pauperl/pandas-shark-project

Pandas-Shark-Project

     In this project I will be exploring a mess of a dataframe, and hope not to make an even bigger mess out of it. As its my first time please be wary that the code may not be the cleanest and may hurt your brain/eyes (Fernando, Pau, other genius' in class). 

What I will be doing!

     We have been assigned a dataframe that is an absolute clustertruck and must explore it and present a hypothesis, then tidy it up and try to prove or disprove the hypothesis. 

My Hypothesis

   So I believe that if the psychopaths that decide to dive deep underwater and do water related activities that involve great depth are more prone to shark attacks than someone who is just Wading or chilling on the shore.
 
    Some other things I will be trying to prove:

• The number of attacks has gone up over the years (Not True)
• The most dangerous watersport category is hands down underwater sport (True)

Data

Figure 1.

     In figure 1 the number of attacks by year is displayed. Here we see a peak in attacks (unprovoked and provoked) in the year 2015, then a decrease in 2017 which could be due to lack of data. However, we can assume that it only decreased by a small margin, but still indeed does decrease.

Figure 2.

     In figure 2 we can see the number of shark attacks in water related activities. The highest amount is in surfing.

Figure 3.

     In figure 3 however; We see that the number of shark attack that were fatal and non-fatal. We can see that the most dangerous is the Underwaters sports as its a smaller amount of participants doing the activities but it is almost the same amount as surfing. If there were more people diving underwater there would be more fatalities. However that is not the case because diving deep is spooky.

Figure 4.

     In figure 4 we see the number of fatal and non-fatal attacks in the related years. This graph does not really provide much on whether human behaviour is more or less cautious when it comes to participating in water related activities. We are unsure whether people taking more precautions as the years go on because it is clear that these atacks ar still on going. 

Conclusion

    To conclude, most people on average will continue doing water activities. The only real danger is deep diving as it is one of the most common fatal activities in the data depiction. Some data may not be completely accurate due to a poor clean up of data, or due to a tremendous amount of missing values in the data set.