Data Overview

Turn raw data into answers. Short, practical lessons that take data from messy to model‑ready.

Pandas

Load, explore, and reshape data fast

Read files, select rows/columns, filter, group, merge, and tidy your datasets so analysis feels smooth, not painful.

You’ll learn: Importing data, cleaning columns, joins, groupby, and quick summaries

Visualization

Make patterns visible

Tell a clear story with plots that highlight trends, comparisons, and outliers using Matplotlib and Seaborn.

You’ll learn: Histograms, box plots, scatter plots, line charts, and choosing the right chart for the question

Data wrangling

From messy to usable

Handle missing values, fix types, engineer features, and prepare datasets that models can learn from.

You’ll learn: Imputation, encoding, scaling, datetime handling, and feature creation

Data collection

Get the data you need

Pull data from files, APIs, and the web—then store it in formats that are easy to use and share.

You’ll learn: CSV/Parquet basics, calling APIs, simple scraping, and organizing raw vs. processed data

SQL databases

Query data with confidence

Use SQL to select, join, aggregate, and filter data directly where it lives—fast and reproducible.

You’ll learn: SELECT, WHERE, JOIN, GROUP BY, HAVING, and writing queries for analysis

NoSQL (MongoDB)

Work with flexible data

Store and query JSON‑like documents for logs, events, and semi‑structured sources common in ML workflows.

You’ll learn: Inserting documents, filtering with queries, projections, and basic aggregations

---

Start with a small dataset, answer one question with a plot, then clean and shape the data for a simple model. Repeat—each pass makes the story (and the model) sharper.