends in revenue and orders from Olist.

Visualize order time intervals using the TimeArray olist_ta with two side-by-side plots for five Brazilian cities and global customers, then map 73 categories to 7 timeslots and 8 weekdays.

Explore linear regression using the least squares method to minimize residuals and derive the regression line y = ax + b for simple and multiple regression.

Set working directory, import body brain weight CSV, create 2-column df with body weight independent and brain weight dependent, then split into training and test sets with shuffle for reproducibility.

Build a multiple linear regression model in Julia to predict medical insurance charges from age, bmi, children, sex, smoker, and region, with data import, encoding, and train-test split.

Explore polynomial regression to fit curves to data, extending simple linear regression with higher degrees using least squares. Relate years of experience to salary by estimating coefficients a0, a1, a2.

Develop a polynomial regression model to predict CTC from years of experience, convert the first column to numeric, split data into training and test sets, and visualize results.