/ohlcv-processing

name: ohlcv-processing
description: Market data preparation including OHLCV resampling, gap handling, anomaly detection, normalization, and multi-source merging

OHLCV Processing — Market Data Preparation

Clean, consistent OHLCV data is the foundation of every trading analysis. Garbage in, garbage out — a single anomalous candle can trigger false signals, corrupt indicator calculations, and produce misleading backtest results. This skill covers the full data preparation pipeline: validation, cleaning, resampling, normalization, and multi-source merging.

**Why this matters**: Crypto OHLCV data is messier than traditional markets. 24/7 trading means no official close, DEX aggregators disagree on prices, low-liquidity tokens produce impossible candles, and API outages create gaps. Every analysis workflow should start with this pipeline.

Quick Start

1. Install Dependencies

uv pip install pandas numpy httpx

2. Standard OHLCV DataFrame Format

All processing functions expect this canonical format:

import pandas as pd

# Canonical OHLCV DataFrame
# - DatetimeIndex in UTC
# - Columns: open, high, low, close, volume (lowercase)
# - Sorted ascending by timestamp
# - No duplicate timestamps

df = pd.DataFrame({
    "open": [1.10, 1.12, 1.11],
    "high": [1.15, 1.14, 1.13],
    "low": [1.08, 1.10, 1.09],
    "close": [1.12, 1.11, 1.12],
    "volume": [50000, 48000, 52000],
}, index=pd.to_datetime([
    "2025-01-01 00:00:00",
    "2025-01-01 00:01:00",
    "2025-01-01 00:02:00",
], utc=True))
df.index.name = "timestamp"

3. Full Processing Pipeline

import pandas as pd
import numpy as np

def process_ohlcv(df: pd.DataFrame) -> pd.DataFrame:
    """Run complete OHLCV processing pipeline."""
    df = standardize_columns(df)
    df = validate_ohlcv(df)
    df = handle_gaps(df, method="ffill")
    df = detect_and_flag_anomalies(df)
    return df

Data Validation

Column Checks

REQUIRED_COLUMNS = {"open", "high", "low", "close", "volume"}

def standardize_columns(df: pd.DataFrame) -> pd.DataFrame:
    """Normalize column names to lowercase standard."""
    df.columns = df.columns.str.lower().str.strip()
    # Common renames
    rename_map = {"vol": "volume", "v": "volume", "o": "open",
                  "h": "high", "l": "low", "c": "close"}
    df = df.rename(columns=rename_map)
    missing = REQUIRED_COLUMNS - set(df.columns)
    if missing:
        raise ValueError(f"Missing columns: {missing}")
    return df[["open", "high", "low", "close", "volume"]]

Structural Validation

def validate_ohlcv(df: pd.DataFrame) -> pd.DataFrame:
    """Validate OHLCV structural integrity."""
    # Ensure DatetimeIndex in UTC
    if not isinstance(df.index, pd.DatetimeIndex):
        df.index = pd.to_datetime(df.index, utc=True)
    if df.index.tz is None:
        df.index = df.index.tz_localize("UTC")

    # Sort and deduplicate
    df = df.sort_index()
    dupes = df.index.duplicated(keep="last")
    if dupes.any():
        print(f"Warning: Removed {dupes.sum()} duplicate timestamps")
        df = df[~dupes]

    # Type enforcement
    for col in ["open", "high", "low", "close", "volume"]:
        df[col] = pd.to_numeric(df[col], errors="coerce")

    return df

Impossible Candle Detection

def find_impossible_candles(df: pd.DataFrame) -> pd.DataFrame:
    """Find candles that violate OHLC constraints."""
    issues = pd.DataFrame(index=df.index)
    issues["high_lt_low"] = df["high"] < df["low"]
    issues["high_lt_open"] = df["high"] < df["open"]
    issues["high_lt_close"] = df["high"] < df["close"]
    issues["low_gt_open"] = df["low"] > df["open"]
    issues["low_gt_close"] = df["low"] > df["close"]
    issues["negative_price"] = (df[["open", "high", "low", "close"]] < 0).any(axis=1)
    issues["negative_volume"] = df["volume"] < 0
    issues["any_issue"] = issues.any(axis=1)
    return issues[issues["any_issue"]]

Gap Handling

Crypto trades 24/7, but gaps still occur from API outages, low liquidity, or aggregator downtime.

Detect Gaps

def detect_gaps(df: pd.DataFrame, expected_freq: str = "1min") -> pd.Series:
    """Find missing timestamps based on expected frequency."""
    full_index = pd.date_range(
        start=df.index.min(), end=df.index.max(), freq=expected_freq, tz="UTC"
    )
    missing = full_index.difference(df.index)
    return missing

Fill Gaps

def handle_gaps(
    df: pd.DataFrame,
    freq: str = "1min",
    method: str = "ffill",
    max_gap: int = 5,
) -> pd.DataFrame:
    """Fill gaps in OHLCV data.

    Args:
        df: OHLCV DataFrame with DatetimeIndex.
        freq: Expected bar frequency.
        method: 'ffill' (forward fill) or 'interpolate'.
        max_gap: Maximum consecutive bars to fill. Larger gaps are left as NaN.
    """
    full_index = pd.date_range(
        start=df.index.min(), end=df.index.max(), freq=freq, tz="UTC"
    )
    df = df.reindex(full_index)
    df.index.name = "timestamp"

    # Mark which bars were filled
    df["is_filled"] = df["close"].isna()

    if method == "ffill":
        # Forward fill OHLC (flat candle), zero volume
        df[["open", "high", "low", "close"]] = (
            df[["open", "high", "low", "close"]].ffill(limit=max_gap)
        )
        df["volume"] = df["volume"].fillna(0)
    elif method == "interpolate":
        df[["open", "high", "low", "close"]] = (
            df[["open", "high", "low", "close"]].interpolate(
                method="time", limit=max_gap
            )
        )
        df["volume"] = df["volume"].fillna(0)

    return df

Anomaly Detection

See `references/data_quality.md` for the complete anomaly taxonomy.

Price Spike Detection

def detect_price_spikes(
    df: pd.DataFrame, window: int = 20, threshold: float = 3.0
) -> pd.Series:
    """Flag bars where return exceeds threshold * rolling std."""
    returns = df["close"]