Spaces:
Sleeping
Sleeping
File size: 5,331 Bytes
b8086d5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
import yfinance as yf
import pandas as pd
import numpy as np
from datetime import datetime, timedelta
class DataProcessor:
def __init__(self):
self.ticker = "GC=F"
self.fundamentals_cache = {}
def get_gold_data(self, interval="1d", period="max"):
"""Fetch gold futures data from Yahoo Finance"""
try:
# Map internal intervals to yfinance format
interval_map = {
"5m": "5m",
"15m": "15m",
"30m": "30m",
"1h": "60m",
"4h": "240m",
"1d": "1d",
"1wk": "1wk",
"1mo": "1mo",
"3mo": "3mo"
}
yf_interval = interval_map.get(interval, "1d")
# Determine appropriate period based on interval
if interval in ["5m", "15m", "30m", "1h", "4h"]:
period = "60d" # Intraday data limited to 60 days
elif interval in ["1d"]:
period = "1y"
elif interval in ["1wk"]:
period = "2y"
else:
period = "max"
ticker = yf.Ticker(self.ticker)
df = ticker.history(interval=yf_interval, period=period)
if df.empty:
raise ValueError("No data retrieved from Yahoo Finance")
# Ensure proper column names
df.columns = [col.capitalize() for col in df.columns]
return df
except Exception as e:
print(f"Error fetching data: {e}")
return pd.DataFrame()
def calculate_indicators(self, df):
"""Calculate technical indicators"""
if df.empty:
return df
# Simple Moving Averages
df['SMA_20'] = df['Close'].rolling(window=20).mean()
df['SMA_50'] = df['Close'].rolling(window=50).mean()
# Exponential Moving Averages
df['EMA_12'] = df['Close'].ewm(span=12, adjust=False).mean()
df['EMA_26'] = df['Close'].ewm(span=26, adjust=False).mean()
# MACD
df['MACD'] = df['EMA_12'] - df['EMA_26']
df['MACD_signal'] = df['MACD'].ewm(span=9, adjust=False).mean()
df['MACD_histogram'] = df['MACD'] - df['MACD_signal']
# RSI
delta = df['Close'].diff()
gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()
loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()
rs = gain / loss
df['RSI'] = 100 - (100 / (1 + rs))
# Bollinger Bands
df['BB_middle'] = df['Close'].rolling(window=20).mean()
bb_std = df['Close'].rolling(window=20).std()
df['BB_upper'] = df['BB_middle'] + (bb_std * 2)
df['BB_lower'] = df['BB_middle'] - (bb_std * 2)
# Average True Range (ATR)
high_low = df['High'] - df['Low']
high_close = np.abs(df['High'] - df['Close'].shift())
low_close = np.abs(df['Low'] - df['Close'].shift())
ranges = pd.concat([high_low, high_close, low_close], axis=1)
true_range = ranges.max(axis=1)
df['ATR'] = true_range.rolling(window=14).mean()
# Volume indicators
df['Volume_SMA'] = df['Volume'].rolling(window=20).mean()
df['Volume_ratio'] = df['Volume'] / df['Volume_SMA']
return df
def get_fundamental_data(self):
"""Get fundamental gold market data"""
try:
ticker = yf.Ticker(self.ticker)
info = ticker.info
# Mock some gold-specific fundamentals as yfinance may not have all
fundamentals = {
"Gold Strength Index": round(np.random.uniform(30, 80), 1),
"Dollar Index": round(np.random.uniform(90, 110), 1),
"Real Interest Rate": f"{np.random.uniform(-2, 5):.2f}%",
"Gold Volatility": f"{np.random.uniform(10, 40):.1f}%",
"Commercial Hedgers (Net)": f"{np.random.uniform(-50000, 50000):,.0f}",
"Managed Money (Net)": f"{np.random.uniform(-100000, 100000):,.0f}",
"Market Sentiment": np.random.choice(["Bullish", "Neutral", "Bearish"]),
"Central Bank Demand": np.random.choice(["High", "Medium", "Low"]),
"Jewelry Demand Trend": np.random.choice(["Increasing", "Stable", "Decreasing"])
}
return fundamentals
except Exception as e:
print(f"Error fetching fundamentals: {e}")
return {"Error": str(e)}
def prepare_for_chronos(self, df, lookback=100):
"""Prepare data for Chronos model"""
if df.empty or len(df) < lookback:
return None
# Use close prices and normalize
prices = df['Close'].iloc[-lookback:].values
prices = prices.astype(np.float32)
# Normalize to help model performance
mean = np.mean(prices)
std = np.std(prices)
normalized = (prices - mean) / (std + 1e-8)
return {
'values': normalized,
'mean': mean,
'std': std,
'original': prices
} |