吴恩达第五部分序列模型 week1—— 搭建循环神经网络、LSTM

未来应该不太接触NLP，所以就大概看了下视频。主要完成了用numpy构造RNN和LSTM前向，后向不推导了。最后附基于LSTM参加比赛的代码，LSTM时间序列模型比赛利器。

RNN构造：

import numpy as np
import rnn_utils


def rnn_unit(apre, x, wax, waa, wya, ba, by):
    a = np.tanh(np.dot(wax, x.T) + np.dot(waa, apre)+ba)
    y = rnn_utils.softmax(np.dot(wya, a) + by)  # ex/sum(ex)
    return a, y


def rnn_init(apre, x, n, y):
    np.random.seed(1)
    wax = np.random.randn(n, x.shape[2])  # 10*14
    waa = np.random.randn(n,  apre.shape[0])  # 10*5
    wya = np.random.randn(y.shape[2], n)  # 10*10
    ba = np.zeros((n,x.shape[1]))
    by = np.zeros((y.shape[2],x.shape[1]))
    param = {
        "wax": wax,
        "waa": waa,
        "wya": wya,
        "ba": ba,
        "by": by
    }
    return param


def model(x, y, n):  # 假设x维度为8*100*14 8个100*14的数据 y为8*100*10  8个含有10种分类的结果
    a0 = np.random.randn(n, x.shape[1])  # 5*100
    p = rnn_init(a0, x, n, y)
    a1, y1 = rnn_unit(a0, x[0],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a2, y2 = rnn_unit(a1, x[1],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a3, y3 = rnn_unit(a2, x[2],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a4, y4 = rnn_unit(a3, x[3],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a5, y5 = rnn_unit(a4, x[4],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a6, y6 = rnn_unit(a5, x[5],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a7, y7 = rnn_unit(a6, x[6],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])
    a8, y8 = rnn_unit(a7, x[7],  p["wax"], p["waa"], p["wya"], p["ba"], p["by"])


x = np.random.randn(8,100,14)
y = np.random.randn(8,100,10)
model(x,y,5)

 LSTM构造：

import numpy as np
import rnn_utils


def LSTM_unit(x, apre, cpre, p):
    wca = p["wca"]
    wcx = p["wcx"]
    bc = p["bc"]
    wua = p["wua"]
    wux = p["wux"]
    bu = p["bu"]
    wfa = p["wfa"]
    wfx = p["wfx"]
    bf = p["bf"]
    woa = p["woa"]
    wox = p["wox"]
    bo = p["bo"]
    wya = p["wya"]
    by = p["by"]
    c_temp = np.tanh(np.dot(wca, apre) + np.dot(wcx, x.T) + bc)
    gateu = rnn_utils.sigmoid(np.dot(wua, apre) + np.dot(wux, x.T) + bu)
    gatef = rnn_utils.sigmoid(np.dot(wfa, apre) + np.dot(wfx, x.T) + bf)
    gateo = rnn_utils.sigmoid(np.dot(woa, apre) + np.dot(wox, x.T) + bo)
    c = gateu * c_temp + gatef * cpre
    a = gateo * np.tanh(c)
    y_hat = rnn_utils.softmax(np.dot(wya, a) + by)  # ex/sum(ex)
    return a, c, y_hat


def LSTM_init(a, x, y, n):
    wca = np.random.randn(n, a.shape[0])
    wcx = np.random.randn(n, x.shape[2])
    wua = np.random.randn(n, a.shape[0])
    wux = np.random.randn(n, x.shape[2])
    wfa = np.random.randn(n, a.shape[0])
    wfx = np.random.randn(n, x.shape[2])
    woa = np.random.randn(n, a.shape[0])
    wox = np.random.randn(n, x.shape[2])
    wya = np.random.randn(y.shape[2], n)
    bc = np.zeros((n, x.shape[1]))
    bu = np.zeros((n, x.shape[1]))
    bf = np.zeros((n, x.shape[1]))
    bo = np.zeros((n, x.shape[1]))
    by = np.zeros((y.shape[2], x.shape[1]))
    param = {
        "wca": wca,
        "wcx": wcx,
        "wua": wua,
        "wux": wux,
        "wfa": wfa,
        "wfx": wfx,
        "woa": woa,
        "wox": wox,
        "wya": wya,
        "bc": bc,
        "bu": bu,
        "bf": bf,
        "bo": bo,
        "by": by
    }
    return param


def model(x, y, n):  # 假设x维度为8*100*14 8个100*14的数据 y为8*100*10  8个含有10种分类的结果
    a0 = np.random.randn(n, x.shape[1])  # 1*100
    c0 = np.random.randn(n, x.shape[1])
    p = LSTM_init(a0, x, y, n)
    a1, c1, y_hat1 = LSTM_unit(x[0], a0, c0, p)
    print(a1.shape,c1.shape,y_hat1.shape)
    a2, c2, y_hat2 = LSTM_unit(x[1], a1, c1, p)
    a3, c3, y_hat3 = LSTM_unit(x[2], a2, c2, p)
    a4, c4, y_hat4 = LSTM_unit(x[3], a3, c3, p)
    a5, c5, y_hat5 = LSTM_unit(x[4], a4, c4, p)
    a6, c6, y_hat6 = LSTM_unit(x[5], a5, c5, p)
    a7, c7, y_hat7 = LSTM_unit(x[6], a6, c6, p)
    a8, c8, y_hat8 = LSTM_unit(x[7], a7, c7, p)


x = np.random.randn(8,100,14)
y = np.random.randn(8,100,10)
model(x,y,5)

没怎么仔细学，只是根据公式打了代码。若有错误，敬请指正。

下面这个是我用keras构建LSTM模型参加比赛代码：根据上个月份出行数据，预测本月是否出行。

比赛还没结束，就不透露太多了。

def LSTM(train_x,train_y, test_x):
    timesteps=8
    data_dim=10
    LSTM_train_x=train_x.loc[:,"2021-11-06home":"2021-11-28other_time"]
    LSTM_test_x=test_x.loc[:,"2021-11-06home":"2021-11-28other_time"]
    #display(LSTM_train_x)
    LSTM_train_x=np.array(LSTM_train_x).reshape((LSTM_train_x.shape[0],timesteps,data_dim))
    LSTM_test_x=np.array(LSTM_test_x).reshape((LSTM_test_x.shape[0],timesteps,data_dim))
    #display(LSTM_train_x)
    #display(LSTM_test_x)
    model=ks.Sequential()
    model.add(ks.layers.LSTM(4,input_shape=(timesteps,data_dim)))
    model.add(ks.layers.Dropout(0.5))
    model.add(ks.layers.Dense(1,activation="sigmoid"))
    model.compile(loss='binary_crossentropy', optimizer=ks.optimizers.Adam(),
    metrics=['accuracy'])
    print(model.summary())
    history = model.fit( LSTM_train_x, train_y, epochs=300, batch_size=512, verbose=15)
    # plot history
    train_pred = model.predict(LSTM_train_x)
    test_pred = model.predict(LSTM_test_x)
    return train_pred, test_pred 

然后融合LGB和XGB模型，目前测试集f1 score:0.86

训练验证集f1 score:0.8991