Merge branch 'branch-24.02' into test-notebooks-deps

.github/workflows/pr.yaml

@@ -116,7 +116,7 @@ jobs:
       build_type: pull-request
       script: ci/test_wheel_cudf.sh
   wheel-build-dask-cudf:
-    needs: wheel-tests-cudf
+    needs: wheel-build-cudf
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:

ci/build_wheel.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Copyright (c) 2023, NVIDIA CORPORATION.
+# Copyright (c) 2023-2024, NVIDIA CORPORATION.
 
 set -euo pipefail
 
@@ -23,7 +23,7 @@ pyproject_file="${package_dir}/pyproject.toml"
 
 sed -i "s/^name = \"${package_name}\"/name = \"${package_name}${PACKAGE_CUDA_SUFFIX}\"/g" ${pyproject_file}
 echo "${version}" > VERSION
-sed -i "/^__git_commit__/ s/= .*/= \"${commit}\"/g" "${package_dir}/${package_name}/_version.py"
+sed -i "/^__git_commit__/ s/= .*/= \"${commit}\"/g" "${package_dir}/${package_name//-/_}/_version.py"
 
 # For nightlies we want to ensure that we're pulling in alphas as well. The
 # easiest way to do so is to augment the spec with a constraint containing a
@@ -34,7 +34,7 @@ if ! rapids-is-release-build; then
     alpha_spec=',>=0.0.0a0'
 fi
 
-if [[ ${package_name} == "dask_cudf" ]]; then
+if [[ ${package_name} == "dask-cudf" ]]; then
     sed -r -i "s/cudf==(.*)\"/cudf${PACKAGE_CUDA_SUFFIX}==\1${alpha_spec}\"/g" ${pyproject_file}
     sed -r -i "s/dask-cuda==(.*)\"/dask-cuda==\1${alpha_spec}\"/g" ${pyproject_file}
     sed -r -i "s/rapids-dask-dependency==(.*)\"/rapids-dask-dependency==\1${alpha_spec}\"/g" ${pyproject_file}

ci/build_wheel_dask_cudf.sh

@@ -1,11 +1,11 @@
 #!/bin/bash
-# Copyright (c) 2023, NVIDIA CORPORATION.
+# Copyright (c) 2023-2024, NVIDIA CORPORATION.
 
 set -euo pipefail
 
 package_dir="python/dask_cudf"
 
-./ci/build_wheel.sh dask_cudf ${package_dir}
+./ci/build_wheel.sh dask-cudf ${package_dir}
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen ${RAPIDS_CUDA_VERSION})"
 RAPIDS_PY_WHEEL_NAME="dask_cudf_${RAPIDS_PY_CUDA_SUFFIX}" rapids-upload-wheels-to-s3 ${package_dir}/dist

conda/environments/all_cuda-118_arch-x86_64.yaml

@@ -51,7 +51,6 @@ dependencies:
 - librdkafka>=1.9.0,<1.10.0a0
 - librmm==24.2.*
 - make
-- mimesis>=4.1.0
 - moto>=4.0.8
 - msgpack-python
 - myst-nb

conda/environments/all_cuda-120_arch-x86_64.yaml

@@ -50,7 +50,6 @@ dependencies:
 - librdkafka>=1.9.0,<1.10.0a0
 - librmm==24.2.*
 - make
-- mimesis>=4.1.0
 - moto>=4.0.8
 - msgpack-python
 - myst-nb

dependencies.yaml

@@ -603,7 +603,6 @@ dependencies:
           - cramjam
           - fastavro>=0.22.9
           - hypothesis
-          - mimesis>=4.1.0
           - pytest-benchmark
           - pytest-cases
           - python-snappy>=0.6.0

python/cudf/cudf/testing/dataset_generator.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
 # This module is for generating "synthetic" datasets. It was originally
 # designed for testing filtered reading. Generally, it should be useful
@@ -11,11 +11,9 @@
 import uuid
 from multiprocessing import Pool
 
-import mimesis
 import numpy as np
 import pandas as pd
 import pyarrow as pa
-from mimesis import Generic
 from pyarrow import parquet as pq
 
 import cudf
@@ -35,8 +33,7 @@ class ColumnParameters:
     null_frequency : 0.1
         Probability of a generated value being null
     generator : Callable
-        Function for generating random data. It is passed a Mimesis Generic
-        provider and returns an Iterable that generates data.
+        Function for generating random data.
     is_sorted : bool
         Sort this column. Columns are sorted in same order as ColumnParameters
         instances stored in column_params of Parameters. If there are one or
@@ -51,7 +48,10 @@ def __init__(
         self,
         cardinality=100,
         null_frequency=0.1,
-        generator=lambda g: [g.address.country for _ in range(100)],
+        generator=lambda: [
+            _generate_string(string.ascii_letters, random.randint(4, 8))
+            for _ in range(100)
+        ],
         is_sorted=True,
         dtype=None,
     ):
@@ -235,15 +235,9 @@ def get_dataframe(parameters, use_threads):
     if parameters.seed is not None:
         np.random.seed(parameters.seed)
 
-    # For each column, use a generic Mimesis producer to create an Iterable
-    # for generating data
-    for i, column_params in enumerate(parameters.column_parameters):
-        if column_params.dtype is None:
-            column_params.generator = column_params.generator(
-                Generic("en", seed=parameters.seed)
-            )
-        else:
-            column_params.generator = column_params.generator()
+    # For each column, invoke the data generator
+    for column_params in parameters.column_parameters:
+        column_params.generator = column_params.generator()
 
     # Get schema for each column
     table_fields = []
@@ -343,7 +337,6 @@ def rand_dataframe(
     # Apply seed
     random.seed(seed)
     np.random.seed(seed)
-    mimesis.random.random.seed(seed)
 
     column_params = []
     for meta in dtypes_meta:

python/cudf/cudf/tests/test_parquet.py

@@ -1,11 +1,12 @@
-# Copyright (c) 2019-2023, NVIDIA CORPORATION.
+# Copyright (c) 2019-2024, NVIDIA CORPORATION.
 
 import datetime
 import glob
 import math
 import os
 import pathlib
 import random
+import string
 from contextlib import contextmanager
 from io import BytesIO
 from string import ascii_letters
@@ -432,13 +433,20 @@ def test_parquet_read_filtered(tmpdir, rdg_seed):
                 dg.ColumnParameters(
                     cardinality=40,
                     null_frequency=0.05,
-                    generator=lambda g: [g.address.city() for _ in range(40)],
+                    generator=lambda: [
+                        "".join(
+                            random.sample(
+                                string.ascii_letters, random.randint(4, 8)
+                            )
+                        )
+                        for _ in range(40)
+                    ],
                     is_sorted=False,
                 ),
                 dg.ColumnParameters(
                     40,
                     0.2,
-                    lambda g: [g.person.age() for _ in range(40)],
+                    lambda: np.random.default_rng().integers(0, 100, size=40),
                     True,
                 ),
             ],

python/cudf/pyproject.toml

@@ -56,7 +56,6 @@ test = [
     "cramjam",
     "fastavro>=0.22.9",
     "hypothesis",
-    "mimesis>=4.1.0",
     "msgpack",
     "pytest",
     "pytest-benchmark",

python/dask_cudf/pyproject.toml

@@ -8,7 +8,7 @@ requires = [
 ] # This list was generated by `rapids-dependency-file-generator`. To make changes, edit ../../dependencies.yaml and run `rapids-dependency-file-generator`.
 
 [project]
-name = "dask_cudf"
+name = "dask-cudf"
 dynamic = ["version"]
 description = "Utilities for Dask and cuDF interactions"
 readme = { file = "README.md", content-type = "text/markdown" }