Sync from GitHub

analytics/metrics.py

@@ -0,0 +1,26 @@
+import numpy as np
+import pandas as pd
+
+def compute_metrics(returns, sofr):
+
+    sofr_daily = sofr.reindex(returns.index).fillna(method="ffill")["sofr"] / 252
+    excess = returns - sofr_daily
+
+    sharpe = np.sqrt(252) * excess.mean() / excess.std()
+
+    equity = (1 + returns).cumprod()
+    cagr = equity.iloc[-1] ** (252 / len(equity)) - 1
+
+    vol = returns.std() * np.sqrt(252)
+
+    rolling_max = equity.cummax()
+    drawdown = equity / rolling_max - 1
+    max_dd = drawdown.min()
+
+    return {
+        "sharpe": sharpe,
+        "cagr": cagr,
+        "vol": vol,
+        "max_dd": max_dd
+    }
+

app.py

@@ -0,0 +1,70 @@
+import streamlit as st
+import os
+
+from data.hf_store import load_dataset
+from data.updater import update_market_data
+from data.fred import get_sofr_series
+from engine.backtest import run_backtest
+from analytics.metrics import compute_metrics
+
+st.set_page_config(layout="wide")
+
+st.title("📊 P2 ETF Trend Suite")
+st.markdown("Institutional ETF Trend + Volatility Targeting Engine")
+
+# ========================
+# Sidebar Controls
+# ========================
+
+st.sidebar.header("Controls")
+
+initial_capital = st.sidebar.number_input("Initial Capital", value=100000, step=10000)
+vol_target = st.sidebar.slider("Target Annual Volatility", 0.05, 0.30, 0.15)
+lookback = st.sidebar.slider("Momentum Lookback (days)", 50, 300, 200)
+
+refresh = st.sidebar.button("🔄 Refresh Market Data")
+
+# ========================
+# Data Load
+# ========================
+
+with st.spinner("Loading ETF dataset..."):
+    df = load_dataset()
+
+if refresh:
+    with st.spinner("Updating market data from yfinance..."):
+        df = update_market_data(df)
+    st.success("Dataset updated successfully.")
+
+# ========================
+# Backtest
+# ========================
+
+with st.spinner("Pulling SOFR from FRED..."):
+    sofr = get_sofr_series()
+
+with st.spinner("Running backtest..."):
+    results = run_backtest(
+        df=df,
+        initial_capital=initial_capital,
+        vol_target=vol_target,
+        lookback=lookback,
+    )
+
+metrics = compute_metrics(results["returns"], sofr)
+
+# ========================
+# Layout
+# ========================
+
+col1, col2, col3, col4 = st.columns(4)
+
+col1.metric("CAGR", f"{metrics['cagr']:.2%}")
+col2.metric("Sharpe (SOFR)", f"{metrics['sharpe']:.2f}")
+col3.metric("Max Drawdown", f"{metrics['max_dd']:.2%}")
+col4.metric("Volatility", f"{metrics['vol']:.2%}")
+
+st.line_chart(results["equity_curve"])
+
+st.subheader("Current Allocation")
+st.dataframe(results["latest_allocation"])

data/fred.py

@@ -0,0 +1,11 @@
+import os
+import pandas as pd
+from fredapi import Fred
+
+def get_sofr_series():
+    fred = Fred(api_key=os.getenv("FRED_API_KEY"))
+    sofr = fred.get_series("SOFR")
+    sofr = sofr.to_frame("sofr")
+    sofr.index = pd.to_datetime(sofr.index)
+    sofr["sofr"] = sofr["sofr"] / 100
+    return sofr

data/hf_store.py

@@ -0,0 +1,17 @@
+import pandas as pd
+from datasets import load_dataset as hf_load_dataset
+
+DATASET_PATH = "P2SAMAPA/etf_trend_data"
+
+def load_dataset():
+    dataset = hf_load_dataset(DATASET_PATH)
+
+    # Handle split safely
+    if isinstance(dataset, dict) and "train" in dataset:
+        dataset = dataset["train"]
+
+    df = dataset.to_pandas()
+    df["date"] = pd.to_datetime(df["date"])
+    df = df.sort_values(["ticker", "date"])
+
+    return df

data/updater.py

@@ -0,0 +1,55 @@
+import os
+import pandas as pd
+import yfinance as yf
+from huggingface_hub import HfApi
+
+DATASET_PATH = "P2SAMAPA/etf_trend_data"
+
+def update_market_data(df):
+
+    tickers = df["ticker"].unique()
+    all_new = []
+
+    for ticker in tickers:
+        last_date = df[df["ticker"] == ticker]["date"].max()
+        start_date = (last_date + pd.Timedelta(days=1)).strftime("%Y-%m-%d")
+
+        new_data = yf.download(ticker, start=start_date, progress=False)
+
+        if new_data.empty:
+            continue
+
+        new_data.reset_index(inplace=True)
+        new_data["ticker"] = ticker
+        new_data.rename(columns={
+            "Date": "date",
+            "Open": "open",
+            "High": "high",
+            "Low": "low",
+            "Close": "close",
+            "Adj Close": "adjusted_close",
+            "Volume": "volume"
+        }, inplace=True)
+
+        all_new.append(new_data)
+
+    if not all_new:
+        return df
+
+    new_df = pd.concat(all_new)
+    df = pd.concat([df, new_df])
+    df.drop_duplicates(subset=["date", "ticker"], inplace=True)
+    df.sort_values(["ticker", "date"], inplace=True)
+
+    df.to_parquet("updated.parquet")
+
+    api = HfApi()
+    api.upload_file(
+        path_or_fileobj="updated.parquet",
+        path_in_repo="data/train-00000-of-00001.parquet",
+        repo_id=DATASET_PATH,
+        repo_type="dataset",
+        token=os.getenv("HF_TOKEN")
+    )
+
+    return df

engine/backtest.py

@@ -0,0 +1,46 @@
+import pandas as pd
+import numpy as np
+
+def run_backtest(df, initial_capital, vol_target, lookback):
+
+    df = df.sort_values(["ticker", "date"])
+    prices = df.pivot(index="date", columns="ticker", values="adjusted_close")
+    returns = prices.pct_change().dropna()
+
+    momentum = prices.pct_change(lookback)
+    signal = momentum.rank(axis=1, ascending=False)
+    top = signal <= 3
+
+    weights = top.div(top.sum(axis=1), axis=0)
+
+    rolling_cov = returns.rolling(60).cov()
+    vol = []
+
+    for date in weights.index:
+        if date not in rolling_cov.index:
+            vol.append(0)
+            continue
+
+        w = weights.loc[date].values
+        cov = rolling_cov.loc[date].values.reshape(len(w), len(w))
+        portfolio_vol = np.sqrt(w @ cov @ w) * np.sqrt(252)
+
+        scale = vol_target / portfolio_vol if portfolio_vol > 0 else 0
+        weights.loc[date] = w * scale
+        vol.append(portfolio_vol)
+
+    strategy_returns = (weights.shift(1) * returns).sum(axis=1)
+    equity_curve = (1 + strategy_returns).cumprod() * initial_capital
+
+    latest_weights = weights.iloc[-1]
+    allocation = pd.DataFrame({
+        "Ticker": latest_weights.index,
+        "Weight": latest_weights.values
+    }).sort_values("Weight", ascending=False)
+
+    return {
+        "returns": strategy_returns,
+        "equity_curve": equity_curve,
+        "latest_allocation": allocation
+    }
+

hf_space/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

hf_space/Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.13.5-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+COPY src/ ./src/
+
+RUN pip3 install -r requirements.txt
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

hf_space/README.md

@@ -0,0 +1,19 @@
+---
+title: P2 ETF TREND SUITE
+emoji: 🚀
+colorFrom: red
+colorTo: red
+sdk: docker
+app_port: 8501
+tags:
+- streamlit
+pinned: false
+short_description: Streamlit template space
+---
+
+# Welcome to Streamlit!
+
+Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+
+If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
+forums](https://discuss.streamlit.io).

hf_space/requirements.txt

@@ -0,0 +1,3 @@
+altair
+pandas
+streamlit

hf_space/src/streamlit_app.py

@@ -0,0 +1,40 @@
+import altair as alt
+import numpy as np
+import pandas as pd
+import streamlit as st
+
+"""
+# Welcome to Streamlit!
+
+Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
+If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
+forums](https://discuss.streamlit.io).
+
+In the meantime, below is an example of what you can do with just a few lines of code:
+"""
+
+num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
+num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+
+indices = np.linspace(0, 1, num_points)
+theta = 2 * np.pi * num_turns * indices
+radius = indices
+
+x = radius * np.cos(theta)
+y = radius * np.sin(theta)
+
+df = pd.DataFrame({
+    "x": x,
+    "y": y,
+    "idx": indices,
+    "rand": np.random.randn(num_points),
+})
+
+st.altair_chart(alt.Chart(df, height=700, width=700)
+    .mark_point(filled=True)
+    .encode(
+        x=alt.X("x", axis=None),
+        y=alt.Y("y", axis=None),
+        color=alt.Color("idx", legend=None, scale=alt.Scale()),
+        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
+    ))

requirements.txt

@@ -1,3 +1,8 @@
-altair
+streamlit
 pandas
-streamlit
+numpy
+yfinance
+datasets
+huggingface_hub
+fredapi
+scipy