neon_recording

Modules:

• calib –

  Camera calibration utils

• neon_recording –

  Neon Recording

• timeseries –

Classes:

• AudioTimeseries –

  Audio frames

• BlinkTimeseries –

  Blink event data.

• EventTimeseries –

  Event annotations

• FixationTimeseries –

  Fixation event data.

• IMUTimeseries –

  Motion and orientation data

• NeonRecording –
• Timeseries –

  Base class for all Neon timeseries data.

• VideoTimeseries –

  Video frames from a camera

AudioTimeseries

AudioTimeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: BaseAVTimeseries

Audio frames

Attributes:

• data –

  Data as a numpy array

• pd –

  Data as a pandas DataFrame

• time –

  The moment these data were recorded

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

data property

data

Data as a numpy array

pd property

pd

Data as a pandas DataFrame

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

BlinkTimeseries

BlinkTimeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: Timeseries[BlinkArray, BlinkRecord], BlinkProps

Blink event data.

Attributes:

• data –

  Data as a numpy array

• pd –

  Data as a pandas DataFrame

• start_time –

  Start timestamp of the blink.

• stop_time –

  Stop timestamp of the blink.

• time –

  The moment these data were recorded

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

data property

data

Data as a numpy array

pd property

pd

Data as a pandas DataFrame

start_time class-attribute instance-attribute

start_time = fields[int64]('start_time')

Start timestamp of the blink.

stop_time class-attribute instance-attribute

stop_time = fields[int64]('stop_time')

Stop timestamp of the blink.

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

EventTimeseries

EventTimeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: Timeseries[EventArray, EventRecord], EventProps

Event annotations

Attributes:

• by_name –

  Return a dict of event_name => all ts

• data –

  Data as a numpy array

• event (NDArray[str_]) –

  Event name

• pd –

  Data as a pandas DataFrame

• time –

  The moment these data were recorded

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

by_name cached property

by_name

Return a dict of event_name => all ts

data property

data

Data as a numpy array

event class-attribute instance-attribute

event: NDArray[str_] = fields[str_]('event')

Event name

pd property

pd

Data as a pandas DataFrame

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

FixationTimeseries

FixationTimeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: Timeseries[FixationArray, FixationRecord], FixationProps

Fixation event data.

Attributes:

• data –

  Data as a numpy array

• mean_gaze_point –

  Mean gaze position in pixels. Note that this value may be a poor representation

• pd –

  Data as a pandas DataFrame

• start_gaze_point –

  Start gaze position in pixels.

• start_time –

  Start timestamp of fixation.

• stop_gaze_point –

  Stop gaze position in pixels.

• stop_time –

  Stop timestamp of fixation.

• time –

  The moment these data were recorded

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

data property

data

Data as a numpy array

mean_gaze_point class-attribute instance-attribute

mean_gaze_point = fields[float32](['mean_gaze_x', 'mean_gaze_y'])

Mean gaze position in pixels. Note that this value may be a poor representation of the fixation in the presence of VOR movements.

pd property

pd

Data as a pandas DataFrame

start_gaze_point class-attribute instance-attribute

start_gaze_point = fields[float32](['start_gaze_x', 'start_gaze_y'])

Start gaze position in pixels.

start_time class-attribute instance-attribute

start_time = fields[int64]('start_time')

Start timestamp of fixation.

stop_gaze_point class-attribute instance-attribute

stop_gaze_point = fields[float32](['stop_gaze_x', 'stop_gaze_y'])

Stop gaze position in pixels.

stop_time class-attribute instance-attribute

stop_time = fields[int64]('stop_time')

Stop timestamp of fixation.

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

IMUTimeseries

IMUTimeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: Timeseries[ImuArray, ImuRecord], ImuProps

Motion and orientation data

Attributes:

• acceleration –

  Translational acceleration data.

• angular_velocity –

  Angular velocity data.

• data –

  Data as a numpy array

• pd –

  Data as a pandas DataFrame

• rotation –

  Rotation as a quaternion given as xyzw.

• time –

  The moment these data were recorded

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

acceleration class-attribute instance-attribute

acceleration = fields[float64](['acceleration_x', 'acceleration_y', 'acceleration_z'])

Translational acceleration data.

angular_velocity class-attribute instance-attribute

angular_velocity = fields[float64](['angular_velocity_x', 'angular_velocity_y', 'angular_velocity_z'])

Angular velocity data.

data property

data

Data as a numpy array

pd property

pd

Data as a pandas DataFrame

rotation class-attribute instance-attribute

rotation = fields[float64](['quaternion_x', 'quaternion_y', 'quaternion_z', 'quaternion_w'])

Rotation as a quaternion given as xyzw.

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

NeonRecording

NeonRecording(rec_dir_in: Path | str)

Parameters:

• rec_dir_in (Path | str) –

  Path to the recording directory.

Raises:

• FileNotFoundError –

  If the directory does not exist or is not valid.

• SensorError –

  If accessing a stream that is missing

Methods:

• audio –

  Audio from the scene video

• blinks –

  Blink data

• events –

  Event annotations

• eye –

  Frames of video from the eye cameras

• eyeball –

  Eye state data

• eyelid –

  Eyelid data

• fixations –

  Fixations data

• gaze –

  2D bincular gaze data in scene-camera space

• gaze_monocular_left –

  2D gaze data from the left-eye in scene-camera space

• gaze_monocular_right –

  2D gaze data from the right-eye in scene-camera space

• imu –

  Motion and orientation data

• pupil –

  Pupil diameter data

• saccades –

  Saccades data

• scene –

  Frames of video from the scene camera

• worn –

  Worn (headset on/off) data

Attributes:

• calibration (Calibration | None) –

  Device camera calibration data

• device_serial (str | None) –

  Device serial number

• duration (int) –

  Recording Duration (nanoseconds)

• id (str | None) –

  UUID of the recording

• info (dict) –

  Information loaded from info.json

• start_time (int) –

  Start timestamp (nanoseconds since 1970-01-01)

• stop_time (int) –

  Stop timestamp (nanoseconds since 1970-01-01)

• wearer (dict) –

  Wearer information containing uuid and name

Source code in src/pupil_labs/neon_recording/neon_recording.py

def __init__(self, rec_dir_in: pathlib.Path | str):
    """Initialize the NeonRecording object

    Args:
        rec_dir_in: Path to the recording directory.

    Raises:
        FileNotFoundError: If the directory does not exist or is not valid.
        NeonRecording.SensorError: If accessing a stream that is missing

    """
    self._rec_dir = UPath(rec_dir_in).resolve()
    if not self._rec_dir.exists() or not self._rec_dir.is_dir():
        raise FileNotFoundError(
            f"Directory not found or not valid: {self._rec_dir}"
        )

calibration cached property

calibration: Calibration | None

Device camera calibration data

device_serial property

device_serial: str | None

Device serial number

duration property

duration: int

Recording Duration (nanoseconds)

id property

id: str | None

UUID of the recording

info cached property

info: dict

Information loaded from info.json

start_time property

start_time: int

Start timestamp (nanoseconds since 1970-01-01)

stop_time property

stop_time: int

Stop timestamp (nanoseconds since 1970-01-01)

wearer cached property

wearer: dict

Wearer information containing uuid and name

audio

audio() -> AudioTimeseries

Audio from the scene video

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def audio(self) -> AudioTimeseries:
    """Audio from the scene video"""
    return AudioTimeseries(self)

blinks

blinks() -> BlinkTimeseries

Blink data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def blinks(self) -> BlinkTimeseries:
    """Blink data"""
    return BlinkTimeseries(self)

events

events() -> EventTimeseries

Event annotations

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def events(self) -> EventTimeseries:
    """Event annotations"""
    return EventTimeseries(self)

eye

eye() -> EyeVideoTimeseries

Frames of video from the eye cameras

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def eye(self) -> EyeVideoTimeseries:
    """Frames of video from the eye cameras"""
    return EyeVideoTimeseries(self)

eyeball

eyeball() -> EyeballTimeseries

Eye state data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def eyeball(self) -> EyeballTimeseries:
    """Eye state data"""
    return EyeballTimeseries(self)

eyelid

eyelid() -> EyelidTimeseries

Eyelid data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def eyelid(self) -> EyelidTimeseries:
    """Eyelid data"""
    return EyelidTimeseries(self)

fixations

fixations() -> FixationTimeseries

Fixations data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def fixations(self) -> FixationTimeseries:
    """Fixations data"""
    return FixationTimeseries(self)

gaze

gaze() -> GazeTimeseries

2D bincular gaze data in scene-camera space

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def gaze(self) -> GazeTimeseries:
    """2D bincular gaze data in scene-camera space"""
    return GazeTimeseries(self)

gaze_monocular_left

gaze_monocular_left() -> GazeLeftTimeseries

2D gaze data from the left-eye in scene-camera space

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def gaze_monocular_left(self) -> GazeLeftTimeseries:
    """2D gaze data from the left-eye in scene-camera space"""
    return GazeLeftTimeseries(self)

gaze_monocular_right

gaze_monocular_right() -> GazeRightTimeseries

2D gaze data from the right-eye in scene-camera space

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def gaze_monocular_right(self) -> GazeRightTimeseries:
    """2D gaze data from the right-eye in scene-camera space"""
    return GazeRightTimeseries(self)

imu

imu() -> IMUTimeseries

Motion and orientation data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def imu(self) -> IMUTimeseries:
    """Motion and orientation data"""
    return IMUTimeseries(self)

pupil

pupil() -> PupilTimeseries

Pupil diameter data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def pupil(self) -> PupilTimeseries:
    """Pupil diameter data"""
    return PupilTimeseries(self)

saccades

saccades() -> SaccadeTimeseries

Saccades data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def saccades(self) -> SaccadeTimeseries:
    """Saccades data"""
    return SaccadeTimeseries(self)

scene

scene() -> SceneVideoTimeseries

Frames of video from the scene camera

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def scene(self) -> SceneVideoTimeseries:
    """Frames of video from the scene camera"""
    return SceneVideoTimeseries(self)

worn

worn() -> WornTimeseries

Worn (headset on/off) data

Source code in src/pupil_labs/neon_recording/neon_recording.py

@sensor_loader
def worn(self) -> WornTimeseries:
    """Worn (headset on/off) data"""
    return WornTimeseries(self)

Timeseries

Timeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: TimeseriesProps, Generic[ArrayType, RecordType]

Base class for all Neon timeseries data.

Attributes:

• data –

  Data as a numpy array

• pd –

  Data as a pandas DataFrame

• time –

  The moment these data were recorded

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

data property

data

Data as a numpy array

pd property

pd

Data as a pandas DataFrame

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

VideoTimeseries

VideoTimeseries(recording: NeonRecording, data: ArrayType | None = None)

Bases: BaseAVTimeseries

Video frames from a camera

Attributes:

• data –

  Data as a numpy array

• height (int | None) –

  Height of the video

• pd –

  Data as a pandas DataFrame

• time –

  The moment these data were recorded

• width (int | None) –

  Width of the video

Source code in src/pupil_labs/neon_recording/timeseries/timeseries.py

def __init__(self, recording: "NeonRecording", data: ArrayType | None = None):
    self.recording = recording
    if data is None:
        data = self._load_data_from_recording(recording)
    self._data = data

data property

data

Data as a numpy array

height cached property

height: int | None

Height of the video

pd property

pd

Data as a pandas DataFrame

time class-attribute instance-attribute

time = fields[int64](TIMESTAMP_FIELD_NAME)

The moment these data were recorded

width cached property

width: int | None

Width of the video