Summary
This is a data visualization of the Titanic Dataset taken from the Kaggle website. This dataset contains a sample of 891 individuals from the 2224 individuals present on the Titanic Ship.
In this data visualization project, I would like to showcase the fact that:
- The Females were more likely to be saved than Males. The gender of the individual mattered in their survival.
- The Upper-class individuals were twice more likely to be saved than the individuals from the lower class.
- The age of an individual also played it's part in his survival.
- Children bellow 10 years had 30 % more chance of survival than individuals in age group 60-70 years. It got more worse for individuals more than 70 years old.
Being in one or more favorable categories increases your chance at survival significantly.
Design
To draw comparisons between the survival of an individual and various categories they belong to, I chose Bar charts. Bar Charts enabled me to visually distinguish how the chance of survival of an Individual varied for various categories.
I choose "Red" color to show the individuals who perished and "Blue" color to show the individuals who survived. Having an experience of working in the Stock Market, I have a bias of red being negative and Blue being a positive indicator of share's price. So, I made my color choice based on this bias.
I chose to show the graphs in two modes/views.
- Count
- Percentage
Count view enabled the viewer to look at the no of persons in various categories , whereas the percent view enabled the users to look at percentages which enabled the viewer to compare the survival in the different type of categories. So while percentage provided the differentiation among different categories, count provided the no of persons it affected.
Both of the views help a viewer to understand both, the difference of survival in a category and how many peoples does this impacts.
Feedback
From Prasad
Please add some Heading to the graphs. The Font of the axis seems very dull. Please use better titles for the Axis. some issue with the Count and Percent buttons.
The feedback was taken into consideration and changes were made in the second iteration of the Project.
From Raman
Visualizations seems fine. The whole page could have a better feel to it. You could improve upon your front-end and give a sense of story to whole page.
From Kanav
Looks Good. I understand your message. Keep learning.
From Udacity Mentor
Make visualizations to be Explanatory rather than Exploratory. To sew a story or a narrative around the visualizations created by writing a paragraph about it. Only use visualizations that seem relevant to your findings from the dataset.
The feedback was taken into consideration and I created a story and a narrative based on the visualizations created.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent