orca-sdk 0.1.10__py3-none-any.whl → 0.1.12__py3-none-any.whl

orca_sdk/_utils/data_parsing_test.py

@@ -1,244 +0,0 @@
-import json
-import pickle
-import tempfile
-from collections import namedtuple
-from dataclasses import dataclass
-
-import pandas as pd
-import pytest
-from datasets import Dataset
-from datasets.exceptions import DatasetGenerationError
-from torch.utils.data import DataLoader as TorchDataLoader
-from torch.utils.data import Dataset as TorchDataset
-
-from ..conftest import SAMPLE_DATA
-from .data_parsing import hf_dataset_from_disk, hf_dataset_from_torch
-
-
-class PytorchDictDataset(TorchDataset):
-    def __init__(self):
-        self.data = SAMPLE_DATA
-
-    def __getitem__(self, i):
-        return self.data[i]
-
-    def __len__(self):
-        return len(self.data)
-
-
-def test_hf_dataset_from_torch_dict():
-    # Given a Pytorch dataset that returns a dictionary for each item
-    dataset = PytorchDictDataset()
-    hf_dataset = hf_dataset_from_torch(dataset)
-    # Then the HF dataset should be created successfully
-    assert isinstance(hf_dataset, Dataset)
-    assert len(hf_dataset) == len(dataset)
-    assert set(hf_dataset.column_names) == {"value", "label", "key", "score", "source_id", "partition_id"}
-
-
-class PytorchTupleDataset(TorchDataset):
-    def __init__(self):
-        self.data = SAMPLE_DATA
-
-    def __getitem__(self, i):
-        return self.data[i]["value"], self.data[i]["label"]
-
-    def __len__(self):
-        return len(self.data)
-
-
-def test_hf_dataset_from_torch_tuple():
-    # Given a Pytorch dataset that returns a tuple for each item
-    dataset = PytorchTupleDataset()
-    # And the correct number of column names passed in
-    hf_dataset = hf_dataset_from_torch(dataset, column_names=["value", "label"])
-    # Then the HF dataset should be created successfully
-    assert isinstance(hf_dataset, Dataset)
-    assert len(hf_dataset) == len(dataset)
-    assert hf_dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_torch_tuple_error():
-    # Given a Pytorch dataset that returns a tuple for each item
-    dataset = PytorchTupleDataset()
-    # Then the HF dataset should raise an error if no column names are passed in
-    with pytest.raises(DatasetGenerationError):
-        hf_dataset_from_torch(dataset)
-
-
-def test_hf_dataset_from_torch_tuple_error_not_enough_columns():
-    # Given a Pytorch dataset that returns a tuple for each item
-    dataset = PytorchTupleDataset()
-    # Then the HF dataset should raise an error if not enough column names are passed in
-    with pytest.raises(DatasetGenerationError):
-        hf_dataset_from_torch(dataset, column_names=["value"])
-
-
-DatasetTuple = namedtuple("DatasetTuple", ["value", "label"])
-
-
-class PytorchNamedTupleDataset(TorchDataset):
-    def __init__(self):
-        self.data = SAMPLE_DATA
-
-    def __getitem__(self, i):
-        return DatasetTuple(self.data[i]["value"], self.data[i]["label"])
-
-    def __len__(self):
-        return len(self.data)
-
-
-def test_hf_dataset_from_torch_named_tuple():
-    # Given a Pytorch dataset that returns a namedtuple for each item
-    dataset = PytorchNamedTupleDataset()
-    # And no column names are passed in
-    hf_dataset = hf_dataset_from_torch(dataset)
-    # Then the HF dataset should be created successfully
-    assert isinstance(hf_dataset, Dataset)
-    assert len(hf_dataset) == len(dataset)
-    assert hf_dataset.column_names == ["value", "label"]
-
-
-@dataclass
-class DatasetItem:
-    text: str
-    label: int
-
-
-class PytorchDataclassDataset(TorchDataset):
-    def __init__(self):
-        self.data = SAMPLE_DATA
-
-    def __getitem__(self, i):
-        return DatasetItem(text=self.data[i]["value"], label=self.data[i]["label"])
-
-    def __len__(self):
-        return len(self.data)
-
-
-def test_hf_dataset_from_torch_dataclass():
-    # Given a Pytorch dataset that returns a dataclass for each item
-    dataset = PytorchDataclassDataset()
-    hf_dataset = hf_dataset_from_torch(dataset)
-    # Then the HF dataset should be created successfully
-    assert isinstance(hf_dataset, Dataset)
-    assert len(hf_dataset) == len(dataset)
-    assert hf_dataset.column_names == ["text", "label"]
-
-
-class PytorchInvalidDataset(TorchDataset):
-    def __init__(self):
-        self.data = SAMPLE_DATA
-
-    def __getitem__(self, i):
-        return [self.data[i]["value"], self.data[i]["label"]]
-
-    def __len__(self):
-        return len(self.data)
-
-
-def test_hf_dataset_from_torch_invalid_dataset():
-    # Given a Pytorch dataset that returns a list for each item
-    dataset = PytorchInvalidDataset()
-    # Then the HF dataset should raise an error
-    with pytest.raises(DatasetGenerationError):
-        hf_dataset_from_torch(dataset)
-
-
-def test_hf_dataset_from_torchdataloader():
-    # Given a Pytorch dataloader that returns a column-oriented batch of items
-    dataset = PytorchDictDataset()
-
-    def collate_fn(x: list[dict]):
-        return {"value": [item["value"] for item in x], "label": [item["label"] for item in x]}
-
-    dataloader = TorchDataLoader(dataset, batch_size=3, collate_fn=collate_fn)
-    hf_dataset = hf_dataset_from_torch(dataloader)
-    # Then the HF dataset should be created successfully
-    assert isinstance(hf_dataset, Dataset)
-    assert len(hf_dataset) == len(dataset)
-    assert hf_dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_disk_pickle_list():
-    with tempfile.NamedTemporaryFile(suffix=".pkl") as temp_file:
-        # Given a pickle file with test data that is a list
-        test_data = [{"value": f"test_{i}", "label": i % 2} for i in range(30)]
-        with open(temp_file.name, "wb") as f:
-            pickle.dump(test_data, f)
-        dataset = hf_dataset_from_disk(temp_file.name)
-        # Then the HF dataset should be created successfully
-        assert isinstance(dataset, Dataset)
-        assert len(dataset) == 30
-        assert dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_disk_pickle_dict():
-    with tempfile.NamedTemporaryFile(suffix=".pkl") as temp_file:
-        # Given a pickle file with test data that is a dict
-        test_data = {"value": [f"test_{i}" for i in range(30)], "label": [i % 2 for i in range(30)]}
-        with open(temp_file.name, "wb") as f:
-            pickle.dump(test_data, f)
-        dataset = hf_dataset_from_disk(temp_file.name)
-        # Then the HF dataset should be created successfully
-        assert isinstance(dataset, Dataset)
-        assert len(dataset) == 30
-        assert dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_disk_json():
-    with tempfile.NamedTemporaryFile(suffix=".json") as temp_file:
-        # Given a JSON file with test data
-        test_data = [{"value": f"test_{i}", "label": i % 2} for i in range(30)]
-        with open(temp_file.name, "w") as f:
-            json.dump(test_data, f)
-        dataset = hf_dataset_from_disk(temp_file.name)
-        # Then the HF dataset should be created successfully
-        assert isinstance(dataset, Dataset)
-        assert len(dataset) == 30
-        assert dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_disk_jsonl():
-    with tempfile.NamedTemporaryFile(suffix=".jsonl") as temp_file:
-        # Given a JSONL file with test data
-        test_data = [{"value": f"test_{i}", "label": i % 2} for i in range(30)]
-        with open(temp_file.name, "w") as f:
-            for item in test_data:
-                f.write(json.dumps(item) + "\n")
-        dataset = hf_dataset_from_disk(temp_file.name)
-        # Then the HF dataset should be created successfully
-        assert isinstance(dataset, Dataset)
-        assert len(dataset) == 30
-        assert dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_disk_csv():
-    with tempfile.NamedTemporaryFile(suffix=".csv") as temp_file:
-        # Given a CSV file with test data
-        test_data = [{"value": f"test_{i}", "label": i % 2} for i in range(30)]
-        with open(temp_file.name, "w") as f:
-            f.write("value,label\n")
-            for item in test_data:
-                f.write(f"{item['value']},{item['label']}\n")
-        dataset = hf_dataset_from_disk(temp_file.name)
-        # Then the HF dataset should be created successfully
-        assert isinstance(dataset, Dataset)
-        assert len(dataset) == 30
-        assert dataset.column_names == ["value", "label"]
-
-
-def test_hf_dataset_from_disk_parquet():
-    with tempfile.NamedTemporaryFile(suffix=".parquet") as temp_file:
-        # Given a Parquet file with test data
-        data = {
-            "value": [f"test_{i}" for i in range(30)],
-            "label": [i % 2 for i in range(30)],
-        }
-        df = pd.DataFrame(data)
-        df.to_parquet(temp_file.name)
-        dataset = hf_dataset_from_disk(temp_file.name)
-        # Then the HF dataset should be created successfully
-        assert isinstance(dataset, Dataset)
-        assert len(dataset) == 30
-        assert dataset.column_names == ["value", "label"]

orca_sdk-0.1.10.dist-info/RECORD

@@ -1,41 +0,0 @@
-orca_sdk/__init__.py,sha256=xyjNwkLQXaX8A-UYgGwYDjv2btOXArT_yiMTfmW7KA8,1003
-orca_sdk/_shared/__init__.py,sha256=3Kt0Hu3QLI5FEp9nqGTxqAm3hAoBJKcagfaGQZ-lbJQ,223
-orca_sdk/_shared/metrics.py,sha256=faeL1B1ftmns1ikfKrIlU3xOn6j0iAGLNUupxvAFza8,24968
-orca_sdk/_shared/metrics_test.py,sha256=vDIXoj8EuuLcdPJz_7EiVPgQ-FXiVT81JG30jxsg9HM,20752
-orca_sdk/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-orca_sdk/_utils/analysis_ui.py,sha256=R0xc4RyJKyBHJEEF_ztI4Dm5w8Y1uF0Wpkn4LQgXqBE,9258
-orca_sdk/_utils/analysis_ui_style.css,sha256=q_ba_-_KtgztepHg829zLzypaxKayl7ySC1-oYDzV3k,836
-orca_sdk/_utils/auth.py,sha256=nC252O171_3_wn4KBAN7kg8GNvoZFiQ5Xtzkrm5dWDo,2645
-orca_sdk/_utils/auth_test.py,sha256=ygVWv1Ex53LaxIP7p2hzPHl8l9qYyBD5IGmEFJMps6s,1056
-orca_sdk/_utils/common.py,sha256=wUm2pNDWytEecC5WiDWd02-yCZw3Akx0bIutG4lHsFA,805
-orca_sdk/_utils/data_parsing.py,sha256=5vaTpvUOS-ldlcgnSARYw7s9mce-imzkU7kA48-pdIM,5396
-orca_sdk/_utils/data_parsing_test.py,sha256=u7BEjxtsU9gMs3tAZI0lJ--vOLlwKwH3hemdCedzxA0,8826
-orca_sdk/_utils/pagination.py,sha256=986z0QPZixrZeurJWorF6eMgnTRdDF84AagEA6qNbMw,4245
-orca_sdk/_utils/pagination_test.py,sha256=BUylCrcHnwoKEBmMUzVr0lwLpA35ivcCwdBK4rMw9y8,4887
-orca_sdk/_utils/prediction_result_ui.css,sha256=sqBlkRLnovb5X5EcUDdB6iGpH63nVRlTW4uAmXuD0WM,258
-orca_sdk/_utils/prediction_result_ui.py,sha256=Ur_FY7dz3oWNmtPiP3Wl3yRlEMgK8q9UfT-SDu9UPxA,4805
-orca_sdk/_utils/tqdm_file_reader.py,sha256=Lw7Cg1UgNuRUoN6jjqZb-IlV00H-kbRcrZLdudr1GxE,324
-orca_sdk/_utils/value_parser.py,sha256=c3qMABCCDQcIjn9N1orYYnlRwDW9JWdGwW_2TDZPLdI,1286
-orca_sdk/_utils/value_parser_test.py,sha256=OybsiC-Obi32RRi9NIuwrVBRAnlyPMV1xVAaevSrb7M,1079
-orca_sdk/async_client.py,sha256=PM7N-ggmtucfcUF1vQGtTZOCJpSNTOgd7l3LDNF5kP4,137192
-orca_sdk/classification_model.py,sha256=C58euWnNvwXnthR9RtVVCOcgPEbxCjjp3sHMb86V6YA,50197
-orca_sdk/classification_model_test.py,sha256=ElqxtR6gNwwk8dNXwfwAhpT7l0ZIP3H4pHmOyFXyTWk,37370
-orca_sdk/client.py,sha256=SKZv3zGG6OwLe_FlB5wL2cxltOLPCcHvoo2CbMwyKgA,136241
-orca_sdk/conftest.py,sha256=0O1VY-SPKNAvi9fBLdY1RMnYVgZvMjP92y99bNAqqiw,12461
-orca_sdk/credentials.py,sha256=2SwC3tq5akP-F_u2s4xMZDp8mlsKMUT1T5T9Z99-eSY,6588
-orca_sdk/credentials_test.py,sha256=TLbXJMz3IlThvtSrHeLM7jRsKnrncA_ahOTpHg15Ei4,4089
-orca_sdk/datasource.py,sha256=Qn5QloE84UXeyPk2wcy1lWe5wmh1iDBS044eWnxck_E,22371
-orca_sdk/datasource_test.py,sha256=sCk3IcQJbDut5oN4Wf7PXhTxyMwalxMuCXJekSxy9wk,16665
-orca_sdk/embedding_model.py,sha256=vLGnlO9I-cN1lklNBl_LxZ8m9oK3vkegFOpvYYw8u8g,28038
-orca_sdk/embedding_model_test.py,sha256=Lc6fZ0ifT0hh6ldkUfjwMPcP6OgN0Umlzu8XDLs7UO4,8144
-orca_sdk/job.py,sha256=wHwVt-s7i-v8udhLGybB-90Kp4dwOLrY806bE4Tam5Q,13092
-orca_sdk/job_test.py,sha256=nRSWxd_1UIfrj9oMVvrXjt6OBkBpddYAjb2y6P-DTUg,4327
-orca_sdk/memoryset.py,sha256=06v34fHabpkEaOv9VCKc0NhpMi_mNZGbQP_9GiW_nuE,157157
-orca_sdk/memoryset_test.py,sha256=O2o42XETtffXtZy0kbLk2b8cUDXU-w2ZAzXLi5-vDPQ,51278
-orca_sdk/regression_model.py,sha256=AXRzJG15sDJQSiDCDfRdcLnZDNkJWORYjhHqKyyL-Fc,33960
-orca_sdk/regression_model_test.py,sha256=90EyrhaMk1kTf87RFkMNz1PTItmeUISs6AvHmyp08DU,25447
-orca_sdk/telemetry.py,sha256=ZyCMiyyo_SchjadWZH55TlLrC4Ucq5S316NbW26LL4Y,27834
-orca_sdk/telemetry_test.py,sha256=eT66C5lFdNg-pQdo2I__BP7Tn5fTc9aTkVo9ZhWwhU0,5519
-orca_sdk-0.1.10.dist-info/METADATA,sha256=j_TIalbL8oztP39lnXjyAI6Aosvb6rnJKUc3gcuxD0k,3710
-orca_sdk-0.1.10.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-orca_sdk-0.1.10.dist-info/RECORD,,