data = data.drop(, axis=1) # check for missing valuesĪge and Embarked have missing values. And most probably we dot need Name, Ticket, Cabin. In the dataset, Name, Sex, Ticket, Cabin, and Embarked are categorical features. It’s a good idea to check for categorical data types during this stage. # necessary importsįrom sklearn.preprocessing import LabelEncoderįrom trics import accuracy_scoreįrom sklearn.model_selection import train_test_split # load the CSV files I hope that the code will be self-explanatory. As our intention is to explore the features of XGBoost, we will go through this phase with a little less explanation. In this section, we will load the data, analyze it and also preprocess (clean) the data. Loading, Analyzing and Preprocessing of Data # of parents / children aboard the TitanicĬ = Cherbourg, Q = Queenstown, S = Southampton # of siblings / spouses aboard the Titanic The following is the features table for the dataset. We have to predict the survival key for the test CSV file. The training file contains the various features of passengers and whether a passenger survived ( survival feature) or not (0 or 1). We are given the train CSV file and the test CSV file. So, what do we need to do in this dataset. Note: If you follow along with the code on your local machine, then I suggest that you use Jupyter Notebook, although you can follow any IDE of your choice as well. You can either download the dataset to your local machine or try to follow with the code using Kaggle Kernels. This dataset is not very big yet it has enough traction to it that we will be able to explore many aspects when dealing with a machine learning problem. Our aim in this article is to learn about the various usages of XGBoost and this is one of the best datasets to do so. But why this dataset only? This is one of the most famous datasets for beginners in the world of machine learning. We will use the very popular Titanic dataset from Kaggle. Now you are all set to follow along with this article. If you have not installed XGBoost till now, then you can install it easily using the pip command: Exploring the simple XGBoost classification.
It is also about what types of insights we can gain using the data and tools that we have.ġ.
When using machine learning libraries, it is not only about building state-of-the-art models. This article will mainly aim towards exploring many of the useful features of XGBoost. In my previous article, I gave a brief introduction about XGBoost on how to use it. XGBoost is one of the most reliable machine learning libraries when dealing with huge datasets. In this article, we will take a look at the various aspects of the XGBoost library.
0 kommentar(er)
