[python]基于LSTM模型大乐透预测简化版

大乐透程序预测

import numpy as np

from keras.models import Sequential

from keras.layers import LSTM, Dense

from sklearn.preprocessing import MinMaxScaler

# 已知的最近二十期数据

data = [

[4,5,16,21,31],

[25,27,35,3,7],

[4,12,19,25,27],

[1,18,21,26,33],

[23,29,27,26,33],

[13,29,5,17,33],

[15,29,25,24,22],

[6,8,14,16,28],

[3,13,15,17,22],

[9,10,14,31,32],

[3,18,14,4,26],

[16,18,17,35,27],

[20,18,17,31,25],

[7,12,16,33,34],

[4,20,21,32,34],

[8,17,26,32,28],

[3,27,24,5,28],

[34,27,14,15,25],

[30,29,34,6,5],

[2,4,25,26,31]

]

# 数据预处理

scaler = MinMaxScaler(feature_range=(0, 1))

data_scaled = scaler.fit_transform(data)

# 创建序列数据

def create_sequences(data, seq_length=5):

X, Y = [], []

for i in range(len(data) - seq_length):

X.append(data[i:(i + seq_length)])

Y.append(data[i + seq_length])

return np.array(X), np.array(Y)

X, Y = create_sequences(data_scaled)

Python基于LSTM的预测模型

# 分割训练集和测试集

split = int(0.8 * len(X))

X_train, X_test = X[:split], X[split:]

Y_train, Y_test = Y[:split], Y[split:]

# 重塑输入数据为[LSTM时间步长, 特征数量]

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))

X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))

# 创建LSTM模型

model = Sequential()

model.add(LSTM(50, input_shape=(X_train.shape[1], X_train.shape[2])))

model.add(Dense(5))

model.compile(loss='mean_squared_error', optimizer='adam')

人工智能训练

# 训练模型

model.fit(X_train, Y_train, epochs=100, batch_size=1, verbose=1)

# 预测下一期号码

last_sequence = X[-1].reshape(1, 5, 1) # 取最后一期作为预测的起始点

predicted_numbers = model.predict(last_sequence, verbose=0)

# 逆归一化

predicted_numbers = scaler.inverse_transform(predicted_numbers)

print("预测的下一期号码是:", predicted_numbers[0])