Python for Data Science and Machine Learning beginners

Explore Python basics including boolean logic, floor division, absolute value, and case-sensitive variables, then master conditional operators, comparison with ==, and for and while loops.

Join a student community for real-time doubt solving, access to questions and answers, and updates on data science and machine learning, plus career guidance via WhatsApp, Facebook, and YouTube.

Explore Python basics, basic operations, loop constructs for and while, and data types in this module, forming the foundation for beginner data science and machine learning topics.

Master terminology for strings in Python for data science and machine learning beginners, including indexes, accessing characters by position, and extracting substrings from complete strings.

Explore Python strings by indexing and slicing, splitting into lists, formatting and replacing text, handling line breaks, and printing results in loops.

Explore lists with heterogeneous elements, extend and append lists, create nested lists, remove duplicates, and sort, while highlighting the mutability difference between lists and tuples.

learn two ways to define dictionaries in python, use keys and values, access items, convert lists to dicts, and perform pop, pop item, and clear operations.

Install the library with pip and import numpy in a Jupyter notebook. Define a 3x3 matrix as a list of lists and examine its elements, brackets, and dimensions.

Create numpy arrays from lists, inspect their shape, and reshape one-dimensional arrays into 2x3 or 3x2. Use range to generate sequences and create empty arrays for loops.

Explore numpy array operations in notebooks: create and store arrays, locate max and min indices with argmax and argmin, use where for condition-based indexing, and copy for safe deep copies.

explains normal distribution, the mean, and how increasing sample size broadens the curve, contrasts normal with poisoned and left-skewed distributions, and previews generating samples with num by.

Explore numpy random numbers: generate integers and samples, produce normally distributed data, and build multi-dimensional arrays; fix seeds for reproducibility and visualize distributions with histograms, including poisson with lambda=1.

Explore dot and cross products, and matrix multiplication with simple vector and matrix examples. Learn to convert linear equations to matrix form for linear regression, including determinants and adjoint concepts.

Learn advanced NumPy techniques to generate random samples, manipulate matrices, compute dot and cross products, determinants and inverses, solve linear equations, and find eigenvalues and eigenvectors.

Learn to manipulate data frames with pandas, starting from cities with labels. Create and convert data frames from lists, dictionaries, and numpy arrays, and inspect columns and indices.

Explore descriptive statistics in pandas, compute correlations among numerical columns, apply moving average and NaN handling (fill, pad, interpolate), and perform group by aggregations.

Create and customize figures with matplotlib by initializing a figure, adding axes, labeling x and y, plotting a sine wave from data, and setting titles and labels.

Learn to create and arrange subplots in matplotlib, initialize a figure with random data, and place plots in 1x1 up to 3x3 grids across specified axes positions.

Explore data visualization with matplotlib by generating line, bar (vertical and horizontal), scatter, pie charts, and heatmaps, using sample ranges and accessible documentation to practice different plot types.

Explore the basics of data science, including regression, univariate and bivariate problems, and classification, clustering, and data types like categorical and numerical.

Explore a World Bank data set in a Jupyter notebook, load and clean data, perform univariate analysis, and plot a time series of population to illustrate data exploration.

Explore univariate categorical data in Python, distinguish it from numerical data, analyze unique values with value_counts, create a random sample, and visualize distributions using a pie chart.

Explore unbiased sample estimates for univariate data by computing the mean as an unbiased estimator and estimating variance from squared deviations using n-1, with a preview of correlation and covariance.

Explore covariance and correlation to assess whether two data sets share the same trend, learn their formulas, and apply mean subtraction and standard deviation in practical examples.

Explore hypothesis testing in data exploration by contrasting null and alternate hypotheses, illustrated with Newton's gravity example, sampling, p-values, and detecting outliers.

Apply a two-sample t-test in Python to compare two normal samples, using equal and unequal variance cases, and interpret p-values to assess population similarity.

Apply the z-test to test a sample against a known population mean and standard deviation. Compare the z-test and t-test by variance and sample size, with an Excel example.

Learn how to treat NaN values in a data frame by filling with the mean, forward filling, backfilling, dropping rows, or interpolating (linear and quadratic) with adjustable order.

This lecture covers modeling basics for supervised and unsupervised learning, explaining regression and classification with X and Y, and introducing methods like decision trees, logistic regression, neural networks, and clustering.

Learn how linear regression models the relationship between two variables, fits a line with slope and intercept using y = mx + c, and uses it to predict values.

Learn to classify three wine types using logistic regression on a wide eleven-feature dataset, with a three-class setup and train-test splits at 60/40 and 70/30, plus confusion-matrix evaluation.

Apply a complete flight delay prediction project using January 2019 and 2020 data, build a data dictionary, load with pandas, and explore decision tree, random forest, and logistic regression models.

Explore flight delay prediction data preprocessing using Kaggle data, creating a data dictionary, converting airport and time features to categorical, and cleaning with pandas profiling to prepare features for modeling.

Generate features for flight delay prediction by mapping categorical string columns, preparing X and y, performing a train-test split, and training a decision tree classifier to achieve about 78% accuracy.

Learn to build and evaluate a random forest classifier for flight delay prediction, including training, predicting, confusion metrics, accuracy comparison with decision trees, and hyperparameter tweaking.

Train the model on full data to forecast flight delays using random forest, leveraging future schedules and features like airline name, origin IDs, and destination IDs.