Data analysis and visualization with PYTHON Pandas

Learning Outcomes

Learn how to extract and represent data using Python data structures, descriptive statistics

Learn how to deal with missing data

Learn data manipulation, cleaning, and processing using Python Pandas library

Learn data visualization Python libraries such as Matplotlib and Seaborn

In this course you will gain industry-specific data science skills.

Course Details

12 hours in total (two sessions per week) instructor-led course on data analysis using Python Pandas. You will gain practical experience of the most commonly used Python modules for data scientists.

We will explore Numpy (‘Numerical Python'), Pandas (data analysis library), Matplotlib and Seaborn Library.

Our lecture material is going to be in Jupyter notebook - you can download them ftom our private GitHub repository.

Session 1: Introduction to Pandas ( 3 hours)

• Data types and data structures: Lists, Tuples, Dictionaries, Sets
• Data Structures in Pandas
• Series Data Structures: Creating and Manipulating
• Dataframe Data Structures
• Creating DataFrame from Arrays, lists and Series
• Indexing and Slicing
• Group by - single column, multiple columns
• Group by - Aggregate, Aggregate for multiple functions
• Sorting
• Applying Function
• Iteration Data in DataFrame
• Joining multiple data frames
• Conditional selection and boolean masking
• .set_index() and .reset_index()

Code Challenge

Session 2: Data Cleaning and Preparation ( 3 hours)

• Dealing with Duplicates
• Regex
• Replacing Values.
• Transforming data using function and mapping,
• Renaming Axis Indexes, Discretization, and Binning.
• Dealing with Categorical Data
• Dealing with Text Data (Strings and String Objects)

Code Challenge

Session 3: Dealing with missing data ( 3 hours)

• Identifying missing data
• Visualizing Missing Data
• Imputation Techniques for Numerical and categorical variables
• Imputing Time Series Data

Code Challenge

Session 4: Plotting and Visualization ( 3 hours)

• Introduction to Visualization
• Visualization with Scatter Plots, Bar Plots, Line Plots
• Visualization with Distributions
• Visualization with Heatmaps
• Visualization with multi-plot grids

Who this course is for:

The course is useful for

• professionals who apply data analysis as part of there professional work
• students who are interested in data science or machine learning jobs
• anyone who is using excel for data analysis. Using pandas will make your data analysis process more efficient and quicker
• for anyone with a STEM background looking to change career.

Prerequisites

Understanding of programming is desirable. Pre-course foundation module can be made available for beginners.