df_sh = gsd.get_code_list_by_classification(classification="上证50成份股")['code']
# print(len(df_sh))
#train dataset
fac = []
ret = []
#test dataset
facT = []
retT = []
for ishare in df_sh:
df = gsd.get_stock_data_daily_df(ishare)
num = math.floor(len(df) / days) * days + 1 - days * 2
newfac = gsd.getDataX(df, num=num, days=days)
newret = gsd.getDataY(df, num=num, days=days)
# if len(newfac)/len(newret) != 5 :
# print(ishare)
# print(num)
# print(len(newfac))
# print(len(newret))
#fac.append(newfac)
for i in range(len(newfac)):
fac.append(newfac[i])
for i in range(len(newret)):
ret.append(newret[i])
# newfacT = gsd.getDataX(df=df,num = math.floor(len(df)/days)*days+1 )
# newretT = gsd.getDataY(df=df,num = math.floor(len(df)/days)*days+1,days = -1 * days )
newfacT = gsd.getDataX(df=df, num=num, days=days)
newretT = gsd.getDataY(df=df, num=num, days=days)
days = 5
df_sh = ts.get_sz50s()['code']
#train dataset
fac = []
ret = []
#test dataset
facT = []
retT = []
for ishare in df_sh:
df = gsd.get_stock_data_daily_df(ishare)
num = math.floor(len(df) / days) * days + 1 - days * 2
newfac = gsd.getDataX(df, num=num)
newret = gsd.getDataY(df, num=num, days=-1 * days)
#if len(newfac)/len(newret) != 5 :
# print(ishare)
# print(num)
# print(len(newfac))
# print(len(newret))
#fac.append(newfac)
for i in range(len(newfac)):
fac.append(newfac[i])
for i in range(len(newret)):
ret.append(newret[i])
#print(len(df))
#print(len(fac))
def trainOneByOne(code=[],daysago=365,inited = False):
# print(len(df_sh))
#train dataset
fac = []
ret = []
#test dataset
facT = []
retT = []
for ishare in code:
df = gsd.get_stock_data_daily_df_daysago(ishare, daysago)
num = math.floor(len(df)/days)*days+1-days*2
newfac = gsd.getDataX(df , num = num , days = days )
newret = gsd.getDataY(df , num = num , days = days )
# if len(newfac)/len(newret) != 5 :
# print(ishare)
# print(num)
# print(len(newfac))
# print(len(newret))
#fac.append(newfac)
for i in range(len(newfac)):
fac.append(newfac[i])
for i in range(len(newret)):
ret.append(newret[i])
# newfacT = gsd.getDataX(df=df,num = math.floor(len(df)/days)*days+1 )
# newretT = gsd.getDataY(df=df,num = math.floor(len(df)/days)*days+1,days = -1 * days )
newfacT = gsd.getDataX(df=df,num = num, days = days )
newretT = gsd.getDataY(df=df,num = num, days = days )
#fac.append(newfac)
for i in range(len(newfacT)):
facT.append(newfacT[i])
for i in range(len(newretT)):
retT.append(newretT[i])
newf = []
newfa = []
for i in range(len(fac)):
if((i+1)%days!=0):
newf.append(fac[i])
else:
newf.append(fac[i])
newfa.append(newf)
newf = []
fac = np.array(newfa)
ret = np.array(ret)
newfT = []
newfaT = []
for i in range(len(facT)):
if((i+1)%5!=0):
newfT.append(facT[i])
else:
newfT.append(facT[i])
newfaT.append(newfT)
newfT = []
facT = np.array(newfaT)
retT = np.array(retT)
# print("**")
# print(len(facT))
# print(len(retT))
# print("**")
fac = np.array(fac)
ret = np.array(ret)
learning_rate = 0.001
#Number of images entered into the model
batch_size = 10
#training_iters = int(fac.shape[0]/batch_size)
#display_step = 10
graph = tf.Graph()
with graph.as_default() :
# tf Graph input
x = tf.placeholder('float',[None, n_steps, n_input])
y = tf.placeholder('float',[None, n_classes])
# # tf Graph input
# x = tf.placeholder("float", [None, n_steps, n_input])
# y = tf.placeholder("float", [None, n_classes])
# Define weights
weights = {
# Hidden layer weights => 2*n_hidden because of forward + backward cells
'out': tf.Variable(tf.random_normal([2*n_hidden, n_classes]))
}
biases = {
'out': tf.Variable(tf.random_normal([n_classes]))
}
pred = BiRNN(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.global_variables_initializer()
saver = tf.train.Saver()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
filename = "D:/stockcheckpoint/others/"+code[0]+".ckpt"
if os.path.exists(filename+".meta"):
saver.restore(sess,filename)
print("restored " + filename )
else :
filename = "D:/stockcheckpoint/sz50/sz50.ckpt"
if os.path.exists(filename+".meta"):
saver.restore(sess,filename)
print("restored "+ filename)
filename = "D:/stockcheckpoint/others/"+code[0]+".ckpt"
#step = 1
for step in range(20):
for i in range(int(len(fac)/batch_size)):
#print(fac.shape)
#print(ret.shape)
batch_x = fac[i*batch_size:(i+1)*batch_size].reshape([batch_size,n_steps,n_input])
batch_y = ret[i*batch_size:(i+1)*batch_size].reshape([batch_size,n_classes])
#print(batch_x.shape)
#print(batch_y.shape)
sess.run(optimizer,feed_dict={x:batch_x,y:batch_y})
#if i % display_step ==0:
#print(i,'----',(int(len(fac)/batch_size)))
#loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,y: batch_y})
#print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc))
save_path = saver.save(sess,filename)
print("%s saved" %save_path )
print("Optimization Finished!")
# Calculate accuracy for 128 mnist test images
#test_len = 1280
print("Accuracy in data set")
test_data = fac[:batch_size].reshape([batch_size,n_steps,n_input])
test_label = ret[:batch_size].reshape([batch_size,n_classes])
Accuracy_in_ds = sess.run(accuracy, feed_dict={x: test_data, y: test_label})
print("Testing Accuracy:", Accuracy_in_ds)
#print("Accuracy out of data set")
#test_dataT = facT[:batch_size].reshape([batch_size,n_steps,n_input])
#test_labelT = retT[:batch_size].reshape([batch_size,n_classes])
#print("Testing Accuracy:", sess.run(accuracy, feed_dict={x: test_dataT, y: test_labelT}))
sess.close()
# del x
# del y
# del weights
# del biases
# del pred
# del cost
# del optimizer
# del correct_pred
# del accuracy
# del init
# del saver
# del sess
return Accuracy_in_ds
# df_sh = ts.get_sz50s()['code']
df_sh = gsd.get_code_list_by_classification(classification="上证50成份股")['code']
#df_sh = ['600000']
# print(len(df_sh))
#train dataset
fac = np.array([]).reshape(-1,5,32)
ret = np.array([]).reshape(-1,3)
#test dataset
facT = np.array([]).reshape(-1,5,32)
retT = np.array([]).reshape(-1,3)
for ishare in df_sh:
df = gsd.get_stock_data_daily_df(ishare)
newfac = gsd.getDataX(df , days = days,pred_days = pred_days )
newret = gsd.getDataY(df , days = days,pred_days = pred_days )
fac = np.append(fac , newfac , axis=0)
ret = np.append(ret , newret , axis=0)
newfacT = gsd.getDataX(df=df, days = days ,pred_days = pred_days )
newretT = gsd.getDataY(df=df, days = days ,pred_days = pred_days )
facT = np.append(facT , newfacT , axis=0)
retT = np.append(retT , newretT , axis=0)
fac = np.array(fac)
ret = np.array(ret)
facT = np.array(facT)
retT = np.array(retT)