我有以下代码来分析来自雅虎财经的股票价格,但我一直遇到错误。
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
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 = str(input('enter the company symbol '))
company = 'FB'
start = dt.datetime(2011,1,1)
end = dt.datetime(2019,1,1)
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))
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))
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(x_train, y_train, epochs=25, batch_size=32)
test_start=dt.datetime(2019,1,1)
test_end = dt.datetime.now()
test_data = web.DataReader(company, 'yahoo', test_start, test_end)
actual_prices = test_data['Close'].values
total_dataset = pd.concat((data['Close'],test_data['Close']), axis=0)
model_inputs = total_dataset[len(total_dataset)- len(test_data) - prediction_days:].values
model_inputs = model_inputs.reshape(-1,1)
model_inputs = scaler.transform(model_inputs)
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)
plt.plot(actual_prices, color = 'black', label = f"Actual{company} price")
plt.plot(predicted_prices, color = 'green', label = f"Predicted{company} price")
plt.title(f"{company} share price")
plt.xlabel ('Time')
plt.ylabel(f"{company} share price")
plt.legend()
plt.show()
我收到以下错误
RemoteDataError: Unable to read URL: https://finance.yahoo.com/quote/FB/history?
period1=1293854400&period2=1546401599&interval=1d&frequency=1d&filter=history
Response Text:
b'<!DOCTYPE html>\n <html lang="en-us"><head>\n <meta http-equiv="content-type"
content="text/html; charset=UTF-8">\n <meta charset="utf-8">\n
<title>Yahoo</title>\n <meta name="viewport" content="width=device-width,initial-
scale=1,minimal-ui">\n <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">\n
<style>\n html {\n height: 100%;\n }\n body {\n background: #fafafc
url(https://s.yimg.com/nn/img/sad-panda-201402200631.png) 50% 50%;\n background-size:
cover;\n height: 100%;\n text-align: center;\n font: 300 18px "helvetica neue",
helvetica, verdana, tahoma, arial, sans-serif;\n }\n table {\n height: 100%;\n
width: 100%;\n table-layout: fixed;\n border-collapse: collapse;\n border-
spacing: 0;\n border: none;\n }\n h1 {\n font-size: 42px;\n font-weight:
400;\n color: #400090;\n }\n p {\n color: #1A1A1A;\n }\n #message-1 {\n
font-weight: bold;\n margin: 0;\n }\n #message-2 {\n display: inline-block;\n
*display: inline;\n zoom: 1;\n max-width: 17em;\n _width: 17em;\n }\n
</style>\n <script>\n document.write(\'<img src="//geo.yahoo.com/b?s=1197757129&t=\'+new
Date().getTime()+\'&src=aws&err_url=\'+encodeURIComponent(document.URL)+\'&err=%
<pssc>&test=\'+encodeURIComponent(\'%<{Bucket}cqh[:200]>\')+\'" width="0px"
height="0px"/>\');var
beacon = new Image();beacon.src="//bcn.fp.yahoo.com/p?s=1197757129&t="+ne...
我之前知道 API 有问题,但我认为现在已经解决了。有没有其他方法可以从 API 中提取数据? 任何关于如何解决这个问题的建议将不胜感激。 不知道为什么我一直收到这个。几周前这曾经可以正常工作。 此外,我正在使用 GoogleColab 运行此代码。
有什么建议吗?
答案 0 :(得分:0)
雅虎财经改为yfinance
。所以pip install yfinance
然后你可以做
import yfinance as yf
yf.pdr_override()
from pandas_datareader import data as pdr
temp_df = pdr.get_data_yahoo("FB", start, end)
它返回一个数据框 temp_df
。