Reformatted files with updated black version (#4395)

* Initial commit

* Updated release notes

docs/source/release_notes.rst

@@ -2,6 +2,7 @@ Release Notes
 -------------
 **Future Releases**
     * Enhancements
+        * Reformatted files with updated black version :pr:`4395`
     * Fixes
     * Changes
     * Documentation Changes

evalml/__init__.py

@@ -1,4 +1,5 @@
 """EvalML."""
+
 import warnings
 
 # hack to prevent warnings from skopt

evalml/automl/__init__.py

@@ -1,4 +1,5 @@
 """AutoMLSearch and related modules."""
+
 from evalml.automl.automl_search import AutoMLSearch, search_iterative, search
 from evalml.automl.utils import (
     get_default_primary_search_objective,

evalml/automl/automl_algorithm/__init__.py

@@ -1,4 +1,5 @@
 """AutoML algorithms that power EvalML."""
+
 from evalml.automl.automl_algorithm.automl_algorithm import (
     AutoMLAlgorithm,
     AutoMLAlgorithmException,

evalml/automl/automl_algorithm/automl_algorithm.py

@@ -1,4 +1,5 @@
 """Base class for the AutoML algorithms which power EvalML."""
+
 import inspect
 from abc import ABC, abstractmethod
 

evalml/automl/automl_algorithm/default_algorithm.py

@@ -1,4 +1,5 @@
 """An automl algorithm that consists of two modes: fast and long, where fast is a subset of long."""
+
 import logging
 
 import numpy as np

evalml/automl/automl_algorithm/iterative_algorithm.py

@@ -1,4 +1,5 @@
 """An automl algorithm which first fits a base round of pipelines with default parameters, then does a round of parameter tuning on each pipeline in order of performance."""
+
 import logging
 import warnings
 from operator import itemgetter

evalml/automl/automl_search.py

@@ -1,4 +1,5 @@
 """EvalML's core AutoML object."""
+
 import copy
 import logging
 import pickle

evalml/automl/callbacks.py

@@ -1,4 +1,5 @@
 """Callbacks available to pass to AutoML."""
+
 import logging
 
 from evalml.exceptions import PipelineScoreError

evalml/automl/engine/__init__.py

@@ -1,4 +1,5 @@
 """EvalML Engine classes used to evaluate pipelines in AutoMLSearch."""
+
 from evalml.automl.engine.engine_base import (
     EngineBase,
     EngineComputation,

evalml/automl/engine/cf_engine.py

@@ -1,4 +1,5 @@
 """Custom CFClient API to match Dask's CFClient and allow context management."""
+
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor
 
 from evalml.automl.engine.engine_base import (

evalml/automl/engine/dask_engine.py

@@ -1,4 +1,5 @@
 """A Future-like wrapper around jobs created by the DaskEngine."""
+
 import joblib
 from dask.distributed import Client, LocalCluster
 

evalml/automl/engine/engine_base.py

@@ -1,4 +1,5 @@
 """Base class for EvalML engines."""
+
 import sys
 import time
 import traceback

evalml/automl/engine/sequential_engine.py

@@ -1,4 +1,5 @@
 """A Future-like api for jobs created by the SequentialEngine, an Engine that sequentially computes the submitted jobs."""
+
 from evalml.automl.engine.engine_base import (
     EngineBase,
     EngineComputation,

evalml/automl/pipeline_search_plots.py

@@ -1,4 +1,5 @@
 """Plots displayed during pipeline search."""
+
 from evalml.utils import import_or_raise, jupyter_check
 
 

evalml/automl/progress.py

@@ -1,4 +1,5 @@
 """Progress abstraction holding stopping criteria and progress information."""
+
 import logging
 import time
 

evalml/automl/utils.py

@@ -1,4 +1,5 @@
 """Utilities useful in AutoML."""
+
 from collections import namedtuple
 
 import pandas as pd

evalml/data_checks/__init__.py

@@ -1,4 +1,5 @@
 """Data checks."""
+
 from evalml.data_checks.data_check import DataCheck
 from evalml.data_checks.data_check_message_code import DataCheckMessageCode
 from evalml.data_checks.data_check_action import DataCheckAction

evalml/data_checks/class_imbalance_data_check.py

@@ -2,6 +2,7 @@
 
 Use for classification problems.
 """
+
 import numpy as np
 import pandas as pd
 

evalml/data_checks/data_check.py

@@ -1,4 +1,5 @@
 """Base class for all data checks."""
+
 from abc import ABC, abstractmethod
 
 from evalml.utils import classproperty

evalml/data_checks/data_check_action.py

@@ -74,7 +74,9 @@ def convert_dict_to_action(action_dict):
         return DataCheckAction(
             action_code=DataCheckActionCode._all_values[action_dict["code"]],
             metadata=action_dict["metadata"],
-            data_check_name=action_dict["data_check_name"]
-            if "data_check_name" in action_dict
-            else None,
+            data_check_name=(
+                action_dict["data_check_name"]
+                if "data_check_name" in action_dict
+                else None
+            ),
         )

evalml/data_checks/data_check_action_code.py

@@ -1,4 +1,5 @@
 """Enum for data check action code."""
+
 from enum import Enum
 
 from evalml.utils import classproperty

evalml/data_checks/data_check_action_option.py

@@ -1,4 +1,5 @@
 """Recommended action returned by a DataCheck."""
+
 from enum import Enum
 
 from evalml.data_checks.data_check_action import DataCheckAction
@@ -124,12 +125,14 @@ def convert_dict_to_option(action_dict):
         return DataCheckActionOption(
             action_code=DataCheckActionCode._all_values[action_dict["code"]],
             metadata=action_dict["metadata"],
-            data_check_name=action_dict["data_check_name"]
-            if "data_check_name" in action_dict
-            else None,
-            parameters=action_dict["parameters"]
-            if "parameters" in action_dict
-            else None,
+            data_check_name=(
+                action_dict["data_check_name"]
+                if "data_check_name" in action_dict
+                else None
+            ),
+            parameters=(
+                action_dict["parameters"] if "parameters" in action_dict else None
+            ),
         )
 
     def _validate_parameters(self):

evalml/data_checks/data_check_message.py

@@ -1,4 +1,5 @@
 """Messages returned by a DataCheck, tagged by name."""
+
 from evalml.data_checks.data_check_message_type import DataCheckMessageType
 
 

evalml/data_checks/data_check_message_code.py

@@ -1,4 +1,5 @@
 """Enum for data check message code."""
+
 from enum import Enum
 
 

evalml/data_checks/data_check_message_type.py

@@ -1,4 +1,5 @@
 """Enum for type of data check message."""
+
 from enum import Enum
 
 

evalml/data_checks/data_checks.py

@@ -1,4 +1,5 @@
 """A collection of data checks."""
+
 import inspect
 
 from evalml.data_checks import DataCheck

evalml/data_checks/datetime_format_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if the datetime column has equally spaced intervals and is monotonically increasing or decreasing in order to be supported by time series estimators."""
+
 import pandas as pd
 from woodwork.statistics_utils import infer_frequency
 
@@ -448,9 +449,11 @@ def validate(self, X, y):
                 series_message = f"Input datetime column '{col_name}' for series '{series}' contains NaN values. Please impute NaN values or drop these rows."
                 messages.append(
                     DataCheckError(
-                        message=f"Input datetime column '{col_name}' contains NaN values. Please impute NaN values or drop these rows."
-                        if not is_multiseries
-                        else series_message,
+                        message=(
+                            f"Input datetime column '{col_name}' contains NaN values. Please impute NaN values or drop these rows."
+                            if not is_multiseries
+                            else series_message
+                        ),
                         data_check_name=self.name,
                         message_code=DataCheckMessageCode.DATETIME_HAS_NAN,
                     ).to_dict(),
@@ -461,9 +464,11 @@ def validate(self, X, y):
                 series_message = f"Column '{col_name}' for series '{series}' has more than one row with the same datetime value."
                 messages.append(
                     DataCheckError(
-                        message=f"Column '{col_name}' has more than one row with the same datetime value."
-                        if not is_multiseries
-                        else series_message,
+                        message=(
+                            f"Column '{col_name}' has more than one row with the same datetime value."
+                            if not is_multiseries
+                            else series_message
+                        ),
                         data_check_name=self.name,
                         message_code=DataCheckMessageCode.DATETIME_HAS_REDUNDANT_ROW,
                     ).to_dict(),
@@ -474,9 +479,11 @@ def validate(self, X, y):
                 series_message = f"Column '{col_name}' for series '{series}' has datetime values missing between start and end date."
                 messages.append(
                     DataCheckError(
-                        message=f"Column '{col_name}' has datetime values missing between start and end date."
-                        if not is_multiseries
-                        else series_message,
+                        message=(
+                            f"Column '{col_name}' has datetime values missing between start and end date."
+                            if not is_multiseries
+                            else series_message
+                        ),
                         data_check_name=self.name,
                         message_code=DataCheckMessageCode.DATETIME_IS_MISSING_VALUES,
                     ).to_dict(),
@@ -487,9 +494,11 @@ def validate(self, X, y):
                 series_message = f"Column '{col_name}' for series '{series}' has datetime values that do not align with the inferred frequency."
                 messages.append(
                     DataCheckError(
-                        message=f"Column '{col_name}' has datetime values that do not align with the inferred frequency."
-                        if not is_multiseries
-                        else series_message,
+                        message=(
+                            f"Column '{col_name}' has datetime values that do not align with the inferred frequency."
+                            if not is_multiseries
+                            else series_message
+                        ),
                         data_check_name=self.name,
                         message_code=DataCheckMessageCode.DATETIME_HAS_MISALIGNED_VALUES,
                     ).to_dict(),
@@ -505,9 +514,11 @@ def validate(self, X, y):
                 series_message = f"No frequency could be detected in column '{col_name}' for series '{series}', possibly due to uneven intervals or too many duplicate/missing values."
                 messages.append(
                     DataCheckError(
-                        message=f"No frequency could be detected in column '{col_name}', possibly due to uneven intervals or too many duplicate/missing values."
-                        if not is_multiseries
-                        else series_message,
+                        message=(
+                            f"No frequency could be detected in column '{col_name}', possibly due to uneven intervals or too many duplicate/missing values."
+                            if not is_multiseries
+                            else series_message
+                        ),
                         data_check_name=self.name,
                         message_code=DataCheckMessageCode.DATETIME_NO_FREQUENCY_INFERRED,
                     ).to_dict(),
@@ -516,9 +527,11 @@ def validate(self, X, y):
                 series_message = f"A frequency was detected in column '{col_name}' for series '{series}', but there are faulty datetime values that need to be addressed."
                 messages.append(
                     DataCheckError(
-                        message=f"A frequency was detected in column '{col_name}', but there are faulty datetime values that need to be addressed."
-                        if not is_multiseries
-                        else series_message,
+                        message=(
+                            f"A frequency was detected in column '{col_name}', but there are faulty datetime values that need to be addressed."
+                            if not is_multiseries
+                            else series_message
+                        ),
                         data_check_name=self.name,
                         message_code=DataCheckMessageCode.DATETIME_HAS_UNEVEN_INTERVALS,
                         action_options=[

evalml/data_checks/default_data_checks.py

@@ -1,4 +1,5 @@
 """A default set of data checks that can be used for a variety of datasets."""
+
 from evalml.data_checks.class_imbalance_data_check import ClassImbalanceDataCheck
 from evalml.data_checks.data_checks import DataChecks
 from evalml.data_checks.datetime_format_data_check import DateTimeFormatDataCheck

evalml/data_checks/invalid_target_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if the target data contains missing or invalid values."""
+
 import woodwork as ww
 
 from evalml.data_checks import (
@@ -262,12 +263,16 @@ def _check_target_has_nan(self, y, messages):
                     "impute_strategy": {
                         "parameter_type": DCAOParameterType.GLOBAL,
                         "type": "category",
-                        "categories": ["mean", "most_frequent"]
-                        if is_regression(self.problem_type)
-                        else ["most_frequent"],
-                        "default_value": "mean"
-                        if is_regression(self.problem_type)
-                        else "most_frequent",
+                        "categories": (
+                            ["mean", "most_frequent"]
+                            if is_regression(self.problem_type)
+                            else ["most_frequent"]
+                        ),
+                        "default_value": (
+                            "mean"
+                            if is_regression(self.problem_type)
+                            else "most_frequent"
+                        ),
                     },
                 },
                 metadata={"is_target": True},

evalml/data_checks/multicollinearity_data_check.py

@@ -1,4 +1,5 @@
 """Data check to check if any set features are likely to be multicollinear."""
+
 from evalml.data_checks import DataCheck, DataCheckMessageCode, DataCheckWarning
 from evalml.utils import infer_feature_types
 

evalml/data_checks/no_variance_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if the target or any of the features have no variance."""
+
 from evalml.data_checks import (
     DataCheck,
     DataCheckActionCode,

evalml/data_checks/null_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if there are any highly-null columns and rows in the input."""
+
 from evalml.data_checks import (
     DataCheck,
     DataCheckActionCode,

evalml/data_checks/outliers_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if there are any outliers in input data by using IQR to determine score anomalies."""
+
 import numpy as np
 from scipy.stats import gamma
 

evalml/data_checks/sparsity_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if there are any columns with sparsely populated values in the input."""
+
 from evalml.data_checks import (
     DataCheck,
     DataCheckActionCode,

evalml/data_checks/target_distribution_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if the target data contains certain distributions that may need to be transformed prior training to improve model performance."""
+
 import numpy as np
 import woodwork as ww
 from scipy.stats import jarque_bera, shapiro

evalml/data_checks/target_leakage_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if any of the features are highly correlated with the target by using mutual information or Pearson correlation."""
+
 from woodwork.config import CONFIG_DEFAULTS
 
 from evalml.data_checks import (

evalml/data_checks/ts_parameters_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks whether the time series parameters are compatible with the data size."""
+
 from evalml.data_checks import DataCheck, DataCheckError, DataCheckMessageCode
 from evalml.utils.gen_utils import (
     are_ts_parameters_valid_for_split,

evalml/data_checks/ts_splitting_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks whether the time series training and validation splits have adequate class representation."""
+
 from sklearn.model_selection import TimeSeriesSplit as SkTimeSeriesSplit
 
 from evalml.data_checks import DataCheck, DataCheckError, DataCheckMessageCode

evalml/data_checks/uniqueness_data_check.py

@@ -1,4 +1,5 @@
 """Data check that checks if there are any columns in the input that are either too unique for classification problems or not unique enough for regression problems."""
+
 from evalml.data_checks import (
     DataCheck,
     DataCheckActionCode,

evalml/data_checks/utils.py

@@ -1,4 +1,5 @@
 """Utility methods for the data checks in EvalML."""
+
 from evalml.data_checks.data_check_action_code import DataCheckActionCode
 
 

evalml/demos/__init__.py

@@ -1,4 +1,5 @@
 """Demo datasets."""
+
 from evalml.demos.breast_cancer import load_breast_cancer
 from evalml.demos.diabetes import load_diabetes
 from evalml.demos.fraud import load_fraud