import lamindb as ln

db = ln.DB("laminlabs/cellxgene")  # a database object for queries
df = db.Artifact.to_dataframe()    # a dataframe listing datasets & models

artifact = db.Artifact.get("BnMwC3KZz0BuKftR")  # a metadata object for a dataset
artifact.describe()                             # describe the context of the dataset

local_path = artifact.cache()  # return a local path from a cache
adata = artifact.load()        # load object into memory
accessor = artifact.open()     # return a streaming accessor

alzheimers = db.bionty.Disease.get(name="Alzheimer disease")
df = db.Artifact.filter(diseases=alzheimers).to_dataframe()

import lamindb as ln
# → connected lamindb: account/instance

open("sample.fasta", "w").write(">seq1\nACGT\n")        # create dataset
ln.Artifact("sample.fasta", key="sample.fasta").save()  # save dataset

import lamindb as ln
# → connected lamindb: account/instance

ln.track()                                              # track code execution
open("sample.fasta", "w").write(">seq1\nACGT\n")        # create dataset
ln.Artifact("sample.fasta", key="sample.fasta").save()  # save dataset
ln.finish()                                             # mark run as finished

artifact = ln.Artifact.get(key="sample.fasta")  # get artifact by key
artifact.describe()      # context of the artifact
artifact.view_lineage()  # fine-grained lineage

import lamindb as ln

@ln.flow()
def create_fasta(fasta_file: str = "sample.fasta"):
    open(fasta_file, "w").write(">seq1\nACGT\n")    # create dataset
    ln.Artifact(fasta_file, key=fasta_file).save()  # save dataset

if __name__ == "__main__":
    create_fasta()

my_label = ln.ULabel(name="My label").save()   # a universal label
project = ln.Project(name="My project").save() # a project label
artifact.ulabels.add(my_label)
artifact.projects.add(project)

ln.Artifact.filter(ulabels=my_label, projects=project).to_dataframe()

ln.Artifact.filter(run=run).to_dataframe()              # by creating run
ln.Artifact.filter(transform=transform).to_dataframe()  # by creating transform
ln.Artifact.filter(size__gt=1e6).to_dataframe()         # size greater than 1MB

ln.Artifact.to_dataframe(include=["created_by__name", "storage__root"])  # include fields from related registries

from datetime import date

ln.Feature(name="gc_content", dtype=float).save()
ln.Feature(name="experiment_note", dtype=str).save()
ln.Feature(name="experiment_date", dtype=date, coerce=True).save()  # accept date strings

artifact.features.set_values({
    "gc_content": 0.55,
    "experiment_note": "Looks great",
    "experiment_date": "2025-10-24",
})

ln.Artifact.filter(experiment_date="2025-10-24").to_dataframe()  # query all artifacts annotated with `experiment_date`

ln.Artifact.to_dataframe(include="features")  # include the feature annotations

ln.Record(name="Sample 1", features={"gc_content": 0.5}).save()

# create a flexible record type to track experiments
experiment_type = ln.Record(name="Experiment", is_type=True).save()

# create a record of type `Experiment` for your first experiment
ln.Record(name="Experiment 1", type=experiment_type).save()

# create a feature to link experiments in records, dataframes, etc.
ln.Feature(name="experiment", dtype=experiment_type).save()

# create a sample record that links the sample to `Experiment 1` via the `experiment` feature
ln.Record(name="Sample 2", features={"gc_content": 0.5, "experiment": "Experiment 1"}).save()

experiment_type.to_dataframe()

import lamindb as ln

ln.track()
open("sample.fasta", "w").write(">seq1\nTGCA\n")  # a new sequence
ln.Artifact("sample.fasta", key="sample.fasta", features={"experiment": "Experiment 1"}).save()  # annotate with the new experiment
ln.finish()

artifact = ln.Artifact.get(key="sample.fasta")  # get artifact by key
artifact.versions.to_dataframe()                # see all versions of that artifact

db = ln.DB("laminlabs/lamindata")
artifact = db.Artifact.get(key="example_datasets/mini_immuno/dataset1.h5ad")
artifact.save()

import pandas as pd

df = pd.DataFrame({
    "sequence_str": ["ACGT", "TGCA"],
    "gc_content": [0.55, 0.54],
    "experiment_note": ["Looks great", "Ok"],
    "experiment_date": [date(2025, 10, 24), date(2025, 10, 25)],
})
ln.Artifact.from_dataframe(df, key="my_datasets/sequences.parquet").save()  # no validation

ln.Feature(name="sequence_str", dtype=str).save()  # define a remaining feature
artifact = ln.Artifact.from_dataframe(
    df,
    key="my_datasets/sequences.parquet",
    schema="valid_features"  # validate columns against features
).save()
artifact.describe()

import anndata as ad
import numpy as np
import pandas as pd

adata = ad.AnnData(
    X=np.ones((21, 10)),
    obs=pd.DataFrame({'cell_type_by_model': ['T cell', 'B cell', 'NK cell'] * 7}),
    var=pd.DataFrame(index=[f'ENSG{i:011d}' for i in range(10)])
)
artifact = ln.Artifact.from_anndata(
    adata,
    key="my_datasets/scrna.h5ad",
    schema="ensembl_gene_ids_and_valid_features_in_obs"
).save()
artifact.describe()

import bionty as bt

bt.CellType.import_source()  # import the default ontology
bt.CellType.to_dataframe()   # your extensible cell type ontology in a simple registry

t_cell = bt.CellType.get(name="T cell")
artifact.cell_types.add(t_cell)