Delete app.py

app.py

@@ -1,165 +0,0 @@
-################### PACKAGES
-import ccxt
-import pandas as pd
-import numpy as np
-from datetime import datetime, timedelta
-import time
-import requests
-from pytrends.request import TrendReq
-import joblib
-import gradio as gr
-from sklearn.preprocessing import StandardScaler
-
-
-################### MODEL LOADING
-# Load XGBoost and NGBoost
-xgb_artifact = joblib.load("xgb_volatility_model.joblib")
-xgb_model = xgb_artifact["model"]
-xgb_features = xgb_artifact["feature_names"]
-
-ngb_artifact = joblib.load("ngb_volatility_model.joblib")
-ngb_model = ngb_artifact["model"]
-ngb_features = ngb_artifact["feature_names"]
-
-forecast_ngb_artifact = joblib.load("Forecast_ngb_volatility_model.joblib")
-forecast_ngb_model = forecast_ngb_artifact["model"]
-forecast_ngb_features = forecast_ngb_artifact["feature_names"]
-
-# Load KMeans + scaler
-kmeans_artifact = joblib.load("kmeans_model.joblib")
-kmeans_model = kmeans_artifact["model"]
-cluster_scaler = kmeans_artifact["scaler"]
-cluster_features_names = kmeans_artifact["feature_names"]
-
-
-################### FEATURE GATHERING
-def fetch_ohlcv_last_6_days(symbol="BTC/USDT", date="2026-01-18", timeframe="1d"):
-    binance = ccxt.binance()
-    user_date = pd.to_datetime(date)
-    start_date = user_date - timedelta(days=5)  # 5 days before
-    since = binance.parse8601(start_date.strftime("%Y-%m-%dT00:00:00Z"))
-    data = binance.fetch_ohlcv(symbol, timeframe=timeframe, since=since, limit=6)
-    df = pd.DataFrame(data, columns=["timestamp","open","high","low","close","volume"])
-    df["timestamp"] = pd.to_datetime(df["timestamp"], unit="ms")
-    df.set_index("timestamp", inplace=True)
-    return df
-
-def fetch_fg_last_6_days(df):
-    url = "https://api.alternative.me/fng/?limit=0&format=json"
-    response = requests.get(url)
-    fg_df = pd.DataFrame(response.json()["data"])
-    fg_df["timestamp"] = pd.to_datetime(fg_df["timestamp"], unit="s")
-    fg_df.set_index("timestamp", inplace=True)
-    fg_df = fg_df[["value"]].astype(float)
-    fg_df.rename(columns={"value":"fg_index"}, inplace=True)
-    fg_df = fg_df.reindex(df.index, method="ffill")
-    df["fg_index"] = fg_df["fg_index"].values
-    return df
-
-def fetch_google_trend_for_date(keyword="Bitcoin", target_date="2024-01-15", window=7):
-    pytrends = TrendReq(hl="en-US", tz=360)
-    target_date = pd.to_datetime(target_date)
-    start_date = (target_date - timedelta(days=window)).strftime("%Y-%m-%d")
-    end_date = target_date.strftime("%Y-%m-%d")
-    timeframe = f"{start_date} {end_date}"
-    try:
-        pytrends.build_payload([keyword], timeframe=timeframe)
-        df = pytrends.interest_over_time()
-        if df.empty:
-            return 0
-        df = df.rename(columns={keyword: "trend"})
-        df = df.drop(columns=["isPartial"], errors="ignore")
-        df.index = pd.to_datetime(df.index)
-        if target_date in df.index:
-            return df.loc[target_date, "trend"]
-        else:
-            return 0
-    except:
-        return 0
-
-
-################### FEATURE ENGINEERING
-def engineer_features(df):
-    df["log_return"] = np.log(df["close"] / df["close"].shift(1))
-    df["hl_spread"] = df["high"] - df["low"]
-    df["co_spread"] = df["close"] - df["open"]
-    df["momentum_3"] = df["close"] - df["close"].shift(3)
-    df["vol_change"] = df["volume"] - df["volume"].shift(1)
-    df["rolling_std_5"] = df["log_return"].rolling(5).std()
-    # Fill NaNs for first few rows
-    df = df.fillna(0)
-    return df
-
-################### ASSIGN CLUSTER
-def assign_cluster(df):
-    cluster_features = df[cluster_features_names]
-    scaled = cluster_scaler.transform(cluster_features)
-    df["cluster"] = kmeans_model.predict(scaled)
-    return df
-
-
-################### PREDICTION FUNCTION
-def predict_volatility(date):
-    # Fetch raw data
-    df = fetch_ohlcv_last_6_days(date=date)
-    df = fetch_fg_last_6_days(df)
-    trend_value = fetch_google_trend_for_date("Bitcoin", date)
-    df["trend"] = trend_value
-    df["trend"] = df["trend"].ffill().fillna(0)
-
-    # Feature engineering
-    df = engineer_features(df)
-
-    # Clustering
-    df = assign_cluster(df)
-
-    # ---------------- NOWCASTING ----------------
-    X_xgb = df.iloc[-1:][xgb_features]
-    X_ngb = df.iloc[-1:][ngb_features]
-
-    point = xgb_model.predict(X_xgb)[0]
-    dist = ngb_model.pred_dist(X_ngb)
-    low, high = dist.ppf([0.025, 0.975])[0]
-
-    # ---------------- FORECASTING (t+1) ----------------
-    X_ngb_fore = df.iloc[-1:][forecast_ngb_features]
-
-    for_point = forecast_ngb_model.predict(X_ngb_fore)[0]
-    for_dist = forecast_ngb_model.pred_dist(X_ngb_fore)
-    for_low, for_high = for_dist.ppf([0.025, 0.975])[0]
-
-    return point, low, high, for_point, for_low, for_high
-
-
-
-################### GRADIO INTERFACE
-def gradio_predict(date):
-    try:
-        pd.to_datetime(date)
-    except:
-        return "❌ Invalid date format. Please use YYYY-MM-DD."
-
-    try:
-        point, low, high, for_point, for_low, for_high = predict_volatility(date)
-
-        return (
-            f"NOWCAST (t)\n"
-            f"Volatility: {point:.4f}\n"
-            f"95% CI: [{low:.4f}, {high:.4f}]\n\n"
-            f"FORECAST (t+1)\n"
-            f"Volatility: {for_point:.4f}\n"
-            f"95% CI: [{for_low:.4f}, {for_high:.4f}]"
-        )
-    except Exception as e:
-        return f"⚠️ Error while computing prediction:\n{str(e)}"
-
-demo = gr.Interface(
-    fn=gradio_predict,
-    inputs=gr.Textbox(label="Date (YYYY-MM-DD)"),
-    outputs=gr.Textbox(label="Prediction"),
-    title="Crypto Volatility Predictor",
-    description="Enter a date to get predicted volatility and 95% confidence interval."
-)
-
-if __name__ == "__main__":
-    demo.launch()