Resample 1-minute OHLCV bars to 5-minute OHLCV bars on Databento

resample_ohlcv.py

import pandas as pd
import databento as db


client = db.Historical()

data = client.timeseries.get_range(
    dataset="XNAS.ITCH",
    schema="ohlcv-1m",
    symbols="AAPL",
    start="2021-04-09",
    end="2021-04-10",
)

df = data.to_df()

# Resample to 5-minute bars
resampled_df = df.resample('5min').agg({
    'open': 'first',          # First value in the 5-minute window
    'high': 'max',            # Maximum high in the 5-minute window
    'low': 'min',             # Minimum low in the 5-minute window
    'close': 'last',          # Last value in the 5-minute window
    'volume': 'sum',          # Sum of volume in the 5-minute window
    'symbol': 'last',         # Last symbol value (should be consistent)
    'instrument_id': 'last',  # Last instrument_id value (should be consistent)
    'publisher_id': 'last',   # Last publisher_id value (should be consistent except for aggregated datasets)
    'rtype': 'last'           # Last rtype value (should be consistent)
}).dropna()

print(resampled_df.head(10))