{"id":1175080,"date":"2025-01-15T17:26:54","date_gmt":"2025-01-15T09:26:54","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1175080.html"},"modified":"2025-01-15T17:26:57","modified_gmt":"2025-01-15T09:26:57","slug":"python%e5%a6%82%e4%bd%95%e8%8e%b7%e5%be%97%e8%82%a1%e7%a5%a8%e5%b9%b4%e7%ba%bf","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1175080.html","title":{"rendered":"python\u5982\u4f55\u83b7\u5f97\u80a1\u7968\u5e74\u7ebf"},"content":{"rendered":"

\"python\u5982\u4f55\u83b7\u5f97\u80a1\u7968\u5e74\u7ebf\"<\/p>\n

\u8981\u83b7\u5f97\u80a1\u7968\u7684\u5e74\u7ebf\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u79cd\u65b9\u5f0f\uff1a\u4f7f\u7528\u7b2c\u4e09\u65b9API\u83b7\u53d6\u80a1\u7968\u6570\u636e\u3001\u4f7f\u7528Python\u5e93\u5982pandas\u548cmatplotlib\u8fdb\u884c\u6570\u636e\u5904\u7406\u548c\u7ed8\u56fe\u3001\u5229\u7528\u673a\u5668\u5b66\u4e60<\/a>\u548c\u6570\u636e\u5206\u6790\u6280\u672f\u8fdb\u884c\u9884\u6d4b\u548c\u5206\u6790<\/strong>\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528\u7b2c\u4e09\u65b9API\u83b7\u53d6\u80a1\u7968\u6570\u636e<\/h3>\n<\/p>\n

\u4f7f\u7528\u7b2c\u4e09\u65b9API\u83b7\u53d6\u80a1\u7968\u6570\u636e\u662f\u6700\u5e38\u89c1\u7684\u65b9\u5f0f\uff0c\u5f88\u591a\u5e73\u53f0\u63d0\u4f9b\u4e86\u514d\u8d39\u7684API\u63a5\u53e3\uff0c\u901a\u8fc7\u8fd9\u4e9b\u63a5\u53e3\u6211\u4eec\u53ef\u4ee5\u83b7\u53d6\u5230\u5386\u53f2\u80a1\u4ef7\u6570\u636e\u5e76\u8fdb\u884c\u5904\u7406\u3002\u5e38\u7528\u7684API\u5305\u62ecAlpha Vantage\u3001Yahoo Finance\u3001\u548cIEX Cloud\u7b49\u3002<\/p>\n<\/p>\n

1. Alpha Vantage API<\/h4>\n<\/p>\n

Alpha Vantage \u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u80a1\u7968\u6570\u636eAPI\uff0c\u901a\u8fc7\u7b80\u5355\u7684HTTP\u8bf7\u6c42\u5373\u53ef\u83b7\u53d6\u6570\u636e\u3002\u9996\u5148\u9700\u8981\u6ce8\u518c\u4e00\u4e2a\u514d\u8d39\u7684API Key\u3002<\/p>\n<\/p>\n

import requests<\/p>\n
import pandas as pd<\/p>\n
def get_stock_data(symbol, api_key):<\/p>\n
    url = f'https:\/\/www.alphavantage.co\/query?function=TIME_SERIES_DAI<\/a>LY&symbol={symbol}&apikey={api_key}&outputsize=full&datatype=csv'<\/p>\n
    response = requests.get(url)<\/p>\n
    with open('stock_data.csv', 'w') as f:<\/p>\n
        f.write(response.text)<\/p>\n
    df = pd.read_csv('stock_data.csv')<\/p>\n
    return df<\/p>\n
api_key = 'your_api_key'<\/p>\n
symbol = 'AAPL'<\/p>\n
stock_data = get_stock_data(symbol, api_key)<\/p>\n
print(stock_data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. Yahoo Finance API<\/h4>\n<\/p>\n
Yahoo Finance \u63d0\u4f9b\u4e86\u66f4\u4e3a\u7b80\u4fbf\u7684\u80a1\u7968\u6570\u636e\u83b7\u53d6\u65b9\u5f0f\uff0c\u53ef\u4ee5\u5229\u7528 yfinance \u5e93\u6765\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n
import yfinance as yf<\/p>\n
def get_stock_data(symbol):<\/p>\n
    stock = yf.Ticker(symbol)<\/p>\n
    data = stock.history(period="1y")<\/p>\n
    return data<\/p>\n
symbol = 'AAPL'<\/p>\n
stock_data = get_stock_data(symbol)<\/p>\n
print(stock_data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Python\u5e93\u8fdb\u884c\u6570\u636e\u5904\u7406\u548c\u7ed8\u56fe<\/h3>\n<\/p>\n
\u83b7\u53d6\u5230\u80a1\u7968\u6570\u636e\u540e\uff0c\u6211\u4eec\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u5904\u7406\u548c\u5206\u6790\u3002\u4e3b\u8981\u4f7f\u7528\u7684\u5e93\u5305\u62ecpandas\u3001numpy\u548cmatplotlib\u3002<\/p>\n<\/p>\n
1. \u6570\u636e\u5904\u7406<\/h4>\n<\/p>\n
\u4f7f\u7528pandas\u8fdb\u884c\u6570\u636e\u6e05\u6d17\u3001\u5904\u7406\u548c\u8ba1\u7b97\u5e74\u7ebf\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
def calculate_yearly_moving_average(data, window=250):<\/p>\n
    data['Yearly_MA'] = data['Close'].rolling(window=window).mean()<\/p>\n
    return data<\/p>\n
stock_data = calculate_yearly_moving_average(stock_data)<\/p>\n
print(stock_data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u6570\u636e\u53ef\u89c6\u5316<\/h4>\n<\/p>\n
\u4f7f\u7528matplotlib\u7ed8\u5236\u80a1\u7968\u5e74\u7ebf\u56fe\u3002<\/p>\n<\/p>\n
import matplotlib.pyplot as plt<\/p>\n
def plot_stock_data(data, symbol):<\/p>\n
    plt.figure(figsize=(14,7))<\/p>\n
    plt.plot(data['Close'], label='Close Price')<\/p>\n
    plt.plot(data['Yearly_MA'], label='Yearly Moving Average', color='orange')<\/p>\n
    plt.title(f'{symbol} Stock Price and Yearly Moving Average')<\/p>\n
    plt.xlabel('Date')<\/p>\n
    plt.ylabel('Price')<\/p>\n
    plt.legend()<\/p>\n
    plt.show()<\/p>\n
plot_stock_data(stock_data, symbol)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u5229\u7528\u673a\u5668\u5b66\u4e60\u548c\u6570\u636e\u5206\u6790\u6280\u672f\u8fdb\u884c\u9884\u6d4b\u548c\u5206\u6790<\/h3>\n<\/p>\n
\u9664\u57fa\u672c\u7684\u5e74\u7ebf\u8ba1\u7b97\u5916\uff0c\u8fd8\u53ef\u4ee5\u5229\u7528\u673a\u5668\u5b66\u4e60\u6280\u672f\u8fdb\u884c\u80a1\u7968\u4ef7\u683c\u9884\u6d4b\u548c\u5206\u6790\u3002<\/p>\n<\/p>\n
1. \u6570\u636e\u9884\u5904\u7406<\/h4>\n<\/p>\n
\u5728\u8fdb\u884c\u673a\u5668\u5b66\u4e60\u4e4b\u524d\uff0c\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u6807\u51c6\u5316\u548c\u7279\u5f81\u5de5\u7a0b\u3002<\/p>\n<\/p>\n
from sklearn.preprocessing import StandardScaler<\/p>\n
def preprocess_data(data):<\/p>\n
    data = data[['Close']].dropna()<\/p>\n
    scaler = StandardScaler()<\/p>\n
    data['Close'] = scaler.fit_transform(data[['Close']])<\/p>\n
    return data, scaler<\/p>\n
processed_data, scaler = preprocess_data(stock_data)<\/p>\n
print(processed_data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u5efa\u7acb\u9884\u6d4b\u6a21\u578b<\/h4>\n<\/p>\n
\u53ef\u4ee5\u5229\u7528LSTM\uff08\u957f\u77ed\u671f\u8bb0\u5fc6\u7f51\u7edc\uff09\u8fdb\u884c\u65f6\u95f4\u5e8f\u5217\u9884\u6d4b\u3002<\/p>\n<\/p>\n
import numpy as np<\/p>\n
import tensorflow as tf<\/p>\n
from tensorflow.keras.models import Sequential<\/p>\n
from tensorflow.keras.layers import LSTM, Dense<\/p>\n
def create_dataset(data, time_step=1):<\/p>\n
    X, y = [], []<\/p>\n
    for i in range(len(data)-time_step-1):<\/p>\n
        X.append(data[i:(i+time_step), 0])<\/p>\n
        y.append(data[i + time_step, 0])<\/p>\n
    return np.array(X), np.array(y)<\/p>\n
def build_lstm_model(input_shape):<\/p>\n
    model = Sequential()<\/p>\n
    model.add(LSTM(50, return_sequences=True, input_shape=input_shape))<\/p>\n
    model.add(LSTM(50, return_sequences=False))<\/p>\n
    model.add(Dense(1))<\/p>\n
    model.compile(optimizer='adam', loss='mean_squared_error')<\/p>\n
    return model<\/p>\n
time_step = 60<\/p>\n
X, y = create_dataset(processed_data.values, time_step)<\/p>\n
X = X.reshape(X.shape[0], X.shape[1], 1)<\/p>\n
model = build_lstm_model((time_step, 1))<\/p>\n
model.fit(X, y, epochs=10, batch_size=32, verbose=1)<\/p>\n
\u9884\u6d4b<\/strong><\/h2>\n
predictions = model.predict(X)<\/p>\n
predictions = scaler.inverse_transform(predictions)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u9884\u6d4b\u7ed3\u679c\u53ef\u89c6\u5316<\/h4>\n<\/p>\n
\u5c06\u9884\u6d4b\u7ed3\u679c\u8fdb\u884c\u53ef\u89c6\u5316\u5c55\u793a\u3002<\/p>\n<\/p>\n
plt.figure(figsize=(14,7))<\/p>\n
plt.plot(stock_data['Close'], label='Actual Stock Price')<\/p>\n
plt.plot(stock_data.index[time_step+1:], predictions, label='Predicted Stock Price', color='orange')<\/p>\n
plt.title(f'{symbol} Stock Price Prediction')<\/p>\n
plt.xlabel('Date')<\/p>\n
plt.ylabel('Price')<\/p>\n
plt.legend()<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u4f7f\u7528\u7b2c\u4e09\u65b9API\u83b7\u53d6\u80a1\u7968\u6570\u636e\u3001\u4f7f\u7528Python\u5e93\u5982pandas\u548cmatplotlib\u8fdb\u884c\u6570\u636e\u5904\u7406\u548c\u7ed8\u56fe\u3001\u5229\u7528\u673a\u5668\u5b66\u4e60\u548c\u6570\u636e\u5206\u6790\u6280\u672f\u8fdb\u884c\u9884\u6d4b\u548c\u5206\u6790<\/strong>\u7b49\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u5730\u83b7\u53d6\u548c\u5206\u6790\u80a1\u7968\u5e74\u7ebf\u6570\u636e\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u72ec\u7279\u7684\u4f18\u70b9\u548c\u9002\u7528\u573a\u666f\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53ef\u4ee5\u63d0\u9ad8\u6211\u4eec\u7684\u6570\u636e\u5206\u6790\u6548\u7387\u548c\u9884\u6d4b\u51c6\u786e\u6027\u3002\u5e0c\u671b\u4ee5\u4e0a\u5185\u5bb9\u80fd\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff0c\u5e76\u80fd\u591f\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\u5e94\u7528\u8fd9\u4e9b\u6280\u672f\u5b9e\u73b0\u80a1\u7968\u6570\u636e\u7684\u5206\u6790\u548c\u9884\u6d4b\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u83b7\u53d6\u80a1\u7968\u5e74\u7ebf\u7684\u6570\u636e\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u91d1\u878d\u6570\u636e\u83b7\u53d6\u5e93\uff0c\u5982yfinance<\/code>\u6216pandas_datareader<\/code>\uff0c\u6765\u83b7\u53d6\u80a1\u7968\u7684\u5e74\u7ebf\u6570\u636e\u3002\u60a8\u53ea\u9700\u5bfc\u5165\u76f8\u5173\u5e93\uff0c\u8f93\u5165\u80a1\u7968\u4ee3\u7801\u548c\u65f6\u95f4\u8303\u56f4\uff0c\u5373\u53ef\u8f7b\u677e\u63d0\u53d6\u51fa\u6240\u9700\u7684\u80a1\u7968\u5e74\u7ebf\u6570\u636e\u3002<\/p>\n
\u83b7\u53d6\u80a1\u7968\u5e74\u7ebf\u6570\u636e\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u4e8b\u9879\uff1f<\/strong>
\u5728\u83b7\u53d6\u80a1\u7968\u5e74\u7ebf\u6570\u636e\u65f6\uff0c\u786e\u4fdd\u9009\u62e9\u7684\u65f6\u95f4\u8303\u56f4\u8db3\u591f\u957f\uff0c\u4ee5\u6db5\u76d6\u81f3\u5c11\u4e00\u5e74\u7684\u6570\u636e\u3002\u6b64\u5916\uff0c\u68c0\u67e5\u6570\u636e\u6e90\u7684\u53ef\u9760\u6027\u548c\u51c6\u786e\u6027\u4e5f\u5f88\u91cd\u8981\uff0c\u4f7f\u7528\u77e5\u540d\u7684\u91d1\u878d\u6570\u636e\u6e90\u53ef\u4ee5\u5e2e\u52a9\u60a8\u83b7\u5f97\u66f4\u9ad8\u8d28\u91cf\u7684\u6570\u636e\u3002<\/p>\n
\u5982\u4f55\u5728Python\u4e2d\u7ed8\u5236\u80a1\u7968\u7684\u5e74\u7ebf\u56fe\uff1f<\/strong>
\u60a8\u53ef\u4ee5\u4f7f\u7528matplotlib<\/code>\u6216seaborn<\/code>\u7b49\u53ef\u89c6\u5316\u5e93\u6765\u7ed8\u5236\u80a1\u7968\u7684\u5e74\u7ebf\u56fe\u3002\u63d0\u53d6\u5230\u5e74\u7ebf\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u5c06\u5176\u4f20\u5165\u53ef\u89c6\u5316\u51fd\u6570\u4e2d\uff0c\u8bbe\u7f6e\u9002\u5f53\u7684\u56fe\u8868\u6837\u5f0f\u548c\u6807\u7b7e\uff0c\u4ece\u800c\u751f\u6210\u76f4\u89c2\u7684\u80a1\u7968\u5e74\u7ebf\u56fe\uff0c\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7406\u89e3\u80a1\u7968\u8d70\u52bf\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u83b7\u5f97\u80a1\u7968\u7684\u5e74\u7ebf\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u79cd\u65b9\u5f0f\uff1a\u4f7f\u7528\u7b2c\u4e09\u65b9API\u83b7\u53d6\u80a1\u7968\u6570\u636e\u3001\u4f7f\u7528Python\u5e93\u5982pandas\u548cmat […]","protected":false},"author":3,"featured_media":1175082,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1175080"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1175080"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1175080\/revisions"}],"predecessor-version":[{"id":1175083,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1175080\/revisions\/1175083"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1175082"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1175080"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1175080"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1175080"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}