根据心情补充，语言都是Python
hash，把所有的文本转化成数字
from sklearn.preprocessing import LabelEncoder
for c in train.columns:if train[c].dtype == 'object':lbl = LabelEncoder()lbl.fit(list(train[c].values) + list(test[c].values))train[c] = lbl.transform(list(train[c].values))test[c] = lbl.transform(list(test[c].values))Xgboost训练
'''Train the xgb model then predict the test data'''
xgb_params = {'n_trees': 520, 'eta': 0.0045,'max_depth': 4,'subsample': 0.93,'objective': 'reg:linear', 'eval_metric': 'rmse','base_score': y_mean, # base prediction = mean(target)'silent': 1
}
# NOTE: Make sure that the class is labeled 'class' in the data filedtrain = xgb.DMatrix(train.drop('y', axis=1), y_train)
dtest = xgb.DMatrix(test)num_boost_rounds = 1250
# train model
model = xgb.train(dict(xgb_params, silent=0), dtrain, num_boost_round=num_boost_rounds)
y_pred = model.predict(dtest)OneHot矩阵转换
enc = OneHotEncoder(handle_unknown='ignore')
enc=enc.fit(pd.concat([X[categorical],X_test[categorical]]))
X_cat_sparse=enc.transform(X[categorical])
X_test_cat_sparse=enc.transform(X_test[categorical])
