resolve some problems with tests

Author: vorel99

src/ydata_profiling/model/alerts.py

@@ -8,7 +8,10 @@
 
 from ydata_profiling.config import Settings
 from ydata_profiling.model.correlations import perform_check_correlation
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import (
+    VarDescription,
+    VarDescriptionHashable,
+)
 
 
 def fmt_percent(value: float, edge_cases: bool = True) -> str:
@@ -163,7 +166,7 @@ def _get_description(self) -> str:
 class ConstantAlert(Alert):
     def __init__(
         self,
-        values: VarDescription,
+        values: VarDescriptionHashable,
         column_name: Optional[str] = None,
         is_empty: bool = False,
     ):
@@ -221,7 +224,7 @@ def _get_description(self) -> str:
 class HighCardinalityAlert(Alert):
     def __init__(
         self,
-        values: VarDescription,
+        values: VarDescriptionHashable,
         column_name: Optional[str] = None,
         is_empty: bool = False,
     ):
@@ -429,7 +432,7 @@ def _get_description(self) -> str:
 class UniqueAlert(Alert):
     def __init__(
         self,
-        values: VarDescription,
+        values: VarDescriptionHashable,
         column_name: Optional[str] = None,
         is_empty: bool = False,
     ):
@@ -532,7 +535,7 @@ def check_table_alerts(table: dict) -> List[Alert]:
     return alerts
 
 
-def numeric_alerts(config: Settings, summary: VarDescription) -> List[Alert]:
+def numeric_alerts(config: Settings, summary: VarDescriptionHashable) -> List[Alert]:
     alerts: List[Alert] = []
 
     # Skewness
@@ -556,7 +559,7 @@ def numeric_alerts(config: Settings, summary: VarDescription) -> List[Alert]:
     return alerts
 
 
-def timeseries_alerts(config: Settings, summary: VarDescription) -> List[Alert]:
+def timeseries_alerts(config: Settings, summary: VarDescriptionHashable) -> List[Alert]:
     alerts: List[Alert] = numeric_alerts(config, summary)
 
     if not summary["stationary"]:
@@ -568,7 +571,9 @@ def timeseries_alerts(config: Settings, summary: VarDescription) -> List[Alert]:
     return alerts
 
 
-def categorical_alerts(config: Settings, summary: VarDescription) -> List[Alert]:
+def categorical_alerts(
+    config: Settings, summary: VarDescriptionHashable
+) -> List[Alert]:
     alerts: List[Alert] = []
 
     # High cardinality
@@ -597,7 +602,7 @@ def categorical_alerts(config: Settings, summary: VarDescription) -> List[Alert]
     return alerts
 
 
-def boolean_alerts(config: Settings, summary: VarDescription) -> List[Alert]:
+def boolean_alerts(config: Settings, summary: VarDescriptionHashable) -> List[Alert]:
     alerts: List[Alert] = []
 
     if (
@@ -618,7 +623,7 @@ def generic_alerts(summary: VarDescription) -> List[Alert]:
     return alerts
 
 
-def supported_alerts(summary: VarDescription) -> List[Alert]:
+def supported_alerts(summary: VarDescriptionHashable) -> List[Alert]:
     alerts: List[Alert] = []
 
     if summary.n_distinct == summary.n:
@@ -637,7 +642,7 @@ def unsupported_alerts(summary: VarDescription) -> List[Alert]:
 
 
 def check_variable_alerts(
-    config: Settings, col: str, description: VarDescription
+    config: Settings, col: str, description: VarDescription | VarDescriptionHashable
 ) -> List[Alert]:
     """Checks individual variables for alerts.
 
@@ -654,7 +659,7 @@ def check_variable_alerts(
 
     if description["type"] == "Unsupported":
         alerts += unsupported_alerts(description)
-    else:
+    elif isinstance(description, VarDescriptionHashable):
         alerts += supported_alerts(description)
 
         if description["type"] == "Categorical":
@@ -665,6 +670,8 @@ def check_variable_alerts(
             alerts += timeseries_alerts(config, description)
         if description["type"] == "Boolean":
             alerts += boolean_alerts(config, description)
+    else:
+        raise ValueError("description should be 'VarDescriptionHashable'")
 
     for idx in range(len(alerts)):
         alerts[idx].column_name = col

src/ydata_profiling/model/description.py

@@ -2,7 +2,10 @@
 from datetime import datetime, timedelta
 from typing import Any, Dict, List, Optional, Union
 
-from ydata_profiling.model.var_description.default import VarDescription
+from ydata_profiling.model.var_description.default import (
+    VarDescription,
+    VarDescriptionHashable,
+)
 
 
 @dataclass
@@ -98,7 +101,7 @@ class BaseDescription:
     analysis: BaseAnalysis
     time_index_analysis: Optional[TimeIndexAnalysis]
     table: Any
-    variables: Dict[str, VarDescription]
+    variables: Dict[str, Union[VarDescriptionHashable, VarDescription]]
     scatter: Any
     correlations: Dict[str, Any]
     missing: Dict[str, Any]

src/ydata_profiling/model/var_description/counts.py

@@ -1,24 +1,24 @@
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, Union
 
 
 @dataclass
 class VarCounts:
     """Data about counts in variable column."""
 
-    n: int
+    n: Union[int, list]
     """Count of rows in the series."""
-    count: int
+    count: Union[int, list]
     """Count of not missing rows in the series."""
-    n_missing: int
+    n_missing: Union[int, list]
     """Count of missing rows in the series."""
-    p_missing: float
+    p_missing: Union[float, list]
     """Proportion of missing rows in the series."""
 
-    hashable: bool
+    hashable: Union[bool, list]
     value_counts_without_nan: Any
     """Counts of values in the series without NaN. Values as index, counts as values."""
     value_counts_index_sorted: Any
     """Sorted counts of values in the series without NaN. Sorted by counts."""
-    ordering: bool
-    memory_size: int
+    ordering: Union[bool, list]
+    memory_size: Union[int, list]

tests/unit/test_comparison.py

@@ -66,5 +66,6 @@ def test_generate_comparison():
 
     p1 = ProfileReport(df1, title="p1")
     p2 = ProfileReport(df2, title="p1")
-    html = p1.compare(p2).to_html()
+    _compare = p1.compare(p2)
+    html = _compare.to_html()
     assert len(html) > 0

tests/unit/test_describe.py

@@ -52,13 +52,13 @@ def test_describe_unique(data, expected, summarizer, typeset):
     desc_1d = describe_1d(config, data, summarizer, typeset)
     if expected["is_unique"] is not None:
         assert (
-            desc_1d["p_unique"] == expected["p_unique"]
+            desc_1d.p_unique == expected["p_unique"]
         ), "Describe 1D p_unique incorrect"
         assert (
-            desc_1d["p_distinct"] == expected["p_distinct"]
+            desc_1d.p_distinct == expected["p_distinct"]
         ), "Describe 1D p_distinct incorrect"
         assert (
-            desc_1d["is_unique"] == expected["is_unique"]
+            desc_1d.is_unique == expected["is_unique"]
         ), "Describe 1D should return unique"
 
 
@@ -562,6 +562,13 @@ def test_describe_df(column, describe_data, expected_results, summarizer):
     for k, v in expected_results[column].items():
         if v == check_is_NaN:
             test_condition = k not in results.variables[column]
+        # values from common description
+        elif k in asdict(results.variables[column]):
+            if isinstance(v, float):
+                assert pytest.approx(v) == getattr(results.variables[column], k)
+            else:
+                assert v == getattr(results.variables[column], k)
+            continue
         elif isinstance(v, float):
             test_condition = pytest.approx(v) == results.variables[column][k]
         else:

tests/unit/test_ge_integration_expectations.py

@@ -1,4 +1,4 @@
-from unittest.mock import Mock, patch
+from unittest.mock import MagicMock, Mock, patch
 
 import pytest
 
@@ -20,14 +20,20 @@ def batch():
 
 
 def test_generic_expectations(batch):
-    generic_expectations("column", {"n_missing": 0, "p_unique": 1.0}, batch)
+    default_desc = MagicMock()
+    default_desc.n_missing = 0
+    default_desc.p_unique = 1.0
+    generic_expectations("column", default_desc, batch)
     batch.expect_column_to_exist.assert_called_once()
     batch.expect_column_values_to_not_be_null.assert_called_once()
     batch.expect_column_values_to_be_unique.assert_called_once()
 
 
 def test_generic_expectations_min(batch):
-    generic_expectations("column", {"n_missing": 1, "p_unique": 0.5}, batch)
+    default_desc = MagicMock()
+    default_desc.n_missing = 1
+    default_desc.p_unique = 0.5
+    generic_expectations("column", default_desc, batch)
     batch.expect_column_to_exist.assert_called_once()
     batch.expect_column_values_to_not_be_null.assert_not_called()
     batch.expect_column_values_to_be_unique.assert_not_called()
@@ -93,22 +99,21 @@ def test_numeric_expectations_min(batch):
 
 
 def test_categorical_expectations(batch):
-    categorical_expectations(
-        "column",
-        {
-            "n_distinct": 1,
-            "p_distinct": 0.1,
-            "value_counts_without_nan": {"val1": 1, "val2": 2},
-        },
-        batch,
-    )
+    default_desc = MagicMock()
+    default_desc.n_distinct = 1
+    default_desc.p_distinct = 0.1
+    default_desc.value_counts_without_nan = {"val1": 1, "val2": 2}
+    categorical_expectations("column", default_desc, batch)
     batch.expect_column_values_to_be_in_set.assert_called_once_with(
         "column", {"val1", "val2"}
     )
 
 
 def test_categorical_expectations_min(batch):
-    categorical_expectations("column", {"n_distinct": 15, "p_distinct": 1.0}, batch)
+    default_desc = MagicMock()
+    default_desc.n_distinct = 15
+    default_desc.p_distinct = 1.0
+    categorical_expectations("column", default_desc, batch)
     batch.expect_column_values_to_be_in_set.assert_not_called()
 
 

tests/unit/test_pandas/test_correlations.py

@@ -1,3 +1,5 @@
+from unittest.mock import MagicMock
+
 import numpy as np
 import pandas as pd
 import pytest
@@ -41,16 +43,24 @@ def test_config():
 
 @pytest.fixture
 def test_summary():
-    summary = {
-        "float_1": {"type": "Numeric", "n_distinct": 10},
-        "float_2": {"type": "Numeric", "n_distinct": 10},
-        "integer_1": {"type": "Numeric", "n_distinct": 10},
-        "integer_2": {"type": "Numeric", "n_distinct": 10},
-        "string_1": {"type": "Categorical", "n_distinct": 10},
-        "string_2": {"type": "Categorical", "n_distinct": 10},
-    }
+    # mock numeric description
+    num_desc = MagicMock()
+    num_desc.n_distinct = 10
+    num_desc.__getitem__.return_value = "Numeric"
 
-    return summary
+    # mock categorical description
+    cat_desc = MagicMock()
+    cat_desc.n_distinct = 10
+    cat_desc.__getitem__.return_value = "Categorical"
+
+    return {
+        "float_1": num_desc,
+        "float_2": num_desc,
+        "integer_1": num_desc,
+        "integer_2": num_desc,
+        "string_1": cat_desc,
+        "string_2": cat_desc,
+    }
 
 
 def test_auto_compute_all(test_config, test_dataframe, test_summary):

tests/unit/test_summary_algos.py

@@ -2,24 +2,20 @@
 import pandas as pd
 import pytest
 
-from ydata_profiling.model.summary_algorithms import (
-    describe_counts,
-    describe_generic,
-    describe_supported,
-)
+from ydata_profiling.model.summary_algorithms import describe_supported
 
 
 def test_count_summary_sorted(config):
     s = pd.Series([1] + [2] * 1000)
-    _, sn, r = describe_counts(config, s, {})
-    assert r["value_counts_without_nan"].index[0] == 2
-    assert r["value_counts_without_nan"].index[1] == 1
+    _, sn, r = describe_supported(config, s, {})
+    assert r.value_counts_without_nan.index[0] == 2
+    assert r.value_counts_without_nan.index[1] == 1
 
 
 def test_count_summary_nat(config):
     s = pd.to_datetime(pd.Series([1, 2] + [np.nan, pd.NaT]))
-    _, sn, r = describe_counts(config, s, {})
-    assert len(r["value_counts_without_nan"].index) == 2
+    _, sn, r = describe_supported(config, s, {})
+    assert len(r.value_counts_without_nan.index) == 2
 
 
 def test_count_summary_category(config):
@@ -29,8 +25,8 @@ def test_count_summary_category(config):
             categories=["Poor", "Neutral", "Excellent"],
         )
     )
-    _, sn, r = describe_counts(config, s, {})
-    assert len(r["value_counts_without_nan"].index) == 2
+    _, sn, r = describe_supported(config, s, {})
+    assert len(r.value_counts_without_nan.index) == 2
 
 
 @pytest.fixture(scope="class")
@@ -39,17 +35,12 @@ def empty_data() -> pd.DataFrame:
 
 
 def test_summary_supported_empty_df(config, empty_data):
-    _, series, summary = describe_counts(config, empty_data["A"], {})
-    assert summary["n_missing"] == 0
-    assert "p_missing" not in summary
-
-    _, series, summary = describe_generic(config, series, summary)
-    assert summary["n_missing"] == 0
-    assert summary["p_missing"] == 0
-    assert summary["count"] == 0
-
-    _, _, summary = describe_supported(config, series, summary)
-    assert summary["n_distinct"] == 0
-    assert summary["p_distinct"] == 0
-    assert summary["n_unique"] == 0
-    assert not summary["is_unique"]
+    _, _, summary = describe_supported(config, empty_data["A"], {})
+    assert summary.n_missing == 0
+    assert summary.n_missing == 0
+    assert summary.p_missing == 0
+    assert summary.count == 0
+    assert summary.n_distinct == 0
+    assert summary.p_distinct == 0
+    assert summary.n_unique == 0
+    assert not summary.is_unique