ludwig-ai--ludwig
wehub-resource-sync
593b94c120
pytest / Unit Tests (push) Has been cancelled
pytest / Integration (integration_tests_a) (push) Has been cancelled
pytest / Integration (integration_tests_b) (push) Has been cancelled
pytest / Integration (integration_tests_c) (push) Has been cancelled
pytest / Integration (integration_tests_d) (push) Has been cancelled
pytest / Integration (integration_tests_e) (push) Has been cancelled
pytest / Integration (integration_tests_f) (push) Has been cancelled
pytest / Integration (integration_tests_g) (push) Has been cancelled
pytest / Integration (integration_tests_h) (push) Has been cancelled
pytest / Integration (integration_tests_i) (push) Has been cancelled
pytest / Integration (integration_tests_j) (push) Has been cancelled
pytest / Distributed (distributed_a) (push) Has been cancelled
pytest / Distributed (distributed_b) (push) Has been cancelled
pytest / Distributed (distributed_c) (push) Has been cancelled
pytest / Distributed (distributed_d) (push) Has been cancelled
pytest / Distributed (distributed_e) (push) Has been cancelled
pytest / Distributed (distributed_f) (push) Has been cancelled
pytest / Minimal Install (push) Has been cancelled
pytest / Event File (push) Has been cancelled
pytest (slow) / py-slow (push) Has been cancelled
Publish JSON Schema / publish-schema (push) Has been cancelled
106 行
2.9 KiB
Python
106 行
2.9 KiB
Python
#! /usr/bin/env python
|
|
# Copyright (c) 2023 Predibase, Inc., 2020 Uber Technologies, Inc.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
# ==============================================================================
|
|
|
|
from abc import ABC, abstractmethod
|
|
|
|
from ludwig.utils.types import DataFrame
|
|
|
|
|
|
class DataFrameEngine(ABC):
|
|
@abstractmethod
|
|
def df_like(self, df, proc_cols):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def parallelize(self, data):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def persist(self, data):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def compute(self, data):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def from_pandas(self, df):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def map_objects(self, series, map_fn, meta=None):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def map_partitions(self, series, map_fn, meta=None, progress_tracker=None):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def map_batches(self, df, map_fn, enable_tensor_extension_casting=True):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def apply_objects(self, series, map_fn, meta=None):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def reduce_objects(self, series, reduce_fn):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def split(self, df, probabilities):
|
|
"""Splits the input DataFrame into sections with the given proportions."""
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def to_parquet(self, df, path, index=False):
|
|
"""Write the input DataFrame to the path in the Parquet format.
|
|
|
|
Optionally includes the DataFrame index in the Parquet file.
|
|
"""
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def write_predictions(self, df: DataFrame, path: str):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def read_predictions(self, path: str) -> DataFrame:
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def to_ray_dataset(self, df):
|
|
raise NotImplementedError()
|
|
|
|
@property
|
|
@abstractmethod
|
|
def array_lib(self):
|
|
raise NotImplementedError()
|
|
|
|
@property
|
|
@abstractmethod
|
|
def df_lib(self):
|
|
raise NotImplementedError()
|
|
|
|
@property
|
|
@abstractmethod
|
|
def partitioned(self):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def set_parallelism(self, parallelism):
|
|
raise NotImplementedError()
|