ludo-technologies/python-best-practices/data-science

# Whole-array operations, not loops / iterrows / apply(axis=1)
df["total"] = df["price"] * df["qty"]
rate = np.select([df["qty"] >= 100, df["qty"] >= 10], [0.2, 0.1], default=0.0)
# Collect, then build once
records = [{"id": item.id, "score": score(item)} for item in items]
results = pd.DataFrame.from_records(records)
combined = pd.concat(frames, ignore_index=True)

# .loc in one step; chained assignment never reaches df under Copy-on-Write
df.loc[df["status"] == "pending", "priority"] = "high"
# Returning form, not inplace=True
df = df.dropna(subset=["email"]).sort_values("created_at")

df = pd.read_csv(
    path,
    dtype={"customer_id": "Int64", "zip_code": "string", "region": "category"},
    parse_dates=["created_at"],
)
SEVERITY = pd.CategoricalDtype(["low", "medium", "high"], ordered=True)
embeddings = np.zeros((n, 768), dtype=np.float32)

import pandera.pandas as pa
from pandera.typing import DataFrame, Series
class OrderSchema(pa.DataFrameModel):
    order_id: Series[int] = pa.Field(unique=True)
    price: Series[float] = pa.Field(ge=0)
    class Config:
        strict = True
def load_orders(path: str) -> DataFrame[OrderSchema]:
    return OrderSchema.validate(pd.read_csv(path))

def run_experiment(seed: int) -> Result:
    rng = np.random.default_rng(seed)
    split_rng, noise_rng = rng.spawn(2)
    ...
def add_noise(x: np.ndarray, rng: np.random.Generator) -> np.ndarray:
    return x + rng.normal(scale=0.1, size=x.shape)

monthly = (
    pd.read_csv("sales.csv", parse_dates=["date"])
    .assign(
        revenue=lambda d: d["price"] * d["qty"],
        month=lambda d: d["date"].dt.to_period("M"),
    )
    .loc[lambda d: d["revenue"] > 0]
    .groupby("month", as_index=False)
    .agg(total_revenue=("revenue", "sum"), orders=("order_id", "count"))
)

import numpy.typing as npt
def to_float32(values: npt.ArrayLike) -> npt.NDArray[np.float32]:
    return np.asarray(values, dtype=np.float32)

np.testing.assert_allclose(result, expected, rtol=1e-6, atol=1e-12)
pd.testing.assert_frame_equal(result_df, expected_df, check_like=True)