Data Science and Machine Learning: A Practical Guide

Learn to work with the date time module, including the date class, time class, and DateTime class, and use Timedelta to compute date differences.

Master built-in regex functions, including find all, search, split, and sub, and learn meta characters like square brackets, period, caret, and dollar for text pattern matching.

Master regex metacharacters by exploring square brackets, period, caret, dollar, star, plus, and the second bracket, and learn to build sets, ranges, and negations with practical examples.

Explore numpy, the numerical python library, and compare it with lists through array creation with np.array and element-wise operations. Use np.dot for dot products and vector operations.

Explore NumPy basics, including ndarrays, array creation with np.array, range, linspace, zeros, ones, and identity matrices. Learn reshaping, transposing, swapping axes, flattening, and random utilities for efficient computation.

Explore numpy operations for sorting 2d arrays by axis, and compute mean, median, max, min, std, and argmax/argmin, plus masking and basic arithmetic on ndarrays.

Learn to use pandas to create data frames, read from csv or excel, and explore data with describe and info on the iris dataset.

Explore pandas header and index operations, including removing headers, rendering a row as header, creating custom headers, and setting or resetting indices.

Explore pandas column operations, distinguishing single versus double brackets for series and data frames, and learn to filter, create, drop columns, and rows with conditions.

Explore pandas loc and iloc for label-based versus position-based data access, learn to select specific rows and columns, and master slicing and dicing with examples.

Master Pandas group by, sorting, and counts to aggregate data by drives and country, computing mean, min, max, and sum for cars per cap and number of cars.

Learn how to merge and concatenate dataframes in pandas, using inner, outer, left, and right joins on a common column, and axis-based concatenation for row or column alignment.

Learn to use the pandas datetime module to convert a time column, extract hours and day of year, filter by date, compute days, and apply value_counts for yearly occurrences.

Explore advanced pandas utilities, including setting separators, renaming headers and values, and applying string functions; learn to convert data types and find the maximum price after removing dollar signs.

Learn to plot graphs with Matplotlib, apply basic customizations like axis labels and ticks, and save figures as PNG while exploring multiple subplots and legends.

Explore the main matplotlib graph types: line plots, scatter plots, bar plots, and histograms, and learn to create and customize them with x and y values, colors, and sizes.

Identify missing values and classify them as MKR (missing completely at random), missing at random, or missing not at random, then compare deletion, imputation, and business-logic approaches.

Identify and handle outliers, including univariate and bivariate types and sources, and apply deletion, capping, imputation, and binning, which affect mean and standard deviation, with interquartile range and z-score detection.

Learn to detect and handle outliers with box plots and scatter plots using IQR and 1.5x bounds, cap extreme item outlet sales, and discuss data cleaning approaches.

Clean and standardize the gnocchi dataset by unifying city names and converting experience and education to numeric formats. Visualize city-wise job distribution and industry and skills trends.

Learn to visualize cleaned data with univariate, bivariate, and multivariate analyses, using Matplotlib, Seaborn, and Plotly to explore correlations, heatmaps, and descriptive, predictive, and prescriptive analytics.

Explore line and area plots with Seaborn and Plotly, learn to customize line width, color, alpha, and confidence intervals, and visualize Gapminder life expectancy by continent.

Visualize data with scatter, box, and violin plots using seaborn and plotly, exploring the iris dataset, descriptive analytics, and interactive 3d visuals.

Visualize maps with plotly by plotting latitude and longitude using scatter_mapbox and scatter_geo. Animate data over time with animation_frame to show changes in population or car hours.

Identify data types: categorical (nominal, ordinal) and numerical (discrete, continuous); apply descriptive statistics (mean, median, mode, range, variance). Explore inferential statistics, normal distribution, skewness, and the central limit theorem.

Learn to form null and alternate hypotheses, distinguish type I and II errors, interpret p-values, and select t, z, ANOVA, or chi-square tests for hypothesis testing.

Master exploratory data analysis (EDA) to build confidence in data, refine feature selection, and visualize insights using the Pandas Profiling library for an instant, comprehensive data report.

Install and import data profiling tools, clean the diabetes data, identify feature types, and generate a comparative HTML report with the VS library for train and test data.

Lead a capstone project by defining the business problem, gathering and cleaning hotel data, analyzing ADR and cancellation rates with visualizations to deliver reports or dashboards.