Delete app.py

app.py

@@ -1,329 +0,0 @@
-# app.py
-# BTC/USD Multi-Model AI Radar: 7 ML models + Groq explanation
-# Gradio app for Hugging Face Spaces.
-# Required packages: gradio, pandas, numpy, scikit-learn, xgboost, groq
-
-import os
-import warnings
-import numpy as np
-import pandas as pd
-import gradio as gr
-
-from sklearn.preprocessing import StandardScaler
-from sklearn.pipeline import Pipeline
-from sklearn.impute import SimpleImputer
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.ensemble import (
-    RandomForestClassifier,
-    ExtraTreesClassifier,
-    HistGradientBoostingClassifier,
-    GradientBoostingClassifier,
-    VotingClassifier,
-)
-from sklearn.linear_model import LogisticRegression
-from sklearn.svm import SVC
-from sklearn.metrics import accuracy_score, balanced_accuracy_score, log_loss
-from sklearn.model_selection import TimeSeriesSplit
-from xgboost import XGBClassifier
-
-try:
-    from groq import Groq
-except Exception:
-    Groq = None
-
-warnings.filterwarnings("ignore")
-CSV_PATH = os.environ.get("BTC_CSV_PATH", "BTCUSD_M30.csv")
-HORIZON = 1
-MIN_ROWS = 120
-
-api_key = os.environ.get("GROQ_API_KEY")
-client = Groq(api_key=api_key) if (api_key and Groq) else None
-
-
-def load_local_csv(path=CSV_PATH):
-    """Reads headerless or headed OHLCV CSV/TSV."""
-    if not os.path.exists(path):
-        return None, f"CSV bulunamadı: {path}"
-
-    try:
-        # Try common separators and both header formats.
-        raw = None
-        for sep in ("\t", ",", ";"):
-            for header in (None, 0):
-                try:
-                    candidate = pd.read_csv(path, sep=sep, header=header)
-                    if candidate.shape[1] >= 6:
-                        raw = candidate
-                        break
-                except Exception:
-                    pass
-            if raw is not None:
-                break
-
-        if raw is None or raw.shape[1] < 6:
-            return None, "CSV en az 6 sütun içermeli: date, open, high, low, close, volume."
-
-        raw = raw.iloc[:, :6].copy()
-        raw.columns = ["date", "open", "high", "low", "close", "volume"]
-
-        # If the first row was actually a header, remove it after numeric conversion.
-        for col in ["open", "high", "low", "close", "volume"]:
-            raw[col] = pd.to_numeric(raw[col], errors="coerce")
-
-        raw["date"] = raw["date"].astype(str)
-        raw = raw.dropna(subset=["open", "high", "low", "close", "volume"])
-        raw = raw[(raw["close"] > 0) & (raw["high"] > 0) & (raw["low"] > 0)]
-        raw = raw.sort_values("date").drop_duplicates("date").reset_index(drop=True)
-
-        if len(raw) < MIN_ROWS:
-            return None, f"En az {MIN_ROWS} geçerli mum gerekli; bulunan: {len(raw)}."
-        return raw, None
-    except Exception as exc:
-        return None, f"CSV okuma hatası: {exc}"
-
-
-def rsi(series, period=14):
-    delta = series.diff()
-    gain = delta.clip(lower=0).ewm(alpha=1 / period, adjust=False).mean()
-    loss = (-delta.clip(upper=0)).ewm(alpha=1 / period, adjust=False).mean()
-    rs = gain / loss.replace(0, np.nan)
-    return 100 - (100 / (1 + rs))
-
-
-def make_features(raw):
-    d = raw.copy()
-    close = d["close"]
-    d["ret_1"] = close.pct_change()
-    d["ret_2"] = close.pct_change(2)
-    d["ret_3"] = close.pct_change(3)
-    d["ret_6"] = close.pct_change(6)
-    d["ret_12"] = close.pct_change(12)
-    d["range_pct"] = (d["high"] - d["low"]) / close
-    d["body_pct"] = (d["close"] - d["open"]) / d["open"]
-    d["upper_wick"] = (d["high"] - d[["open", "close"]].max(axis=1)) / close
-    d["lower_wick"] = (d[["open", "close"]].min(axis=1) - d["low"]) / close
-
-    for window in (5, 10, 20, 50):
-        ma = close.rolling(window).mean()
-        d[f"ma_gap_{window}"] = close / ma - 1
-        d[f"volatility_{window}"] = d["ret_1"].rolling(window).std()
-
-    d["rsi_14"] = rsi(close, 14)
-    ema12 = close.ewm(span=12, adjust=False).mean()
-    ema26 = close.ewm(span=26, adjust=False).mean()
-    d["macd_pct"] = (ema12 - ema26) / close
-    d["macd_signal_pct"] = (d["macd_pct"].ewm(span=9, adjust=False).mean())
-    d["volume_change"] = d["volume"].pct_change()
-    d["volume_z20"] = (
-        (d["volume"] - d["volume"].rolling(20).mean()) /
-        d["volume"].rolling(20).std()
-    )
-    d["target"] = (close.shift(-HORIZON) > close).astype(int)
-    # Last row has no known future label; exclude it from training.
-    d = d.iloc[:-HORIZON].replace([np.inf, -np.inf], np.nan)
-    feature_cols = [
-        c for c in d.columns
-        if c not in ["date", "open", "high", "low", "close", "volume", "target"]
-    ]
-    d = d.dropna(subset=feature_cols + ["target"]).reset_index(drop=True)
-    return d, feature_cols
-
-
-def build_models():
-    # Seven independent classifiers. Scaling is included where distance/margin
-    # methods need it; tree models use the original feature scale.
-    return {
-        "XGBoost": XGBClassifier(
-            n_estimators=180, max_depth=3, learning_rate=0.035,
-            subsample=0.85, colsample_bytree=0.85, reg_lambda=2,
-            objective="binary:logistic", eval_metric="logloss",
-            random_state=42, n_jobs=-1
-        ),
-        "KNN": Pipeline([
-            ("imputer", SimpleImputer(strategy="median")),
-            ("scaler", StandardScaler()),
-            ("model", KNeighborsClassifier(n_neighbors=9, weights="distance"))
-        ]),
-        "Random Forest": RandomForestClassifier(
-            n_estimators=220, max_depth=7, min_samples_leaf=4,
-            class_weight="balanced_subsample", random_state=42, n_jobs=-1
-        ),
-        "Extra Trees": ExtraTreesClassifier(
-            n_estimators=220, max_depth=8, min_samples_leaf=4,
-            class_weight="balanced", random_state=43, n_jobs=-1
-        ),
-        "Hist Gradient Boosting": HistGradientBoostingClassifier(
-            max_iter=160, learning_rate=0.05, max_leaf_nodes=15,
-            l2_regularization=1.0, random_state=44
-        ),
-        "Logistic Regression": Pipeline([
-            ("imputer", SimpleImputer(strategy="median")),
-            ("scaler", StandardScaler()),
-            ("model", LogisticRegression(C=0.5, max_iter=1500, class_weight="balanced"))
-        ]),
-        "SVM": Pipeline([
-            ("imputer", SimpleImputer(strategy="median")),
-            ("scaler", StandardScaler()),
-            ("model", SVC(C=1.0, kernel="rbf", probability=True,
-                          class_weight="balanced", random_state=45))
-        ]),
-    }
-
-
-def fit_and_evaluate(data, features):
-    X = data[features].astype(float)
-    y = data["target"].astype(int)
-
-    # Chronological holdout: no random shuffle and no future-to-past leakage.
-    split = max(int(len(data) * 0.8), 50)
-    split = min(split, len(data) - 20)
-    X_train, X_test = X.iloc[:split], X.iloc[split:]
-    y_train, y_test = y.iloc[:split], y.iloc[split:]
-
-    models = build_models()
-    trained = {}
-    results = {}
-    latest_x = X.iloc[[-1]]
-
-    for name, model in models.items():
-        try:
-            model.fit(X_train, y_train)
-            trained[name] = model
-            prob = model.predict_proba(X_test)[:, 1]
-            latest_prob = float(model.predict_proba(latest_x)[0, 1])
-            pred = (prob >= 0.5).astype(int)
-            results[name] = {
-                "up": latest_prob,
-                "accuracy": accuracy_score(y_test, pred) * 100,
-                "balanced": balanced_accuracy_score(y_test, pred) * 100,
-                "logloss": log_loss(y_test, np.clip(prob, 1e-6, 1 - 1e-6)),
-                "test_n": len(y_test),
-            }
-        except Exception as exc:
-            results[name] = {"error": str(exc)}
-
-    valid = {k: v for k, v in results.items() if "up" in v}
-    if len(valid) < 2:
-        raise RuntimeError("Ensemble için en az iki model başarıyla eğitilemedi.")
-
-    # Equal-weight ensemble keeps a weak/overfit holdout score from dominating.
-    ensemble_up = float(np.mean([v["up"] for v in valid.values()]))
-    return trained, results, ensemble_up, len(X_train), len(X_test)
-
-
-def groq_comment(prompt):
-    if not client:
-        return "Groq açıklaması için GROQ_API_KEY gerekli. Model tahminleri yine çalışır."
-    try:
-        response = client.chat.completions.create(
-            model=os.environ.get("GROQ_MODEL", "openai/gpt-oss-120b"),
-            messages=[
-                {"role": "system", "content": "Türkçe konuşan, temkinli bir nicel piyasa analistisin. Kesinlik veya kâr garantisi verme. Verilmeyen veri uydurma."},
-                {"role": "user", "content": prompt}
-            ],
-            temperature=0.25,
-            max_tokens=1100
-        )
-        return response.choices[0].message.content
-    except Exception as exc:
-        return f"Groq API hatası: {exc}"
-
-
-def analyze():
-    raw, error = load_local_csv()
-    if error:
-        return error, {}, pd.DataFrame()
-
-    try:
-        data, features = make_features(raw)
-        if len(data) < MIN_ROWS - 35:
-            return f"Göstergelerden sonra veri yetersiz: {len(data)} satır.", {}, pd.DataFrame()
-
-        trained, results, ensemble_up, train_n, test_n = fit_and_evaluate(data, features)
-        ensemble_down = 1 - ensemble_up
-        direction = "YUKARI 📈" if ensemble_up >= 0.5 else "AŞAĞI 📉"
-        confidence = max(ensemble_up, ensemble_down) * 100
-
-        rows = []
-        valid_probs = []
-        for name, item in results.items():
-            if "up" in item:
-                valid_probs.append(item["up"])
-                rows.append([
-                    name, f"{item['up'] * 100:.1f}%",
-                    f"{item['accuracy']:.1f}%",
-                    f"{item['balanced']:.1f}%",
-                    f"{item['logloss']:.4f}", item["test_n"]
-                ])
-            else:
-                rows.append([name, "Hata", "-", "-", item["error"][:80], "-"])
-
-        last = raw.iloc[-1]
-        model_table = pd.DataFrame(
-            rows,
-            columns=["Model", "Yükseliş olasılığı", "Test doğruluğu",
-                     "Dengeli doğruluk", "Log-loss / hata", "Test mum"]
-        )
-
-        prompt = f"""
-BTC/USD M30 analizini Türkçe hazırla.
-Son kapanış: {float(last['close']):.2f} USD
-Son tarih: {last['date']}
-Ensemble yükseliş olasılığı: %{ensemble_up*100:.1f}
-Ensemble düşüş olasılığı: %{ensemble_down*100:.1f}
-Yön: {direction}; yön güveni (olasılık): %{confidence:.1f}
-Eğitim mum sayısı: {train_n}; kronolojik test mum sayısı: {test_n}.
-Model sonuçları:
-{model_table.to_string(index=False)}
-Başlıklar:
-1. Çoklu model değerlendirmesi ve modeller arası uzlaşma/ayrışma
-2. Teknik görünüm
-3. Yukarı ve aşağı senaryolar
-4. Risk yönetimi ve belirsizlik
-İşlem fiyatı, stop veya hedef seviyesi uydurma; OHLC verisinden hesaplanmayan seviyeleri açıkça belirt.
-Test doğruluğunun gelecekteki başarı garantisi olmadığını belirt. Yatırım tavsiyesi değildir.
-"""
-        ai_text = groq_comment(prompt)
-        header = (
-            f"## BTC/USD Çoklu Model Radarı\n\n"
-            f"**Son kapanış:** ${float(last['close']):,.2f}  |  "
-            f"**Tarih:** {last['date']}\n\n"
-            f"**Ensemble:** {direction}  |  **Yükseliş:** %{ensemble_up*100:.1f}  |  "
-            f"**Düşüş:** %{ensemble_down*100:.1f}\n\n"
-            f"**Aktif model:** {len(valid_probs)}/7  |  "
-            f"**Eğitim:** {train_n} mum  |  **Test:** {test_n} mum\n\n"
-            f"> Olasılık/güven skoru başarı oranı değildir. Test sonuçları geçmiş veriye aittir.\n\n"
-            f"---\n\n{ai_text}"
-        )
-        labels = {
-            name: float(item["up"])
-            for name, item in results.items() if "up" in item
-        }
-        labels["Ensemble"] = ensemble_up
-        return header, labels, model_table
-    except Exception as exc:
-        return f"Analiz hatası: {exc}", {}, pd.DataFrame()
-
-
-with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange", secondary_hue="slate")) as demo:
-    gr.Markdown(
-        f"""# ₿ BTC/USD Multi-Model AI Radar
-**Veri:** `{CSV_PATH}` · **Zaman dilimi:** M30 · **Model sayısı:** 7 ML modeli + Groq AI açıklaması
-
-CSV biçimi: `date, open, high, low, close, volume` (başlıklı/başlıksız CSV veya TSV).
-"""
-    )
-    with gr.Row():
-        run_btn = gr.Button("📊 CSV'yi Oku ve 7 Modeli Eğit", variant="primary", size="lg")
-    prediction = gr.Label(label="Model yükseliş olasılıkları")
-    report = gr.Markdown("Analizi başlatmak için butona basın.")
-    table = gr.Dataframe(label="Model karşılaştırması — kronolojik holdout testi",
-                         interactive=False, wrap=True)
-    run_btn.click(fn=analyze, inputs=[], outputs=[report, prediction, table])
-    gr.Markdown(
-        "**Not:** Modeller aynı CSV üzerinde eğitilir. Test bölümü kronolojik olarak ayrılır; "
-        "bu bir canlı emir/broker bağlantısı değildir. Geçmiş test performansı geleceği garanti etmez."
-    )
-
-if __name__ == "__main__":
-    demo.launch()