// Sample data array with all columns
const dataEntries = [
{
Minute: 10,
Type: 'Actual',
Price: 123938.73,
Time: '08:06 AM',
Error: 5,
Accuracy: 50.00,
DirectionAccuracy: 70.00
},
{
Minute: 10,
Type: 'Predicted',
Price: 123926.83,
Time: '08:06 AM',
Error: 11.90,
Accuracy: 50.00,
DirectionAccuracy: 70.00
},
// Add more entries as needed
];
// Function to convert time string to minutes
function timeToMinutes(timeStr) {
const [time, meridian] = timeStr.trim().split(' ');
let [hh, mm] = time.split(':').map(Number);
if (meridian === 'PM' && hh !== 12) hh += 12;
if (meridian === 'AM' && hh === 12) hh = 0;
return hh * 60 + mm;
}
// Enhanced calculation function
function calculateEnhancedTargetDecision({
HP,
BDS_score,
MAE,
directionalAccuracy,
actualPrice,
error,
volatilityPercent,
maxDrawdownPercent,
varPercent,
sharpeRatio,
timeString
}) {
const minutes = timeToMinutes(timeString);
const timeFactor = minutes > 1200 ? 0.5 : 1;
const accuracyFactor = directionalAccuracy / 100;
const riskFactor = (volatilityPercent / 100 + maxDrawdownPercent / 100 + varPercent / 100) * accuracyFactor;
const sharpeAdj = 1 + sharpeRatio;
const signPred = HP > actualPrice ? 1 : -1;
const complexVolatility = riskFactor * timeFactor * sharpeAdj;
const baseTarget = HP + (signPred * complexVolatility * HP) - (error * (1 - accuracyFactor));
const baseVolatility = 0.01;
const volatilityCode2 = baseVolatility * accuracyFactor;
const targetPriceCode2 = HP + (signPred * volatilityCode2 * timeFactor * HP) - (error * 0.75);
const targetPrice = (baseTarget + targetPriceCode2) / 2;
let decision = "Neutral ⚪";
if (BDS_score > 0.1) {
decision = "High (↑)";
} else if (BDS_score < -0.1) {
decision = "Low (↓)";
} else {
if (sharpeRatio > 0.02 && (volatilityPercent / 100) < 0.01) {
decision = "Neutral ⚪ (Stable)";
}
const thresholdVolatility = 0.02 * accuracyFactor;
const thresholdPrice = actualPrice * 0.99;
if (signPred > 0 && HP > thresholdPrice && volatilityCode2 < thresholdVolatility) {
decision = "High (↑)";
} else if (signPred < 0 && HP > thresholdPrice) {
decision = "Low (↓)";
}
}
return { targetPrice, decision };
}
// Example volatility and risk params (can be dynamic or from data)
const volatilityPercent = 1.0;
const maxDrawdownPercent = 0.5;
const varPercent = 0.3;
const sharpeRatio = 0.02;
const MAE = 0.002; // example normalized MAE
const BDS_score = 0.36; // example score
// Finding actual and predicted entries for given minute
const actualData = dataEntries.find(e => e.Type === 'Actual' && e.Minute === 10);
const predictedData = dataEntries.find(e => e.Type === 'Predicted' && e.Minute === 10);
if (actualData && predictedData) {
const inputData = {
HP: predictedData.Price,
BDS_score: BDS_score,
MAE: MAE,
directionalAccuracy: predictedData.DirectionAccuracy,
actualPrice: actualData.Price,
error: predictedData.Error,
volatilityPercent: volatilityPercent,
maxDrawdownPercent: maxDrawdownPercent,
varPercent: varPercent,
sharpeRatio: sharpeRatio,
timeString: predictedData.Time
};
const result = calculateEnhancedTargetDecision(inputData);
console.log(`Minute: ${predictedData.Minute}`);
console.log(`Target Price: ${result.targetPrice.toFixed(4)}`);
console.log(`Decision: ${result.decision}`);
} else {
console.log('Required Actual or Predicted data not found for the 10th minute.');
}
# app.py from flask import Flask, jsonify import numpy as np import tensorflow as tf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import LSTM, Dense import requests app = Flask(__name__) # Binance se last 60 minute price data fetch karna def fetch_binance_data(): url = "https://api.binance.com/api/v3/klines?symbol=BTCUSDT&interval=1m&limit=60" data = requests.get(url).json() closes = [float(item[4]) for item in data] return closes # LSTM input prepare karna sliding window ke form me def prepare_data(series, n_steps): X, y = [], [] for i in range(len(series) - n_steps): X.append(series[i:i+n_steps]) y.append(series[i+n_steps]) return np.array(X), np.array(y) # LSTM model train karna def train_model(series): n_steps = 10 X, y = prepare_data(series, n_steps) X = X.reshape((X.shape[0], X.shape[1], 1)) model = Sequential([ LSTM(50, activation='relu', input_shape=...
Comments
Post a Comment