def test(ind):
print("=> test")
test_data = load_data(file='test', norm=True)
func = toolbox.compile(expr=ind)
out = ""
for (i, row) in test_data.iterrows():
x = row[1:].tolist()
# print(f"{func(*x)}")
out += f"{func(*x)}\n"
with open("test.txt", 'w') as f:
f.write(out)
def validate(ind):
print("=> validate")
out = ""
val_data = load_data(file='validate', norm=True)
func = toolbox.compile(expr=ind)
for (i, row) in val_data.iterrows():
x = row[1:].tolist()
y = row[0]
out += f"calc: {func(*x)}, label: {y}\n"
# print(f"calc: {func(*x)}, label: {y}")
with open("validation.txt", 'w') as f:
f.write(out)
def Multi_stocktrain(num, file_name, days, time_stamp, model, epochs,
batch_sizes):
'''
采用随机的方法来选取不同的股票来对同一模型进行训练
:param num: #选取额外的股票数据作为训练集
:param file_name:
:param days:预测未来几天内的收盘价的平均值
:param timestamps:
:param model:模型
:param epochs:
:param batch_sizes:
:return: model 返回训练好的模型
'''
files = os.listdir('stock_data')
files.remove(file_name)
stock_list = random.sample(range(1, len(files)), num)
for i in stock_list:
print(files[i])
file_path = "stock_data\\" + files[i]
data = handle_data.load_data(file_path)
data = handle_data.K_mean(data, days)
scaler = MinMaxScaler(feature_range=(0, 1))
train = scaler.fit_transform(data)
x_train, y_train = [], []
for i in range(time_stamp, len(train) - days + 1):
x_train.append(train[i - time_stamp:i])
y_train.append(train[i, 0])
x_train, y_train = np.array(x_train), np.array(y_train)
model.fit(x_train,
y_train,
epochs=epochs,
batch_size=batch_sizes,
verbose=1)
return model
6) constants are always floats? if they can be integers - how the gaussian noise works?
7) in mutation: arity preservation OR arity disruption?
"""
# take only features
# df = df.iloc[:, 1:]
# dataset = [{'x': x,
# 'y': y,
# LABEL: z}
# for x, y, z in [(3, 6, 16), (4, 12, 45), (5, 10, 48), (2, 9, 13.5)]
# ]
data = normalize(load_data())
variables = [Variable(i) for i in titles]
operators = [PLUS, MULTIPLY, SUBTRACT, DIVIDE] # SQUARED,
components = tuple(variables + operators) # [Constant(range=(2, 6), integer=True)]
max_depth=10
max_nodes=30
class DomainChromosome(GPChromosome):
def __init__(self, components=components, max_depth=max_depth, max_nodes=max_nodes, **kwargs):
super().__init__(components, max_depth=max_depth, max_nodes=max_nodes, **kwargs)
def Modle_preday(file_name, days, time_stamp, division):
'''
:param file_name: 对应的是股票数据的文件名
:param days: 预测未来几天内的收盘价的平均值
:param time_stamp: 一共使用前多少天的数据进行预测
:param division: 把数据分成测试集和训练集的比例
:return:
'''
#提取已经储存好的股票的历史数据
file_path = "stock_data\\" + file_name
data = handle_data.load_data(file_path)
data = handle_data.K_mean(data, days)
# 划分训练集以及测试集
divide = division * data.shape[0]
train = data[data.index <= divide]
test = data[data.index > divide]
# 数据归一化
scaler = MinMaxScaler(feature_range=(0, 1))
s_train = scaler.fit_transform(train)
s_test = scaler.fit_transform(test)
# 测试集与训练集
x_train, y_train = [], []
for i in range(time_stamp, len(train) - days + 1):
x_train.append(s_train[i - time_stamp:i])
y_train.append(s_train[i, 0])
x_train, y_train = np.array(x_train), np.array(y_train)
x_test, y_test = [], []
for i in range(time_stamp, len(s_test) - days + 1):
x_test.append(s_test[i - time_stamp:i])
y_test.append(test.iloc[i, 0])
x_test = np.array(x_test)
history = LossHistory()
# 创建模型
epochs = 10
batch_size = 16
#model = Model_Lstm(x_train.shape[-1], x_train.shape[1])
model = Model_Create(x_train.shape[-1], x_train.shape[1])
model.fit(x_train,
y_train,
epochs=epochs,
batch_size=batch_size,
verbose=1,
callbacks=[history]) # 训练网络
#Multi_stocktrain(2, file_name, days, time_stamp, model, 3, batch_size)
#保存模型
model_file = "model_save\\" + file_name.strip('.csv') + ".h5"
model.save(model_file)
#使用测试集进行预测
predict_price = model.predict(x_test)
scaler.fit_transform(pd.DataFrame(test['close'].values))
predict_price = scaler.inverse_transform(predict_price)
# 模型效果指标
pre = predict_price.reshape(1, -1)[0]
pre = pre.tolist()
handle_data.calPerformance(y_test, pre)
#计算预测误差绝对值的平均数
sum = 0
for i in range(0, len(y_test)):
sum += abs(y_test[i] - pre[i])
err = sum / len(y_test)
print(err)
# 图像展示
dict_data = {'pre': pre, 'close': y_test}
data_pd = pd.DataFrame(dict_data)
data_pd.plot()
plt.plot(data_pd[['pre', 'close']])
plt.show()
#损失值的图像展示
history.loss_plot()
#未来三天的预测值
Strategy(test.iloc[-1, 4], pre[-1], err)
#print(pre[-1])
#把预测数据和目标值存入文件
predata_file = 'pre_data\\' + file_name
data_pd.to_csv(predata_file)
#handle_data.stock_info(20)
#Modle_preday('000001.SZ.csv', 3, 50, 2/3)
# for root, dirs, files in os.walk('stock_data'):
# print(files)
import numpy as np
import csv
from sklearn import linear_model
if __name__ == "__main__":
from handle_data import load_data, dump_results
x, y = load_data("../train.csv")
print "Loaded training set"
x_test, y_test = load_data("../test.csv", test=True)
print "Loaded testing set"
logreg = linear_model.LogisticRegression(solver='lbfgs', n_jobs=3, max_iter=200)
logreg.fit(x, y)
print "Classifier trained"
y_predict = logreg.predict(x_test)
print "Predictions ready"
dump_results()