python - 如何在我的代码中使用自定义 CSV 而不是 Yahoo Finance 数据？

Question

我正在建立一个股票预测神经网络。我正在观看的教程是从 yahoo Finance 导入股票数据。我想通过使其从 CSV 文件中获取数据来改进代码，以便即使您没有连接到互联网也可以使用代码。

我需要在我的代码中进行哪些更改才能让它使用 CSV 文件中的自定义数据？

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import pandas_datareader as web
import datetime as dt

from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM

company = '^GDAXI'

start = dt.datetime(2012,1,1)
end = dt.datetime(2021,1,1)

data = web.DataReader(company, 'yahoo', start, end)

scaler = MinMaxScaler(feature_range=(0,1))
scaled_data = scaler.fit_transform(data['Close'].values.reshape(-1, 1))

prediction_days = 60

x_train = []
y_train = []

for x in range(prediction_days, len(scaled_data)):
    x_train.append(scaled_data[x-prediction_days:x, 0])
    y_train.append(scaled_data[x, 0])

x_train, y_train = np.array(x_train), np.array(y_train)
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))

#BUILD MODEL
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(x_train.shape[1], 1)))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50))
model.add(Dropout(0.2))
model.add(Dense(units=1)) #next day prediction

model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(x_train, y_train, epochs=25, batch_size=32)

#TEST ON EXISTING DATA

test_start = dt.datetime(2020,1,1)
test_end = dt.datetime.now()

test_dataset = web.DataReader(company, 'yahoo', test_start, test_end)
actual_prices = test_dataset['Close'].values

total_dataset = pd.concat((data['Close'], test_dataset['Close']), axis=0)

model_inputs = total_dataset[len(total_dataset)-len(test_dataset)-prediction_days:].values
model_inputs = model_inputs.reshape(-1,1)
model_inputs = scaler.transform(model_inputs)

#PREDICTIONS ON TEST DATA
x_test = []

for x in range(prediction_days, len(model_inputs)):
    x_test.append(model_inputs[x-prediction_days:x, 0])
    
x_test = np.array(x_test)
x_test = np.reshape(x_test,(x_test.shape[0], x_test.shape[1],1))

predicted_prices = model.predict(x_test)
predicted_prices = scaler.inverse_transform(predicted_prices)

#PLOT
plt.plot(actual_prices, color="green", label="Actual Price")
plt.plot(predicted_prices, color="blue", label="Predicted Price")
plt.title("GER40 Share Price")
plt.xlabel('Time')
plt.ylabel('GER40 Price')
plt.legend()
plt.show()

#Predict Next Day
real_dataset = [model_inputs[len(model_inputs)+1-prediction_days:len(model_inputs+1), 0]]
real_dataset = np.array(real_dataset)
real_dataset = np.reshape(real_dataset, (real_dataset.shape[0], real_dataset.shape[1], 1))
prediction = model.predict(real_dataset)
prediction = scaler.inverse_transform(prediction)
print(f"Close: {prediction}")

我使用的 CSV 文件没有标题，但我想我可以使用 excel 添加那些

标签： pythonpandasnumpytensorflowkeras

Answer 1

我认为你应该考虑这样做。

from pandas_datareader import data as wb
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pylab import rcParams
from sklearn.preprocessing import MinMaxScaler

start = '2019-06-30'
end = '2020-06-30'

tickers = ['GOOG']

thelen = len(tickers)

price_data = []
for ticker in tickers:
    prices = wb.DataReader(ticker, start = start, end = end, data_source='yahoo')[['Open','Adj Close']]
    price_data.append(prices.assign(ticker=ticker)[['ticker', 'Open', 'Adj Close']])

#names = np.reshape(price_data, (len(price_data), 1))

df = pd.concat(price_data)
df.reset_index(inplace=True)

for col in df.columns: 
    print(col) 
    
#used for setting the output figure size
rcParams['figure.figsize'] = 20,10
#to normalize the given input data
scaler = MinMaxScaler(feature_range=(0, 1))
#to read input data set (place the file name inside  ' ') as shown below


df['Adj Close'].plot()
plt.legend(loc=2)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()

ntrain = 80
df_train = df.head(int(len(df)*(ntrain/100)))
ntest = -80
df_test = df.tail(int(len(df)*(ntest/100)))


#importing the packages 
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM

#dataframe creation
seriesdata = df.sort_index(ascending=True, axis=0)
new_seriesdata = pd.DataFrame(index=range(0,len(df)),columns=['Date','Adj Close'])
length_of_data=len(seriesdata)
for i in range(0,length_of_data):
    new_seriesdata['Date'][i] = seriesdata['Date'][i]
    new_seriesdata['Adj Close'][i] = seriesdata['Adj Close'][i]
#setting the index again
new_seriesdata.index = new_seriesdata.Date
new_seriesdata.drop('Date', axis=1, inplace=True)
#creating train and test sets this comprises the entire data’s present in the dataset
myseriesdataset = new_seriesdata.values
totrain = myseriesdataset[0:255,:]
tovalid = myseriesdataset[255:,:]
#converting dataset into x_train and y_train
scalerdata = MinMaxScaler(feature_range=(0, 1))
scale_data = scalerdata.fit_transform(myseriesdataset)
x_totrain, y_totrain = [], []
length_of_totrain=len(totrain)
for i in range(60,length_of_totrain):
    x_totrain.append(scale_data[i-60:i,0])
    y_totrain.append(scale_data[i,0])
x_totrain, y_totrain = np.array(x_totrain), np.array(y_totrain)
x_totrain = np.reshape(x_totrain, (x_totrain.shape[0],x_totrain.shape[1],1))


#LSTM neural network
lstm_model = Sequential()
lstm_model.add(LSTM(units=50, return_sequences=True, input_shape=(x_totrain.shape[1],1)))
lstm_model.add(LSTM(units=50))
lstm_model.add(Dense(1))
lstm_model.compile(loss='mean_squared_error', optimizer='adadelta')
lstm_model.fit(x_totrain, y_totrain, epochs=10, batch_size=1, verbose=2)
#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values
myinputs = myinputs.reshape(-1,1)
myinputs  = scalerdata.transform(myinputs)
tostore_test_result = []
for i in range(60,myinputs.shape[0]):
    tostore_test_result.append(myinputs[i-60:i,0])
tostore_test_result = np.array(tostore_test_result)
tostore_test_result = np.reshape(tostore_test_result,(tostore_test_result.shape[0],tostore_test_result.shape[1],1))
myclosing_priceresult = lstm_model.predict(tostore_test_result)
myclosing_priceresult = scalerdata.inverse_transform(myclosing_priceresult)
    
totrain = df_train
tovalid = df_test

#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values

#  Printing the next day’s predicted stock price. 
print(len(tostore_test_result));
print(myclosing_priceresult);

最后结果：

[[1396.532]]