tiledbsoma

import tiledbsoma as soma import os import pandas as pd import pyarrow as pa # Define a path for the SOMA object soma_path = "./my_soma_df_quickstart" # Clean up if it exists if os.path.exists(soma_path): soma.delete(soma_path) # Create a SOMA DataFrame with soma.DataFrame.create( soma_path, schema=pa.schema([ pa.field("gene_id", pa.string()), pa.field("feature_val", pa.float32()), ]), index_column_names=["gene_id"], ) as sdf: # Prepare data data = pd.DataFrame({ "gene_id": ["geneA", "geneB", "geneC"], "feature_val": [1.1, 2.2, 3.3] }) # Write data sdf.write(data) print(f"SOMA DataFrame created at: {soma_path}") # Read data back with soma.DataFrame.open(soma_path) as sdf_read: read_df = sdf_read.read().concat().to_pandas() print("\nRead DataFrame:") print(read_df) # Clean up soma.delete(soma_path) print(f"\nCleaned up {soma_path}")