# Profile: Data · NumPy and pandas. Inspect before deciding what to clean.
from io import StringIO
import pandas as pd
text = "topic,minutes\n Python ,20\ndata,\ncharts,unknown\n,10\ndata,-5\n"
raw = pd.read_csv(StringIO(text), dtype="string", keep_default_na=False)
print("Raw shape:", raw.shape)
print("First two source rows:\n" + raw.head(2).to_string())
print("Raw column types:\n" + raw.dtypes.to_string())
print("Raw missing counts:", raw.isna().sum().to_dict())
print("Empty source minute strings:", int(raw["minutes"].eq("").sum()))
clean = raw.copy()
clean["topic"] = clean["topic"].str.strip().str.lower()
clean["minutes"] = pd.to_numeric(clean["minutes"], errors="coerce")
print("Rows / numeric values:", len(clean), int(clean["minutes"].count()))
print("Converted missing minutes:", int(clean["minutes"].isna().sum()))
print("Negative minutes:", int(clean["minutes"].lt(0).sum()))
print("Empty topics:", int(clean["topic"].eq("").sum()))
valid = clean["topic"].ne("") & clean["minutes"].notna() & clean["minutes"].ge(0)
print("Valid mask:", valid.tolist())
print("Inverse mask:", (~valid).tolist())
print("Accepted source labels:", clean.loc[valid].index.tolist())
# A gapped index shows the distinction between labels and positions.
gapped = raw.loc[[0, 3]].copy()
print("Gapped labels:", gapped.index.tolist())
print("Second positional row equals label 3:", gapped.iloc[1].equals(gapped.loc[3]))
