Predicting-Titanic-Survivors. Kaggle Titanic Machine Learning from Disaster is considered as the first step into the realm of Data Science.
Therefore, we have very good accuracy in train data but very poor accuracy in the test data.This os command will set a default path to the folder in which you have downloaded the files. And since a third submission to the competition costs me nothing, I’ll also make a prediction with the linear model because its accuracy isn’t far behind the other two.Now that I have my trained models (or fighters if you’d prefer that metaphor), it’s time to put them to work.
Source: National Geographic This notebook is a simple example of titanic Disaster in python. So, let’s see how I did.Wow! Given the numbers above, the RF model would have saved two more lives than the XGBoost model. Such as Pandas and Numpy are data manipulation libraries. For now, let’s not take the Age column. That means we can not pass the sex as male or female.We split our data into a train set and a cross-validation set. However, accuracy isn’t always the best measure.
There are packages for creating beautiful plots, building stock portfolios and pretty much anything else you can imagine. We only have enough time to master one martial art before the tournament begins, so we need to figure out which we should study to have the best chance of winning. The training set is used to train the machine learning algorithm. It is a Kaggle Competition, Titanic: Machine Learning from Disaster.It is good for those who are going into the field of Machine learning, Data Analysis or simple introduction to the Kaggle Prediction competition. We can presume whether a person is rich or poor by looking at Passenger class (Pclass).So these are the 3 inputs to our machine learning algorithm: Passenger class, age and sex.We can see that Age has 177 missing values out of 891.
We will cover an easy solution of Kaggle Titanic Solution in python for beginners.
I honestly did not see that coming. Finally, it will fill all of the missing ages with the best guess as to what their age might be.Side note: to go into a description of what an RF model is would completely derail this case study.
Of the 1309 passengers whose data we have, 266 had no age. While the cross-validation set is used to find the model accuracy (as we have the actual output for the cross-validation set).
Although travellers who started their journeys at Cherbourg had a slight statistical improvement on survival. For machine learning we will use classification algorithm Random Forest or Logistic Regression.We use train_test_split function to split the data into train/ test to check and avoid overfitting. Assume that the treatment is harmless if given to someone who doesn’t have the disease, but without the treatment, people with the disease are guaranteed to die.
To extract as much useable information as possible, I will have to transform some of these variables.The first variable I will look at is “Name.” As far as I know, the iceberg that sunk the Titanic didn’t have a personal vendetta against any of the passengers, so simply using the full names of the passengers won’t provide any useful information. The takeaway here is that one should never simply look at the accuracy and make the final judgment based on that.Instead, I will make predictions using both the RF and XGBoost models. It just goes to show that you can do all of the training in the world and sometimes the win simply comes down to luck.To be objective, a score of 78.9% isn’t all that impressive considering there are other submissions that got a perfect score.