XGBoost example (Python)

# This script shows you how to make a submission using a few # useful Python libraries. # It gets a public leaderboard score of 0.76077. # Maybe you can tweak it and do better…? import pandas as pd import xgboost as xgb from sklearn.preprocessing import LabelEncoder import numpy as np # Load the data train_df = pd.read_csv(‘../input/train.csv’, header=0) test_df = pd.read_csv(‘../input/test.csv’, header=0) # We’ll impute missing values using the median for numeric columns and the most # common value for string columns. # This is based on some nice code by ‘sveitser’ at http://stackoverflow.com/a/25562948 from sklearn.base import TransformerMixin class DataFrameImputer(TransformerMixin): def fit(self, X, y=None): self.fill = pd.Series([X[c].value_counts().index[0] if X[c].dtype == np.dtype(‘O’) else X[c].median() for c in X], index=X.columns) return self def transform(self, X, y=None): return X.fillna(self.fill) feature_columns_to_use = [‘Pclass’,’Sex’,’Age’,’Fare’,’Parch’]…


Link to Full Article: XGBoost example (Python)