bug fixes

Author: Daniel15568

README.md

@@ -55,7 +55,7 @@ One import, one line. A clean, sorted DataFrame you can read or feed into the ne
 
 | Function | What it answers |
 |---|---|
-| `profile` | What is wrong with this dataset, and how do I fix it? |
+| `profiler` | What is wrong with this dataset, and how do I fix it? |
 | `change` | Growth as numbers, columns, or a whole series |
 | `vif` | Which features are collinear? |
 | `missing` | How much of each column is missing? |

docs/documentation.md

@@ -45,7 +45,7 @@ polars stays optional: it is only imported when you actually pass a polars objec
 
 ---
 
-## `profile`
+## `profiler`
 
 The flagship: a one-call **data diagnostician**. Instead of dumping statistics for every column, it runs a battery of checks, ranks the problems worst-first, scores the data's health, and tells you how to fix each issue. It composes the rest of the toolkit (`missing`, `imbalance`, and more) under one entry point.
 
@@ -55,14 +55,14 @@ The flagship: a one-call **data diagnostician**. Instead of dumping statistics f
 **Signature**
 
 ```python
-profile(data, target=None)
+profiler(data, target=None)
 ```
 
 **Example**
 
 ```python
 import pandas as pd
-from percentify import profile
+from percentify import profiler
 
 df = pd.DataFrame({
     "user_id": range(100),                                              # identifier
@@ -72,7 +72,7 @@ df = pd.DataFrame({
     "churn":   ["No"] * 96 + ["Yes"] * 4,                              # imbalanced target
 })
 
-report = profile(df, target="churn")
+report = profiler(df, target="churn")
 report.health        # 87
 report.to_frame()
 ```

docs/index.md

@@ -54,7 +54,7 @@ One import, one line. A clean, sorted DataFrame you can read or feed straight in
 
 | Function | What it answers |
 |---|---|
-| `profile` | What is wrong with this dataset, and how do I fix it? |
+| `profiler` | What is wrong with this dataset, and how do I fix it? |
 | `change` | How much did a value grow, across numbers, columns, or a whole series? |
 | `vif` | Which features are collinear? |
 | `missing` | How much of each column is missing? |

percentify/__init__.py

@@ -1,11 +1,11 @@
-from .profiling import profile, ProfileReport, Finding
+from .profiling import profiler, ProfileReport, Finding
 from .stats import (
     change, vif, missing, cv, outliers, r_squared, pca_variance, imbalance,
     difference, split, display, PercentifyWarning,
 )
 
 __all__ = [
-    "profile", "ProfileReport", "Finding",
+    "profiler", "ProfileReport", "Finding",
     "change", "vif", "missing", "cv", "outliers", "r_squared", "pca_variance", "imbalance",
     "difference", "split", "display", "PercentifyWarning",
 ]

percentify/profiling.py

@@ -1,12 +1,12 @@
 """Diagnostic profiling for Percentify.
 
-Unlike descriptive profilers that dump statistics for every column, ``profile``
+Unlike descriptive profilers that dump statistics for every column, ``profiler``
 is a *diagnostician*: it runs a registry of checks, surfaces the problems that
 actually matter, ranks them worst-first, and tells you how to fix each one.
 
-    from percentify import profile
+    from percentify import profiler
 
-    report = profile(df)                 # pandas or polars in, report out
+    report = profiler(df)                # pandas or polars in, report out
     report                               # pretty summary (repr / notebook HTML)
     report.errors                        # just the blocking issues
     assert not report.errors             # drop straight into CI
@@ -37,7 +37,7 @@
 
 from .stats import PercentifyWarning, imbalance, missing
 
-__all__ = ["profile", "ProfileReport", "Finding"]
+__all__ = ["profiler", "ProfileReport", "Finding"]
 
 # Severity ordering and the penalty each level deducts from the health score.
 _SEVERITY_ORDER = {"error": 0, "warning": 1, "info": 2}
@@ -380,7 +380,7 @@ def check_target_imbalance(df: pd.DataFrame, target) -> list[Finding]:
 # --------------------------------------------------------------------------- #
 @dataclass
 class ProfileReport:
-    """The result of :func:`profile`. Also a plain object you can act on."""
+    """The result of :func:`profiler`. Also a plain object you can act on."""
 
     n_rows: int
     n_cols: int
@@ -487,7 +487,7 @@ def _repr_html_(self) -> str:
 # --------------------------------------------------------------------------- #
 # Public entry point
 # --------------------------------------------------------------------------- #
-def profile(data, target: Optional[str] = None) -> ProfileReport:
+def profiler(data, target: Optional[str] = None) -> ProfileReport:
     """Diagnose a DataFrame: rank its problems worst-first, with fixes.
 
     Parameters

tests/test_profiling.py

@@ -1,7 +1,7 @@
 import pytest
 import numpy as np
 import pandas as pd
-from percentify import profile, ProfileReport, Finding, PercentifyWarning
+from percentify import profiler, ProfileReport, Finding, PercentifyWarning
 
 
 @pytest.fixture
@@ -18,72 +18,72 @@ def messy_df():
     })
 
 
-def test_profile_returns_report(messy_df):
-    assert isinstance(profile(messy_df), ProfileReport)
+def test_profiler_returns_report(messy_df):
+    assert isinstance(profiler(messy_df), ProfileReport)
 
 
-def test_profile_all_missing_is_error(messy_df):
-    codes = {(f.column, f.code) for f in profile(messy_df).errors}
+def test_profiler_all_missing_is_error(messy_df):
+    codes = {(f.column, f.code) for f in profiler(messy_df).errors}
     assert ("empty", "all_missing") in codes
 
 
-def test_profile_flags_constant_and_id(messy_df):
-    warn_codes = {f.code for f in profile(messy_df).warnings}
+def test_profiler_flags_constant_and_id(messy_df):
+    warn_codes = {f.code for f in profiler(messy_df).warnings}
     assert "constant" in warn_codes
     assert "id_like" in warn_codes
     assert "collinear" in warn_codes
 
 
-def test_profile_target_imbalance(messy_df):
-    infos = {f.code for f in profile(messy_df, target="churn").infos}
+def test_profiler_target_imbalance(messy_df):
+    infos = {f.code for f in profiler(messy_df, target="churn").infos}
     assert "imbalance" in infos
 
 
-def test_profile_to_frame(messy_df):
-    frame = profile(messy_df).to_frame()
+def test_profiler_to_frame(messy_df):
+    frame = profiler(messy_df).to_frame()
     assert isinstance(frame, pd.DataFrame)
     assert list(frame.columns) == ["severity", "code", "column", "message", "suggestion"]
 
 
-def test_profile_findings_are_findings(messy_df):
-    assert all(isinstance(f, Finding) for f in profile(messy_df).findings)
+def test_profiler_findings_are_findings(messy_df):
+    assert all(isinstance(f, Finding) for f in profiler(messy_df).findings)
 
 
-def test_profile_clean_data_full_health():
+def test_profiler_clean_data_full_health():
     clean = pd.DataFrame({
         "a": [x % 10 for x in range(30)],
         "b": [x % 7 for x in range(30)],
     })
-    report = profile(clean)
+    report = profiler(clean)
     assert report.findings == []
     assert report.health == 100
 
 
-def test_profile_health_drops_with_issues(messy_df):
-    assert profile(messy_df).health < 100
+def test_profiler_health_drops_with_issues(messy_df):
+    assert profiler(messy_df).health < 100
 
 
-def test_profile_target_not_found_warns(messy_df):
+def test_profiler_target_not_found_warns(messy_df):
     with pytest.warns(PercentifyWarning):
-        profile(messy_df, target="does_not_exist")
+        profiler(messy_df, target="does_not_exist")
 
 
-def test_profile_html_escapes_column_names():
+def test_profiler_html_escapes_column_names():
     evil = pd.DataFrame({"<script>": [None] * 200, "ok": range(200)})
-    rendered = profile(evil)._repr_html_()
+    rendered = profiler(evil)._repr_html_()
     assert "&lt;script&gt;" in rendered
     assert "<script>" not in rendered
 
 
-def test_profile_composes_missing_high_warning():
+def test_profiler_composes_missing_high_warning():
     # 60% missing should surface as a high_missing warning (via missing()).
     df = pd.DataFrame({"col": [1.0, 2.0] + [None] * 3})
-    codes = {f.code for f in profile(df).warnings}
+    codes = {f.code for f in profiler(df).warnings}
     assert "high_missing" in codes
 
 
-def test_profile_polars_input(messy_df):
+def test_profiler_polars_input(messy_df):
     pl = pytest.importorskip("polars")
-    report = profile(pl.from_pandas(messy_df), target="churn")
+    report = profiler(pl.from_pandas(messy_df), target="churn")
     assert isinstance(report, ProfileReport)
     assert any(f.code == "all_missing" for f in report.errors)