python機器學習庫xgboost的使用
阿新 • • 發佈:2020-01-21
1.資料讀取
利用原生xgboost庫讀取libsvm資料
import xgboost as xgb data = xgb.DMatrix(libsvm檔案)
使用sklearn讀取libsvm資料
from sklearn.datasets import load_svmlight_file X_train,y_train = load_svmlight_file(libsvm檔案)
使用pandas讀取完資料後在轉化為標準形式
2.模型訓練過程
1.未調參基線模型
使用xgboost原生庫進行訓練
import xgboost as xgb from sklearn.metrics import accuracy_score dtrain = xgb.DMatrix(f_train,label = l_train) dtest = xgb.DMatrix(f_test,label = l_test) param = {'max_depth':2,'eta':1,'silent':0,'objective':'binary:logistic' } num_round = 2 bst = xgb.train(param,dtrain,num_round) train_preds = bst.predict(dtrain) train_predictions = [round(value) for value in train_preds] #進行四捨五入的操作--變成0.1(算是設定閾值的符號函式) train_accuracy = accuracy_score(l_train,train_predictions) #使用sklearn進行比較正確率 print ("Train Accuary: %.2f%%" % (train_accuracy * 100.0)) from xgboost import plot_importance #顯示特徵重要性 plot_importance(bst)#列印重要程度結果。 pyplot.show()
使用XGBClassifier進行訓練
# 未設定早停止, 未進行矩陣變換 from xgboost import XGBClassifier from sklearn.datasets import load_svmlight_file #用於直接讀取svmlight檔案形式, 否則就需要使用xgboost.DMatrix(檔名)來讀取這種格式的檔案 from sklearn.metrics import accuracy_score from matplotlib import pyplot num_round = 100 bst1 =XGBClassifier(max_depth=2,learning_rate=1,n_estimators=num_round,#弱分類樹太少的話取不到更多的特徵重要性 silent=True,objective='binary:logistic') bst1.fit(f_train,l_train) train_preds = bst1.predict(f_train) train_accuracy = accuracy_score(l_train,train_preds) print ("Train Accuary: %.2f%%" % (train_accuracy * 100.0)) preds = bst1.predict(f_test) test_accuracy = accuracy_score(l_test,preds) print("Test Accuracy: %.2f%%" % (test_accuracy * 100.0)) from xgboost import plot_importance #顯示特徵重要性 plot_importance(bst1)#列印重要程度結果。 pyplot.show()
2.兩種交叉驗證方式
使用cross_val_score進行交叉驗證
#利用model_selection進行交叉訓練 from xgboost import XGBClassifier from sklearn.model_selection import StratifiedKFold from sklearn.model_selection import cross_val_score from sklearn.metrics import accuracy_score from matplotlib import pyplot param = {'max_depth':2,'objective':'binary:logistic' } num_round = 100 bst2 =XGBClassifier(max_depth=2,learning_rate=0.1,silent=True,objective='binary:logistic') bst2.fit(f_train,l_train) kfold = StratifiedKFold(n_splits=10,random_state=7) results = cross_val_score(bst2,f_train,l_train,cv=kfold)#對資料進行十折交叉驗證--9份訓練,一份測試 print(results) print("CV Accuracy: %.2f%% (%.2f%%)" % (results.mean()*100,results.std()*100)) from xgboost import plot_importance #顯示特徵重要性 plot_importance(bst2)#列印重要程度結果。 pyplot.show()
使用GridSearchCV進行網格搜尋
#使用sklearn中提供的網格搜尋進行測試--找出最好引數,並作為預設訓練引數 from xgboost import XGBClassifier from sklearn.model_selection import GridSearchCV from sklearn.metrics import accuracy_score from matplotlib import pyplot params = {'max_depth':2,'eta':0.1,'objective':'binary:logistic' } bst =XGBClassifier(max_depth=2,objective='binary:logistic') param_test = { 'n_estimators': range(1,51,1) } clf = GridSearchCV(estimator = bst,param_grid = param_test,scoring='accuracy',cv=5)# 5折交叉驗證 clf.fit(f_train,l_train) #預設使用最優的引數 preds = clf.predict(f_test) test_accuracy = accuracy_score(l_test,preds) print("Test Accuracy of gridsearchcv: %.2f%%" % (test_accuracy * 100.0)) clf.cv_results_,clf.best_params_,clf.best_score_
3.早停止調參–early_stopping_rounds(檢視的是損失是否變化)
#進行提早停止的單獨例項 import xgboost as xgb from xgboost import XGBClassifier from sklearn.metrics import accuracy_score from matplotlib import pyplot param = {'max_depth':2,'objective':'binary:logistic' } num_round = 100 bst =XGBClassifier(max_depth=2,objective='binary:logistic') eval_set =[(f_test,l_test)] bst.fit(f_train,early_stopping_rounds=10,eval_metric="error",eval_set=eval_set,verbose=True) #early_stopping_rounds--當多少次的效果差不多時停止 eval_set--用於顯示損失率的資料 verbose--顯示錯誤率的變化過程 # make prediction preds = bst.predict(f_test) test_accuracy = accuracy_score(l_test,preds) print("Test Accuracy: %.2f%%" % (test_accuracy * 100.0))
4.多資料觀察訓練損失
#多引數順 import xgboost as xgb from xgboost import XGBClassifier from sklearn.metrics import accuracy_score from matplotlib import pyplot num_round = 100 bst =XGBClassifier(max_depth=2,objective='binary:logistic') eval_set = [(f_train,l_train),(f_test,eval_metric=["error","logloss"],verbose=True) # make prediction preds = bst.predict(f_test) test_accuracy = accuracy_score(l_test,preds) print("Test Accuracy: %.2f%%" % (test_accuracy * 100.0))
5.模型儲存與讀取
#模型儲存 bst.save_model('demo.model') #模型讀取與預測 modelfile = 'demo.model' # 1 bst = xgb.Booster({'nthread':8},model_file = modelfile) # 2 f_test1 = xgb.DMatrix(f_test) #儘量使用xgboost的自己的資料矩陣 ypred1 = bst.predict(f_test1) train_predictions = [round(value) for value in ypred1] test_accuracy1 = accuracy_score(l_test,train_predictions) print("Test Accuracy: %.2f%%" % (test_accuracy1 * 100.0))
以上就是本文的全部內容,希望對大家的學習有所幫助,也希望大家多多支援我們。