chore: convert DatasetDict to dict and add __repr__ for Dataset

.github/workflows/python-CI.yml

@@ -25,10 +25,10 @@ jobs:
         steps:
             - name: Checkout Repository
               uses: actions/checkout@v3
-            - name: Set up python 3.10
+            - name: Set up python 3.8
               uses: actions/setup-python@v4
               with:
-                  python-version: "3.10"
+                  python-version: "3.8"
             - name: Install dependencies
               run: |
                   python -m pip install --upgrade pip==${{ env.pip-version }}

src/phoenix/datasets/dataset.py

@@ -90,6 +90,9 @@ def __init__(
         self.to_disc()
         logger.info(f"""Dataset: {self.__name} initialized""")
 
+    def __repr__(self) -> str:
+        return f'<Dataset "{self.name}">'
+
     @cached_property
     def start_time(self) -> datetime:
         """Returns the datetime of the earliest inference in the dataset"""

src/phoenix/datasets/fixtures.py

@@ -1,7 +1,7 @@
 import logging
 import os
 from dataclasses import dataclass, replace
-from typing import Dict, Tuple
+from typing import Tuple
 
 from pandas import read_parquet
 
@@ -325,9 +325,10 @@ def _download_and_persist_dataset_if_missing(
     return dataset
 
 
-@dataclass(frozen=True)
-class DatasetDict(Dict[str, Dataset]):
-    """A dictionary of datasets, split out by dataset type (primary, reference)."""
+class DatasetDict(dict):
+    """
+    A dictionary of datasets, split out by dataset type (primary, reference).
+    """
 
     primary: Dataset
     reference: Dataset

src/phoenix/metrics/mixins.py

@@ -186,7 +186,7 @@ def calc(self, dataframe: pd.DataFrame) -> float:
             how="outer",
         ).fillna(0)
         # remove rows with all zeros
-        merged_counts = merged_counts.loc[(merged_counts > 0).any(axis=1)]  # type: ignore
+        merged_counts = merged_counts.loc[(merged_counts > 0).any(axis=1)]
         primary_histogram = merged_counts.primary_histogram
         reference_histogram = merged_counts.reference_histogram
         return self.divergence(