examples: migrate to the native data layer (drop ws/coder-websocket/jackson/jsonlite) (#316)
Stacked on #315 (the native Binance REST fetcher). Retarget to `main` once #315 merges. Migrates the runnable examples off third-party data-I/O packages onto Wickra's native data layer (`CandleReader`, `Resampler`, `BinanceFeed`, `fetch_*klines`). ## Third-party packages removed (the zero-dep selling point) - **Node**: `ws` (live feed → BinanceFeed) — dropped from package.json + lockfile - **Go**: `github.com/coder/websocket` — dropped from go.mod / go.sum (`go mod tidy`) - **Java**: `jackson-databind` (live feed + REST fetch) — dropped from pom.xml - **R**: `jsonlite` + `websocket` + `later` — dropped from the README notes Each language's CSV loading now goes through `CandleReader`, manual resampling through `Resampler`, the live feed through `BinanceFeed`, and (Java/R) the REST download through the native fetcher. ## Verification Ran the offline examples per language against the bundled data — backtest and multi_timeframe produce identical output across Python / Node / Go / Java / R (e.g. ATR(14) last 345.1010; 1h→5m resamples to 240 bars, →15m to 80 bars). C# / C / WASM (stdlib-only, no third-party deps to remove) follow in this branch. Note: the streaming `strategy_*` examples have pre-existing candle-indicator runtime bugs (CI only syntax-smokes them); the CSV migration preserves their shape and leaves those bugs for a separate fix.
This commit is contained in:
kingchenc
@@ -1,9 +1,9 @@
|
||||
"""Compute indicators on multiple timeframes from a single 1-minute feed.
|
||||
|
||||
Wickra exposes resampling on the Rust side (in `wickra-data`); from Python we
|
||||
roll up bars manually using NumPy because most users already have their data
|
||||
in a NumPy array and don't need the streaming-resample infrastructure for
|
||||
offline analysis.
|
||||
Loads the 1-minute history with Wickra's native ``CandleReader`` and rolls it up
|
||||
to coarser timeframes with the native ``Resampler`` — no manual CSV parsing and
|
||||
no hand-written bucketing. NumPy is used only to run the batch indicators over
|
||||
each resampled series.
|
||||
|
||||
Run with::
|
||||
|
||||
@@ -13,104 +13,45 @@ Run with::
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import csv
|
||||
from typing import Iterable, List, Tuple
|
||||
from typing import List, Tuple
|
||||
|
||||
import numpy as np
|
||||
|
||||
import wickra as ta
|
||||
|
||||
|
||||
# Columns the OHLCV layout requires; the CSV header must name every one.
|
||||
REQUIRED_COLUMNS = ("timestamp", "open", "high", "low", "close", "volume")
|
||||
# A candle as the data layer yields it: (open, high, low, close, volume, timestamp).
|
||||
Candle = Tuple[float, float, float, float, float, int]
|
||||
|
||||
|
||||
def read_csv(path: str) -> Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
|
||||
"""Read an OHLCV CSV into typed columns.
|
||||
|
||||
Raises:
|
||||
ValueError: if the file has no header, is missing a required column,
|
||||
holds no data rows, or contains a non-numeric value (the message
|
||||
names the offending row).
|
||||
"""
|
||||
ts, o, h, l, c, v = [], [], [], [], [], []
|
||||
with open(path, newline="") as f:
|
||||
reader = csv.DictReader(f)
|
||||
if reader.fieldnames is None:
|
||||
raise ValueError(f"{path}: CSV has no header row")
|
||||
missing = [col for col in REQUIRED_COLUMNS if col not in reader.fieldnames]
|
||||
if missing:
|
||||
raise ValueError(
|
||||
f"{path}: CSV is missing required column(s): "
|
||||
f"{', '.join(missing)}; found: {', '.join(reader.fieldnames)}"
|
||||
)
|
||||
for line_no, row in enumerate(reader, start=2):
|
||||
try:
|
||||
ts.append(int(row["timestamp"]))
|
||||
o.append(float(row["open"]))
|
||||
h.append(float(row["high"]))
|
||||
l.append(float(row["low"]))
|
||||
c.append(float(row["close"]))
|
||||
v.append(float(row["volume"]))
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValueError(
|
||||
f"{path}: row {line_no} has a non-numeric value: {exc}"
|
||||
) from exc
|
||||
if not ts:
|
||||
raise ValueError(f"{path}: CSV has a header but no data rows")
|
||||
return (
|
||||
np.asarray(ts, dtype=np.int64),
|
||||
np.asarray(o, dtype=np.float64),
|
||||
np.asarray(h, dtype=np.float64),
|
||||
np.asarray(l, dtype=np.float64),
|
||||
np.asarray(c, dtype=np.float64),
|
||||
np.asarray(v, dtype=np.float64),
|
||||
)
|
||||
def load(path: str) -> List[Candle]:
|
||||
"""Read an OHLCV CSV into candles with ``CandleReader`` (validates the
|
||||
``timestamp,open,high,low,close,volume`` header; raises ``ValueError`` on a
|
||||
malformed header or row)."""
|
||||
with open(path, encoding="utf-8") as f:
|
||||
return ta.CandleReader(f.read()).read()
|
||||
|
||||
|
||||
def resample(
|
||||
ts: np.ndarray,
|
||||
o: np.ndarray,
|
||||
h: np.ndarray,
|
||||
l: np.ndarray,
|
||||
c: np.ndarray,
|
||||
v: np.ndarray,
|
||||
bucket: int,
|
||||
) -> Tuple[np.ndarray, ...]:
|
||||
"""Aggregate bar-level columns into coarser buckets of size `bucket`.
|
||||
|
||||
Raises:
|
||||
ValueError: if the input series is empty.
|
||||
"""
|
||||
if ts.size == 0:
|
||||
raise ValueError("resample received an empty series")
|
||||
bucket_index = (ts // bucket).astype(np.int64)
|
||||
boundaries = np.diff(bucket_index, prepend=bucket_index[0] - 1) != 0
|
||||
group_ids = np.cumsum(boundaries) - 1
|
||||
n_groups = int(group_ids.max()) + 1
|
||||
|
||||
new_ts = np.empty(n_groups, dtype=np.int64)
|
||||
new_o = np.empty(n_groups, dtype=np.float64)
|
||||
new_h = np.empty(n_groups, dtype=np.float64)
|
||||
new_l = np.empty(n_groups, dtype=np.float64)
|
||||
new_c = np.empty(n_groups, dtype=np.float64)
|
||||
new_v = np.empty(n_groups, dtype=np.float64)
|
||||
|
||||
for g in range(n_groups):
|
||||
mask = group_ids == g
|
||||
new_ts[g] = ts[mask][0]
|
||||
new_o[g] = o[mask][0]
|
||||
new_h[g] = h[mask].max()
|
||||
new_l[g] = l[mask].min()
|
||||
new_c[g] = c[mask][-1]
|
||||
new_v[g] = v[mask].sum()
|
||||
return new_ts, new_o, new_h, new_l, new_c, new_v
|
||||
def resample(candles: List[Candle], bucket_ms: int) -> List[Candle]:
|
||||
"""Aggregate 1-minute candles into ``bucket_ms``-sized candles with the
|
||||
native streaming ``Resampler``."""
|
||||
r = ta.Resampler(bucket_ms)
|
||||
out: List[Candle] = []
|
||||
for o, h, l, c, v, ts in candles:
|
||||
agg = r.update(o, h, l, c, v, ts)
|
||||
if agg is not None:
|
||||
out.append(agg)
|
||||
tail = r.flush()
|
||||
if tail is not None:
|
||||
out.append(tail)
|
||||
return out
|
||||
|
||||
|
||||
def summarize(label: str, close: np.ndarray, high: np.ndarray, low: np.ndarray) -> None:
|
||||
if close.size == 0:
|
||||
def summarize(label: str, candles: List[Candle]) -> None:
|
||||
if not candles:
|
||||
print(f" {label:<10} (empty series — nothing to summarize)")
|
||||
return
|
||||
# Transpose into contiguous 1-D columns (batch() needs C-contiguous arrays).
|
||||
_o, high, low, close, _v, _ts = (np.array(col, dtype=np.float64) for col in zip(*candles))
|
||||
rsi = ta.RSI(14).batch(close)
|
||||
macd = ta.MACD().batch(close)
|
||||
adx = ta.ADX(14).batch(high, low, close)
|
||||
@@ -130,16 +71,15 @@ def main() -> int:
|
||||
p.add_argument("path", help="Path to a 1-minute OHLCV CSV (timestamps in milliseconds)")
|
||||
args = p.parse_args()
|
||||
|
||||
ts, o, h, l, c, v = read_csv(args.path)
|
||||
candles = load(args.path)
|
||||
one_minute = 60_000
|
||||
|
||||
print(f"Multi-timeframe view of {args.path}")
|
||||
summarize("1m", c, h, l)
|
||||
summarize("1m", candles)
|
||||
for label, bucket in [("5m", 5), ("15m", 15), ("1h", 60), ("4h", 240), ("1d", 1440)]:
|
||||
if ts.size < bucket:
|
||||
if len(candles) < bucket:
|
||||
continue
|
||||
rs_ts, rs_o, rs_h, rs_l, rs_c, rs_v = resample(ts, o, h, l, c, v, bucket * one_minute)
|
||||
summarize(label, rs_c, rs_h, rs_l)
|
||||
summarize(label, resample(candles, bucket * one_minute))
|
||||
return 0
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user