Zarr Python Agent Skill

uv pip install "zarr==3.2.1"

uv pip install "zarr[remote]==3.2.1" "s3fs==2026.4.0" "gcsfs==2026.5.0"

import zarr
import numpy as np

# Create a 2D array with chunking and compression
z = zarr.create_array(
    store="data/my_array.zarr",
    shape=(10000, 10000),
    chunks=(1000, 1000),
    dtype="f4"
)

# Write data using NumPy-style indexing
z[:, :] = np.random.random((10000, 10000))

# Read data
data = z[0:100, 0:100]  # Returns NumPy array

# Create empty array
z = zarr.zeros(shape=(10000, 10000), chunks=(1000, 1000), dtype='f4',
               store='data.zarr')

# Create filled arrays
z = zarr.ones((5000, 5000), chunks=(500, 500))
z = zarr.full((1000, 1000), fill_value=42, chunks=(100, 100))

# Create from existing data
data = np.arange(10000).reshape(100, 100)
z = zarr.array(data, chunks=(10, 10), store='data.zarr')

# Create like another array
z2 = zarr.zeros_like(z)  # Matches shape, chunks, dtype of z

# Open array (read/write mode by default)
z = zarr.open_array('data.zarr', mode='r+')

# Read-only mode
z = zarr.open_array('data.zarr', mode='r')

# The open() function auto-detects arrays vs groups
z = zarr.open('data.zarr')  # Returns Array or Group

# Write entire array
z[:] = 42

# Write slices
z[0, :] = np.arange(100)
z[10:20, 50:60] = np.random.random((10, 10))

# Read data (returns NumPy array)
data = z[0:100, 0:100]
row = z[5, :]

# Advanced indexing
z.vindex[[0, 5, 10], [2, 8, 15]]  # Coordinate indexing
z.oindex[0:10, [5, 10, 15]]       # Orthogonal indexing
z.blocks[0, 0]                     # Block/chunk indexing

# Resize array (v3: pass shape as a tuple)
z.resize((15000, 15000))

# Append data along an axis
z.append(np.random.random((1000, 10000)), axis=0)  # Adds rows

# Create root group
root = zarr.group(store='data/hierarchy.zarr')

# Create sub-groups
temperature = root.create_group('temperature')
precipitation = root.create_group('precipitation')

# Create arrays within groups
temp_array = temperature.create_array(
    name='t2m',
    shape=(365, 720, 1440),
    chunks=(1, 720, 1440),
    dtype='f4'
)

precip_array = precipitation.create_array(
    name='prcp',
    shape=(365, 720, 1440),
    chunks=(1, 720, 1440),
    dtype='f4'
)

# Access using paths
array = root['temperature/t2m']

# Visualize hierarchy
print(root.tree())
# Output:
# /
#  ├── temperature
#  │   └── t2m (365, 720, 1440) f4
#  └── precipitation
#      └── prcp (365, 720, 1440) f4

root = zarr.group('data.zarr')
arr = root.create_array('my_data', shape=(1000, 1000), chunks=(100, 100), dtype='f4')

grp = root.require_group('subgroup')
arr2 = grp.require_array('array', shape=(500, 500), chunks=(50, 50), dtype='i4')

# Add attributes to array
z = zarr.zeros((1000, 1000), chunks=(100, 100))
z.attrs['description'] = 'Temperature data in Kelvin'
z.attrs['units'] = 'K'
z.attrs['created'] = '2024-01-15'
z.attrs['processing_version'] = 2.1

# Attributes are stored as JSON
print(z.attrs['units'])  # Output: K

# Add attributes to groups
root = zarr.group('data.zarr')
root.attrs['project'] = 'Climate Analysis'
root.attrs['institution'] = 'Research Institute'

# Attributes persist with the array/group
z2 = zarr.open('data.zarr')
print(z2.attrs['description'])