hyperstudy 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

hyperstudy/__init__.py

@@ -19,7 +19,7 @@ from .exceptions import (
     ValidationError,
 )
 
-__version__ = "0.2.0"
+__version__ = "0.2.3"
 
 __all__ = [
     "HyperStudy",

hyperstudy/_dataframe.py

@@ -6,6 +6,51 @@ from typing import Any
 
 import pandas as pd
 
+# Nested dict fields to flatten into top-level columns.
+# Mapping of {field_name: prefix} — sub-keys become ``{prefix}_{sub_key}``.
+FLATTEN_FIELDS: dict[str, str] = {
+    "sparseRatingData": "sparseRatingData",
+    "metadata": "metadata",
+}
+
+
+def _flatten_nested_dicts(
+    data: list[dict[str, Any]],
+    fields: dict[str, str] | None = None,
+) -> list[dict[str, Any]]:
+    """Promote sub-keys of nested dict fields to top-level keys.
+
+    For each *field* present in a record whose value is a ``dict``, every
+    sub-key is copied to ``{prefix}_{sub_key}``.  The original nested dict
+    is preserved for backward compatibility.
+
+    Records where the target field is ``None`` or missing are left
+    untouched — downstream DataFrame construction fills those columns
+    with ``NaN`` / ``null``.
+    """
+    if not data:
+        return data
+
+    fields = fields if fields is not None else FLATTEN_FIELDS
+
+    # Quick check on first record — skip work when no target fields exist.
+    sample = data[0]
+    targets = [f for f in fields if f in sample and isinstance(sample[f], dict)]
+    if not targets:
+        return data
+
+    out: list[dict[str, Any]] = []
+    for record in data:
+        record = dict(record)  # shallow copy to avoid mutating caller's data
+        for field in targets:
+            nested = record.get(field)
+            if isinstance(nested, dict):
+                prefix = fields[field]
+                for sub_key, sub_val in nested.items():
+                    record[f"{prefix}_{sub_key}"] = sub_val
+        out.append(record)
+    return out
+
 
 def _post_process(df: pd.DataFrame) -> pd.DataFrame:
     """Shared post-processing for pandas DataFrames.
@@ -32,6 +77,7 @@ def to_pandas(data: list[dict[str, Any]]) -> pd.DataFrame:
     """Convert API response data to a pandas DataFrame with post-processing."""
     if not data:
         return pd.DataFrame()
+    data = _flatten_nested_dicts(data)
     df = pd.DataFrame(data)
     return _post_process(df)
 
@@ -51,6 +97,7 @@ def to_polars(data: list[dict[str, Any]]):
     if not data:
         return pl.DataFrame()
 
+    data = _flatten_nested_dicts(data)
     df = pl.DataFrame(data)
 
     # Parse timestamps

hyperstudy/_downloads.py

@@ -0,0 +1,76 @@
+"""Helpers for downloading recording files from signed URLs."""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+from typing import Any
+
+import requests
+
+_CHUNK_SIZE = 65536  # 64 KB — good balance for large video files
+_UNSAFE_RE = re.compile(r"[^\w\-]")
+
+
+def get_download_url(recording: dict[str, Any]) -> str | None:
+    """Return the best download URL from a recording dict, or ``None``."""
+    return recording.get("downloadUrl") or recording.get("url") or None
+
+
+def build_filename(recording: dict[str, Any]) -> str:
+    """Build a filesystem-safe filename from recording metadata.
+
+    Pattern: ``{participantName}_{type}_{recordingId}.{ext}``
+    """
+    name = recording.get("participantName") or recording.get("participantId") or "unknown"
+    name = _UNSAFE_RE.sub("_", name)
+
+    meta = recording.get("metadata") or {}
+    rec_type = meta.get("type") or "recording"
+
+    rec_id = recording.get("recordingId") or recording.get("egressId") or "unknown"
+
+    fmt = recording.get("format")
+    if not fmt:
+        fmt = "webm" if rec_type == "audio" else "mp4"
+
+    return f"{name}_{rec_type}_{rec_id}.{fmt}"
+
+
+def download_file(url: str, dest: Path, timeout: int = 300) -> int:
+    """Stream-download *url* to *dest* and return bytes written.
+
+    Verifies ``Content-Length`` (when the server provides it) against bytes
+    actually written. On any error — HTTP, mid-stream disconnect, or length
+    mismatch — the partial file on disk is removed so ``skip_existing``
+    logic won't mistake it for a complete download on retry.
+    """
+    resp = requests.get(url, stream=True, timeout=timeout)
+    resp.raise_for_status()
+
+    expected: int | None
+    if "Content-Length" in resp.headers:
+        try:
+            expected = int(resp.headers["Content-Length"])
+        except (TypeError, ValueError):
+            expected = None
+    else:
+        expected = None
+
+    written = 0
+    # BaseException so Ctrl-C also cleans up, not just exceptions.
+    try:
+        with open(dest, "wb") as fh:
+            for chunk in resp.iter_content(chunk_size=_CHUNK_SIZE):
+                fh.write(chunk)
+                written += len(chunk)
+
+        if expected is not None and written != expected:
+            raise IOError(
+                f"Truncated download: wrote {written} of {expected} bytes for {dest.name}"
+            )
+    except BaseException:
+        dest.unlink(missing_ok=True)
+        raise
+
+    return written

hyperstudy/_http.py

@@ -63,8 +63,14 @@ class HttpTransport:
     # Public helpers
     # ------------------------------------------------------------------
 
-    def get(self, path: str, params: dict[str, Any] | None = None) -> dict:
-        return self._request("GET", path, params=params)
+    def get(
+        self,
+        path: str,
+        params: dict[str, Any] | None = None,
+        *,
+        timeout: int | float | None = None,
+    ) -> dict:
+        return self._request("GET", path, params=params, timeout=timeout)
 
     def post(self, path: str, json: dict[str, Any] | None = None) -> dict:
         return self._request("POST", path, json=json)
@@ -81,7 +87,8 @@ class HttpTransport:
 
     def _request(self, method: str, path: str, **kwargs) -> dict:
         url = f"{self.base_url}/{path.lstrip('/')}"
-        kwargs.setdefault("timeout", self.timeout)
+        if kwargs.get("timeout") is None:
+            kwargs["timeout"] = self.timeout
 
         resp = self._session.request(method, url, **kwargs)
         return self._handle_response(resp)

hyperstudy/_pagination.py

@@ -16,6 +16,7 @@ def fetch_all_pages(
     *,
     page_size: int = 1000,
     progress: bool = True,
+    timeout: int | float | None = None,
 ) -> tuple[list[dict], dict]:
     """Fetch every page of a paginated endpoint.
 
@@ -28,7 +29,7 @@ def fetch_all_pages(
     params.setdefault("offset", 0)
 
     # First request to learn total
-    body = transport.get(path, params=params)
+    body = transport.get(path, params=params, timeout=timeout)
     metadata = body.get("metadata", {})
     pagination = metadata.get("pagination", {})
     total = pagination.get("total", 0)
@@ -43,7 +44,7 @@ def fetch_all_pages(
     while has_more:
         params["offset"] = pagination.get("nextOffset", params["offset"] + page_size)
 
-        body = transport.get(path, params=params)
+        body = transport.get(path, params=params, timeout=timeout)
         metadata = body.get("metadata", {})
         pagination = metadata.get("pagination", {})
 

hyperstudy/client.py

@@ -2,12 +2,18 @@
 
 from __future__ import annotations
 
+import warnings
+from pathlib import Path
 from typing import Any
 
+from tqdm.auto import tqdm
+
 from ._dataframe import to_pandas, to_polars
+from ._downloads import build_filename, download_file, get_download_url
 from ._http import HttpTransport
 from ._pagination import fetch_all_pages
 from ._types import Scope
+from .exceptions import HyperStudyError
 from .experiments import ExperimentMixin
 
 
@@ -466,6 +472,145 @@ class HyperStudy(ExperimentMixin):
             "consent": self.get_consent(participant_id, **common),
         }
 
+    # ------------------------------------------------------------------
+    # Recording downloads
+    # ------------------------------------------------------------------
+
+    def download_recording(
+        self,
+        recording: dict[str, Any],
+        output_dir: str = ".",
+    ) -> Path:
+        """Download a single recording file to disk.
+
+        Args:
+            recording: A recording dict (from ``get_recordings(output="dict")``).
+            output_dir: Directory to save the file.
+
+        Returns:
+            Path to the downloaded file.
+        """
+        url = get_download_url(recording)
+        if not url:
+            raise ValueError("Recording has no downloadUrl or url field")
+
+        dest_dir = Path(output_dir)
+        dest_dir.mkdir(parents=True, exist_ok=True)
+
+        filename = build_filename(recording)
+        dest = dest_dir / filename
+        download_file(url, dest)
+        return dest
+
+    def download_recordings(
+        self,
+        scope_id: str,
+        *,
+        output_dir: str,
+        scope: str = "experiment",
+        deployment_id: str | None = None,
+        room_id: str | None = None,
+        recording_type: str | None = None,
+        progress: bool = True,
+        skip_existing: bool = True,
+    ):
+        """Download recording files to disk.
+
+        Fetches recording metadata, downloads each file from its signed
+        URL, writes a ``recordings_metadata.csv`` sidecar, and returns a
+        DataFrame with a ``local_path`` column.
+
+        Args:
+            scope_id: Experiment, room, or participant ID.
+            output_dir: Directory to save files.
+            scope: ``"experiment"``, ``"room"``, or ``"participant"``.
+            deployment_id: Filter by deployment (experiment scope only).
+            room_id: Filter by room.
+            recording_type: ``"audio"``, ``"video"``, or ``None`` (both).
+            progress: Show progress bar.
+            skip_existing: Skip files already on disk with matching size.
+
+        Returns:
+            pandas DataFrame with recording metadata plus ``local_path``
+            and ``download_status`` columns.
+        """
+        try:
+            # Signing per-recording GCS URLs scales with count; 30s default is too short.
+            recordings = self._fetch_data(
+                "recordings",
+                scope_id,
+                scope=scope,
+                deployment_id=deployment_id,
+                room_id=room_id,
+                output="dict",
+                timeout=300,
+            )
+        except Exception as exc:
+            raise HyperStudyError(
+                f"Failed to list recordings for {scope}={scope_id!r}: {exc}",
+                code=getattr(exc, "code", "LIST_RECORDINGS_FAILED"),
+                status_code=getattr(exc, "status_code", None),
+                details=getattr(exc, "details", None),
+            ) from exc
+
+        if recording_type:
+            recordings = [
+                r for r in recordings
+                if (r.get("metadata") or {}).get("type") == recording_type
+            ]
+
+        dest_dir = Path(output_dir)
+        dest_dir.mkdir(parents=True, exist_ok=True)
+
+        local_paths: list[str | None] = []
+        statuses: list[str] = []
+
+        for rec in tqdm(recordings, desc="Downloading recordings", disable=not progress):
+            filename = build_filename(rec)
+            dest = dest_dir / filename
+
+            url = get_download_url(rec)
+            if not url:
+                local_paths.append(None)
+                statuses.append("failed")
+                warnings.warn(f"Recording {rec.get('recordingId')} has no download URL")
+                continue
+
+            if skip_existing and dest.exists():
+                expected_size = rec.get("fileSize")
+                # Require positive size match; missing size → re-download to
+                # avoid trusting a truncated file from a prior failed run.
+                if expected_size is not None and dest.stat().st_size == expected_size:
+                    local_paths.append(str(dest.resolve()))
+                    statuses.append("skipped")
+                    continue
+
+            try:
+                download_file(url, dest)
+                local_paths.append(str(dest.resolve()))
+                statuses.append("downloaded")
+            except Exception as exc:
+                local_paths.append(None)
+                statuses.append("failed")
+                warnings.warn(
+                    f"Failed to download recording {rec.get('recordingId')}: {exc}"
+                )
+
+        failed_count = sum(1 for s in statuses if s == "failed")
+        if failed_count:
+            warnings.warn(
+                f"{failed_count}/{len(recordings)} recordings failed to download; "
+                "see the 'download_status' column for per-file results."
+            )
+
+        df = to_pandas(recordings)
+        if not df.empty:
+            df["local_path"] = local_paths
+            df["download_status"] = statuses
+            df.to_csv(dest_dir / "recordings_metadata.csv", index=False)
+
+        return df
+
     # ------------------------------------------------------------------
     # Internal helpers
     # ------------------------------------------------------------------
@@ -525,6 +670,7 @@ class HyperStudy(ExperimentMixin):
         offset: int = 0,
         output: str = "pandas",
         progress: bool = True,
+        timeout: int | float | None = None,
         **extra_params,
     ):
         """Generic data-fetching logic shared by all ``get_*`` methods."""
@@ -551,11 +697,15 @@ class HyperStudy(ExperimentMixin):
         # Single page or all pages
         if limit is not None:
             params["limit"] = limit
-            body = self._transport.get(path, params=params)
+            body = self._transport.get(path, params=params, timeout=timeout)
             data = body.get("data", [])
         else:
             data, _ = fetch_all_pages(
-                self._transport, path, params=params, progress=progress
+                self._transport,
+                path,
+                params=params,
+                progress=progress,
+                timeout=timeout,
             )
 
         return self._convert_output(data, output)

{hyperstudy-0.2.1.dist-info → hyperstudy-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hyperstudy
-Version: 0.2.1
+Version: 0.2.3
 Summary: Python SDK for the HyperStudy experiment platform API
 Project-URL: Homepage, https://hyperstudy.io
 Project-URL: Documentation, https://docs.hyperstudy.io/developers/python-sdk

hyperstudy-0.2.3.dist-info/RECORD

@@ -0,0 +1,14 @@
+hyperstudy/__init__.py,sha256=-FMsxfDASUokTGR0-iES4eb-SUEjTuThGMqPIg-Imyw,733
+hyperstudy/_dataframe.py,sha256=8pjuMG8phMv8vwdY7sgZ-aF_6_o0UMgP2XXNp5muZ0s,3620
+hyperstudy/_display.py,sha256=5svr4NFOUJkVif57-xJzrXNOSdA5O9tKesu8UhE_jYo,1896
+hyperstudy/_downloads.py,sha256=MKUjzz9UDfo0V-n22UCdLEH2-tQxBeJMN_JoJ2spIT8,2459
+hyperstudy/_http.py,sha256=_RS0ZaRAcKvFQ2NF9II7PpcojE-lTYT6CslaJNlgfPQ,4569
+hyperstudy/_pagination.py,sha256=2NbvNGW_jFQkYquSTi3SNkAmGgsbKop7J9LkGaZWwWA,1812
+hyperstudy/_types.py,sha256=22JTOlM68eGJ4hg4OH-oT-hmARG2CgbhnERJ5hGxHk8,614
+hyperstudy/client.py,sha256=raAEBNxRsFPr260JWOFlOZNwmFk2SB80L2bsMoojUt0,24376
+hyperstudy/exceptions.py,sha256=z_1Ngiq-RU-1yyDI_JqvQ5CvYm2jQ_lyJ9TUbqUKKv8,1529
+hyperstudy/experiments.py,sha256=BHNf-ctKUA9uzy8Kya11nIyHPrsmOslqC_IJ5t4LxKA,4372
+hyperstudy-0.2.3.dist-info/METADATA,sha256=l1DluLkNI41NjQxrCEUAMeWMfi8jZFhXOUdC9RPb_f0,4833
+hyperstudy-0.2.3.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+hyperstudy-0.2.3.dist-info/licenses/LICENSE,sha256=WJdwRhBIOiiQ6lyK4l95u5IJYuuT-XxzwYRraS31NME,1067
+hyperstudy-0.2.3.dist-info/RECORD,,

hyperstudy-0.2.1.dist-info/RECORD

@@ -1,13 +0,0 @@
-hyperstudy/__init__.py,sha256=aNCOChRV0HeP81B8L6vaXx4GTO0mbsNy_GfDRJT3nlg,733
-hyperstudy/_dataframe.py,sha256=gOHPE6RRoZ_a4Qkdl9XykkGTqH6I7P6pedKoFuAvKek,1966
-hyperstudy/_display.py,sha256=5svr4NFOUJkVif57-xJzrXNOSdA5O9tKesu8UhE_jYo,1896
-hyperstudy/_http.py,sha256=wMVAhgxNcp4-zcrc4lTHU_GHGSqsFiyMFWsrLP5EGFM,4430
-hyperstudy/_pagination.py,sha256=Fdr2nW84r6NtXiYQs5jyJEUOjFvXl-RclpDIi-SPDlM,1738
-hyperstudy/_types.py,sha256=22JTOlM68eGJ4hg4OH-oT-hmARG2CgbhnERJ5hGxHk8,614
-hyperstudy/client.py,sha256=fOmXnr9zQKw-Z1ajxBVPCZUgZhi6DlfAtZy_6OJTFP4,18966
-hyperstudy/exceptions.py,sha256=z_1Ngiq-RU-1yyDI_JqvQ5CvYm2jQ_lyJ9TUbqUKKv8,1529
-hyperstudy/experiments.py,sha256=BHNf-ctKUA9uzy8Kya11nIyHPrsmOslqC_IJ5t4LxKA,4372
-hyperstudy-0.2.1.dist-info/METADATA,sha256=x2hcUowRrTiDU2PDOhWgd4RkTg-VLp8xmosp3VoJyb4,4833
-hyperstudy-0.2.1.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-hyperstudy-0.2.1.dist-info/licenses/LICENSE,sha256=WJdwRhBIOiiQ6lyK4l95u5IJYuuT-XxzwYRraS31NME,1067
-hyperstudy-0.2.1.dist-info/RECORD,,