Data Wrangling Training

Course Duration : 14 Weeks

Level : All Levels

Instructor-Led Training : Yes

Live Classroom: Yes

Live-Online : Yes

Launch your career in Data Wrangling. By mastering the skills and techniques covered in these courses, students will be better equipped to handle the challenges of real-world data analysis.

What you'll learn

Define techniques and methods for collecting data from various sources including files, web, databases, etc.

Identify statistical analysis and visualization techniques that can be used to gain insights into the data.

Calculate and apply techniques for data preprocessing such as dealing with missing values, outliers, sampling, normalization, and discretization.

Advance your subject-matter expertise

Learn in-demand skills from university and industry experts

Master a subject or tool with hands-on projects

Develop a deep understanding of key concepts

Earn a career certificate from the University of Colorado Boulder

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV

Share it on social media and in your performance review

Weeks Duration

Hr/Week Therory

Hr/Week Lab

Students

Introduction to Data Wrangling

What is Data Wrangling?
Definition and importance in data science.

review of the data wrangling process: Cleaning, transforming, and enriching data.

Real-world examples of data wrangling in different domains.
Basic Data Types and Structures
Numeric, categorical, and textual data types.

Understanding arrays, lists, dictionaries, and data frames.

Common data formats: CSV, JSON, XML, Excel, and databases.

Data Acquisition

Loading Data from Files
Using Python libraries (e.g., pandas and numpy) to load CSV, Excel, and JSON files.

Dealing with missing or incomplete data.
Accessing Data from APIs
RESTful APIs and how to retrieve data using requests or HTTP. client.

Introduction to API authentication and working with JSON responses.
Scraping Data from the Web
Introduction to web scraping using BeautifulSoup and Selenium.

Ethical considerations and rules for web scraping.

Data Cleaning

Handling Missing Data
Strategies for detecting and handling missing data: Imputation, deletion, and interpolation.

How to use pandas for handling missing data.
Data Standardization and Normalization
Converting data to a common format (e.g., date/time, text casing, etc.).

Normalizing numeric values using scaling techniques (Min-Max scaling, Z-score normalization).
Dealing with Duplicates and Outliers
Detecting and removing duplicate records.

Identifying outliers using statistical techniques (Z-score, IQR) and handling them.
Text Cleaning
Tokenization, stemming, lemmatization.

Removing stopwords, punctuation, and handling special characters.

Data Transformation

Data Type Conversion
Converting data types (e.g., string to date time, numeric to categorical).
Data Reshaping
Techniques for pivoting, melting, and stacking data using pandas.

Aggregating data using group by and summarizing functions (e.g., sum, mean, median).
Feature Engineering
Creating new features from existing data (e.g., deriving a “month” column from a date).

Binning and bucketing data for better representation.
Dealing with Large Datasets
Optimizing memory usage (downcasting, loading chunks of data).

Using Dask or PySpark for wrangling large datasets.

Data Enrichment

Merging and Joining Data
Types of joins (inner, outer, left, right) and how to use them.

Combining data from multiple sources.
Geospatial Data Wrangling
Handling geographic data using libraries like geopandas.

Understanding and using shapefiles and geocoding.
Time Series Data Wrangling
Resampling, rolling windows, and time zone handling.

Working with time-indexed data using pandas.

Advanced Topics in Data Wrangling

Data Validation
Ensuring data accuracy and consistency.

Implementing validation checks and constraints (e.g., unique IDs, value ranges).
Handling Unstructured Data
Techniques for dealing with images, audio, and text data.

Introduction to Natural Language Processing (NLP) for text wrangling.
Automation of Data Wrangling
Writing reusable functions and pipelines for recurring tasks.

Introduction to libraries like Airflow for scheduling and automating data workflows.

Tools for Data Wrangling

Using Excel for Data Wrangling
Excel formulas and pivot tables for small datasets.

Data cleaning techniques in Excel.
Python for Data Wrangling
Mastering pandas, numpy, and matplotlib for handling and visualizing data.

Introduction to PySpark for big data wrangling.
SQL for Data Wrangling
Writing complex SQL queries for extracting and transforming data.

Data cleaning and joining in relational databases.

Case Studies and Projects

Real-world Data Wrangling Challenges
Case study examples in finance, healthcare, e-commerce, and more.

Group projects to solve complex data-wrangling problems using the learned techniques.
Capstone Project
Complete a full data wrangling project from acquisition to cleaning, transformation, and enrichment.

Present findings and insights from the wrangled data.

Best Practices in Data Wrangling

Reproducibility and Documentation
Documenting each step of the data wrangling process.

Version control for data pipelines and datasets (e.g., using Git).
Ethical Considerations in Data Wrangling
Handling sensitive data, data privacy, and compliance (GDPR, HIPAA).

Avoiding biased or misrepresented data transformations.