文章目錄
- 一、前言
- 二、前期工作
- 1. 設置GPU（如果使用的是CPU可以忽略這步）
- 2. 導入數據
- 四、數據預處理
- 1.歸一化
- 2.設置測試集訓練集
- 五、構建模型
- 六、激活模型
- 七、訓練模型
- 八、結果可視化
- 1.繪制loss圖
- 2.預測
- 3.評估
一、前言
我的環境：
- 語言環境：Python3.6.5
- 編譯器：jupyter notebook
- 深度學習環境：TensorFlow2.4.1
往期精彩內容：
- 卷積神經網絡（CNN）實現mnist手寫數字識別
- 卷積神經網絡（CNN）多種圖片分類的實現
- 卷積神經網絡（CNN）衣服圖像分類的實現
- 卷積神經網絡（CNN）鮮花識別
- 卷積神經網絡（CNN）天氣識別
- 卷積神經網絡（VGG-16）識別海賊王草帽一伙
- 卷積神經網絡（ResNet-50）鳥類識別
來自專欄：機器學習與深度學習算法推薦
二、前期工作
1. 設置GPU（如果使用的是CPU可以忽略這步）
import tensorflow as tfgpus = tf.config.list_physical_devices("GPU")if gpus:tf.config.experimental.set_memory_growth(gpus[0], True) #設置GPU顯存用量按需使用tf.config.set_visible_devices([gpus[0]],"GPU")
2. 導入數據
import os,math
from tensorflow.keras.layers import Dropout, Dense, SimpleRNN
from sklearn.preprocessing import MinMaxScaler
from sklearn import metrics
import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
# 支持中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用來正常顯示中文標簽
plt.rcParams['axes.unicode_minus'] = False # 用來正常顯示負號
data = pd.read_csv('./datasets/SH600519.csv') # 讀取股票文件data
| Unnamed: 0 | date | open | close | high | low | volume | code | |
|---|---|---|---|---|---|---|---|---|
| 0 | 74 | 2010-04-26 | 88.702 | 87.381 | 89.072 | 87.362 | 107036.13 | 600519 |
| 1 | 75 | 2010-04-27 | 87.355 | 84.841 | 87.355 | 84.681 | 58234.48 | 600519 |
| 2 | 76 | 2010-04-28 | 84.235 | 84.318 | 85.128 | 83.597 | 26287.43 | 600519 |
| 3 | 77 | 2010-04-29 | 84.592 | 85.671 | 86.315 | 84.592 | 34501.20 | 600519 |
| 4 | 78 | 2010-04-30 | 83.871 | 82.340 | 83.871 | 81.523 | 85566.70 | 600519 |
| … | … | … | … | … | … | … | … | … |
| 2421 | 2495 | 2020-04-20 | 1221.000 | 1227.300 | 1231.500 | 1216.800 | 24239.00 | 600519 |
| 2422 | 2496 | 2020-04-21 | 1221.020 | 1200.000 | 1223.990 | 1193.000 | 29224.00 | 600519 |
| 2423 | 2497 | 2020-04-22 | 1206.000 | 1244.500 | 1249.500 | 1202.220 | 44035.00 | 600519 |
| 2424 | 2498 | 2020-04-23 | 1250.000 | 1252.260 | 1265.680 | 1247.770 | 26899.00 | 600519 |
| 2425 | 2499 | 2020-04-24 | 1248.000 | 1250.560 | 1259.890 | 1235.180 | 19122.00 | 600519 |
2426 rows × 8 columns
training_set = data.iloc[0:2426 - 300, 2:3].values
test_set = data.iloc[2426 - 300:, 2:3].values
四、數據預處理
1.歸一化
sc = MinMaxScaler(feature_range=(0, 1))
training_set = sc.fit_transform(training_set)
test_set = sc.transform(test_set)
2.設置測試集訓練集
x_train = []
y_train = []x_test = []
y_test = []"""
使用前60天的開盤價作為輸入特征x_train第61天的開盤價作為輸入標簽y_trainfor循環共構建2426-300-60=2066組訓練數據。共構建300-60=260組測試數據
"""
for i in range(60, len(training_set)):x_train.append(training_set[i - 60:i, 0])y_train.append(training_set[i, 0])for i in range(60, len(test_set)):x_test.append(test_set[i - 60:i, 0])y_test.append(test_set[i, 0])# 對訓練集進行打亂
np.random.seed(7)
np.random.shuffle(x_train)
np.random.seed(7)
np.random.shuffle(y_train)
tf.random.set_seed(7)
"""
將訓練數據調整為數組（array）調整后的形狀：
x_train:(2066, 60, 1)
y_train:(2066,)
x_test :(240, 60, 1)
y_test :(240,)
"""
x_train, y_train = np.array(x_train), np.array(y_train) # x_train形狀為：(2066, 60, 1)
x_test, y_test = np.array(x_test), np.array(y_test)"""
輸入要求：[送入樣本數， 循環核時間展開步數， 每個時間步輸入特征個數]
"""
x_train = np.reshape(x_train, (x_train.shape[0], 60, 1))
x_test = np.reshape(x_test, (x_test.shape[0], 60, 1))
五、構建模型
model = tf.keras.Sequential([SimpleRNN(80, return_sequences=True), #布爾值。是返回輸出序列中的最后一個輸出，還是全部序列。Dropout(0.2), #防止過擬合SimpleRNN(80),Dropout(0.2),Dense(1)
])
六、激活模型
# 該應用只觀測loss數值，不觀測準確率，所以刪去metrics選項，一會在每個epoch迭代顯示時只顯示loss值
model.compile(optimizer=tf.keras.optimizers.Adam(0.001),loss='mean_squared_error') # 損失函數用均方誤差
七、訓練模型
history = model.fit(x_train, y_train, batch_size=64, epochs=20, validation_data=(x_test, y_test), validation_freq=1) #測試的epoch間隔數model.summary()
Epoch 1/20
33/33 [==============================] - 6s 123ms/step - loss: 0.1809 - val_loss: 0.0310
Epoch 2/20
33/33 [==============================] - 3s 105ms/step - loss: 0.0257 - val_loss: 0.0721
Epoch 3/20
33/33 [==============================] - 3s 85ms/step - loss: 0.0165 - val_loss: 0.0059
Epoch 4/20
33/33 [==============================] - 3s 85ms/step - loss: 0.0097 - val_loss: 0.0111
Epoch 5/20
33/33 [==============================] - 3s 90ms/step - loss: 0.0099 - val_loss: 0.0139
Epoch 6/20
33/33 [==============================] - 3s 105ms/step - loss: 0.0067 - val_loss: 0.0167
Epoch 7/20
33/33 [==============================] - 3s 86ms/step - loss: 0.0067 - val_loss: 0.0095
Epoch 8/20
33/33 [==============================] - 3s 91ms/step - loss: 0.0063 - val_loss: 0.0218
Epoch 9/20
33/33 [==============================] - 3s 99ms/step - loss: 0.0052 - val_loss: 0.0109
Epoch 10/20
33/33 [==============================] - 3s 99ms/step - loss: 0.0043 - val_loss: 0.0120
Epoch 11/20
33/33 [==============================] - 3s 92ms/step - loss: 0.0044 - val_loss: 0.0167
Epoch 12/20
33/33 [==============================] - 3s 89ms/step - loss: 0.0039 - val_loss: 0.0032
Epoch 13/20
33/33 [==============================] - 3s 88ms/step - loss: 0.0041 - val_loss: 0.0052
Epoch 14/20
33/33 [==============================] - 3s 93ms/step - loss: 0.0035 - val_loss: 0.0179
Epoch 15/20
33/33 [==============================] - 4s 110ms/step - loss: 0.0033 - val_loss: 0.0124
Epoch 16/20
33/33 [==============================] - 3s 95ms/step - loss: 0.0035 - val_loss: 0.0149
Epoch 17/20
33/33 [==============================] - 4s 111ms/step - loss: 0.0028 - val_loss: 0.0111
Epoch 18/20
33/33 [==============================] - 4s 110ms/step - loss: 0.0029 - val_loss: 0.0061
Epoch 19/20
33/33 [==============================] - 3s 104ms/step - loss: 0.0027 - val_loss: 0.0110
Epoch 20/20
33/33 [==============================] - 3s 90ms/step - loss: 0.0028 - val_loss: 0.0037
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
simple_rnn (SimpleRNN) (None, 60, 80) 6560
_________________________________________________________________
dropout (Dropout) (None, 60, 80) 0
_________________________________________________________________
simple_rnn_1 (SimpleRNN) (None, 80) 12880
_________________________________________________________________
dropout_1 (Dropout) (None, 80) 0
_________________________________________________________________
dense (Dense) (None, 1) 81
=================================================================
Total params: 19,521
Trainable params: 19,521
Non-trainable params: 0
_________________________________________________________________
八、結果可視化
1.繪制loss圖
plt.plot(history.history['loss'] , label='Training Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')
plt.legend()
plt.show()
2.預測
predicted_stock_price = model.predict(x_test) # 測試集輸入模型進行預測
predicted_stock_price = sc.inverse_transform(predicted_stock_price) # 對預測數據還原---從（0，1）反歸一化到原始范圍
real_stock_price = sc.inverse_transform(test_set[60:]) # 對真實數據還原---從（0，1）反歸一化到原始范圍# 畫出真實數據和預測數據的對比曲線
plt.plot(real_stock_price, color='red', label='Stock Price')
plt.plot(predicted_stock_price, color='blue', label='Predicted Stock Price')
plt.title('Stock Price Prediction by K同學啊')
plt.xlabel('Time')
plt.ylabel('Stock Price')
plt.legend()
plt.show()
3.評估
MSE = metrics.mean_squared_error(predicted_stock_price, real_stock_price)
RMSE = metrics.mean_squared_error(predicted_stock_price, real_stock_price)**0.5
MAE = metrics.mean_absolute_error(predicted_stock_price, real_stock_price)
R2 = metrics.r2_score(predicted_stock_price, real_stock_price)print('均方誤差: %.5f' % MSE)
print('均方根誤差: %.5f' % RMSE)
print('平均絕對誤差: %.5f' % MAE)
print('R2: %.5f' % R2)
均方誤差: 1833.92534
均方根誤差: 42.82435
平均絕對誤差: 36.23424
R2: 0.72347
- 簡單應用)
![[C++ 從入門到精通] 13.派生類、調用順序、繼承方式、函數遮蔽](http://pic.xiahunao.cn/[C++ 從入門到精通] 13.派生類、調用順序、繼承方式、函數遮蔽)
】紅黑樹深度剖析--手撕紅黑樹!)
