The widespread use of the World Wide Web and social media has resulted in the creation and access to enormous amount of data becoming available. The data needs to be analyzed to be able to apply the information in useful ways in many fields including business, science, and social science. The course will teach you to apply your Python programming skills to complex data analysis problems. You will learn to use Pandas for data analysis and Seaborn for data visualization, with JupyterLab as your IDE. Additionally, you’ll learn how to get, clean, prepare, and analyze data, including time-series data. Moreover, you’ll learn to use linear regression models to predict unknown and future values.
Audience
Previous experience with Python programming.
Prerequisites
Basic Python programming experience. You should be comfortable working with strings, lists, tuples, dictionaries loops and conditionals and writing your own functions.
Course OutlineIntroduction to Python for data analysis
- What data analysis is
- The Python skills that you need for data analysis
- How to use JupyterLab as your IDE
- How to split the screen between two Notebooks
- How to use Magic Commands
The Pandas essentials for data analysis
- Introduction to the Pandas DataFrame
- How to examine the data
- How to access the columns and rows
- How to work with the data
- How to shape the data
- How to analyze the data
The Pandas essentials for data visualization
- Introduction to data visualization
- How to create 8 types of plots
- How to enhance a plot
The Seaborn essentials for data visualization
- Introduction to Seaborn
- How to enhance and save plots
- How to create relational plots
- How to create categorical plots
- How to create distribution plots
- Other techniques for enhancing a plot
How to get the data
- How to find the data that you want to analyze
- How to import data into a DataFrame
- How to get database data into a DataFrame
- How to work with a Stata file
- How to work with a JSON file
How to clean the data
- Introduction to data cleaning
- How to simplify the data
- How to find and fix missing values
- How to fix data type problems
- How find and fix outliers
How to prepare the data
- How to add and modify columns
- How to apply functions and lambda expressions
- How to work with indexes
- How to combine DataFrames
- How to handle the SettingWithCopyWarning
How to analyze the data
- How to create and plot long data
- How to group and aggregate the data
- How to create and use pivot tables
- How to work with bins
- More skills for data analysis
How to analyze time-series data
- How to reindex time-series data
- How to resample time-series data
- How to work with rolling windows
- How to work with running totals
How to make predictions with a linear regression model
- Introduction to predictive analysis
- How to find correlations between variables
- How to use Scikit-learn to work with a linear regression
- How to plot regression models with Seaborn
How to make predictions with a multiple regression model
- A simple regression model for a Cars dataset
- How to work with a multiple regression model
- How to work with categorical variables
- How to improve a multiple regression model
