Merge pull request #52 from StreetEasy/validation

rename `validate_df` to `validate` in root

dfschema/__init__.py

@@ -1,4 +1,4 @@
-from .validate import validate_df
+from .validate import validate
 from .utils import generate_scheme, schema_to_dtypes
 from .core.core import DfSchema
 from .core.exceptions import (
@@ -9,7 +9,7 @@
 
 
 __all__ = [
-    "validate_df",
+    "validate",
     "DfSchema",
     "generate_scheme",
     "schema_to_dtypes",

dfschema/validate.py

@@ -3,7 +3,7 @@
 from .core import DfSchema
 
 
-def validate_df(df: pd.DataFrame, schema: dict, summary: bool = True) -> None:
+def validate(df: pd.DataFrame, schema: dict, summary: bool = True) -> None:
     """validate dataframe against the schema
 
     validate dataframe agains the schema as a dictionary. will raise

notebooks/benchmarks.ipynb

@@ -124,12 +124,12 @@
    "source": [
     "tests = {\n",
     "    'SE': 'validate_df(sample, schema_p1)',\n",
-    "    'dfs_s_p1': 'dfs.validate_df(sample, schema_p1, summary=True)',\n",
-    "    'dfs_f_p1': 'dfs.validate_df(sample, schema_p1, summary=False)',\n",
-    "    'dfs_s_p2': 'dfs.validate_df(sample, schema_p2, summary=True)',\n",
-    "    'dfs_f_p2': 'dfs.validate_df(sample, schema_p2, summary=False)',\n",
-    "    'dfs_S_s': 'S.validate_df(sample, summary=True)',\n",
-    "    'dfs_S_f': 'S.validate_df(sample, summary=False)'\n",
+    "    'dfs_s_p1': 'dfs.validate(sample, schema_p1, summary=True)',\n",
+    "    'dfs_f_p1': 'dfs.validate(sample, schema_p1, summary=False)',\n",
+    "    'dfs_s_p2': 'dfs.validate(sample, schema_p2, summary=True)',\n",
+    "    'dfs_f_p2': 'dfs.validate(sample, schema_p2, summary=False)',\n",
+    "    'dfs_S_s': 'S.validate(sample, summary=True)',\n",
+    "    'dfs_S_f': 'S.validate(sample, summary=False)'\n",
     "}"
    ]
   },

tests/test_categorical.py

@@ -6,7 +6,7 @@
 
 
 def test_df_oneof():
-    from dfschema import validate_df, DataFrameSummaryError
+    from dfschema import validate, DataFrameSummaryError
 
     df = pd.DataFrame({"x": [1, 2, 3], "y": [0.2, 0.5, 0.99], "z": ["A", "A", "Q"]})
     schema = {
@@ -19,16 +19,16 @@ def test_df_oneof():
         "strict_cols": True,
     }
 
-    validate_df(df, schema)
+    validate(df, schema)
 
     df.loc[1, "z"] = "B"
     with pytest.raises(DataFrameSummaryError):
-        validate_df(df, schema)
+        validate(df, schema)
 
 
 # @given(df=cat_df_include())
 def test_df_include():
-    from dfschema import validate_df, DataFrameSummaryError
+    from dfschema import validate, DataFrameSummaryError
 
     df = pd.DataFrame({"x": [1, 2, 3], "y": [0.2, 0.5, 0.99], "z": ["A", "Q", "Q"]})
 
@@ -41,15 +41,15 @@ def test_df_include():
         "strict_cols": True,
     }
 
-    validate_df(df, schema)
+    validate(df, schema)
 
     schema["columns"]["z"]["include"].append("B")
     with pytest.raises(DataFrameSummaryError):
-        validate_df(df, schema)
+        validate(df, schema)
 
 
 def test_df_unique():
-    from dfschema import validate_df, DataFrameSummaryError
+    from dfschema import validate, DataFrameSummaryError
 
     df = pd.DataFrame({"x": [1, 2, 3], "y": [0.2, 0.5, 0.99], "z": ["A", "B", "C"]})
     schema = {
@@ -61,9 +61,9 @@ def test_df_unique():
         "strict_cols": True,
     }
 
-    validate_df(df, schema)
+    validate(df, schema)
 
     df["z"] = "A"
 
     with pytest.raises(DataFrameSummaryError):
-        validate_df(df, schema)
+        validate(df, schema)

tests/test_invalid.py

@@ -2,8 +2,8 @@
 
 
 def test_df_validate_invalid_schema(df1, bad_schema: dict):
-    from dfschema import validate_df
+    from dfschema import validate
     from pydantic import ValidationError
 
     with pytest.raises(ValidationError):
-        validate_df(df1, bad_schema["schema"])
+        validate(df1, bad_schema["schema"])

tests/test_numeric.py

@@ -60,16 +60,16 @@
 
 @pytest.mark.parametrize("schema", max_min_correct["df1"])
 def test_validate_df1_max_min(df1, schema):
-    from dfschema import validate_df
+    from dfschema import validate
 
-    validate_df(df1, schema)
+    validate(df1, schema)
 
 
 @pytest.mark.parametrize("schema", max_min_correct["df2"])
 def test_validate_df2_max_min(df2, schema):
-    from dfschema import validate_df
+    from dfschema import validate
 
-    validate_df(df2, schema)
+    validate(df2, schema)
 
 
 wrong_schemas_max_min_df2 = [
@@ -84,7 +84,7 @@ def test_validate_df2_max_min(df2, schema):
 
 @pytest.mark.parametrize("schema", wrong_schemas_max_min_df2)
 def test_validate_df2_max_min_raises(df2, schema):
-    from dfschema import validate_df, DataFrameValidationError
+    from dfschema import validate, DataFrameValidationError
 
     with pytest.raises(DataFrameValidationError):
-        validate_df(df2, schema)
+        validate(df2, schema)

tests/test_validate.py

@@ -26,9 +26,9 @@
 
 @pytest.mark.parametrize("schema", good_schemas)
 def test_validate_df(df1, schema):
-    from dfschema import validate_df
+    from dfschema import validate
 
-    validate_df(df1, schema)
+    validate(df1, schema)
 
 
 wrong_schemas = [
@@ -48,15 +48,15 @@ def test_validate_df(df1, schema):
 @pytest.mark.parametrize("schema", wrong_schemas)
 def test_validate_df_raises(df1, summary, schema):
     from dfschema import (
-        validate_df,
+        validate,
         DataFrameValidationError,
         DataFrameSummaryError,
     )
 
     e = [DataFrameValidationError, DataFrameSummaryError][summary]
 
     with pytest.raises(e):
-        validate_df(df1, schema, summary=summary)
+        validate(df1, schema, summary=summary)
 
 
 good_schemas2 = [
@@ -86,24 +86,24 @@ def test_validate_df_raises(df1, summary, schema):
 
 @pytest.mark.parametrize("schema", good_schemas2)
 def test_validate_df2(df2, schema):
-    from dfschema import validate_df
+    from dfschema import validate
 
-    validate_df(df2, schema)
+    validate(df2, schema)
 
 
 @pytest.mark.parametrize("summary", [False, True])
 @pytest.mark.parametrize("schema", wrong_schemas2)
 def test_validate_df2_raises(df2, summary, schema):
     from dfschema import (
-        validate_df,
+        validate,
         DataFrameValidationError,
         DataFrameSummaryError,
     )
 
     e = [DataFrameValidationError, DataFrameSummaryError][summary]
 
     with pytest.raises(e):
-        validate_df(df2, schema, summary=summary)
+        validate(df2, schema, summary=summary)
 
 
 good_schemas3 = [
@@ -128,14 +128,14 @@ def test_validate_df2_raises(df2, summary, schema):
 
 @pytest.mark.parametrize("schema", good_schemas3)
 def test_validate_nan_str(df3, schema):
-    from dfschema import validate_df
+    from dfschema import validate
 
-    validate_df(df3, schema)
+    validate(df3, schema)
 
 
 @pytest.mark.parametrize("schema", wrong_schemas3)
 def test_validate_df3_raises(df3, schema):
-    from dfschema import validate_df, DataFrameValidationError
+    from dfschema import validate, DataFrameValidationError
 
     with pytest.raises(DataFrameValidationError):
-        validate_df(df3, schema)
+        validate(df3, schema)