|
import ccxt |
|
import pandas as pd |
|
import streamlit as st |
|
import xgboost as xgb |
|
from sklearn.metrics import r2_score |
|
from sklearn.model_selection import train_test_split |
|
|
|
exchange = ccxt.mexc({ |
|
'apiKey': 'mx0vglbkoCOwmqV5tn', |
|
'secret': 'c6d8cc8953fd405787ed54e3488ae0db', |
|
'enableRateLimit': True, |
|
}) |
|
|
|
|
|
|
|
|
|
def fetch_ohlcv_data(symbol, timeframe, limit): |
|
data = [] |
|
start_time = None |
|
while len(data) < limit: |
|
ohlcv_data = exchange.fetch_ohlcv(symbol, timeframe, since=start_time, limit=limit) |
|
data.extend(ohlcv_data) |
|
start_time = ohlcv_data[-1][0] + 1 |
|
return data |
|
|
|
|
|
def data_to_dataframe(data): |
|
df = pd.DataFrame(data, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume']) |
|
df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms') |
|
df.set_index('timestamp', inplace=True) |
|
return df |
|
|
|
def prepare_dataset(df, lags): |
|
X = pd.DataFrame() |
|
y = pd.DataFrame() |
|
|
|
for lag in range(1, lags + 1): |
|
shifted_close = df['close'].shift(lag) |
|
X[f'close_lag_{lag}'] = shifted_close |
|
|
|
y = df['close'].shift(-1) |
|
return X, y |
|
|
|
def train_xgboost_model(X_train, y_train): |
|
dtrain = xgb.DMatrix(X_train, label=y_train) |
|
params = { |
|
'objective': 'reg:squarederror', |
|
'eval_metric': 'rmse', |
|
} |
|
|
|
model = xgb.train(params, dtrain) |
|
return model |
|
|
|
def predict_next_hour_price(df, model, lags): |
|
X_test = pd.DataFrame() |
|
|
|
for lag in range(1, lags + 1): |
|
shifted_close = df['close'].shift(lag) |
|
X_test[f'close_lag_{lag}'] = shifted_close |
|
|
|
X_test = X_test.tail(1) |
|
dtest = xgb.DMatrix(X_test) |
|
next_hour_price = model.predict(dtest) |
|
return next_hour_price |
|
|
|
def evaluate_prediction_accuracy(y_test, y_pred): |
|
accuracy = r2_score(y_test, y_pred) |
|
return accuracy |
|
|
|
def execute_trade(exchange, symbol, side, amount): |
|
order = exchange.create_market_order(symbol, side, amount) |
|
return order |
|
|
|
symbol = 'BTC/USDT' |
|
timeframe = '1h' |
|
limit = 7200 |
|
lags = 12 |
|
test_size = 0.3 |
|
|
|
ohlcv_data = fetch_ohlcv_data(symbol, timeframe, limit) |
|
df = data_to_dataframe(ohlcv_data) |
|
|
|
if st.button("hoo"): |
|
st.write(df) |
|
|
|
X, y = prepare_dataset(df, lags) |
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size) |
|
|
|
model = train_xgboost_model(X_train, y_train) |
|
y_pred = model.predict(X_test) |
|
accuracy = evaluate_prediction_accuracy(y_test, y_pred) |
|
|
|
if accuracy > 0.9: |
|
latest_data = df.tail(lags) |
|
predicted_price = predict_next_hour_price(latest_data, model, lags) |
|
current_price = latest_data['close'].iloc[-1] |
|
|
|
if predicted_price > current_price: |
|
|
|
amount = 0.001 |
|
order = execute_trade(exchange, symbol, 'buy', amount) |
|
print(f"Bought {amount} BTC at {current_price}") |
|
elif predicted_price < current_price: |
|
|
|
amount = 0.001 |
|
order = execute_trade(exchange, symbol, 'sell', amount) |
|
print(f"Sold {amount} BTC at {current_price}") |
|
else: |
|
print("Accuracy is low, not placing order.") |
|
|