############導(dǎo)入必要的庫######### import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.preprocessing import MinMaxScaler from keras.models import Sequential from keras.layers import Dense, LSTM, Dropout, GRU from keras.optimizers import SGD在這里插入代碼片

數(shù)據(jù)的加載

## 將date這一列設(shè)為索引 dataset = pd.read_csv("datasets_8388_11883_IBM_2006-01-01_to_2018-01-01.csv", index_col='Date', parse_dates=['Date']) dataset.head() #顯示的是前10列 dataset.shape #獲取的是數(shù)據(jù)集的維度 >>(3020, 6) # 檢查數(shù)據(jù)是否有缺失值 # 獲取了其中的一列當(dāng)做訓(xùn)練集與測試集 train_set = dataset[:'2016'].iloc[:, 1:2].values # 訓(xùn)練集，獲取到第一列的數(shù)據(jù) test_set = dataset['2017':].iloc[:,1:2].values # 測試集，獲取到第一列的數(shù)據(jù) train_set.shape >>(2769, 1) test_set.shape >>(251, 1)

定義顯示函數(shù)

def plot_predictions(test_result, predict_restult):"""test_result: 真實(shí)值predict_result: 預(yù)測值"""plt.plot(test_result, color='red', label='IBM True Stock Price')plt.plot(predict_restult, color='blue', label="IMB prdicted Stock Price")plt.title("IBM Stock Price")plt.xlabel("Time")plt.ylabel("Stock Price")plt.legend() # 給圖加上圖例plt.show()

繪制測試集與訓(xùn)練集的數(shù)目

dataset['High'][:"2016"].plot(figsize=(16, 4), legend=True) dataset['High']["2017":].plot(figsize=(16, 4), legend=True) plt.title("IBM Stock Price") plt.legend(['Train set(before 2016)', 'Test set(after 2017)']) plt.show()

如何制作數(shù)據(jù)將數(shù)據(jù)喂到模型里

# 正則化：將每一維的特征映射到指定的區(qū)間：【0，1】 sc = MinMaxScaler(feature_range=[0, 1]) train_set_scaled = sc.fit_transform(train_set) # 創(chuàng)建序列數(shù)據(jù)集（訓(xùn)練和測試） # 這個代碼的意思就是制作一個時間序列的預(yù)處理 # 60個時間步為一個樣本，1個輸出 X_train = [] ##這里是列表 y_train = [] for i in range(60, 2769):X_train.append(train_set_scaled[i-60:i, 0]) y_train.append(train_set_scaled[i, 0])X_train, y_train = np.array(X_train), np.array(y_train) # numpy類型變換 X_train.shape >>>(2709, 60) X_train[0] >>>array([0.06065089, 0.06029868, 0.06311637, 0.0781206 , 0.07262609,0.07171034, 0.07657087, 0.07058326, 0.0669907 , 0.06494787,0.075796 , 0.07361229, 0.06417301, 0.05621302, 0.05783319,0.05409975, 0.05431107, 0.05515638, 0.05543815, 0.05677656,0.05846717, 0.05388842, 0.04811214, 0.04233587, 0.04402649,0.0490279 , 0.04832347, 0.05297267, 0.05614258, 0.05290223,0.05325444, 0.04909834, 0.04994365, 0.04797126, 0.05431107,0.05212736, 0.04726684, 0.04895745, 0.04656241, 0.04839391,0.04416737, 0.0485348 , 0.04719639, 0.04825303, 0.05395886,0.05663567, 0.05853762, 0.05959425, 0.06375035, 0.06917442,0.06889265, 0.06670893, 0.06910397, 0.07783883, 0.07565511,0.07276698, 0.06889265, 0.0656523 , 0.06656805, 0.06769513]) ### lstm的輸入模塊 # LSTM的輸入：(samples, sequence_length, features) # reshape: 訓(xùn)練集(2709,60) ---> (2709, 60, 1) X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1)) X_train.shape >>> (2709, 60, 1)

構(gòu)建lstm網(wǎng)絡(luò)

model = Sequential() # LSTM 第一層 ##輸入的是步數(shù)與維度 model.add(LSTM(128, return_sequences=True, input_shape=(X_train.shape[1], 1))) model.add(Dropout(0.2))# LSTM 第二層 model.add(LSTM(128, return_sequences=True)) model.add(Dropout(0.2))# LSTM 第三層 model.add(LSTM(128)) model.add(Dropout(0.2))# Dense層 model.add(Dense(units=1)) # 模型編譯 model.compile(optimizer='rmsprop', loss='mse') # 模型訓(xùn)練 model.fit(X_train, y_train, epochs=20, batch_size=32) >>>Output exceeds the size limit. Open the full output data in a text editor Epoch 1/20 85/85 [==============================] - 30s 357ms/step - loss: 0.0666 Epoch 2/20 85/85 [==============================] - 32s 372ms/step - loss: 0.0124 Epoch 3/20 85/85 [==============================] - 31s 370ms/step - loss: 0.0080 Epoch 4/20 85/85 [==============================] - 34s 399ms/step - loss: 0.0063 Epoch 5/20 85/85 [==============================] - 45s 527ms/step - loss: 0.0055 Epoch 6/20 85/85 [==============================] - 45s 532ms/step - loss: 0.0048 Epoch 7/20 85/85 [==============================] - 46s 543ms/step - loss: 0.0039 Epoch 8/20 85/85 [==============================] - 45s 530ms/step - loss: 0.0039 Epoch 9/20 85/85 [==============================] - 47s 551ms/step - loss: 0.0034 Epoch 10/20 85/85 [==============================] - 49s 582ms/step - loss: 0.0032 Epoch 11/20 85/85 [==============================] - 49s 571ms/step - loss: 0.0029 Epoch 12/20 85/85 [==============================] - 48s 563ms/step - loss: 0.0026 Epoch 13/20 ... Epoch 19/20 85/85 [==============================] - 39s 460ms/step - loss: 0.0019 Epoch 20/20 85/85 [==============================] - 30s 351ms/step - loss: 0.0018 <tensorflow.python.keras.callbacks.History at 0x13f4a7ac8>

構(gòu)建數(shù)據(jù)集，進(jìn)行預(yù)測

dataset_total = pd.concat((dataset['High'][:"2016"], dataset['High']["2017":]), axis=0) dataset_total.shape >>>(3020,) dataset_total >>>Date 2006-01-03 82.55 2006-01-04 82.50 2006-01-05 82.90 2006-01-06 85.03 2006-01-09 84.25... 2017-12-22 153.00 2017-12-26 153.86 2017-12-27 153.18 2017-12-28 154.12 2017-12-29 154.72 Name: High, Length: 3020, dtype: float64 inputs = dataset_total[len(train_set):].values #測試集 inputs = inputs.reshape(-1, 1) ###轉(zhuǎn)換成一列 inputs.shape >>>(251, 1) inputs_scaled = sc.fit_transform(inputs) #歸一化

構(gòu)建測試集

dataset_total = pd.concat((dataset['High'][:"2016"], dataset['High']["2017":]), axis=0) # 獲取輸入數(shù)據(jù) inputs = dataset_total[len(dataset_total) - len(test_set) - 60:].values inputs >>>Output exceeds the size limit. Open the full output data in a text editor array([157.43, 157.7 , 158.49, 156.95, 154.97, 154.22, 155.53, 155.89,151. , 152.45, 152.9 , 151.15, 151.52, 151.16, 152.94, 154.06,154.44, 154.33, 153.91, 153.34, 153.74, 153.64, 156.11, 155.93,155.56, 161.16, 161.34, 161.86, 159.15, 159.55, 159.93, 160.72,163. , 163. , 162.38, 163.19, 164.66, 164.41, 163.8 , 162.2 ,160.29, 161.15, 160.79, 165.18, 166. , 166.72, 166.79, 169.95,169.89, 169.85, 169.11, 167.26, 168.25, 167.94, 168.23, 167.49,167.98, 167.74, 166.99, 166.7 , 167.87, 169.87, 169.39, 169.92,169.8 , 168.09, 167.76, 168.01, 168.48, 168.18, 168.59, 167.45,170.64, 171.25, 176. , 179.25, 178.88, 179.2 , 177.07, 175.58,175.7 , 174.97, 176.34, 175.98, 178.62, 177.5 , 177.8 , 178.87,179.9 , 180.13, 181.92, 182.79, 181.57, 180.79, 181.34, 182.5 ,181.49, 181.25, 180.63, 182.55, 181.88, 181.32, 180.99, 181.29,180.95, 179.25, 179.49, 178.06, 176.82, 176.28, 179. , 176.79,176.18, 176.23, 175.06, 175.67, 175.5 , 174.16, 175. , 174.49,174.59, 174.95, 174.87, 174.96, 176.33, 173.47, 172.93, 172.56,171.23, 171.2 , 171.36, 171.3 , 171.69, 162.64, 162.4 , 162.11,161.57, 162.04, 161.1 , 160.48, 160.59, 160.42, 159.49, 159.45,159.14, 155.78, 153.47, 153.1 , 152.37, 151.15, 151.26, 151.83,153.99, 154.14, 151.33, 152.46, 152.84, 153.68, 152.76, 153.73,153. , 152.67, 152.8 , 152.87, 153.2 , 152.93, 152.89, 154.2 ,152.82, 154.26, 157.2 , 155.48, 154.94, 154.69, 155.42, 155.86,155.39, 155.79, 154.99, 154.68, 155.75, 155.34, 155.55, 155.74,154.5 , 156.02, 155.89, 153.83, 153.49, 153.89, 153.65, 154.24,154.19, 154.62, 153.88, 154.29, 150.25, 148.83, 147.87, 147.04, ...153.47, 151.82, 151.51, 151.79, 151.8 , 150.89, 149. , 148.97,148.7 , 149.65, 150.15, 151.95, 152.45, 152.39, 152.2 , 152.49,152.93, 153.61, 154.41, 155.02, 156.8 , 156.74, 156.22, 154.45,155.03, 155.89, 157.85, 156.73, 155.11, 153.8 , 154.18, 154.17,153.89, 153.46, 153. , 153.86, 153.18, 154.12, 154.72]) # 歸一化 inputs = inputs.reshape(-1, 1) inputs = sc.transform(inputs) inputs.shape >>>(311, 1) # 準(zhǔn)備測試集X_test,進(jìn)行股價預(yù)測 X_test = [] for i in range(60, 311):X_test.append(inputs[i-60:i, 0])X_test = np.array(X_test) # numpy 類型轉(zhuǎn)換X_test.shape >>>(251, 60) ###構(gòu)造數(shù)據(jù)集 X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1)) X_test.shape >>>(251, 60, 1) ###預(yù)測 predict_test = model.predict(X_test) # 預(yù)測 predict_test.shape >>>(251, 1) ###反歸一化 predict_stock_price = sc.inverse_transform(predict_test) predict_stock_price >>>([[168.57092],[168.69382],[169.65242],[170.35161],[170.84596],[171.02237],[170.4601 ],[169.75737],[169.38156],[169.46404],[169.58615],[169.80162],[169.56326],[170.3292 ],[171.34633],[173.63313],[176.39796],[178.01892],[178.7997 ],[178.39485],[177.41373],[176.70485],[176.20074],[176.44489],[176.7224 ], ...[154.5936 ],[154.30226],[154.3495 ],[154.2771 ],[154.49394]], dtype=float32)# 繪制測試結(jié)果和預(yù)測結(jié)果plot_predictions(test_set, predict_stock_price)

基于GRU

model_gru = Sequential() model_gru.add(GRU(50, return_sequences=True, input_shape=(X_train.shape[1], 1), activation='tanh')) model_gru.add(Dropout(0.2)) model_gru.add(GRU(50, activation='tanh')) model_gru.add(Dropout(0.2)) model_gru.add(Dense(1)) ###模型編譯 model_gru.compile(optimizer=SGD(lr=0.01, decay=1e-7, momentum=0.9), loss='mse' ###模型的訓(xùn)練 model_gru.fit(X_train, y_train, epochs=20, batch_size=32) >>>Output exceeds the size limit. Open the full output data in a text editor Epoch 1/20 85/85 [==============================] - 18s 209ms/step - loss: 0.0351 Epoch 2/20 85/85 [==============================] - 18s 217ms/step - loss: 0.0032 Epoch 3/20 85/85 [==============================] - 19s 224ms/step - loss: 0.0026 Epoch 4/20 85/85 [==============================] - 19s 225ms/step - loss: 0.0023 Epoch 5/20 85/85 [==============================] - 19s 221ms/step - loss: 0.0021 Epoch 6/20 85/85 [==============================] - 19s 225ms/step - loss: 0.0019 Epoch 7/20 85/85 [==============================] - 19s 226ms/step - loss: 0.0018 Epoch 8/20 85/85 [==============================] - 19s 223ms/step - loss: 0.0017 Epoch 9/20 85/85 [==============================] - 19s 229ms/step - loss: 0.0016 Epoch 10/20 85/85 [==============================] - 19s 227ms/step - loss: 0.0015 Epoch 11/20 85/85 [==============================] - 19s 226ms/step - loss: 0.0016 Epoch 12/20 85/85 [==============================] - 15s 177ms/step - loss: 0.0014 Epoch 13/20 ... Epoch 19/20 85/85 [==============================] - 11s 135ms/step - loss: 0.0013 Epoch 20/20 85/85 [==============================] - 12s 139ms/step - loss: 0.0012 <tensorflow.python.keras.callbacks.History at 0x140e4feb8> # 準(zhǔn)備測試集X_test,進(jìn)行股價預(yù)測 X_test = [] for i in range(60, 311):X_test.append(inputs[i-60:i, 0])X_test = np.array(X_test) # numpy 類型轉(zhuǎn)換X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1)) #################### GRU_predicted = model_gru.predict(X_test) GRU_predicted_stock_price = sc.inverse_transform(GRU_predicted) # 可視化 plot_predictions(test_set, GRU_predicted_stock_price)

總結(jié)

以上是生活随笔為你收集整理的lstm单变量预测的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。