import pandas as pd
from pandas.api.types import CategoricalDtype

df = pd.DataFrame(
    {
        "ticket": [101, 102, 103, 104, 105, 106],
        "team": ["api", "frontend", "api", "ops", "frontend", "api"],
        "priority": ["normal", "urgent", "low", "normal", "low", "urgent"],
    }
)

print(f"pandas {pd.__version__}")
print()

print("source dtypes")
print(df.dtypes)
print()

df["team"] = df["team"].astype("category")

print("team dtype")
print(df["team"].dtype)
print()

print("team categories")
print(df["team"].cat.categories)
print()

label_sample = pd.Series(["api", "frontend", "ops", "api"] * 1000, dtype="str")
memory = pd.Series(
    {
        "str_bytes": label_sample.memory_usage(deep=True),
        "category_bytes": label_sample.astype("category").memory_usage(deep=True),
    }
)

print("memory check")
print(memory)
print()

priority_dtype = CategoricalDtype(
    categories=["low", "normal", "urgent"],
    ordered=True,
)
df["priority"] = df["priority"].astype(priority_dtype)

print("priority dtype")
print(df["priority"].dtype)
print()

print("priority categories")
print(df["priority"].cat.categories)
print()

print("priority ordered")
print(df["priority"].cat.ordered)
print()

print("sorted by priority")
print(df.sort_values("priority").filter(["ticket", "priority"]).to_string(index=False))
print()

print("missing after conversion")
print(df.filter(["team", "priority"]).isna().sum())