def main():
start = "2003-01-01"
end = "2018-01-01"
hist.get_stock_data("AAPL", start_date=start, end_date=end)
process = DataProcessing("stock_prices.csv", 0.9)
process.gen_test(10)
process.gen_train(10)
X_train = process.X_train / 200
Y_train = process.Y_train / 200
X_test = process.X_test / 200
Y_test = process.Y_test / 200
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(100, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(100, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(1, activation=tf.nn.relu))
model.compile(optimizer="adam", loss="mean_squared_error")
model.fit(X_train, Y_train, epochs=100)
print(model.evaluate(X_test, Y_test))
def main():
process = DataProcessing("sales.csv", 0.9)
process.gen_test(10)
process.gen_train(10)
X_train = process.X_train.reshape((239, 10, 1)) / 200
Y_train = process.Y_train / 200
X_test = process.X_test.reshape(9, 10, 1) / 200
Y_test = process.Y_test / 200
model = tf.keras.Sequential()
model.add(KL.LSTM(20, input_shape=(10, 1), return_sequences=True))
model.add(KL.LSTM(20))
model.add(KL.Dense(1, activation=tf.nn.relu))
model.compile(optimizer="adam", loss="mean_squared_error")
history = model.fit(X_train, Y_train, validation_data=(X_test, Y_test), epochs=50, verbose=0)
print(model.evaluate(X_test, Y_test))
data = pandas.read_csv('sales_with_header.csv', sep=',').sample(n=10)
prices = data["Price"]
X_predict = np.array(prices).reshape((1, 10, 1)) / 200
print("Predictions" + str(model.predict(X_predict) * 200))
# If instead of a full backtest, you just want to see how accurate the model is for a particular prediction, run this:
# data = pdr.get_data_yahoo("AAPL", "2017-12-19", "2018-01-03")
# stock = data["Adj Close"]
# X_predict = np.array(stock).reshape((1, 10)) / 200
# print(model.predict(X_predict)*200)
pyplot.title('Loss / Mean Squared Error')
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()
import tensorflow as tf
from preprocessing import DataProcessing
import pandas_datareader.data as pdr
import yfinance as fix
import matplotlib.pyplot as plt
import WXBizSendMsg
fix.pdr_override()
start = "2000-01-01"
end = "2019-08-22"
stock = "000001.SS"
hist.get_stock_data(stock, start_date=start, end_date=end)
process = DataProcessing("stock_prices.csv", 0.9)
process.gen_test(10)
process.gen_train(10)
X_train = process.X_train / np.array([process.value_max, process.volume_max
]) # 归一化， 包括Adj Close 和 Volume
Y_train = process.Y_train / process.value_max
X_test = process.X_test / np.array([process.value_max, process.volume_max])
Y_test = process.Y_test / process.value_max
model = tf.keras.Sequential()
model.add(tf.keras.layers.LSTM(20, input_shape=(10, 2), return_sequences=True))
model.add(tf.keras.layers.LSTM(20))
model.add(tf.keras.layers.Dense(1))
import matplotlib.pyplot as plt
import quandl as quandl
import keras
from preprocessing import DataProcessing
# live data extraction
TICKER = "WGC/GOLD_DAILY_USD"
data = quandl.get("WGC/GOLD_DAILY_USD", authtoken="FUw5PPY7UX5AW-svaskC")
data = data[37:] # before index 37, prices were not daily
# optimizable variables
PERCENTAGE_OF_DATA_FOR_TRAINING = 0.8
SEQ_LENGTH = 30
N_DAY_FORECAST = 7
data_processor = DataProcessing(
data, PERCENTAGE_OF_DATA_FOR_TRAINING, N_DAY_FORECAST)
data_processor.generate_validation_set(SEQ_LENGTH)
data_processor.generate_training_set(SEQ_LENGTH)
# typically normalize by substracting average and dividing by standard deviation
# but we want to use the output and check against live trade data thus not entirely feasible
# hence simply divide by a constant to ensure weights in network do not become too large
NORMALIZATION_CONSTANT = 500
# "normalization" of training data
X_training = data_processor.X_training.reshape(
len(data_processor.X_training), SEQ_LENGTH, 1) / NORMALIZATION_CONSTANT
Y_training = data_processor.Y_training / NORMALIZATION_CONSTANT
# "normalization" of validation data
X_validation = data_processor.X_validation.reshape(
import get_prices as hist
import tensorflow as tf
from preprocessing import DataProcessing
# import pandas_datareader.data as pdr if using the single test below
import pandas_datareader.data as pdr
import yfinance as fix
import numpy as np
#import matplotlib.pyplot as plt
fix.pdr_override()
start = "2003-01-01"
end = "2018-01-01"
hist.get_stock_data("AAPL", start_date=start, end_date=end)
process = DataProcessing("stock_prices.csv", 0.9)
process.gen_test(10) #滑动窗口构建测试样本
process.gen_train(10) #滑动窗口构建训练样本
X_train = process.X_train / 200 #归一化方法？是否比x' = (x-min/max-min)更靠谱？min=0,max=200
Y_train = process.Y_train / 200
X_test = process.X_test / 200
Y_test = process.Y_test / 200
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(32, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(64, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(1, activation=tf.nn.relu))
model.compile(optimizer="adam", loss="mean_squared_error")