Complete Data Analyst Bootcamp From Basics To Advanced

Learn how Python variables are declared and assigned, follow naming conventions, and explore types, type checking, and conversions, dynamic typing, practical examples, input handling, and common errors.

Learn to use Python conditional statements, including if, elif, and else, with nested structures and real-world examples, plus common errors and best practices.

Explore real world uses of Python lists, a to do list, organizing student grades, inventory management, and user feedback analysis. Learn how append, remove, and membership checks enable data handling.

Master Python functions by defining and calling them, covering syntax, parameters, default values, and variable-length arguments; explore positional and keyword arguments, docstrings, and return statements.

Learn how to manage files and directories with Python's os and os.path, including creating directories, listing contents, and building absolute and relative paths.

Learn to handle errors gracefully in Python using try, except, else, and finally blocks. Explore common exceptions, implement user-friendly messages, and ensure clean resource management with file and database examples.

Explore NumPy, the fundamental Python library for scientific computing, and learn to create, reshape, and perform vectorized operations on arrays and matrices.

Distinguish population data, the complete set of observations, from sample data, a subset used to estimate population parameters such as mu and sigma square.

Explore the four primary scales of data measurement, nominal, ordinal, interval, and ratio, and learn how each defines data categories, order, intervals, and true zeros.

Explore measure of central tendency, including mean, median, and mode, and learn how they describe the center of a data set while handling outliers and guiding feature engineering.

Learn how percentiles and quartiles describe distributions, with formulas to compute values below which a percentage lies and to identify first, second, and third quartiles.

Master the five-number summary—minimum, Q1, median, Q3, and maximum—to build a box plot, compute lower and upper fences, and identify outliers using seaborn in Python.

Explore covariance and correlation as measures of how two continuous variables relate, including positive and negative co-movement, and when to use Pearson or Spearman correlations for linear and non-linear patterns.

Explore the normal or Gaussian distribution, a continuous bell-curve distribution with mean equals median equals mode. Learn its symmetric nature, mean and variance, the pdf, and the 68-95-99.7% empirical rule.

Explore continuous and discrete uniform distributions, defined by bounds a and b, with pdf 1/(b-a) or pmf 1/n, and examine their cdf, mean, and variance through candies and dice examples.

Determine whether to use t test or z test by checking whether the population standard deviation is known and the sample size, guiding the appropriate test.

Explore Bayes statistics, Bayes theorem, and conditional probability, with examples of independent and dependent events, and apply Naive Bayes to predict outcomes from features.

Explore the chi square test for goodness of fit, a nonparametric method for categorical data, and learn to compare observed versus expected counts for population proportions.

Apply chi-square goodness-of-fit to compare 2010 weight category proportions with 2020 observed counts. With alpha 0.05, compute expected counts from 2010, obtain chi-square 26.66, reject H0, conclude weights differ.

Learn how to perform one-way anova to compare means across three dosage groups using an f test, with null and alternate hypotheses and variance partition.

Master feature engineering to handle missing data, including MCAR, MAR, and not at random, with mean, median, mode, and random-sampling imputation. Learn to decide when to drop rows or columns.

Learn data encoding for categorical features, including one hot, label, and target guided ordinal encoding, converting categories to numerical values and addressing sparse matrices.

Compare label encoding and ordinal encoding for converting categorical data to numbers. See how label encoding assigns unique labels, while ordinal encoding assigns ordered ranks, using sklearn's LabelEncoder and OrdinalEncoder.