Shark Attack Project

CLEANING DATA, PYTHON, PANDAS, SEABORN, MATPLOTLIB.

Project made to train some skills learned in class:

• Data Cleaning
• Plotting Graphs
• Do some questions to the data

Data Cleaning

• Dropping nonsense structures.
• Using Regex to Filter data.
• Do a Unique question, and answer it with the data.

Pipeline Followed in Jupyter notebook:

• Importing Libraries
• Reading the file
• Transforming the values to work with them
• Cleaning some columns
• Saving to csv
• The first thought: I was thinking that the most provoked sharks were the most who killed, but it isn't here is the analysis to conclude this.
• The thesis: what is the riskiest activity
• Conclusion

Conclusion

From 1423 attacks, we can see in the following bar charts

We can see that the Surfing is the most attacked activitie followed by Swimming, Spearfishing, Wading and fishing

Analysing the data, Swimming is the riskiests activity, followed by Surfimg, Spearfishing and Wading. When people was fishing, we see there isn't any death.

Resources:

The full Presentation is at:

Prezi https://prezi.com/view/1ip4YLe89PS9NibBMrot/

The dataset:

DataSet https://www.kaggle.com/teajay/global-shark-attacks

The Recommendations about the fields: http://www.sharkattackfile.net/recommendations.htm