arize-phoenix 0.0.18__tar.gz → 0.0.19__tar.gz

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: arize-phoenix
-Version: 0.0.18
+Version: 0.0.19
 Summary: ML Observability in your notebook
 Project-URL: Documentation, https://docs.arize.com/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues
@@ -47,16 +47,22 @@ Description-Content-Type: text/markdown
     </a>
     <br/>
     <br/>
-    <a href="https://join.slack.com/t/arize-ai/shared_invite/zt-1px8dcmlf-fmThhDFD_V_48oU7ALan4Q">
+    <a href="https://docs.arize.com/phoenix/">
+        <img src="https://img.shields.io/static/v1?message=Docs&logo=data:image/png;base64,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&labelColor=grey&color=blue&logoColor=white&label=%20"/>
+    </a>
+    <a target="_blank" href="https://join.slack.com/t/arize-ai/shared_invite/zt-1px8dcmlf-fmThhDFD_V_48oU7ALan4Q">
         <img src="https://img.shields.io/static/v1?message=Community&logo=slack&labelColor=grey&color=blue&logoColor=white&label=%20"/>
     </a>
-    <a href="https://pypi.org/project/arize-phoenix/">
+    <a target="_blank" href="https://twitter.com/ArizePhoenix">
+        <img src="https://img.shields.io/badge/-ArizePhoenix-blue.svg?color=blue&labelColor=gray&logo=twitter">
+    </a>
+    <a target="_blank" href="https://pypi.org/project/arize-phoenix/">
         <img src="https://img.shields.io/pypi/v/arize-phoenix?color=blue">
     </a>
-    <a href="https://anaconda.org/conda-forge/arize-phoenix">
+    <a target="_blank" href="https://anaconda.org/conda-forge/arize-phoenix">
         <img src="https://img.shields.io/conda/vn/conda-forge/arize-phoenix.svg?color=blue">
     </a>
-    <a href="https://pypi.org/project/arize-phoenix/">
+    <a target="_blank" href="https://pypi.org/project/arize-phoenix/">
         <img src="https://img.shields.io/pypi/pyversions/arize-phoenix">
     </a>
 </p>
@@ -183,6 +189,7 @@ Join our community to connect with thousands of machine learning practitioners a
 -   💡 Ask questions and provide feedback in the _#phoenix-support_ channel.
 -   🌟 Leave a star on our [GitHub](https://github.com/Arize-ai/phoenix).
 -   🐞 Report bugs with [GitHub Issues](https://github.com/Arize-ai/phoenix/issues).
+-   🐣 Follow us on [twitter](https://twitter.com/ArizePhoenix).
 -   💌️ Sign up for our [mailing list](https://phoenix.arize.com/#updates).
 -   🗺️ Check out our [roadmap](https://github.com/orgs/Arize-ai/projects/45) to see where we're heading next.
 -   🎓 Learn the fundamentals of ML observability with our [introductory](https://arize.com/ml-observability-fundamentals/) and [advanced](https://arize.com/blog-course/) courses.

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/README.md

@@ -4,16 +4,22 @@
     </a>
     <br/>
     <br/>
-    <a href="https://join.slack.com/t/arize-ai/shared_invite/zt-1px8dcmlf-fmThhDFD_V_48oU7ALan4Q">
+    <a href="https://docs.arize.com/phoenix/">
+        <img src="https://img.shields.io/static/v1?message=Docs&logo=data:image/png;base64,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&labelColor=grey&color=blue&logoColor=white&label=%20"/>
+    </a>
+    <a target="_blank" href="https://join.slack.com/t/arize-ai/shared_invite/zt-1px8dcmlf-fmThhDFD_V_48oU7ALan4Q">
         <img src="https://img.shields.io/static/v1?message=Community&logo=slack&labelColor=grey&color=blue&logoColor=white&label=%20"/>
     </a>
-    <a href="https://pypi.org/project/arize-phoenix/">
+    <a target="_blank" href="https://twitter.com/ArizePhoenix">
+        <img src="https://img.shields.io/badge/-ArizePhoenix-blue.svg?color=blue&labelColor=gray&logo=twitter">
+    </a>
+    <a target="_blank" href="https://pypi.org/project/arize-phoenix/">
         <img src="https://img.shields.io/pypi/v/arize-phoenix?color=blue">
     </a>
-    <a href="https://anaconda.org/conda-forge/arize-phoenix">
+    <a target="_blank" href="https://anaconda.org/conda-forge/arize-phoenix">
         <img src="https://img.shields.io/conda/vn/conda-forge/arize-phoenix.svg?color=blue">
     </a>
-    <a href="https://pypi.org/project/arize-phoenix/">
+    <a target="_blank" href="https://pypi.org/project/arize-phoenix/">
         <img src="https://img.shields.io/pypi/pyversions/arize-phoenix">
     </a>
 </p>
@@ -140,6 +146,7 @@ Join our community to connect with thousands of machine learning practitioners a
 -   💡 Ask questions and provide feedback in the _#phoenix-support_ channel.
 -   🌟 Leave a star on our [GitHub](https://github.com/Arize-ai/phoenix).
 -   🐞 Report bugs with [GitHub Issues](https://github.com/Arize-ai/phoenix/issues).
+-   🐣 Follow us on [twitter](https://twitter.com/ArizePhoenix).
 -   💌️ Sign up for our [mailing list](https://phoenix.arize.com/#updates).
 -   🗺️ Check out our [roadmap](https://github.com/orgs/Arize-ai/projects/45) to see where we're heading next.
 -   🎓 Learn the fundamentals of ML observability with our [introductory](https://arize.com/ml-observability-fundamentals/) and [advanced](https://arize.com/blog-course/) courses.

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/src/phoenix/__init__.py

@@ -7,7 +7,7 @@ from .datasets import (
 )
 from .session import Session, active_session, close_app, launch_app
 
-__version__ = "0.0.18"
+__version__ = "0.0.19"
 
 # module level doc-string
 __doc__ = """

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/src/phoenix/core/model_schema.py

@@ -331,7 +331,7 @@ class EmbeddingDimension(Dimension):
             object.__setattr__(self, "display_name", self.name)
 
     @classmethod
-    def from_(cls, emb: Embedding, **kwargs: Any) -> "EmbeddingDimension":
+    def from_dimension(cls, emb: Embedding, **kwargs: Any) -> "EmbeddingDimension":
         """Use `from_` instead of `__init__` because the latter is needed by
         replace() and we don't want to clobber the generated version.
         """
@@ -981,7 +981,7 @@ class Schema(SchemaSpec):
                 else:
                     yield ScalarDimension(spec, role=role, data_type=data_type)
             elif isinstance(spec, Embedding):
-                yield EmbeddingDimension.from_(spec, role=role, data_type=data_type)
+                yield EmbeddingDimension.from_dimension(spec, role=role, data_type=data_type)
             else:
                 raise TypeError(f"{role} has unrecognized type: {type(spec)}")
 

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/src/phoenix/datasets/fixtures.py

@@ -1,12 +1,17 @@
+import json
 import logging
-import os
 from dataclasses import dataclass, replace
-from typing import Optional, Tuple
+from pathlib import Path
+from typing import Iterator, NamedTuple, Optional, Tuple
+from urllib import request
+from urllib.parse import quote, urljoin
 
 from pandas import read_parquet
 
-from .dataset import Dataset
-from .schema import EmbeddingColumnNames, Schema
+from phoenix.config import DATASET_DIR
+from phoenix.core.model_schema import DatasetRole
+from phoenix.datasets.dataset import Dataset
+from phoenix.datasets.schema import EmbeddingColumnNames, Schema
 
 logger = logging.getLogger(__name__)
 
@@ -15,13 +20,22 @@ logger = logging.getLogger(__name__)
 class Fixture:
     name: str
     description: str
-    primary_dataset_url: str
-    reference_dataset_url: Optional[str]
+    prefix: str
+    primary_file_name: str
+    reference_file_name: Optional[str]
     primary_schema: Schema
     reference_schema: Schema
 
+    def paths(self) -> Iterator[Tuple[DatasetRole, Path]]:
+        return (
+            (role, Path(self.prefix) / name)
+            for role, name in zip(
+                DatasetRole,
+                (self.primary_file_name, self.reference_file_name),
+            )
+            if name
+        )
 
-FIXTURE_URL_PREFIX = "http://storage.googleapis.com/arize-assets/phoenix/datasets/"
 
 sentiment_classification_language_drift_schema = Schema(
     prediction_id_column_name="prediction_id",
@@ -53,16 +67,9 @@ sentiment_classification_language_drift_fixture = Fixture(
     """,
     primary_schema=sentiment_classification_language_drift_schema,
     reference_schema=sentiment_classification_language_drift_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/nlp/sentiment-classification-language-drift",
-        "sentiment_classification_language_drift_production.parquet",
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/nlp/sentiment-classification-language-drift",
-        "sentiment_classification_language_drift_training.parquet",
-    ),
+    prefix="unstructured/nlp/sentiment-classification-language-drift",
+    primary_file_name="sentiment_classification_language_drift_production.parquet",
+    reference_file_name="sentiment_classification_language_drift_training.parquet",
 )
 
 image_classification_schema = Schema(
@@ -86,12 +93,9 @@ image_classification_fixture = Fixture(
     """,
     primary_schema=replace(image_classification_schema, actual_label_column_name=None),
     reference_schema=image_classification_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX, "unstructured/cv/human-actions/human_actions_production.parquet"
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX, "unstructured/cv/human-actions/human_actions_training.parquet"
-    ),
+    prefix="unstructured/cv/human-actions",
+    primary_file_name="human_actions_production.parquet",
+    reference_file_name="human_actions_training.parquet",
 )
 
 fashion_mnist_primary_schema = Schema(
@@ -117,14 +121,9 @@ fashion_mnist_fixture = Fixture(
     """,
     primary_schema=fashion_mnist_primary_schema,
     reference_schema=fashion_mnist_reference_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/cv/fashion-mnist/fashion_mnist_production.parquet",
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/cv/fashion-mnist/fashion_mnist_train.parquet",
-    ),
+    prefix="unstructured/cv/fashion-mnist",
+    primary_file_name="fashion_mnist_production.parquet",
+    reference_file_name="fashion_mnist_train.parquet",
 )
 
 ner_token_drift_schema = Schema(
@@ -156,14 +155,9 @@ ner_token_drift_fixture = Fixture(
     """,
     primary_schema=ner_token_drift_schema,
     reference_schema=ner_token_drift_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/nlp/named-entity-recognition/ner_token_drift_production.parquet",
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/nlp/named-entity-recognition/ner_token_drift_train.parquet",
-    ),
+    prefix="unstructured/nlp/named-entity-recognition",
+    primary_file_name="ner_token_drift_production.parquet",
+    reference_file_name="ner_token_drift_train.parquet",
 )
 
 credit_card_fraud_schema = Schema(
@@ -194,13 +188,9 @@ credit_card_fraud_fixture = Fixture(
     """,
     primary_schema=credit_card_fraud_schema,
     reference_schema=credit_card_fraud_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX, "structured/credit-card-fraud/credit_card_fraud_production.parquet"
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "structured/credit-card-fraud/credit_card_fraud_train.parquet",
-    ),
+    prefix="structured/credit-card-fraud",
+    primary_file_name="credit_card_fraud_production.parquet",
+    reference_file_name="credit_card_fraud_train.parquet",
 )
 
 click_through_rate_schema = Schema(
@@ -228,12 +218,9 @@ click_through_rate_fixture = Fixture(
     """,
     primary_schema=click_through_rate_schema,
     reference_schema=click_through_rate_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX, "structured/click-through-rate/click_through_rate_production.parquet"
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX, "structured/click-through-rate/click_through_rate_train.parquet"
-    ),
+    prefix="structured/click-through-rate",
+    primary_file_name="click_through_rate_production.parquet",
+    reference_file_name="click_through_rate_train.parquet",
 )
 
 wide_data_primary_schema = Schema(
@@ -250,14 +237,9 @@ wide_data_fixture = Fixture(
     """,
     primary_schema=wide_data_primary_schema,
     reference_schema=wide_data_reference_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "structured/wide-data/wide_data_production.parquet",
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "structured/wide-data/wide_data_train.parquet",
-    ),
+    prefix="structured/wide-data",
+    primary_file_name="wide_data_production.parquet",
+    reference_file_name="wide_data_train.parquet",
 )
 
 deep_data_primary_schema = Schema(
@@ -274,14 +256,9 @@ deep_data_fixture = Fixture(
     """,
     primary_schema=deep_data_primary_schema,
     reference_schema=deep_data_reference_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "structured/deep-data/deep_data_production.parquet",
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "structured/deep-data/deep_data_train.parquet",
-    ),
+    prefix="structured/deep-data",
+    primary_file_name="deep_data_production.parquet",
+    reference_file_name="deep_data_train.parquet",
 )
 
 
@@ -305,14 +282,9 @@ llm_summarization_fixture = Fixture(
     """,
     primary_schema=llm_summarization_schema,
     reference_schema=llm_summarization_schema,
-    primary_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/llm/summarization/llm_summarization_prod.parquet",
-    ),
-    reference_dataset_url=os.path.join(
-        FIXTURE_URL_PREFIX,
-        "unstructured/llm/summarization/llm_summarization_baseline.parquet",
-    ),
+    prefix="unstructured/llm/summarization",
+    primary_file_name="llm_summarization_prod.parquet",
+    reference_file_name="llm_summarization_baseline.parquet",
 )
 
 FIXTURES: Tuple[Fixture, ...] = (
@@ -329,23 +301,30 @@ FIXTURES: Tuple[Fixture, ...] = (
 NAME_TO_FIXTURE = {fixture.name: fixture for fixture in FIXTURES}
 
 
-def download_fixture_if_missing(fixture_name: str) -> Tuple[Dataset, Optional[Dataset]]:
+def get_datasets(
+    fixture_name: str,
+    no_internet: bool = False,
+) -> Tuple[Dataset, Optional[Dataset]]:
     """
     Downloads primary and reference datasets for a fixture if they are not found
     locally.
     """
     fixture = _get_fixture_by_name(fixture_name=fixture_name)
-    primary_dataset = _download_dataset_if_missing(
-        dataset_name="production",
-        dataset_url=fixture.primary_dataset_url,
-        schema=fixture.primary_schema,
+    if no_internet:
+        paths = {role: DATASET_DIR / path for role, path in fixture.paths()}
+    else:
+        paths = dict(_download(fixture, DATASET_DIR))
+    primary_dataset = Dataset(
+        read_parquet(paths[DatasetRole.PRIMARY]),
+        fixture.primary_schema,
+        "production",
     )
     reference_dataset = None
-    if fixture.reference_dataset_url is not None:
-        reference_dataset = _download_dataset_if_missing(
-            dataset_name="training",
-            dataset_url=fixture.reference_dataset_url,
-            schema=fixture.reference_schema,
+    if fixture.reference_file_name is not None:
+        reference_dataset = Dataset(
+            read_parquet(paths[DatasetRole.REFERENCE]),
+            fixture.reference_schema,
+            "training",
         )
     return primary_dataset, reference_dataset
 
@@ -361,25 +340,6 @@ def _get_fixture_by_name(fixture_name: str) -> Fixture:
     return NAME_TO_FIXTURE[fixture_name]
 
 
-def _download_dataset_if_missing(dataset_name: str, dataset_url: str, schema: Schema) -> Dataset:
-    """
-    Downloads a dataset from the given URL if it is not found locally.
-    """
-    try:
-        return Dataset.from_name(dataset_name)
-    except FileNotFoundError:
-        pass
-
-    logger.info(f'Downloading dataset: "{dataset_name}"')
-    dataset = Dataset(
-        dataframe=read_parquet(dataset_url),
-        schema=schema,
-        name=dataset_name,
-    )
-    logger.info("Download complete.")
-    return dataset
-
-
 @dataclass
 class ExampleDatasets:
     """
@@ -414,8 +374,61 @@ def load_example(use_case: str) -> ExampleDatasets:
 
     """
     fixture = _get_fixture_by_name(use_case)
-    primary_dataset, reference_dataset = download_fixture_if_missing(use_case)
+    primary_dataset, reference_dataset = get_datasets(use_case)
     print(f"📥 Loaded {use_case} example datasets.")
     print("ℹ️ About this use-case:")
     print(fixture.description)
     return ExampleDatasets(primary=primary_dataset, reference=reference_dataset)
+
+
+class Metadata(NamedTuple):
+    path: str
+    mediaLink: str
+    md5Hash: str
+
+    def save_artifact(self, location: Path) -> Path:
+        data_file_path = location / self.path
+        md5_file = data_file_path.with_name(data_file_path.stem + ".md5")
+        data_file_path.parents[0].mkdir(parents=True, exist_ok=True)
+        if data_file_path.is_file() and md5_file.is_file():
+            with open(md5_file, "r") as f:
+                if f.readline() == self.md5Hash:
+                    return data_file_path
+        request.urlretrieve(self.mediaLink, data_file_path)
+        with open(md5_file, "w") as f:
+            f.write(self.md5Hash)
+        return data_file_path
+
+
+class GCSAssets(NamedTuple):
+    host: str = "https://storage.googleapis.com/"
+    bucket: str = "arize-assets"
+    prefix: str = "phoenix/datasets/"
+
+    def metadata(self, path: Path) -> Metadata:
+        url = urljoin(
+            urljoin(self.host, f"storage/v1/b/{self.bucket}/o/"),
+            quote(urljoin(self.prefix, str(path)), safe=""),
+        )
+        resp = json.loads(request.urlopen(request.Request(url)).read())
+        return Metadata(
+            resp["name"][len(self.prefix) :],
+            resp["mediaLink"],
+            resp["md5Hash"],
+        )
+
+
+def _download(fixture: Fixture, location: Path) -> Iterator[Tuple[DatasetRole, Path]]:
+    for role, path in fixture.paths():
+        yield role, GCSAssets().metadata(path).save_artifact(location)
+
+
+# Download all fixtures
+if __name__ == "__main__":
+    import time
+
+    for fixture in FIXTURES:
+        start_time = time.time()
+        print(f"getting {fixture.name}", end="...")
+        dict(_download(fixture, DATASET_DIR))
+        print(f"done ({time.time() - start_time:.2f}s)")

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/src/phoenix/metrics/metrics.py

@@ -59,7 +59,7 @@ class Mean(UnaryOperator, BaseMetric):
     def calc(self, dataframe: pd.DataFrame) -> float:
         data = self.get_operand_column(dataframe)
         numeric_data = pd.to_numeric(data, errors="coerce")
-        return cast(float, numeric_data.mean())
+        return numeric_data.mean()
 
 
 @dataclass
@@ -100,7 +100,7 @@ class Cardinality(UnaryOperator, BaseMetric):
 class PercentEmpty(UnaryOperator, BaseMetric):
     def calc(self, dataframe: pd.DataFrame) -> float:
         data = self.get_operand_column(dataframe)
-        return cast(float, data.isna().mean() * 100)
+        return data.isna().mean() * 100
 
 
 @dataclass

{arize_phoenix-0.0.18 → arize_phoenix-0.0.19}/src/phoenix/metrics/timeseries.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import datetime, timedelta, timezone
 from functools import partial
 from itertools import accumulate, repeat
 from typing import Any, Callable, Iterable, Iterator, Tuple, cast
@@ -195,9 +195,15 @@ def _results(
         # pandas row indexing is stop-exclusive
         row_slice = slice(row_start, row_stop)
         filtered = dataframe.iloc[row_slice, :]
-        yield filtered.groupby(
+        res = filtered.groupby(
             group,
             group_keys=True,
         ).apply(
             calculate_metrics,
-        ).loc[result_slice, :]
+        )
+
+        # NB: on ubuntu, we lose the timezone information when there is no data
+        if res.index.tzinfo is None:  # type: ignore
+            res = res.set_axis(res.index.tz_localize(timezone.utc), axis=0)  # type: ignore
+
+        yield res.loc[result_slice, :]

arize_phoenix-0.0.19/src/phoenix/server/api/input_types/TimeRange.py

@@ -0,0 +1,28 @@
+from datetime import datetime, timezone
+
+import strawberry
+
+
+@strawberry.input
+class TimeRange:
+    start: datetime = strawberry.field(
+        description="The start of the time range",
+    )
+    end: datetime = strawberry.field(
+        description="The end of the time range. Right exclusive.",
+    )
+
+    def __post_init__(self) -> None:
+        setattr(
+            self,
+            "start",
+            self.start.astimezone(timezone.utc),
+        )
+        setattr(
+            self,
+            "end",
+            self.end.astimezone(timezone.utc),
+        )
+
+    def is_valid(self) -> bool:
+        return self.start < self.end

arize_phoenix-0.0.19/src/phoenix/server/api/types/DatasetRole.py

@@ -0,0 +1,11 @@
+from enum import Enum
+
+import strawberry
+
+from phoenix.core.model_schema import PRIMARY, REFERENCE
+
+
+@strawberry.enum
+class DatasetRole(Enum):
+    primary = PRIMARY
+    reference = REFERENCE