ltc-code 0.1.91__tar.gz → 0.1.92__tar.gz

{ltc_code-0.1.91 → ltc_code-0.1.92}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.1.91
+Version: 0.1.92
 Summary: Add your description here
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown

{ltc_code-0.1.91 → ltc_code-0.1.92}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.1.91"
+version = "0.1.92"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.1.91 → ltc_code-0.1.92}/src/ltc_code/june7.py

@@ -403,4 +403,163 @@ final = df.pipe(
         "waitlist": "waitlist_school",
         "withdraw": "withdraw_school",
     },
+)
+
+
+
+
+
+
+
+
+
+from typing import Mapping, Optional, Sequence, Union
+
+import polars as pl
+
+
+DEFAULT_PRIORITY_PATTERNS_BY_CMO = {
+    "default": {
+        "flags": {
+            "sibling": [
+                r"\bsibling\s+attending\b",
+            ],
+            "staff": [
+                r"\bemployee\b",
+            ],
+            "zoned": [
+                r"\bisd\b",
+                r"\bzoned\s+for\b",
+                r"\bdynamic\s+sa\b",
+            ],
+            "transfer": [
+                r"(?:^|\s{2,})transfer(?:\s{2,}|$)",
+            ],
+        },
+        "repeat_flags": {
+            "sib_repeat": [
+                r"\bsibling\s+attending\b",
+            ],
+            "zoned_repeat": [
+                r"\bzoned\s+for\b",
+            ],
+        },
+    },
+
+    # Same as default for now, but this gives you a place to customize later.
+    "yes_prep": {
+        "flags": {
+            "sibling": [
+                r"\bsibling\s+attending\b",
+            ],
+            "staff": [
+                r"\bemployee\b",
+            ],
+            "zoned": [
+                r"\bisd\b",
+                r"\bzoned\s+for\b",
+                r"\bdynamic\s+sa\b",
+            ],
+            "transfer": [
+                r"(?:^|\s{2,})transfer(?:\s{2,}|$)",
+            ],
+        },
+        "repeat_flags": {
+            "sib_repeat": [
+                r"\bsibling\s+attending\b",
+            ],
+            "zoned_repeat": [
+                r"\bzoned\s+for\b",
+            ],
+        },
+    },
+}
+
+
+def add_priority_flags(
+    df: Union[pl.DataFrame, pl.LazyFrame],
+    priority_col: str,
+    cmo: str = "default",
+    patterns_by_cmo: Optional[Mapping[str, Mapping[str, Mapping[str, Sequence[str]]]]] = None,
+) -> Union[pl.DataFrame, pl.LazyFrame]:
+    """Create priority flags from a long priority string column.
+
+    Adds:
+        sibling
+        staff
+        zoned
+        transfer
+        sib_repeat
+        zoned_repeat
+
+    The helper lowercases the priority string and normalizes dashes/pluses to
+    spaces before matching regex patterns.
+    """
+    if not isinstance(df, (pl.DataFrame, pl.LazyFrame)):
+        raise TypeError("df must be a polars DataFrame or LazyFrame.")
+
+    columns = df.collect_schema().names() if isinstance(df, pl.LazyFrame) else df.columns
+    if priority_col not in columns:
+        raise ValueError("Missing priority column: %s" % priority_col)
+
+    patterns_by_cmo = patterns_by_cmo or DEFAULT_PRIORITY_PATTERNS_BY_CMO
+    if cmo not in patterns_by_cmo:
+        raise ValueError(
+            "No priority pattern mapping found for cmo=%r. Available CMOs: %s"
+            % (cmo, sorted(patterns_by_cmo))
+        )
+
+    config = patterns_by_cmo[cmo]
+    flag_patterns = config.get("flags", {})
+    repeat_patterns = config.get("repeat_flags", {})
+
+    def _combined_regex(patterns: Sequence[str]) -> str:
+        return "|".join("(%s)" % pattern for pattern in patterns)
+
+    def _count_expr(patterns: Sequence[str]) -> pl.Expr:
+        if not patterns:
+            return pl.lit(0)
+        return pl.sum_horizontal(
+            [
+                pl.col("_priority_text").str.count_matches(pattern)
+                for pattern in patterns
+            ]
+        )
+
+    result = df.with_columns(
+        pl.col(priority_col)
+        .cast(pl.Utf8, strict=False)
+        .fill_null("")
+        .str.to_lowercase()
+        .str.replace_all(r"[-+]", " ")
+        .alias("_priority_text")
+    )
+
+    result = result.with_columns(
+        [
+            pl.col("_priority_text")
+            .str.contains(_combined_regex(patterns))
+            .cast(pl.Int8)
+            .alias(flag_name)
+            for flag_name, patterns in flag_patterns.items()
+        ]
+    )
+
+    result = result.with_columns(
+        [
+            (_count_expr(patterns) > 1)
+            .cast(pl.Int8)
+            .alias(flag_name)
+            for flag_name, patterns in repeat_patterns.items()
+        ]
+    )
+
+    return result.drop("_priority_text")
+
+
+
+df = df.pipe(
+    add_priority_flags,
+    priority_col="priority_group_name",
+    cmo="yes_prep",
 )