"get_regression_points",
"get_regression_summaries",
"tidy_summary",
+ "count_missing",
]
@@ -442,6 +443,35 @@ Source code for moderndive.modeling
}
return pl.DataFrame(rows, schema=schema)
+
+
+
+[docs]
+def count_missing(data, columns: list[str] | None = None) -> pl.DataFrame:
+ """Count missing (``null``) values in each column.
+
+ A beginner-friendly alternative to ``df.select(pl.all().is_null().sum())``:
+ it returns a tidy two-column data frame with one row per column
+ (``column``, ``n_missing``), sorted from most to fewest missing values so the
+ columns needing attention surface first.
+
+ Parameters
+ ----------
+ data:
+ A polars (or pandas) data frame.
+ columns:
+ Optional list of column names to check; defaults to every column.
+ """
+ df = data if isinstance(data, pl.DataFrame) else pl.from_pandas(data)
+ columns = columns or df.columns
+ return pl.DataFrame(
+ {
+ "column": columns,
+ "n_missing": [int(df[col].null_count()) for col in columns],
+ },
+ schema={"column": pl.Utf8, "n_missing": pl.Int64},
+ ).sort("n_missing", descending=True)
+
Count missing (null) values in each column.
A beginner-friendly alternative to df.select(pl.all().is_null().sum()):
+it returns a tidy two-column data frame with one row per column
+(column, n_missing), sorted from most to fewest missing values so the
+columns needing attention surface first.
prop_test_two_sample()count_missing reports how many null values each column has, sorted worst-first
+— handy for a quick data-quality check:
from moderndive import count_missing
+
+count_missing(md.load_evals())
+| column | n_missing |
|---|---|
| str | i64 |
| "ID" | 0 |
| "prof_ID" | 0 |
| "score" | 0 |
| "age" | 0 |
| "bty_avg" | 0 |
| … | … |
| "pic_outfit" | 0 |
| "pic_color" | 0 |
| "cls_did_eval" | 0 |
| "cls_students" | 0 |
| "cls_level" | 0 |
| column | n_missing |
|---|---|
| str | i64 |
| "ID" | 0 |
| "prof_ID" | 0 |
| "score" | 0 |
| "age" | 0 |
| "bty_avg" | 0 |
| … | … |
| "pic_outfit" | 0 |
| "pic_color" | 0 |
| "cls_did_eval" | 0 |
| "cls_students" | 0 |
| "cls_level" | 0 |