def rf(train_data,train_label,val_data,val_label,test_data,name="RandomForest_submission.csv"): print "Start training Random forest..." rfClf = RandomForestClassifier(n_estimators=400,n_jobs=-1) rfClf.fit(train_data,train_label) #evaluate on validation set val_pred_label = rfClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss print "Start classify test set..." test_label = rfClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def knn(train_data,train_label,val_data,val_label,test_data,name = "knn_submission.csv"): print "Start training KNN Classifier..." knnClf = KNeighborsClassifier(n_neighbors=20) knnClf.fit(train_data,train_label) #evaluate on validation set val_pred_label = knnClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss print "Start classify test set..." test_label = knnClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def ab(train_data,train_label,val_data,val_label,test_data,name="adaboost_submission.csv"): print "Start training AdaBoost..." abClf = AdaBoostClassifier() abClf.fit(train_data,train_label) #evaluate on validation set val_pred_label = abClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss print "Start classify test set..." test_label = abClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def et(train_data,train_label,val_data,val_label,test_data,name="extratrees_submission.csv"): print "start training ExtraTrees..." etClf = ExtraTreesClassifier(n_estimators=10) etClf.fit(train_data,train_label) #evaluate on validation set val_pred_label = etClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss print "Start classify test set..." test_label = etClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def gb(train_data,train_label,val_data,val_label,test_data,name="GradientBoosting_submission.csv"): print "start training GradientBoosting..." gbClf = GradientBoostingClassifier() # params: by default gbClf.fit(train_data,train_label) #evaluate on validation set val_pred_label = gbClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss print "Start classify test set..." test_label = gbClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def rf(train_data,train_label,val_data,val_label,test_data,name="RandomForest_submission.csv"): print "Start training Random forest..." rfClf = RandomForestClassifier(n_estimators=400,n_jobs=-1) rfClf.fit(train_data,train_label) #evaluate on validation set val_pred_label = rfClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss print "Start classify test set..." test_label = rfClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def knn(train_data,
train_label,
val_data,
val_label,
test_data,
name="knn_submission.csv"):
print "Start training KNN Classifier..."
knnClf = KNeighborsClassifier(n_neighbors=20)
knnClf.fit(train_data, train_label)
#evaluate on validation set
val_pred_label = knnClf.predict_proba(val_data)
logloss = preprocess.evaluation(val_label, val_pred_label)
print "logloss of validation set:", logloss
print "Start classify test set..."
test_label = knnClf.predict_proba(test_data)
preprocess.saveResult(test_label, filename=name)
def et(train_data,
train_label,
val_data,
val_label,
test_data,
name="extratrees_submission.csv"):
print "start training ExtraTrees..."
etClf = ExtraTreesClassifier(n_estimators=10)
etClf.fit(train_data, train_label)
#evaluate on validation set
val_pred_label = etClf.predict_proba(val_data)
logloss = preprocess.evaluation(val_label, val_pred_label)
print "logloss of validation set:", logloss
print "Start classify test set..."
test_label = etClf.predict_proba(test_data)
preprocess.saveResult(test_label, filename=name)
def ab(train_data,
train_label,
val_data,
val_label,
test_data,
name="adaboost_submission.csv"):
print "Start training AdaBoost..."
abClf = AdaBoostClassifier()
abClf.fit(train_data, train_label)
#evaluate on validation set
val_pred_label = abClf.predict_proba(val_data)
logloss = preprocess.evaluation(val_label, val_pred_label)
print "logloss of validation set:", logloss
print "Start classify test set..."
test_label = abClf.predict_proba(test_data)
preprocess.saveResult(test_label, filename=name)
def gb(train_data,
train_label,
val_data,
val_label,
test_data,
name="GradientBoosting_submission.csv"):
print "start training GradientBoosting..."
gbClf = GradientBoostingClassifier() # params: by default
gbClf.fit(train_data, train_label)
#evaluate on validation set
val_pred_label = gbClf.predict_proba(val_data)
logloss = preprocess.evaluation(val_label, val_pred_label)
print "logloss of validation set:", logloss
print "Start classify test set..."
test_label = gbClf.predict_proba(test_data)
preprocess.saveResult(test_label, filename=name)
def rf(train_data,train_label,val_data,val_label,test_data,name="kdd-randomforest.csv"): print "Start training Random forest..." rfClf = RandomForestClassifier(n_estimators=300,n_jobs=-1) rfClf.fit(train_data,train_label) #evaluate on validation set print np.mean(cross_validation.cross_val_score(rfClf, val_data, val_label, cv=10, scoring='roc_auc')) '''#evaluate on validation set val_pred_label = rfClf.predict_proba(val_data) logloss = preprocess.evaluation(val_label,val_pred_label) print "logloss of validation set:",logloss ''' print "Start classify test set..." test_label = rfClf.predict_proba(test_data) preprocess.saveResult(test_label,filename = name)
def rf(train_data,
train_label,
val_data,
val_label,
test_data,
name="RandomForest_submission.csv"):
print("Start training Random forest...")
rfClf = RandomForestClassifier(n_jobs=4,
n_estimators=1000,
max_features=20,
min_samples_split=3,
bootstrap=False,
verbose=3,
random_state=23) #建立分类型决策树
rfClf.fit(train_data, train_label) #训练模型
val_pred_label = rfClf.predict_proba(val_data) #判定结果
logloss = preprocess.evaluation(val_label, val_pred_label) #根据官方评估公式计算
print("logloss of validation set:", logloss)
print("Start classify test set...")
test_label = rfClf.predict_proba(test_data)
preprocess.saveResult(test_label, filename=name)
