# pattern: Imperative Shell
"""Exercise 2: Read and Inspect — PROC CONTENTS + PROC PRINT (OBS=) + PROC MEANS.

Before you start: read lessons/02_read_and_inspect.md and run demos/demo02.py.

How to run (platform notes: README, "How to run the scripts"):
    python exercises/ex02_read_and_inspect.py

This is a fill-in-the-blank exercise. Replace each ____ with the right
method, attribute, or value. Until every blank is filled, running the file
stops with an AttributeError or NameError that names '____' — that means
"you missed a blank" (lesson 00 shows how to read the traceback). When your
answers are right you'll see:
    All checks passed.

SAS framing:
  - df.schema       ≈ PROC CONTENTS (variable names, types)
  - df.head(10)     ≈ PROC PRINT (OBS=10)
  - df.describe()   ≈ PROC MEANS (min, max, mean, std, etc.)
  - df.null_count() ≈ counts of missing values (like PROC FREQ with MISSING)
"""

from pathlib import Path

import polars as pl

DATA_PATH = Path(__file__).parent.parent / "data" / "dispensing.parquet"


def main() -> None:
    # ------------------------------------------------------------------ #
    # TODO 1: Read data/dispensing.parquet into a DataFrame.
    # Blank: the polars function that reads a Parquet file.
    # ------------------------------------------------------------------ #
    df = pl.____(DATA_PATH)

    # ------------------------------------------------------------------ #
    # TODO 2: Print the shape — a (rows, columns) tuple.
    # Blank: the attribute (no parentheses) holding that tuple.
    # ------------------------------------------------------------------ #
    print(f"Shape: {df.____}")

    # ------------------------------------------------------------------ #
    # TODO 3: Print the schema (column names and dtypes).
    # Blank: the attribute (no parentheses) mapping names to dtypes.
    # ------------------------------------------------------------------ #
    print(f"Schema: {df.____}")

    # ------------------------------------------------------------------ #
    # TODO 4: Print the first 10 rows.
    # Blank: how many rows to show.
    # ------------------------------------------------------------------ #
    print("Head (10):")
    print(df.head(____))

    # ------------------------------------------------------------------ #
    # TODO 5: Print summary statistics.
    # Blank: the method (with parentheses) that summarizes every column.
    # ------------------------------------------------------------------ #
    print("Describe:")
    print(df.____())

    # ------------------------------------------------------------------ #
    # TODO 6: Print the null count for each column.
    # Blank: the method that counts missing values per column.
    # ------------------------------------------------------------------ #
    print("Null counts:")
    print(df.____())

    # --- Assertions ---------------------------------------------------- #
    assert df.shape[0] == 199_613, f"Expected 199613 rows, got {df.shape[0]}"
    assert "RxDate" in df.columns
    assert df.schema["RxDate"] == pl.Date, f"Expected Date, got {df.schema['RxDate']}"
    assert "PatID" in df.columns and df.schema["PatID"] == pl.Int64

    print("All checks passed.")


if __name__ == "__main__":
    main()