Merge branch '54-add-library-parameter-checker' of https://github.com/pylint-dev/pylint-ml into 54-add-library-parameter-checker

Author: Peter Hamfelt

pylint_ml/checkers/numpy/numpy_parameter.py

@@ -22,56 +22,51 @@ class NumPyParameterChecker(BaseChecker):
 
     REQUIRED_PARAMS = {
         # Array Creation
-        'array': ['object'],
-        'zeros': ['shape'],
-        'ones': ['shape'],
-        'full': ['shape', 'fill_value'],
-        'empty': ['shape'],
-        'arange': ['start'],
-        'linspace': ['start', 'stop'],
-        'logspace': ['start', 'stop'],
-        'eye': ['N'],
-        'identity': ['n'],
-
+        "array": ["object"],
+        "zeros": ["shape"],
+        "ones": ["shape"],
+        "full": ["shape", "fill_value"],
+        "empty": ["shape"],
+        "arange": ["start"],
+        "linspace": ["start", "stop"],
+        "logspace": ["start", "stop"],
+        "eye": ["N"],
+        "identity": ["n"],
         # Random Sampling
-        'random.rand': ['d0'],
-        'random.randn': ['d0'],
-        'random.randint': ['low', 'high'],
-        'random.choice': ['a'],
-        'random.uniform': ['low', 'high'],
-        'random.normal': ['loc', 'scale'],
-
+        "random.rand": ["d0"],
+        "random.randn": ["d0"],
+        "random.randint": ["low", "high"],
+        "random.choice": ["a"],
+        "random.uniform": ["low", "high"],
+        "random.normal": ["loc", "scale"],
         # Mathematical Functions
-        'sum': ['a'],
-        'mean': ['a'],
-        'median': ['a'],
-        'std': ['a'],
-        'var': ['a'],
-        'prod': ['a'],
-        'min': ['a'],
-        'max': ['a'],
-        'ptp': ['a'],
-
+        "sum": ["a"],
+        "mean": ["a"],
+        "median": ["a"],
+        "std": ["a"],
+        "var": ["a"],
+        "prod": ["a"],
+        "min": ["a"],
+        "max": ["a"],
+        "ptp": ["a"],
         # Array Manipulation
-        'reshape': ['newshape'],
-        'transpose': [],
-        'concatenate': ['arrays'],
-        'stack': ['arrays'],
-        'vstack': ['arrays'],
-        'hstack': ['arrays'],
-
+        "reshape": ["newshape"],
+        "transpose": [],
+        "concatenate": ["arrays"],
+        "stack": ["arrays"],
+        "vstack": ["arrays"],
+        "hstack": ["arrays"],
         # Linear Algebra
-        'dot': ['a', 'b'],
-        'matmul': ['a', 'b'],
-        'linalg.inv': ['a'],
-        'linalg.eig': ['a'],
-        'linalg.solve': ['a', 'b'],
-
+        "dot": ["a", "b"],
+        "matmul": ["a", "b"],
+        "linalg.inv": ["a"],
+        "linalg.eig": ["a"],
+        "linalg.solve": ["a", "b"],
         # Statistical Functions
-        'percentile': ['a', 'q'],
-        'quantile': ['a', 'q'],
-        'corrcoef': ['x'],
-        'cov': ['m'],
+        "percentile": ["a", "q"],
+        "quantile": ["a", "q"],
+        "corrcoef": ["x"],
+        "cov": ["m"],
     }
 
     @only_required_for_messages("numpy-parameter")
@@ -105,6 +100,5 @@ def _get_full_method_name(node: nodes.Call) -> str:
 
         # Check if the root of the chain is "np" (as NumPy functions are expected to use np. prefix)
         if isinstance(func, nodes.Name) and func.name == "np":
-            return '.'.join(method_chain)
+            return ".".join(method_chain)
         return ""
-

pylint_ml/checkers/pandas/pandas_parameter.py

@@ -23,53 +23,43 @@ class PandasParameterChecker(BaseChecker):
     # Define required parameters for specific Pandas classes and methods
     REQUIRED_PARAMS = {
         # DataFrame creation
-        'DataFrame': ['data'],  # The primary input data for DataFrame creation
-
+        "DataFrame": ["data"],  # The primary input data for DataFrame creation
         # Concatenation
-        'concat': ['objs'],  # The list or dictionary of DataFrames/Series to concatenate
-
+        "concat": ["objs"],  # The list or dictionary of DataFrames/Series to concatenate
         # DataFrame I/O (Input/Output)
-        'read_csv': ['filepath_or_buffer', 'dtype'],  # Path to CSV file or file-like object; column data types
-        'read_excel': ['io', 'dtype'],  # Path to Excel file or file-like object; column data types
-        'read_table': ['filepath_or_buffer', 'dtype'],  # Path to delimited text-file or file object; column data types
-        'to_csv': ['path_or_buf'],  # File path or buffer to write the DataFrame to
-        'to_excel': ['excel_writer'],  # File path or ExcelWriter object to write the data to
-
+        "read_csv": ["filepath_or_buffer", "dtype"],  # Path to CSV file or file-like object; column data types
+        "read_excel": ["io", "dtype"],  # Path to Excel file or file-like object; column data types
+        "read_table": ["filepath_or_buffer", "dtype"],  # Path to delimited text-file or file object; column data types
+        "to_csv": ["path_or_buf"],  # File path or buffer to write the DataFrame to
+        "to_excel": ["excel_writer"],  # File path or ExcelWriter object to write the data to
         # Merging and Joining
-        'merge': ['right', 'how', 'on', 'validate'],  # The DataFrame or Serie to merge with
-        'join': ['other'],  # The DataFrame or Series to join
-
+        "merge": ["right", "how", "on", "validate"],  # The DataFrame or Serie to merge with
+        "join": ["other"],  # The DataFrame or Series to join
         # DataFrame Operations
-        'pivot_table': ['index'],  # The column to pivot on (values and columns have defaults)
-        'groupby': ['by'],  # The key or list of keys to group by
-        'resample': ['rule'],  # The frequency rule to resample by
-
+        "pivot_table": ["index"],  # The column to pivot on (values and columns have defaults)
+        "groupby": ["by"],  # The key or list of keys to group by
+        "resample": ["rule"],  # The frequency rule to resample by
         # Data Cleaning and Transformation
-        'fillna': ['value'],  # Value to use to fill NA/NaN values
-        'drop': ['labels'],  # Labels to drop
-        'drop_duplicates': ['subset'],  # Subset of columns to consider when dropping duplicates
-        'replace': ['to_replace'],  # Values to replace
-
+        "fillna": ["value"],  # Value to use to fill NA/NaN values
+        "drop": ["labels"],  # Labels to drop
+        "drop_duplicates": ["subset"],  # Subset of columns to consider when dropping duplicates
+        "replace": ["to_replace"],  # Values to replace
         # Plotting
-        'plot': ['x'],  # x-values or index for plotting
-        'hist': ['column'],  # Column to plot the histogram for
-        'boxplot': ['column'],  # Column(s) to plot boxplot for
-
+        "plot": ["x"],  # x-values or index for plotting
+        "hist": ["column"],  # Column to plot the histogram for
+        "boxplot": ["column"],  # Column(s) to plot boxplot for
         # DataFrame Sorting
-        'sort_values': ['by'],  # Column(s) to sort by
-        'sort_index': ['axis'],  # Axis to sort along (index=0, columns=1)
-
+        "sort_values": ["by"],  # Column(s) to sort by
+        "sort_index": ["axis"],  # Axis to sort along (index=0, columns=1)
         # Statistical Functions
-        'corr': ['method'],  # Method to use for correlation ('pearson', 'kendall', 'spearman')
-        'describe': [],  # No required parameters, but additional ones could be specified
-
+        "corr": ["method"],  # Method to use for correlation ('pearson', 'kendall', 'spearman')
+        "describe": [],  # No required parameters, but additional ones could be specified
         # Windowing/Resampling Functions
-        'rolling': ['window'],  # Size of the moving window
-        'ewm': ['span'],  # Span for exponentially weighted calculations
-
+        "rolling": ["window"],  # Size of the moving window
+        "ewm": ["span"],  # Span for exponentially weighted calculations
         # Miscellaneous Functions
-        'apply': ['func'],  # Function to apply to the data
-        'agg': ['func'],  # Function or list of functions for aggregation
+        "apply": ["func"],  # Function to apply to the data
+        "agg": ["func"],  # Function or list of functions for aggregation
     }
 
     @only_required_for_messages("pandas-parameter")

pylint_ml/checkers/scipy/scipy_parameter.py

@@ -23,24 +23,21 @@ class ScipyParameterChecker(BaseChecker):
     # Define required parameters for specific Scipy classes and methods
     REQUIRED_PARAMS = {
         # scipy.optimize
-        'minimize': ['fun', 'x0'],
-        'curve_fit': ['f', 'xdata', 'ydata'],
-        'root': ['fun', 'x0'],
-
+        "minimize": ["fun", "x0"],
+        "curve_fit": ["f", "xdata", "ydata"],
+        "root": ["fun", "x0"],
         # scipy.integrate
-        'quad': ['func', 'a', 'b'],
-        'dblquad': ['func', 'a', 'b', 'gfun', 'hfun'],
-        'solve_ivp': ['fun', 't_span', 'y0'],
-
+        "quad": ["func", "a", "b"],
+        "dblquad": ["func", "a", "b", "gfun", "hfun"],
+        "solve_ivp": ["fun", "t_span", "y0"],
         # scipy.stats
-        'ttest_ind': ['a', 'b'],
-        'ttest_rel': ['a', 'b'],
-        'norm.pdf': ['x'],
-
+        "ttest_ind": ["a", "b"],
+        "ttest_rel": ["a", "b"],
+        "norm.pdf": ["x"],
         # scipy.spatial
-        'distance.euclidean': ['u', 'v'],  # Full chain
-        'euclidean': ['u', 'v'],  # Direct import of euclidean
-        'KDTree.query': ['x'],
+        "distance.euclidean": ["u", "v"],  # Full chain
+        "euclidean": ["u", "v"],  # Direct import of euclidean
+        "KDTree.query": ["x"],
     }
 
     @only_required_for_messages("scipy-parameter")
@@ -75,4 +72,4 @@ def _get_full_method_name(self, node: nodes.Call) -> str:
         if isinstance(func, nodes.Name):
             method_chain.insert(0, func.name)
 
-        return '.'.join(method_chain)
+        return ".".join(method_chain)

tests/checkers/test_numpy/test_numpy_parameter.py

@@ -19,13 +19,13 @@ def test_array_missing_object(self):
         array_call = node.value
 
         with self.assertAddsMessages(
-                pylint.testutils.MessageTest(
-                    msg_id="numpy-parameter",
-                    confidence=HIGH,
-                    node=array_call,
-                    args=("object", "array"),
-                ),
-                ignore_position=True,
+            pylint.testutils.MessageTest(
+                msg_id="numpy-parameter",
+                confidence=HIGH,
+                node=array_call,
+                args=("object", "array"),
+            ),
+            ignore_position=True,
         ):
             self.checker.visit_call(array_call)
 
@@ -40,13 +40,13 @@ def test_zeros_without_shape(self):
         zeros_call = node.value
 
         with self.assertAddsMessages(
-                pylint.testutils.MessageTest(
-                    msg_id="numpy-parameter",
-                    confidence=HIGH,
-                    node=zeros_call,
-                    args=("shape", "zeros"),
-                ),
-                ignore_position=True,
+            pylint.testutils.MessageTest(
+                msg_id="numpy-parameter",
+                confidence=HIGH,
+                node=zeros_call,
+                args=("shape", "zeros"),
+            ),
+            ignore_position=True,
         ):
             self.checker.visit_call(zeros_call)
 
@@ -61,13 +61,13 @@ def test_random_rand_without_shape(self):
         rand_call = node.value
 
         with self.assertAddsMessages(
-                pylint.testutils.MessageTest(
-                    msg_id="numpy-parameter",
-                    confidence=HIGH,
-                    node=rand_call,
-                    args=("d0", "random.rand"),
-                ),
-                ignore_position=True,
+            pylint.testutils.MessageTest(
+                msg_id="numpy-parameter",
+                confidence=HIGH,
+                node=rand_call,
+                args=("d0", "random.rand"),
+            ),
+            ignore_position=True,
         ):
             self.checker.visit_call(rand_call)
 
@@ -82,13 +82,13 @@ def test_dot_without_b(self):
         dot_call = node.value
 
         with self.assertAddsMessages(
-                pylint.testutils.MessageTest(
-                    msg_id="numpy-parameter",
-                    confidence=HIGH,
-                    node=dot_call,
-                    args=("b", "dot"),
-                ),
-                ignore_position=True,
+            pylint.testutils.MessageTest(
+                msg_id="numpy-parameter",
+                confidence=HIGH,
+                node=dot_call,
+                args=("b", "dot"),
+            ),
+            ignore_position=True,
         ):
             self.checker.visit_call(dot_call)
 
@@ -103,12 +103,12 @@ def test_percentile_without_q(self):
         percentile_call = node.value
 
         with self.assertAddsMessages(
-                pylint.testutils.MessageTest(
-                    msg_id="numpy-parameter",
-                    confidence=HIGH,
-                    node=percentile_call,
-                    args=("q", "percentile"),
-                ),
-                ignore_position=True,
+            pylint.testutils.MessageTest(
+                msg_id="numpy-parameter",
+                confidence=HIGH,
+                node=percentile_call,
+                args=("q", "percentile"),
+            ),
+            ignore_position=True,
         ):
             self.checker.visit_call(percentile_call)