update holidays

.pre-commit-config.yaml

@@ -25,18 +25,15 @@ repos:
     hooks:
       - id: add-trailing-comma
         name: Add trailing comma
-  - repo: https://github.com/python/black
-    rev: 22.12.0
-    hooks:
-      - id: black
-        args:
-          - --config=./pyproject.toml
-        additional_dependencies: [".[jupyter]"]
-        types_or: [python, jupyter]
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.239'
+    rev: 'v0.1.6'
     hooks:
       - id: ruff
+        types_or: [ python, pyi, jupyter ]
         args:
-          - --config=./pyproject.toml
           - --fix
+          - --config=./pyproject.toml
+      - id: ruff-format
+        types_or: [ python, pyi, jupyter ]
+        args:
+          - --config=./pyproject.toml

.readthedocs.yaml

@@ -20,7 +20,7 @@ build:
     - graphviz
     - openjdk-11-jre-headless
   jobs:
-    post_build: 
+    post_build:
       - export JAVA_HOME="/usr/lib/jvm/java-11-openjdk-amd64"
 
 python:

Makefile

@@ -9,14 +9,14 @@ clean:
 .PHONY: lint
 lint:
 	python docs/notebook_version_standardizer.py check-execution
-	black . --config=./pyproject.toml --check
-	ruff . --config=./pyproject.toml
+	ruff check . --config=./pyproject.toml
+	ruff format . --check --config=./pyproject.toml
 
 .PHONY: lint-fix
 lint-fix:
 	python docs/notebook_version_standardizer.py standardize
-	black . --config=./pyproject.toml
-	ruff . --fix --config=./pyproject.toml
+	ruff check . --fix --config=./pyproject.toml
+	ruff format . --config=./pyproject.toml
 
 .PHONY: test
 test:

docs/source/getting_started/primitives.ipynb

@@ -186,11 +186,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from featuretools.primitives import AggregationPrimitive, TransformPrimitive\n",
-    "from featuretools.tests.testing_utils import make_ecommerce_entityset\n",
+    "import pandas as pd\n",
     "from woodwork.column_schema import ColumnSchema\n",
     "from woodwork.logical_types import Datetime, NaturalLanguage\n",
-    "import pandas as pd"
+    "\n",
+    "from featuretools.primitives import AggregationPrimitive, TransformPrimitive\n",
+    "from featuretools.tests.testing_utils import make_ecommerce_entityset"
    ]
   },
   {

docs/source/guides/advanced_custom_primitives.ipynb

@@ -13,13 +13,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from featuretools.primitives import TransformPrimitive\n",
-    "from featuretools.tests.testing_utils import make_ecommerce_entityset\n",
+    "import re\n",
+    "\n",
+    "import numpy as np\n",
     "from woodwork.column_schema import ColumnSchema\n",
     "from woodwork.logical_types import Datetime, NaturalLanguage\n",
+    "\n",
     "import featuretools as ft\n",
-    "import numpy as np\n",
-    "import re"
+    "from featuretools.primitives import TransformPrimitive\n",
+    "from featuretools.tests.testing_utils import make_ecommerce_entityset"
    ]
   },
   {

docs/source/guides/feature_selection.ipynb

@@ -24,16 +24,15 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "import featuretools as ft\n",
     "\n",
+    "import featuretools as ft\n",
+    "from featuretools.demo.flight import load_flight\n",
     "from featuretools.selection import (\n",
     "    remove_highly_correlated_features,\n",
     "    remove_highly_null_features,\n",
     "    remove_single_value_features,\n",
     ")\n",
     "\n",
-    "from featuretools.demo.flight import load_flight\n",
-    "\n",
     "es = load_flight(nrows=50)\n",
     "es"
    ]

docs/source/guides/time_series.ipynb

@@ -12,10 +12,11 @@
     "import warnings\n",
     "\n",
     "warnings.filterwarnings(\"ignore\")\n",
+    "import pandas as pd\n",
+    "\n",
     "import featuretools as ft\n",
-    "from featuretools.primitives import RollingMean, Lag, RollingMin\n",
     "from featuretools.demo.weather import load_weather\n",
-    "import pandas as pd"
+    "from featuretools.primitives import Lag, RollingMean, RollingMin"
    ]
   },
   {

docs/source/guides/using_dask_entitysets.ipynb

@@ -42,9 +42,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import featuretools as ft\n",
-    "import pandas as pd\n",
     "import dask.dataframe as dd\n",
+    "import pandas as pd\n",
+    "\n",
+    "import featuretools as ft\n",
     "\n",
     "id = [0, 1, 2, 3, 4]\n",
     "values = [12, -35, 14, 103, -51]\n",

docs/source/guides/using_spark_entitysets.ipynb

@@ -64,9 +64,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import featuretools as ft\n",
     "import pyspark.pandas as ps\n",
     "\n",
+    "import featuretools as ft\n",
+    "\n",
     "ps.set_option(\"compute.default_index_type\", \"distributed\")\n",
     "\n",
     "id = [0, 1, 2, 3, 4]\n",

docs/source/resources/frequently_asked_questions.ipynb

@@ -15,10 +15,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import featuretools as ft\n",
     "import pandas as pd\n",
-    "import numpy as np\n",
-    "import woodwork as ww"
+    "import woodwork as ww\n",
+    "\n",
+    "import featuretools as ft"
    ]
   },
   {
@@ -720,7 +720,7 @@
     "        },\n",
     "        # For mode, ignore the \"sessions\" DataFrame and only include \"brands\" in the\n",
     "        # \"products\" dataframe and \"product_id\" in the \"transactions\" DataFrame\n",
-    "        (\"count\", \"mean\"): {\"include_dataframes\": [\"sessions\", \"transactions\"]}\n",
+    "        (\"count\", \"mean\"): {\"include_dataframes\": [\"sessions\", \"transactions\"]},\n",
     "        # For count and mean, only include the dataframes \"sessions\" and \"transactions\"\n",
     "    },\n",
     ")"
@@ -1472,6 +1472,7 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
+    "\n",
     "import featuretools as ft\n",
     "\n",
     "df = pd.DataFrame(\n",
@@ -1689,9 +1690,9 @@
    "source": [
     "from featuretools.primitives import (\n",
     "    TimeSince,\n",
-    "    TimeSincePrevious,\n",
-    "    TimeSinceLast,\n",
     "    TimeSinceFirst,\n",
+    "    TimeSinceLast,\n",
+    "    TimeSincePrevious,\n",
     ")\n",
     "\n",
     "time_since = TimeSince(unit=\"minutes\")\n",

docs/source/resources/transition_to_ft_v1.0.ipynb

@@ -98,9 +98,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import featuretools as ft\n",
     "import pandas as pd\n",
-    "import woodwork as ww"
+    "\n",
+    "import featuretools as ft"
    ]
   },
   {

featuretools/feature_base/feature_descriptions.py

@@ -148,8 +148,7 @@ def generate_description(feature, feature_descriptions, primitive_templates):
 
 def get_direct_description(feature):
     direct_description = (
-        ' the instance of "{}" associated with this '
-        'instance of "{}"'.format(
+        ' the instance of "{}" associated with this ' 'instance of "{}"'.format(
             feature.relationship_path[-1][1].parent_dataframe.ww.name,
             feature.dataframe_name,
         )

featuretools/primitives/standard/transform/datetime/distance_to_holiday.py

@@ -59,7 +59,10 @@ def __init__(self, holiday="New Year's Day", country="US"):
 
         available_holidays = list(set(self.holidayUtil.federal_holidays.values()))
         if self.holiday not in available_holidays:
-            error = "must be one of the available holidays:\n%s" % available_holidays
+            error = "{} must be one of the available holidays:\n{}".format(
+                self.holiday,
+                available_holidays,
+            )
             raise ValueError(error)
 
     def get_function(self):

featuretools/synthesis/deep_feature_synthesis.py

@@ -1290,8 +1290,11 @@ def check_primitive(
     primitive = handle_primitive(primitive)
     if not isinstance(primitive, supertype):
         raise ValueError(
-            "Primitive {} in {} is not {} "
-            "primitive".format(type(primitive), arg_name, s),
+            "Primitive {} in {} is not {} " "primitive".format(
+                type(primitive),
+                arg_name,
+                s,
+            ),
         )
     return primitive
 

featuretools/tests/primitive_tests/test_feature_serialization.py

@@ -462,7 +462,7 @@ def test_deserializer_uses_common_primitive_instances_with_args(es, tmp_path):
     # Test primitive with multiple args - pandas only due to primitive compatibility
     if es.dataframe_type == Library.PANDAS:
         distance_to_holiday = DistanceToHoliday(
-            holiday="Victoria Day",
+            holiday="Canada Day",
             country="Canada",
         )
         features = dfs(
@@ -491,7 +491,7 @@ def test_deserializer_uses_common_primitive_instances_with_args(es, tmp_path):
         assert all(
             [f.primitive is new_distance_primitive for f in new_distance_features],
         )
-        assert new_distance_primitive.holiday == "Victoria Day"
+        assert new_distance_primitive.holiday == "Canada Day"
         assert new_distance_primitive.country == "Canada"
 
     # Test primitive with list arg

featuretools/tests/primitive_tests/test_rolling_primitive_utils.py

@@ -542,12 +542,14 @@ def count_wrapper(sub_s):
 def test_roll_series_with_gap_incorrect_types(window_series_pd):
     error = "Window length must be either an offset string or an integer."
     with pytest.raises(TypeError, match=error):
-        roll_series_with_gap(
-            window_series_pd,
-            window_length=4.2,
-            gap=4,
-            min_periods=1,
-        ),
+        (
+            roll_series_with_gap(
+                window_series_pd,
+                window_length=4.2,
+                gap=4,
+                min_periods=1,
+            ),
+        )
 
     error = "Gap must be either an offset string or an integer."
     with pytest.raises(TypeError, match=error):

featuretools/tests/primitive_tests/transform_primitive_tests/test_distancetoholiday_primitive.py

@@ -1,10 +1,8 @@
 from datetime import datetime
 
-import holidays
 import numpy as np
 import pandas as pd
 import pytest
-from packaging.version import parse
 
 from featuretools.primitives import DistanceToHoliday
 
@@ -26,7 +24,7 @@ def test_distanceholiday():
 
 
 def test_holiday_out_of_range():
-    date_to_holiday = DistanceToHoliday("Boxing Day", country="Canada")
+    date_to_holiday = DistanceToHoliday("Canada Day", country="Canada")
 
     array = pd.Series(
         [
@@ -36,22 +34,12 @@ def test_holiday_out_of_range():
             datetime(2020, 12, 31),
         ],
     )
-    days_to_boxing_day = -157 if parse(holidays.__version__) >= parse("0.15.0") else 209
-    edge_case_first_day_of_year = (
-        -6 if parse(holidays.__version__) >= parse("0.17.0") else np.nan
+    answer = [181, 31, -30, 182]
+    pd.testing.assert_series_equal(
+        date_to_holiday(array),
+        pd.Series(answer),
+        check_names=False,
     )
-    edge_case_last_day_of_year = (
-        -5 if parse(holidays.__version__) >= parse("0.17.0") else np.nan
-    )
-    answer = pd.Series(
-        [
-            edge_case_first_day_of_year,
-            days_to_boxing_day,
-            148,
-            edge_case_last_day_of_year,
-        ],
-    )
-    pd.testing.assert_series_equal(date_to_holiday(array), answer, check_names=False)
 
 
 def test_unknown_country_error():
@@ -82,7 +70,7 @@ def test_nat():
 
 
 def test_valid_country():
-    distance_to_holiday = DistanceToHoliday("Victoria Day", country="Canada")
+    distance_to_holiday = DistanceToHoliday("Canada Day", country="Canada")
     case = pd.Series(
         [
             "2010-01-01",
@@ -91,7 +79,7 @@ def test_valid_country():
             "2020-12-31",
         ],
     ).astype("datetime64[ns]")
-    answer = [143, -10, -70, 144]
+    answer = [181, 31, -30, 182]
     given_answer = distance_to_holiday(case).astype("float")
     np.testing.assert_array_equal(given_answer, answer)
 

featuretools/utils/recommend_primitives.py

@@ -6,18 +6,16 @@
 from featuretools.primitives.utils import get_transform_primitives
 from featuretools.synthesis import dfs, get_valid_primitives
 
-ORDERED_PRIMITIVES = (
-    [  # non-numeric primitives that require specific ordering or a time index to be set
-        "cum_count",
-        "cumulative_time_since_last_false",
-        "cumulative_time_since_last_true",
-        "diff",
-        "diff_datetime",
-        "is_first_occurrence",
-        "is_last_occurrence",
-        "time_since_previous",
-    ]
-)
+ORDERED_PRIMITIVES = [  # non-numeric primitives that require specific ordering or a time index to be set
+    "cum_count",
+    "cumulative_time_since_last_false",
+    "cumulative_time_since_last_true",
+    "diff",
+    "diff_datetime",
+    "is_first_occurrence",
+    "is_last_occurrence",
+    "time_since_previous",
+]
 
 
 DEPRECATED_PRIMITIVES = [