File size: 5,010 Bytes
d6d5f77 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
import os
import yfinance as yf
import pandas as pd
from newsapi import NewsApiClient
from transformers import pipeline
import tensorflow as tf
from tensorflow import keras
from sklearn.preprocessing import MinMaxScaler
import numpy as np
from datetime import datetime, timedelta
import alpaca_trade_api as tradeapi
import logging
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Load environment variables with fallback
NEWSAPI_KEY = os.getenv('NEWSAPI_KEY', 'your_newsapi_key')
ALPACA_API_KEY = os.getenv('ALPACA_API_KEY', 'your_alpaca_api_key')
ALPACA_SECRET_KEY = os.getenv('ALPACA_SECRET_KEY', 'your_alpaca_secret_key')
APCA_API_KEY_ID = os.getenv('APCA_API_KEY_ID', ALPACA_API_KEY)
APCA_API_SECRET_KEY = os.getenv('APCA_API_SECRET_KEY', ALPACA_SECRET_KEY)
# Check if all necessary keys are available
if not all([NEWSAPI_KEY, APCA_API_KEY_ID, APCA_API_SECRET_KEY]):
raise ValueError("Ensure all API keys and secret keys are set as environment variables.")
# Initialize NewsAPI client
newsapi = NewsApiClient(api_key=NEWSAPI_KEY)
# Initialize Alpaca Trade API client
alpaca_api = tradeapi.REST(APCA_API_KEY_ID, APCA_API_SECRET_KEY, base_url='https://paper-api.alpaca.markets')
def collect_market_data(ticker):
data = yf.download(ticker, start=(datetime.now() - timedelta(days=365)).strftime('%Y-%m-%d'), end=datetime.now().strftime('%Y-%m-%d'))
data.to_csv(f'{ticker}_market_data.csv')
logger.info(f'Market data for {ticker} collected successfully.')
def collect_news_data(query, from_date, to_date):
all_articles = newsapi.get_everything(q=query, from_param=from_date, to=to_date, language='en', sort_by='relevancy')
if all_articles['status'] == 'ok':
articles_df = pd.DataFrame(all_articles['articles'])
articles_df.to_csv('news_data.csv')
logger.info(f'News data for {query} collected successfully.')
else:
logger.error(f'Error collecting news data: {all_articles["message"]}')
def perform_sentiment_analysis():
sentiment_pipeline = pipeline("sentiment-analysis")
try:
news_data = pd.read_csv('news_data.csv')
news_data['sentiment'] = news_data['description'].apply(lambda x: sentiment_pipeline(x)[0]['label'] if pd.notna(x) else 'NEUTRAL')
news_data.to_csv('sentiment_data.csv', index=False)
logger.info('Sentiment analysis performed successfully.')
except Exception as e:
logger.error(f'Error performing sentiment analysis: {e}')
def train_price_prediction_model(ticker):
data = pd.read_csv(f'{ticker}_market_data.csv')
data = data[['Date', 'Close']].set_index('Date')
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(data)
X = []
y = []
for i in range(60, len(scaled_data)):
X.append(scaled_data[i-60:i, 0])
y.append(scaled_data[i, 0])
X = np.array(X)
y = np.array(y)
X = np.reshape(X, (X.shape[0], X.shape[1], 1))
model = keras.Sequential([
keras.layers.LSTM(50, return_sequences=True, input_shape=(X.shape[1], 1)),
keras.layers.LSTM(50, return_sequences=False),
keras.layers.Dense(25),
keras.layers.Dense(1)
])
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X, y, batch_size=1, epochs=1)
model.save(f'{ticker}_price_prediction_model.h5')
logger.info('Price prediction model trained successfully.')
def make_trade_decision(ticker):
model = keras.models.load_model(f'{ticker}_price_prediction_model.h5')
data = pd.read_csv(f'{ticker}_market_data.csv')
last_60_days = data['Close'].tail(60).values
last_60_days_scaled = MinMaxScaler(feature_range=(0, 1)).fit_transform(last_60_days.reshape(-1, 1))
X_test = []
X_test.append(last_60_days_scaled)
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
predicted_price = model.predict(X_test)
predicted_price = MinMaxScaler(feature_range=(0, 1)).inverse_transform(predicted_price)
current_price = yf.download(ticker, period='1d')['Close'].values[0]
if predicted_price > current_price:
alpaca_api.submit_order(
symbol=ticker,
qty=1,
side='buy',
type='market',
time_in_force='gtc'
)
logger.info(f'Bought 1 share of {ticker}')
else:
alpaca_api.submit_order(
symbol=ticker,
qty=1,
side='sell',
type='market',
time_in_force='gtc'
)
logger.info(f'Sold 1 share of {ticker}')
if __name__ == "__main__":
TICKER = 'AAPL'
QUERY = 'Apple Inc'
FROM_DATE = (datetime.now() - timedelta(days=30)).strftime('%Y-%m-%d')
TO_DATE = datetime.now().strftime('%Y-%m-%d')
collect_market_data(TICKER)
collect_news_data(QUERY, FROM_DATE, TO_DATE)
perform_sentiment_analysis()
train_price_prediction_model(TICKER)
make_trade_decision(TICKER)
|