- Using HTML, CSS, JavaScript combining with the characteristics of DOM (Data Object Model), Creating Web page based Visualizations.
- Using WampServer, which is a web development environment which allows you to create web applications. It installs local server environment on your windows system, Local Server being setup.
- Using Text editors like Sublime (preferred) / Visula Studio, Code workspace is setup.
- Visualize the Data by combining the capabilities of DOM using HTML, JS & CSS as Coding Interface.
Comparing Different Classification Models on the cleaned data and comparing the Confusion Matrix of all the designed Models
- Using R, I Analyze the Accident Data for US Data: Our dataset is the second-hand data we collect from Kaggle (https://www.kaggle.com/sobhanmoosavi/us-accidents) We’ll use the US accident data to identify the factors that contribute to car accidents that cause most interference in traffic, classify the accidents by their severity into two classes, then use the identified predict variables to see how to predict the accident risk classes. The prediction model is expected to provide the car accident risk guidance when weather is bad and in the high accident area to mitigate the risk in certain conditions. We’ll try to find the damage cost of car accident to estimate the damage reduction if our prediction model is applied to help on the driving. We hoped that the analysis with the data exploration and model building will answer the following questions:
- How car accidents are associated to road, weather, season, month, the time of day?
- Can the accidents be predicted with the available attributes?
- How good the car accident prediction model?
- Will the car accident prediction model be useful to guide the driving in what conditions?
- Any findings from the car accident prediction modeling.
- Peak Hour Traffic
- Wind Direction Category
- Summary of All the Models
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent