anndata_quickstart_init_metadata_and_slicing.py

1import numpy as np
2import pandas as pd
3import anndata as ad
4
5# 1. Initialize data
6counts = np.random.poisson(1, size=(100, 2000))
7obs = pd.DataFrame(index=[f"cell_{i}" for i in range(100)])
8var = pd.DataFrame(index=[f"gene_{i}" for i in range(2000)])
9
10# 2. Create the AnnData object
11adata = ad.AnnData(counts, obs=obs, var=var)
12
13# 3. Add metadata
14adata.obs["batch"] = np.random.choice(["a", "b"], size=100)
15adata.var["highly_variable"] = np.random.choice([True, False], size=2000)
16
17# 4. Slicing and view
18# Subset to the first 5 cells and genes marked as highly variable
19subset = adata[:5, adata.var["highly_variable"]]
20
21print(adata)
22print(subset)