chore: sort imports

.pre-commit-config.yaml

@@ -35,7 +35,7 @@ repos:
         - LICENSE_HEADER
         - --use-current-year
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.4.0
+  rev: v5.0.0
   hooks:
     - id: end-of-file-fixer
     - id: trailing-whitespace

mostlyai/qa/_accuracy.py

@@ -18,38 +18,37 @@
 import logging
 import math
 import time
-from typing import Any, Literal
 from collections.abc import Callable, Iterable
+from typing import Any, Literal
 
 import numpy as np
 import pandas as pd
 import phik.phik
 import scipy.cluster
 import scipy.stats
-from joblib import Parallel, delayed, parallel_config, cpu_count
+from joblib import Parallel, cpu_count, delayed, parallel_config
+from plotly import graph_objs as go
 
 from mostlyai.qa._common import (
     CHARTS_COLORS,
     CHARTS_FONTS,
+    CTX_COLUMN_PREFIX,
     EMPTY_BIN,
+    MAX_BIVARIATE_CTX_PLOTS,
+    MAX_BIVARIATE_NXT_PLOTS,
+    MAX_BIVARIATE_TGT_PLOTS,
+    MAX_ENGINE_RARE_CATEGORY_THRESHOLD,
     MAX_TRIVARIATES,
-    NA_BIN,
+    MAX_UNIVARIATE_PLOTS,
     MIN_RARE_CAT_PROTECTION,
+    NA_BIN,
+    NXT_COLUMN_PREFIX,
     OTHER_BIN,
     RARE_BIN,
-    MAX_UNIVARIATE_PLOTS,
-    MAX_BIVARIATE_TGT_PLOTS,
-    MAX_BIVARIATE_CTX_PLOTS,
-    MAX_BIVARIATE_NXT_PLOTS,
-    CTX_COLUMN_PREFIX,
-    TGT_COLUMN_PREFIX,
-    NXT_COLUMN_PREFIX,
-    MAX_ENGINE_RARE_CATEGORY_THRESHOLD,
     TGT_COLUMN,
+    TGT_COLUMN_PREFIX,
 )
-from plotly import graph_objs as go
-
-from mostlyai.qa._filesystem import TemporaryWorkspace, Statistics
+from mostlyai.qa._filesystem import Statistics, TemporaryWorkspace
 
 _LOG = logging.getLogger(__name__)
 

mostlyai/qa/_coherence.py

@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from joblib import Parallel, cpu_count, delayed, parallel_config
 import pandas as pd
+from joblib import Parallel, cpu_count, delayed, parallel_config
 
 from mostlyai.qa._accuracy import (
     calculate_accuracy,

mostlyai/qa/_distances.py

@@ -14,19 +14,19 @@
 
 import logging
 import time
-import numpy as np
+
 import networkx as nx
-from sklearn.neighbors import NearestNeighbors
+import numpy as np
 from joblib import cpu_count
+from plotly import graph_objs as go
+from sklearn.cluster import SpectralClustering
+from sklearn.neighbors import NearestNeighbors
 
 from mostlyai.qa._common import (
     CHARTS_COLORS,
     CHARTS_FONTS,
 )
-from sklearn.cluster import SpectralClustering
 from mostlyai.qa._filesystem import TemporaryWorkspace
-from plotly import graph_objs as go
-
 
 _LOG = logging.getLogger(__name__)
 

mostlyai/qa/_embeddings.py

@@ -13,11 +13,12 @@
 # limitations under the License.
 
 import logging
+
 import numpy as np
 import pandas as pd
+from pandas.core.dtypes.common import is_datetime64_dtype, is_numeric_dtype
 from sklearn.decomposition import PCA
 from sklearn.preprocessing import QuantileTransformer, normalize
-from pandas.core.dtypes.common import is_numeric_dtype, is_datetime64_dtype
 
 from mostlyai.qa._common import (
     EMPTY_BIN,
@@ -26,7 +27,6 @@
 )
 from mostlyai.qa.assets import load_embedder
 
-
 _LOG = logging.getLogger(__name__)
 
 

mostlyai/qa/_html_report.py

@@ -19,14 +19,15 @@
 
 import pandas as pd
 from jinja2 import Environment, FileSystemLoader
-from mostlyai.qa._accuracy import trim_label, filter_uni_acc_for_plotting, filter_biv_acc_for_plotting
+
+from mostlyai.qa._accuracy import filter_biv_acc_for_plotting, filter_uni_acc_for_plotting, trim_label
 from mostlyai.qa._common import TGT_COLUMN_PREFIX
 from mostlyai.qa._filesystem import TemporaryWorkspace
 from mostlyai.qa.assets import (
     HTML_ASSETS_PATH,
-    read_html_assets,
-    HTML_REPORT_TEMPLATE,
     HTML_REPORT_EARLY_EXIT,
+    HTML_REPORT_TEMPLATE,
+    read_html_assets,
 )
 from mostlyai.qa.metrics import ModelMetrics
 

mostlyai/qa/_sampling.py

@@ -27,27 +27,26 @@
 #  limitations under the License.
 import logging
 import random
-from typing import Any
 import warnings
-from pandas.core.dtypes.common import is_numeric_dtype, is_datetime64_dtype
+from typing import Any
 
 import numpy as np
 import pandas as pd
 import pyarrow as pa
+from pandas.core.dtypes.common import is_datetime64_dtype, is_numeric_dtype
 
-from mostlyai.qa._embeddings import encode_data
 from mostlyai.qa._accuracy import bin_data
 from mostlyai.qa._common import (
+    ACCURACY_MAX_COLUMNS,
+    COUNT_COLUMN,
     CTX_COLUMN_PREFIX,
     EMBEDDINGS_MAX_COLUMNS,
-    TGT_COLUMN_PREFIX,
     NXT_COLUMN_PREFIX,
-    COUNT_COLUMN,
-    ACCURACY_MAX_COLUMNS,
+    TGT_COLUMN_PREFIX,
 )
+from mostlyai.qa._embeddings import encode_data
 from mostlyai.qa.assets import load_tokenizer
 
-
 _LOG = logging.getLogger(__name__)
 
 

mostlyai/qa/_similarity.py

@@ -17,18 +17,18 @@
 
 import numpy as np
 import plotly.graph_objects as go
+import scipy.stats
 from sklearn.decomposition import PCA
+from sklearn.ensemble import HistGradientBoostingClassifier
+from sklearn.metrics import roc_auc_score
 from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.model_selection import StratifiedKFold
 
 from mostlyai.qa._common import (
-    CHARTS_FONTS,
     CHARTS_COLORS,
+    CHARTS_FONTS,
 )
 from mostlyai.qa._filesystem import TemporaryWorkspace
-import scipy.stats
-from sklearn.model_selection import StratifiedKFold
-from sklearn.ensemble import HistGradientBoostingClassifier
-from sklearn.metrics import roc_auc_score
 
 _LOG = logging.getLogger(__name__)
 

mostlyai/qa/logging.py

@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import sys
 import logging
+import sys
 
 _LOG = logging.getLogger(__name__.rsplit(".", 1)[0])  # get the logger with the root module name (mostlyai.qa)
 

mostlyai/qa/metrics.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from pydantic import BaseModel, Field, field_validator, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 
 
 class CustomBaseModel(BaseModel):

mostlyai/qa/random_state.py

@@ -14,8 +14,9 @@
 
 import logging
 import os
-import struct
 import random
+import struct
+
 import numpy as np
 
 _LOG = logging.getLogger(__name__)

mostlyai/qa/reporting.py

@@ -18,25 +18,25 @@
 
 import numpy as np
 import pandas as pd
-from pandas.core.dtypes.common import is_numeric_dtype, is_datetime64_dtype
+from pandas.core.dtypes.common import is_datetime64_dtype, is_numeric_dtype
 
-from mostlyai.qa import _distances, _similarity, _html_report
+from mostlyai.qa import _distances, _html_report, _similarity
 from mostlyai.qa._accuracy import (
     bin_data,
     binning_data,
-    calculate_correlations,
-    plot_store_correlation_matrices,
-    calculate_univariates,
+    calculate_bin_counts,
     calculate_bivariates,
+    calculate_categorical_uni_counts,
+    calculate_correlations,
+    calculate_numeric_uni_kdes,
     calculate_trivariates,
-    plot_store_accuracy_matrix,
-    filter_uni_acc_for_plotting,
+    calculate_univariates,
     filter_biv_acc_for_plotting,
-    calculate_numeric_uni_kdes,
-    calculate_categorical_uni_counts,
-    calculate_bin_counts,
-    plot_store_univariates,
+    filter_uni_acc_for_plotting,
+    plot_store_accuracy_matrix,
     plot_store_bivariates,
+    plot_store_correlation_matrices,
+    plot_store_univariates,
 )
 from mostlyai.qa._coherence import (
     calculate_distinct_categories_per_sequence,
@@ -46,24 +46,24 @@
     plot_store_distinct_categories_per_sequence,
     plot_store_sequences_per_distinct_category,
 )
-from mostlyai.qa.metrics import ModelMetrics, Accuracy, Similarity, Distances
-from mostlyai.qa._sampling import (
-    prepare_data_for_accuracy,
-    prepare_data_for_coherence,
-    prepare_data_for_embeddings,
-)
 from mostlyai.qa._common import (
-    determine_data_size,
-    ProgressCallback,
-    PrerequisiteNotMetError,
-    check_min_sample_size,
-    NXT_COLUMN,
     CTX_COLUMN_PREFIX,
-    TGT_COLUMN_PREFIX,
+    NXT_COLUMN,
     REPORT_CREDITS,
+    TGT_COLUMN_PREFIX,
+    PrerequisiteNotMetError,
+    ProgressCallback,
     ProgressCallbackWrapper,
+    check_min_sample_size,
+    determine_data_size,
 )
 from mostlyai.qa._filesystem import Statistics, TemporaryWorkspace
+from mostlyai.qa._sampling import (
+    prepare_data_for_accuracy,
+    prepare_data_for_coherence,
+    prepare_data_for_embeddings,
+)
+from mostlyai.qa.metrics import Accuracy, Distances, ModelMetrics, Similarity
 
 _LOG = logging.getLogger(__name__)
 

mostlyai/qa/reporting_from_statistics.py

@@ -17,24 +17,24 @@
 
 import pandas as pd
 
-from mostlyai.qa import _accuracy, _sampling, _html_report
+from mostlyai.qa import _accuracy, _html_report, _sampling
 from mostlyai.qa._coherence import (
     calculate_distinct_categories_per_sequence,
     calculate_sequences_per_distinct_category,
     plot_store_distinct_categories_per_sequence,
     plot_store_sequences_per_distinct_category,
 )
-from mostlyai.qa._sampling import prepare_data_for_coherence
 from mostlyai.qa._common import (
-    ProgressCallback,
+    REPORT_CREDITS,
     PrerequisiteNotMetError,
+    ProgressCallback,
+    ProgressCallbackWrapper,
     check_min_sample_size,
     check_statistics_prerequisite,
     determine_data_size,
-    REPORT_CREDITS,
-    ProgressCallbackWrapper,
 )
 from mostlyai.qa._filesystem import Statistics, TemporaryWorkspace
+from mostlyai.qa._sampling import prepare_data_for_coherence
 
 _LOG = logging.getLogger(__name__)
 

pyproject.toml

@@ -80,3 +80,6 @@ build-backend = "hatchling.build"
 [tool.ruff]
 target-version = "py310"
 line-length = 120
+
+[tool.ruff.lint]
+extend-select = ["I"]

tests/end_to_end/test_report.py

@@ -13,14 +13,14 @@
 # limitations under the License.
 
 import uuid
-from pathlib import Path
 import warnings
+from datetime import datetime, timedelta
+from pathlib import Path
 
-import pandas as pd
 import numpy as np
+import pandas as pd
 
 from mostlyai import qa
-from datetime import datetime, timedelta
 
 
 def mock_data(n):