This Dash app serves as a comprehensive tool for visualizing and analyzing the Flight Delay Dataset (2018-2022) for the Machine Learning and Information Visualization Term Project at Virginia Tech. The app is designed to provide users with various functionalities for data cleaning, statistical analysis, correlation and covariance exploration, and visualization of complex plots.(Couldn't add Code due to VT Policies)
Flight Delay Visualization Dashboard
-
Data Cleaning Tab:
- Description: This tab assists users in cleaning and preprocessing the raw dataset. It guides users through the steps involved in cleaning the data, ensuring its quality and suitability for further analysis.
- Steps:
- Importing the dataset
- Handling missing values
- Removing duplicates
- Standardizing data formats
- Outlier detection and treatment
-
Statistical Tab:
- Description: This tab facilitates statistical analysis of the dataset, focusing on normality tests. It includes three commonly used normality tests: KS Test, Shapiro Test, and D'Augustino Pearson Test, providing insights into the distribution of the data.
- Features:
- KS Test: Kolmogorov-Smirnov test for assessing the goodness of fit of a sample distribution to a theoretical distribution.
- Shapiro Test: Shapiro-Wilk test for testing the null hypothesis that a sample comes from a normally distributed population.
- D'Augustino Pearson Test: Omnibus test for assessing normality based on skewness and kurtosis.
-
Correlation and Covariance Tab:
- Description: This tab allows users to explore the relationships between different variables in the dataset by displaying correlation or covariance matrices. Users can select a subset of columns to generate these matrices, enabling deeper insights into the data's interdependencies.
- Features:
- Correlation Matrix: Visualizes pairwise correlations between selected variables using Pearson correlation coefficient.
- Covariance Matrix: Displays the covariance values between selected variables, providing insights into the linear relationship between them.
-
Complex Plots:
- Description: This section presents visually rich and informative plots created to depict complex patterns and trends within the dataset. These plots offer a deeper understanding of the data and can aid in identifying underlying structures or anomalies.
- Types of Plots:
- Time series plots
- Geographic visualizations (if applicable)
- Multivariate scatter plots
- Cluster analyses
- Distribution plots
Note: Users can navigate through different tabs to access specific functionalities and visualize various aspects of the dataset. The app aims to enhance the understanding of flight delay patterns and support informed decision-making processes.