Create app.py

app.py

@@ -0,0 +1,600 @@
+import subprocess
+import sys
+
+def install(pkg):
+    subprocess.check_call([sys.executable, "-m", "pip", "install", pkg, "-q"])
+
+packages = [
+    "gradio==4.44.0",
+    "requests",
+    "pandas",
+    "numpy",
+    "plotly",
+    "xgboost",
+    "scikit-learn",
+    "ta",
+]
+
+for pkg in packages:
+    try:
+        install(pkg)
+    except Exception as e:
+        print(f"Warning: could not install {pkg}: {e}")
+
+import gradio as gr
+import requests
+import pandas as pd
+import numpy as np
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+import json
+import warnings
+warnings.filterwarnings("ignore")
+
+try:
+    import ta
+    TA_AVAILABLE = True
+except ImportError:
+    TA_AVAILABLE = False
+
+try:
+    from xgboost import XGBClassifier
+    XGB_AVAILABLE = True
+except ImportError:
+    XGB_AVAILABLE = False
+
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+
+# ─────────────────────────────────────────────
+# DATA FETCHING
+# ─────────────────────────────────────────────
+
+SYMBOLS = [
+    "BTCUSDT", "ETHUSDT", "SOLUSDT", "BNBUSDT", "XRPUSDT",
+    "ADAUSDT", "DOGEUSDT", "AVAXUSDT", "DOTUSDT", "MATICUSDT",
+    "LINKUSDT", "LTCUSDT", "UNIUSDT", "ATOMUSDT", "NEARUSDT",
+]
+
+INTERVALS = ["5m", "15m", "1h", "4h", "1d"]
+
+def fetch_klines(symbol: str, interval: str, limit: int = 300) -> pd.DataFrame:
+    url = "https://api.binance.com/api/v3/klines"
+    params = {"symbol": symbol, "interval": interval, "limit": limit}
+    try:
+        r = requests.get(url, params=params, timeout=10)
+        r.raise_for_status()
+        raw = r.json()
+    except Exception as e:
+        raise RuntimeError(f"Binance API hatası: {e}")
+
+    df = pd.DataFrame(raw, columns=[
+        "open_time","open","high","low","close","volume",
+        "close_time","quote_vol","trades","taker_buy_base",
+        "taker_buy_quote","ignore"
+    ])
+    for col in ["open","high","low","close","volume"]:
+        df[col] = df[col].astype(float)
+    df["open_time"] = pd.to_datetime(df["open_time"], unit="ms")
+    df.set_index("open_time", inplace=True)
+    return df[["open","high","low","close","volume"]]
+
+# ─────────────────────────────────────────────
+# INDICATORS
+# ─────────────────────────────────────────────
+
+def compute_ema(series: pd.Series, period: int) -> pd.Series:
+    return series.ewm(span=period, adjust=False).mean()
+
+def compute_rsi(series: pd.Series, period: int = 14) -> pd.Series:
+    delta = series.diff()
+    gain = delta.clip(lower=0).rolling(period).mean()
+    loss = (-delta.clip(upper=0)).rolling(period).mean()
+    rs = gain / loss.replace(0, np.nan)
+    return 100 - (100 / (1 + rs))
+
+def compute_macd(series: pd.Series):
+    fast = series.ewm(span=12, adjust=False).mean()
+    slow = series.ewm(span=26, adjust=False).mean()
+    macd_line = fast - slow
+    signal_line = macd_line.ewm(span=9, adjust=False).mean()
+    histogram = macd_line - signal_line
+    return macd_line, signal_line, histogram
+
+def compute_atr(df: pd.DataFrame, period: int = 14) -> pd.Series:
+    h_l = df["high"] - df["low"]
+    h_pc = (df["high"] - df["close"].shift()).abs()
+    l_pc = (df["low"] - df["close"].shift()).abs()
+    tr = pd.concat([h_l, h_pc, l_pc], axis=1).max(axis=1)
+    return tr.rolling(period).mean()
+
+def compute_vwap(df: pd.DataFrame) -> pd.Series:
+    tp = (df["high"] + df["low"] + df["close"]) / 3
+    cum_tp_vol = (tp * df["volume"]).cumsum()
+    cum_vol = df["volume"].cumsum()
+    return cum_tp_vol / cum_vol
+
+def add_indicators(df: pd.DataFrame) -> pd.DataFrame:
+    df = df.copy()
+    df["ema20"]  = compute_ema(df["close"], 20)
+    df["ema50"]  = compute_ema(df["close"], 50)
+    df["ema200"] = compute_ema(df["close"], 200)
+    df["rsi"]    = compute_rsi(df["close"], 14)
+    df["macd"], df["macd_signal"], df["macd_hist"] = compute_macd(df["close"])
+    df["atr"]    = compute_atr(df, 14)
+    df["vwap"]   = compute_vwap(df)
+
+    # Volume Profile (approximate: rolling 20-bar avg)
+    df["vol_ma20"] = df["volume"].rolling(20).mean()
+    df["vol_ratio"] = df["volume"] / df["vol_ma20"].replace(0, np.nan)
+
+    return df.dropna()
+
+# ─────────────────────────────────────────────
+# SIGNAL LOGIC
+# ─────────────────────────────────────────────
+
+def generate_signal(df: pd.DataFrame):
+    """Returns (signal, confidence_tech, sl, tp, rr) on last row."""
+    last = df.iloc[-1]
+    prev = df.iloc[-2]
+
+    buy_conditions = [
+        last["ema20"] > last["ema50"],
+        last["ema50"] > last["ema200"],
+        last["rsi"]   > 50,
+        (last["macd"] > last["macd_signal"]) and (prev["macd"] <= prev["macd_signal"]),
+        last["close"] > last["vwap"],
+    ]
+    sell_conditions = [
+        last["ema20"] < last["ema50"],
+        last["ema50"] < last["ema200"],
+        last["rsi"]   < 50,
+        (last["macd"] < last["macd_signal"]) and (prev["macd"] >= prev["macd_signal"]),
+        last["close"] < last["vwap"],
+    ]
+
+    buy_score  = sum(buy_conditions)
+    sell_score = sum(sell_conditions)
+
+    atr = last["atr"]
+    price = last["close"]
+
+    if buy_score >= 3:
+        signal = "AL 📈"
+        sl = round(price - 1.5 * atr, 4)
+        tp = round(price + 3.0 * atr, 4)
+        tech_conf = int(buy_score / 5 * 100)
+    elif sell_score >= 3:
+        signal = "SAT 📉"
+        sl = round(price + 1.5 * atr, 4)
+        tp = round(price - 3.0 * atr, 4)
+        tech_conf = int(sell_score / 5 * 100)
+    else:
+        signal = "BEKLE ⏳"
+        sl = round(price - 1.5 * atr, 4)
+        tp = round(price + 1.5 * atr, 4)
+        tech_conf = 30
+
+    rr = round(abs(tp - price) / abs(sl - price), 2) if abs(sl - price) > 0 else 0
+    return signal, tech_conf, sl, tp, rr
+
+# ─────────────────────────────────────────────
+# AI MODEL
+# ─────────────────────────────────────────────
+
+def build_features(df: pd.DataFrame) -> pd.DataFrame:
+    d = df.copy()
+    d["ret1"]   = d["close"].pct_change(1)
+    d["ret3"]   = d["close"].pct_change(3)
+    d["ret5"]   = d["close"].pct_change(5)
+    d["ema20_50_cross"] = (d["ema20"] - d["ema50"]) / d["close"]
+    d["ema50_200_cross"] = (d["ema50"] - d["ema200"]) / d["close"]
+    d["rsi_norm"] = d["rsi"] / 100
+    d["macd_norm"] = d["macd"] / d["close"]
+    d["macd_hist_norm"] = d["macd_hist"] / d["close"]
+    d["vwap_dist"] = (d["close"] - d["vwap"]) / d["close"]
+    d["atr_norm"] = d["atr"] / d["close"]
+    d["vol_ratio_feat"] = d["vol_ratio"].clip(0, 5)
+    return d.dropna()
+
+FEATURE_COLS = [
+    "ret1","ret3","ret5",
+    "ema20_50_cross","ema50_200_cross",
+    "rsi_norm","macd_norm","macd_hist_norm",
+    "vwap_dist","atr_norm","vol_ratio_feat"
+]
+
+def train_ai(df: pd.DataFrame):
+    feat_df = build_features(df)
+    if len(feat_df) < 60:
+        return None, None, 50
+
+    feat_df["target"] = (feat_df["close"].shift(-3) > feat_df["close"]).astype(int)
+    feat_df = feat_df.dropna()
+
+    X = feat_df[FEATURE_COLS].values
+    y = feat_df["target"].values
+
+    if len(X) < 40:
+        return None, None, 50
+
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)
+
+    split = int(len(X_scaled) * 0.8)
+    X_train, X_test = X_scaled[:split], X_scaled[split:]
+    y_train, y_test = y[:split], y[split:]
+
+    if not XGB_AVAILABLE:
+        return None, scaler, 50
+
+    try:
+        model = XGBClassifier(
+            n_estimators=50,
+            max_depth=3,
+            learning_rate=0.1,
+            use_label_encoder=False,
+            eval_metric="logloss",
+            verbosity=0,
+            n_jobs=1,
+        )
+        model.fit(X_train, y_train)
+
+        last_feat = build_features(df.tail(50)).tail(1)[FEATURE_COLS].values
+        last_scaled = scaler.transform(last_feat)
+        prob = model.predict_proba(last_scaled)[0][1]
+        ai_conf = int(prob * 100)
+        return model, scaler, ai_conf
+    except Exception:
+        return None, None, 50
+
+# ─────────────────────────────────────────────
+# CHART
+# ─────────────────────────────────────────────
+
+def build_chart(df: pd.DataFrame, symbol: str, signal: str, sl: float, tp: float) -> go.Figure:
+    plot_df = df.tail(120).copy()
+
+    fig = make_subplots(
+        rows=3, cols=1,
+        shared_xaxes=True,
+        row_heights=[0.6, 0.2, 0.2],
+        vertical_spacing=0.03,
+        subplot_titles=["", "RSI", "MACD"]
+    )
+
+    # Candlestick
+    fig.add_trace(go.Candlestick(
+        x=plot_df.index,
+        open=plot_df["open"], high=plot_df["high"],
+        low=plot_df["low"], close=plot_df["close"],
+        name="Fiyat",
+        increasing_line_color="#00e676",
+        decreasing_line_color="#ff5252",
+        increasing_fillcolor="#00e676",
+        decreasing_fillcolor="#ff5252",
+    ), row=1, col=1)
+
+    # EMAs
+    for period, color, width in [(20,"#64b5f6",1.5),(50,"#ffb74d",1.5),(200,"#ce93d8",2)]:
+        fig.add_trace(go.Scatter(
+            x=plot_df.index, y=plot_df[f"ema{period}"],
+            name=f"EMA{period}", line=dict(color=color, width=width)
+        ), row=1, col=1)
+
+    # VWAP
+    fig.add_trace(go.Scatter(
+        x=plot_df.index, y=plot_df["vwap"],
+        name="VWAP", line=dict(color="#f48fb1", width=1.5, dash="dot")
+    ), row=1, col=1)
+
+    # Signal arrows on last bar
+    last_idx = plot_df.index[-1]
+    last_close = plot_df["close"].iloc[-1]
+
+    if "AL" in signal:
+        fig.add_annotation(
+            x=last_idx, y=last_close * 0.995,
+            text="▲ AL", showarrow=False,
+            font=dict(color="#00e676", size=16, family="monospace"),
+            row=1, col=1
+        )
+    elif "SAT" in signal:
+        fig.add_annotation(
+            x=last_idx, y=last_close * 1.005,
+            text="▼ SAT", showarrow=False,
+            font=dict(color="#ff5252", size=16, family="monospace"),
+            row=1, col=1
+        )
+
+    # SL / TP horizontal lines
+    fig.add_hline(y=sl, line_dash="dash", line_color="#ff5252",
+                  annotation_text=f"SL: {sl:,.4f}", row=1, col=1)
+    fig.add_hline(y=tp, line_dash="dash", line_color="#00e676",
+                  annotation_text=f"TP: {tp:,.4f}", row=1, col=1)
+
+    # RSI
+    fig.add_trace(go.Scatter(
+        x=plot_df.index, y=plot_df["rsi"],
+        name="RSI", line=dict(color="#80cbc4", width=1.5)
+    ), row=2, col=1)
+    fig.add_hline(y=70, line_dash="dot", line_color="#ff5252", row=2, col=1)
+    fig.add_hline(y=30, line_dash="dot", line_color="#00e676", row=2, col=1)
+    fig.add_hline(y=50, line_dash="dot", line_color="#888888", row=2, col=1)
+
+    # MACD
+    colors = ["#00e676" if v >= 0 else "#ff5252" for v in plot_df["macd_hist"]]
+    fig.add_trace(go.Bar(
+        x=plot_df.index, y=plot_df["macd_hist"],
+        name="MACD Hist", marker_color=colors, opacity=0.7
+    ), row=3, col=1)
+    fig.add_trace(go.Scatter(
+        x=plot_df.index, y=plot_df["macd"],
+        name="MACD", line=dict(color="#64b5f6", width=1.2)
+    ), row=3, col=1)
+    fig.add_trace(go.Scatter(
+        x=plot_df.index, y=plot_df["macd_signal"],
+        name="Sinyal", line=dict(color="#ffb74d", width=1.2)
+    ), row=3, col=1)
+
+    fig.update_layout(
+        title=dict(
+            text=f"<b>{symbol}</b> — Trading Analizi",
+            font=dict(color="#e0e0e0", size=18, family="'Courier New', monospace")
+        ),
+        paper_bgcolor="#0d0d0d",
+        plot_bgcolor="#111111",
+        font=dict(color="#b0b0b0", family="'Courier New', monospace"),
+        xaxis_rangeslider_visible=False,
+        legend=dict(
+            bgcolor="rgba(20,20,20,0.8)",
+            bordercolor="#333",
+            borderwidth=1,
+            font=dict(size=10)
+        ),
+        height=750,
+        margin=dict(l=50, r=50, t=60, b=20),
+    )
+    for i in range(1, 4):
+        fig.update_xaxes(
+            gridcolor="#1e1e1e", zeroline=False,
+            showspikes=True, spikecolor="#444", row=i, col=1
+        )
+        fig.update_yaxes(
+            gridcolor="#1e1e1e", zeroline=False,
+            showspikes=True, spikecolor="#444", row=i, col=1
+        )
+
+    return fig
+
+# ─────────────────────────────────────────────
+# MAIN ANALYSIS
+# ─────────────────────────────────────────────
+
+def analyze(symbol: str, interval: str):
+    try:
+        df_raw = fetch_klines(symbol, interval, limit=300)
+    except Exception as e:
+        return None, f"❌ Veri alınamadı: {e}", "", "", "", "", "", ""
+
+    df = add_indicators(df_raw)
+
+    if len(df) < 50:
+        return None, "❌ Yeterli veri yok.", "", "", "", "", "", ""
+
+    signal, tech_conf, sl, tp, rr = generate_signal(df)
+    _, _, ai_conf = train_ai(df)
+
+    # Combined confidence
+    final_conf = int(0.5 * tech_conf + 0.5 * ai_conf)
+
+    # Direction
+    if "AL" in signal:
+        direction = "🟢 YUKARI"
+        direction_color = "#00e676"
+    elif "SAT" in signal:
+        direction = "🔴 AŞAĞI"
+        direction_color = "#ff5252"
+    else:
+        direction = "🟡 YATAY"
+        direction_color = "#ffb74d"
+
+    price = df["close"].iloc[-1]
+    rsi_val = df["rsi"].iloc[-1]
+    atr_val = df["atr"].iloc[-1]
+
+    fig = build_chart(df, symbol, signal, sl, tp)
+
+    signal_md = f"""
+<div style="
+  background: linear-gradient(135deg, #0d1117 0%, #161b22 100%);
+  border: 1px solid #30363d;
+  border-radius: 12px;
+  padding: 20px;
+  font-family: 'Courier New', monospace;
+  color: #e6edf3;
+">
+  <h2 style="margin:0 0 16px 0; color:#58a6ff; font-size:1.1em; letter-spacing:2px;">
+    ⚡ SİNYAL ANALİZİ — {symbol} / {interval}
+  </h2>
+  <table style="width:100%; border-collapse:collapse;">
+    <tr>
+      <td style="padding:8px 12px; color:#8b949e; width:40%;">📌 Son Sinyal</td>
+      <td style="padding:8px 12px; font-size:1.2em; font-weight:bold;">{signal}</td>
+    </tr>
+    <tr style="background:rgba(255,255,255,0.03);">
+      <td style="padding:8px 12px; color:#8b949e;">📊 Güven Skoru</td>
+      <td style="padding:8px 12px;">
+        <div style="background:#21262d; border-radius:6px; overflow:hidden; height:20px; width:100%;">
+          <div style="background: linear-gradient(90deg, #238636, #56d364); width:{final_conf}%; height:100%; display:flex; align-items:center; justify-content:center; font-size:12px; font-weight:bold;">{final_conf}%</div>
+        </div>
+      </td>
+    </tr>
+    <tr>
+      <td style="padding:8px 12px; color:#8b949e;">🎯 Teknik Skor</td>
+      <td style="padding:8px 12px;">{tech_conf}% &nbsp; | &nbsp; 🤖 AI Skoru: {ai_conf}%</td>
+    </tr>
+    <tr style="background:rgba(255,255,255,0.03);">
+      <td style="padding:8px 12px; color:#8b949e;">📈 Beklenen Yön</td>
+      <td style="padding:8px 12px; color:{direction_color}; font-weight:bold;">{direction}</td>
+    </tr>
+    <tr>
+      <td style="padding:8px 12px; color:#8b949e;">💰 Güncel Fiyat</td>
+      <td style="padding:8px 12px;">${price:,.4f}</td>
+    </tr>
+    <tr style="background:rgba(255,255,255,0.03);">
+      <td style="padding:8px 12px; color:#ff5252;">🛑 Stop Loss</td>
+      <td style="padding:8px 12px; color:#ff5252; font-weight:bold;">${sl:,.4f}</td>
+    </tr>
+    <tr>
+      <td style="padding:8px 12px; color:#00e676;">✅ Take Profit</td>
+      <td style="padding:8px 12px; color:#00e676; font-weight:bold;">${tp:,.4f}</td>
+    </tr>
+    <tr style="background:rgba(255,255,255,0.03);">
+      <td style="padding:8px 12px; color:#8b949e;">⚖️ Risk/Ödül</td>
+      <td style="padding:8px 12px;">{rr}x</td>
+    </tr>
+    <tr>
+      <td style="padding:8px 12px; color:#8b949e;">📉 RSI (14)</td>
+      <td style="padding:8px 12px;">{rsi_val:.1f}</td>
+    </tr>
+    <tr style="background:rgba(255,255,255,0.03);">
+      <td style="padding:8px 12px; color:#8b949e;">📏 ATR (14)</td>
+      <td style="padding:8px 12px;">${atr_val:,.4f}</td>
+    </tr>
+  </table>
+  <p style="margin:16px 0 0 0; font-size:0.75em; color:#484f58; text-align:center;">
+    ⚠️ Bu uygulama eğitim amaçlıdır. Finansal tavsiye değildir. Her zaman kendi araştırmanızı yapın.
+  </p>
+</div>
+"""
+
+    return fig, signal_md
+
+# ─────────────────────────────────────────────
+# GRADIO UI
+# ─────────────────────────────────────────────
+
+CSS = """
+body, .gradio-container {
+    background: #0a0a0f !important;
+    font-family: 'Courier New', monospace !important;
+}
+.gr-button {
+    background: linear-gradient(135deg, #1a1a2e, #16213e) !important;
+    border: 1px solid #0f3460 !important;
+    color: #e0e0e0 !important;
+    font-family: 'Courier New', monospace !important;
+    letter-spacing: 1px !important;
+    transition: all 0.2s !important;
+}
+.gr-button:hover {
+    background: linear-gradient(135deg, #0f3460, #533483) !important;
+    border-color: #533483 !important;
+    box-shadow: 0 0 12px rgba(83,52,131,0.5) !important;
+}
+.gr-button.primary {
+    background: linear-gradient(135deg, #0f3460, #533483) !important;
+    border-color: #7b68ee !important;
+    font-weight: bold !important;
+}
+.gr-dropdown, .gr-textbox, select, input {
+    background: #111 !important;
+    border: 1px solid #333 !important;
+    color: #e0e0e0 !important;
+    font-family: 'Courier New', monospace !important;
+}
+.gradio-container h1, .gradio-container h2, .gradio-container h3 {
+    font-family: 'Courier New', monospace !important;
+}
+"""
+
+HEADER_HTML = """
+<div style="
+  background: linear-gradient(135deg, #0d0d1a 0%, #0a0a0f 50%, #1a0a1a 100%);
+  border: 1px solid #1e1e3f;
+  border-radius: 16px;
+  padding: 28px 32px;
+  text-align: center;
+  font-family: 'Courier New', monospace;
+  margin-bottom: 8px;
+  position: relative;
+  overflow: hidden;
+">
+  <div style="
+    position: absolute; top: 0; left: 0; right: 0; height: 2px;
+    background: linear-gradient(90deg, transparent, #7b68ee, #00e5ff, #7b68ee, transparent);
+  "></div>
+  <h1 style="
+    margin: 0 0 6px 0;
+    font-size: 2em;
+    letter-spacing: 4px;
+    background: linear-gradient(90deg, #7b68ee, #00e5ff, #7b68ee);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    background-clip: text;
+    text-transform: uppercase;
+  ">⚡ CRYPTO SIGNAL PRO</h1>
+  <p style="margin:0; color:#555; letter-spacing:3px; font-size:0.75em; text-transform:uppercase;">
+    AI-Powered Technical Analysis &amp; Trading Signals
+  </p>
+  <div style="
+    display: flex; justify-content: center; gap: 24px; margin-top: 16px;
+    font-size: 0.7em; color: #444; letter-spacing: 2px;
+  ">
+    <span>EMA · RSI · MACD</span>
+    <span style="color:#333;">|</span>
+    <span>VWAP · ATR · Volume</span>
+    <span style="color:#333;">|</span>
+    <span>XGBoost AI</span>
+  </div>
+</div>
+"""
+
+def run_analysis(symbol, interval):
+    fig, signal_md = analyze(symbol, interval)
+    if fig is None:
+        return None, signal_md
+    return fig, signal_md
+
+with gr.Blocks(css=CSS, title="⚡ Crypto Signal Pro") as demo:
+    gr.HTML(HEADER_HTML)
+
+    with gr.Row():
+        sym_dd = gr.Dropdown(
+            choices=SYMBOLS,
+            value="BTCUSDT",
+            label="📊 Parite",
+            interactive=True,
+        )
+        int_dd = gr.Dropdown(
+            choices=INTERVALS,
+            value="1h",
+            label="⏱ Zaman Dilimi",
+            interactive=True,
+        )
+        analyze_btn = gr.Button("🔍 ANALİZ ET", variant="primary", scale=1)
+
+    chart_out = gr.Plot(label="Grafik", elem_id="chart-area")
+    signal_out = gr.HTML(label="Sinyal Özeti")
+
+    analyze_btn.click(
+        fn=run_analysis,
+        inputs=[sym_dd, int_dd],
+        outputs=[chart_out, signal_out],
+    )
+
+    gr.HTML("""
+    <div style="
+      text-align:center; padding:16px; 
+      color:#2a2a2a; font-size:0.7em;
+      font-family:'Courier New',monospace; letter-spacing:1px;
+    ">
+      CRYPTO SIGNAL PRO · Binance API · XGBoost AI · Plotly Charts<br>
+      ⚠️ Yatırım tavsiyesi değildir — DYOR
+    </div>
+    """)
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)