清华镜像源安装 NGboost XGboost Catboost
pip install catboost -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install ngboost -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xgboost -i https://pypi.tuna.tsinghua.edu.cn/simple
数据比赛常用预测模型:LGB、XGB与ANN
LGB
lightgbm:由于现在的比赛数据越来越大,想要获得一个比较高的预测精度,同时又要减少内存占用以及提升训练速度,lightgbm是一个非常不错的选择,其可达到与xgboost相似的预测效果。
def LGB_predict(train_x,train_y,test_x,res,index):print("LGB test")clf = lgb.LGBMClassifier(boosting_type='gbdt', num_leaves=31, reg_alpha=0.0, reg_lambda=1,max_depth=-1, n_estimators=5000, objective='binary',subsample=0.7, colsample_bytree=0.7, subsample_freq=1,learning_rate=0.05, min_child_weight=50, random_state=2018, n_jobs=-1)clf.fit(train_x, train_y, eval_set=[(train_x, train_y)], eval_metric='auc',early_stopping_rounds=100)res['score'+str(index)] = clf.predict_proba(test_x)[:,1]res['score'+str(index)] = res['score'+str(index)].apply(lambda x: float('%.6f' % x))print(str(index)+' predict finish!')gc.collect()res=res.reset_index(drop=True)return res['score'+str(index)]
XGB
xgboost:在lightgbm出来之前,是打比赛的不二之选,现在由于需要做模型融合以提高预测精度,所以也需要使用到xgboost。
def XGB_predict(train_x,train_y,val_X,val_Y,test_x,res):print("XGB test")# create dataset for lightgbmxgb_val = xgb.DMatrix(val_X, label=val_Y)xgb_train = xgb.DMatrix(X_train, label=y_train)xgb_test = xgb.DMatrix(test_x)# specify your configurations as a dictparams = {'booster': 'gbtree',# 'objective': 'multi:softmax', # 多分类的问题、# 'objective': 'multi:softprob', # 多分类概率'objective': 'binary:logistic','eval_metric': 'auc',# 'num_class': 9, # 类别数,与 multisoftmax 并用'gamma': 0.1, # 用于控制是否后剪枝的参数,越大越保守,一般0.1、0.2这样子。'max_depth': 8, # 构建树的深度,越大越容易过拟合'alpha': 0, # L1正则化系数'lambda': 10, # 控制模型复杂度的权重值的L2正则化项参数,参数越大,模型越不容易过拟合。'subsample': 0.7, # 随机采样训练样本'colsample_bytree': 0.5, # 生成树时进行的列采样'min_child_weight': 3,# 这个参数默认是 1,是每个叶子里面 h 的和至少是多少,对正负样本不均衡时的 0-1 分类而言# ,假设 h 在 0.01 附近,min_child_weight 为 1 意味着叶子节点中最少需要包含 100 个样本。# 这个参数非常影响结果,控制叶子节点中二阶导的和的最小值,该参数值越小,越容易 overfitting。'silent': 0, # 设置成1则没有运行信息输出,最好是设置为0.'eta': 0.03, # 如同学习率'seed': 1000,'nthread': -1, # cpu 线程数'missing': 1,'scale_pos_weight': (np.sum(y==0)/np.sum(y==1)) # 用来处理正负样本不均衡的问题,通常取:sum(negative cases) / sum(positive cases)# 'eval_metric': 'auc'}
plst = list(params.items())num_rounds = 5000 # 迭代次数watchlist = [(xgb_train, 'train'), (xgb_val, 'val')]# 交叉验证# result = xgb.cv(plst, xgb_train, num_boost_round=200, nfold=4, early_stopping_rounds=200, verbose_eval=True, folds=StratifiedKFold(n_splits=4).split(X, y))# 训练模型并保存# early_stopping_rounds 当设置的迭代次数较大时,early_stopping_rounds 可在一定的迭代次数内准确率没有提升就停止训练model = xgb.train(plst, xgb_train, num_rounds, watchlist, early_stopping_rounds=200)res['score'] = model.predict(xgb_test)res['score'] = res['score'].apply(lambda x: float('%.6f' % x))return res
ANN
ANN:得益于现在的计算机技术的高度发展,以及GPU性能的提高,还有Keras,tensorflow,pytorch等多重工具的使用,人工神经网络也可以作为最后模型融合的子模型之一,可以有效地提升最终的预测结果。
imp = Imputer(missing_values='NaN', strategy='mean', axis=0)
X_train = imp.fit_transform(X_train)
sc = StandardScaler(with_mean=False)
sc.fit(X_train)
X_train = sc.transform(X_train)
val_X = sc.transform(val_X)
X_test = sc.transform(X_test)
ann_scale = 1
from keras.layers import Embedding
model = Sequential()
model.add(Embedding(X_train.shape[1] + 1,EMBEDDING_DIM,input_length=MAX_SEQUENCE_LENGTH))
#model.add(Dense(int(256 / ann_scale), input_shape=(X_train.shape[1],)))
model.add(Dense(int(256 / ann_scale)))
model.add(Activation('tanh'))
model.add(Dropout(0.3))
model.add(Dense(int(512 / ann_scale)))
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Dense(int(512 / ann_scale)))
model.add(Activation('tanh'))
model.add(Dropout(0.3))
model.add(Dense(int(256 / ann_scale)))
model.add(Activation('linear'))
model.add(Dense(1))
model.add(Activation('sigmoid'))
# For a multi-class classification problem
model.summary()
class_weight1 = class_weight.compute_class_weight('balanced',np.unique(y),y)
#-----------------------------------------------------------------------------------------------------------------------------------------------------
# AUC for a binary classifier
def auc(y_true, y_pred): ptas = tf.stack([binary_PTA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0) pfas = tf.stack([binary_PFA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0) pfas = tf.concat([tf.ones((1,)) ,pfas],axis=0) binSizes = -(pfas[1:]-pfas[:-1]) s = ptas*binSizes return K.sum(s, axis=0)
# PFA, prob false alert for binary classifier
def binary_PFA(y_true, y_pred, threshold=K.variable(value=0.5)): y_pred = K.cast(y_pred >= threshold, 'float32') # N = total number of negative labels N = K.sum(1 - y_true) # FP = total number of false alerts, alerts from the negative class labels FP = K.sum(y_pred - y_pred * y_true) return FP/N
# P_TA prob true alerts for binary classifier
def binary_PTA(y_true, y_pred, threshold=K.variable(value=0.5)): y_pred = K.cast(y_pred >= threshold, 'float32') # P = total number of positive labels P = K.sum(y_true) # TP = total number of correct alerts, alerts from the positive class labels TP = K.sum(y_pred * y_true) return TP/P
#---------------------------------------------------------------------------------------------------------------------------------------------------
model.compile(loss='binary_crossentropy',optimizer='rmsprop',
# metrics=['accuracy'],metrics=[auc])
epochs = 100
model.fit(X_train, y, epochs=epochs, batch_size=2000, validation_data=(val_X, val_y), shuffle=True,class_weight = class_weight1)