# Constructed data: 4 control and 4 treated mice, 250 cells each, 100 genes; genes 001-005 doubled (log2 fold change 1) in
# treated mice, the other 95 unchanged. Python 3.13, NumPy, pandas. Seed 1, the first one tried.
import numpy as np, pandas as pd
from model import study, GENES
rng = np.random.default_rng(1)
rows = []
for mouse, cond, x in study(rng):
    for c in range(x.shape[0]): rows.append((f"{mouse}_c{c + 1:03d}", mouse, cond, *x[c]))
pd.DataFrame(rows, columns=["cell", "mouse", "condition"] + [f"gene_{g + 1:03d}" for g in range(GENES)]).to_csv("cells.csv", index=False)