import gradio as gr
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import mplfinance as mpf
from data_processor import DataProcessor
from sentiment_analyzer import SentimentAnalyzer
from model_handler import ModelHandler
from trading_logic import TradingLogic
import io
import base64
import plotly.graph_objects as go
asset_map = {
"Gold Futures (GC=F)": "GC=F",
"Bitcoin USD (BTC-USD)": "BTC-USD"
}
data_processor = DataProcessor()
sentiment_analyzer = SentimentAnalyzer()
model_handler = ModelHandler()
trading_logic = TradingLogic()
def create_chart_analysis(interval, asset_name):
try:
ticker = asset_map[asset_name]
df = data_processor.get_asset_data(ticker, interval)
if df.empty:
fig, ax = plt.subplots(figsize=(12, 8), facecolor='white')
fig.patch.set_facecolor('white')
ax.text(0.5, 0.5, f'No data available for {asset_name}\nPlease try a different interval',
ha='center', va='center', transform=ax.transAxes, fontsize=14, color='red')
ax.set_title('Data Error', color='black')
ax.axis('off')
pred_fig = plt.figure(figsize=(10, 4), facecolor='white')
pred_fig.patch.set_facecolor('white')
return fig, {}, pred_fig
df = data_processor.calculate_indicators(df)
ap = []
if 'SMA_20' in df.columns:
ap.append(mpf.make_addplot(df['SMA_20'].iloc[-100:], color='#FFA500', width=1.5, label='SMA 20'))
if 'SMA_50' in df.columns:
ap.append(mpf.make_addplot(df['SMA_50'].iloc[-100:], color='#FF4500', width=1.5, label='SMA 50'))
if 'BB_upper' in df.columns and 'BB_lower' in df.columns:
ap.append(mpf.make_addplot(df['BB_upper'].iloc[-100:], color='#4169E1', width=1, linestyle='dashed', label='BB Upper'))
ap.append(mpf.make_addplot(df['BB_lower'].iloc[-100:], color='#4169E1', width=1, linestyle='dashed', label='BB Lower'))
try:
fig, axes = mpf.plot(
df[-100:],
type='candle',
style='yahoo',
title=f'{asset_name} - {interval}',
ylabel='Price (USD)',
volume=True,
addplot=ap,
figsize=(15, 9),
returnfig=True,
warn_too_much_data=200,
# MENGGUNAKAN scale_padding UNTUK MEMBERI RUANG PADA SUMBU Y KANAN
scale_padding={'right': 1.0, 'left': 0.1}
)
fig.patch.set_facecolor('white')
if axes:
axes[0].set_facecolor('white')
axes[0].grid(True, alpha=0.3)
except Exception as plot_error:
print(f"Mplfinance plot error: {plot_error}")
fig, axes = plt.subplots(figsize=(12, 8), facecolor='white')
fig.patch.set_facecolor('white')
axes.text(0.5, 0.5, f'Chart Plot Error: {str(plot_error)}', ha='center', va='center',
transform=axes.transAxes, fontsize=14, color='red')
axes.set_title('Plot Generation Error', color='black')
axes.axis('off')
prepared_data = data_processor.prepare_for_chronos(df)
predictions = model_handler.predict(prepared_data, horizon=10)
current_price = df['Close'].iloc[-1]
signal, confidence = trading_logic.generate_signal(
predictions, current_price, df
)
tp, sl = trading_logic.calculate_tp_sl(
current_price, df['ATR'].iloc[-1] if 'ATR' in df.columns else 10, signal
)
metrics = {
"Current Price": f"${current_price:,.2f}",
"Signal": signal.upper(),
"Confidence": f"{confidence:.1%}",
"Take Profit": f"${tp:,.2f}" if tp else "N/A",
"Stop Loss": f"${sl:,.2f}" if sl else "N/A",
"RSI": f"{df['RSI'].iloc[-1]:.1f}" if 'RSI' in df.columns else "N/A",
"MACD": f"{df['MACD'].iloc[-1]:.4f}" if 'MACD' in df.columns else "N/A",
"Volume": f"{df['Volume'].iloc[-1]:,.0f}" if 'Volume' in df.columns else "N/A"
}
pred_fig, ax = plt.subplots(figsize=(10, 4), facecolor='white')
pred_fig.patch.set_facecolor('white')
hist_data = df['Close'].iloc[-30:]
hist_dates = df.index[-30:]
ax.plot(hist_dates, hist_data, color='#4169E1', linewidth=2, label='Historical')
if predictions.any() and len(predictions) > 0:
future_dates = pd.date_range(
start=df.index[-1], periods=len(predictions), freq='D'
)
ax.plot(future_dates, predictions, color='#FF6600', linewidth=2,
marker='o', markersize=4, label='Predictions')
ax.plot([hist_dates[-1], future_dates[0]],
[hist_data.iloc[-1], predictions[0]],
color='#FF6600', linewidth=1, linestyle='--')
ax.set_title('Price Prediction (Next 10 Periods)', fontsize=12, color='black')
ax.set_xlabel('Date', color='black')
ax.set_ylabel('Price (USD)', color='black')
ax.legend()
ax.grid(True, alpha=0.3)
ax.tick_params(colors='black')
return fig, metrics, pred_fig
except Exception as e:
fig, ax = plt.subplots(figsize=(12, 8), facecolor='white')
fig.patch.set_facecolor('white')
ax.text(0.5, 0.5, f'Error: {str(e)}', ha='center', va='center',
transform=ax.transAxes, fontsize=14, color='red')
ax.set_title('Chart Generation Error', color='black')
ax.axis('off')
pred_fig = plt.figure(figsize=(10, 4), facecolor='white')
pred_fig.patch.set_facecolor('white')
return fig, {}, pred_fig
def analyze_sentiment(asset_name):
try:
ticker = asset_map[asset_name]
sentiment_score, news_summary = sentiment_analyzer.analyze_market_sentiment(ticker)
fig = go.Figure(go.Indicator(
mode="gauge+number+delta",
value=sentiment_score,
domain={'x': [0, 1], 'y': [0, 1]},
title={'text': f"{ticker} Market Sentiment (Simulated)"},
delta={'reference': 0},
gauge={
'axis': {'range': [-1, 1]},
'bar': {'color': "#FFD700"},
'steps': [
{'range': [-1, -0.5], 'color': "rgba(255,0,0,0.5)"},
{'range': [-0.5, 0.5], 'color': "rgba(100,100,100,0.3)"},
{'range': [0.5, 1], 'color': "rgba(0,255,0,0.5)"}
],
'threshold': {
'line': {'color': "black", 'width': 4},
'thickness': 0.75,
'value': 0
}
}
))
fig.update_layout(
template='plotly_white',
height=300,
paper_bgcolor='white',
plot_bgcolor='white',
font=dict(color='black')
)
return fig, news_summary
except Exception as e:
fig, ax = plt.subplots(figsize=(6, 4), facecolor='white')
fig.patch.set_facecolor('white')
ax.text(0.5, 0.5, f'Sentiment Error: {str(e)}', ha='center', va='center',
transform=ax.transAxes, fontsize=12, color='red')
ax.axis('off')
return fig, f"Error analyzing sentiment: {str(e)}
"
def get_fundamentals(asset_name):
try:
ticker = asset_map[asset_name]
fundamentals = data_processor.get_fundamental_data(ticker)
table_data = []
for key, value in fundamentals.items():
table_data.append([key, value])
df = pd.DataFrame(table_data, columns=['Metric', 'Value'])
fig, ax = plt.subplots(figsize=(6, 4), facecolor='white')
fig.patch.set_facecolor('white')
strength_index = fundamentals.get('Strength Index', 50)
ax.barh([0], [strength_index], height=0.3, color='gold', alpha=0.7)
ax.set_xlim(0, 100)
ax.set_ylim(-0.5, 0.5)
ax.set_title(f'{asset_name} Strength Index', color='black')
ax.set_xlabel('Index Value', color='black')
ax.text(strength_index, 0, f'{strength_index:.1f}',
ha='left', va='center', fontsize=12, color='black', weight='bold')
ax.grid(True, alpha=0.3)
ax.tick_params(colors='black')
return fig, df
except Exception as e:
fig, ax = plt.subplots(figsize=(6, 4), facecolor='white')
fig.patch.set_facecolor('white')
ax.text(0.5, 0.5, f'Fundamentals Error: {str(e)}', ha='center', va='center',
transform=ax.transAxes, fontsize=12, color='red')
ax.axis('off')
return fig, pd.DataFrame()
with gr.Blocks(
theme=gr.themes.Default(primary_hue="blue", secondary_hue="blue"),
title="Trading Analysis & Prediction",
css="""
.gradio-container {background-color: #FFFFFF !important; color: #000000 !important}
.gr-button-primary {background-color: #4169E1 !important; color: #FFFFFF !important}
.gr-button-secondary {border-color: #4169E1 !important; color: #4169E1 !important}
.gr-tab button {color: #000000 !important}
.gr-tab button.selected {background-color: #4169E1 !important; color: #FFFFFF !important}
.gr-highlighted {background-color: #F0F0F0 !important}
.anycoder-link {color: #4169E1 !important; text-decoration: none; font-weight: bold}
.gr-json {background-color: #FFFFFF !important; color: #000000 !important}
.gr-json label {color: #000000 !important}
.gr-textbox, .gr-dropdown, .gr-number {background-color: #FFFFFF !important; color: #000000 !important}
"""
) as demo:
gr.HTML("""
Trading Analysis & Prediction
Advanced AI-powered analysis for Gold and Bitcoin
Built with anycoder
""")
with gr.Row():
with gr.Column(scale=1):
asset_dropdown = gr.Dropdown(
choices=list(asset_map.keys()),
value="Gold Futures (GC=F)",
label="Select Asset",
info="Choose trading pair"
)
with gr.Column(scale=1):
interval_dropdown = gr.Dropdown(
choices=[
"5m", "15m", "30m", "1h", "1d", "1wk", "1mo", "3mo"
],
value="1d",
label="Time Interval",
info="Select analysis timeframe"
)
with gr.Column(scale=1):
refresh_btn = gr.Button("Refresh Data", variant="primary")
with gr.Tabs():
with gr.TabItem("Chart Analysis"):
chart_plot = gr.Plot(label="Price Chart")
with gr.Row():
pred_plot = gr.Plot(label="Price Predictions")
with gr.Row():
metrics_output = gr.JSON(label="Trading Metrics")
with gr.TabItem("Sentiment Analysis"):
with gr.Row():
sentiment_gauge = gr.Plot(label="Sentiment Score")
news_display = gr.HTML(label="Market News")
with gr.TabItem("Fundamentals"):
with gr.Row():
with gr.Column(scale=1):
fundamentals_gauge = gr.Plot(label="Strength Index")
with gr.Column(scale=1):
fundamentals_table = gr.Dataframe(
headers=["Metric", "Value"],
label="Key Fundamentals",
interactive=False
)
def update_all(interval, asset):
chart, metrics, pred = create_chart_analysis(interval, asset)
sentiment, news = analyze_sentiment(asset)
fund_gauge, fund_table = get_fundamentals(asset)
return chart, metrics, pred, sentiment, news, fund_gauge, fund_table
refresh_btn.click(
fn=update_all,
inputs=[interval_dropdown, asset_dropdown],
outputs=[
chart_plot, metrics_output, pred_plot,
sentiment_gauge, news_display,
fundamentals_gauge, fundamentals_table
]
)
demo.load(
fn=update_all,
inputs=[interval_dropdown, asset_dropdown],
outputs=[
chart_plot, metrics_output, pred_plot,
sentiment_gauge, news_display,
fundamentals_gauge, fundamentals_table
]
)
if __name__ == "__main__":
demo.launch(
server_name="0.0.0.0",
server_port=7860,
share=False,
show_api=True
)