Merge branch 'main' into index_align

bigframes/ml/llm.py

@@ -44,7 +44,7 @@
 _GEMINI_PRO_ENDPOINT = "gemini-pro"
 
 _ML_GENERATE_TEXT_STATUS = "ml_generate_text_status"
-_ML_EMBED_TEXT_STATUS = "ml_generate_embedding_status"
+_ML_EMBED_TEXT_STATUS = "ml_embed_text_status"
 
 
 @log_adapter.class_logger
@@ -390,6 +390,13 @@ def predict(self, X: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
         }
 
         df = self._bqml_model.generate_embedding(X, options)
+        df = df.rename(
+            columns={
+                "ml_generate_embedding_result": "text_embedding",
+                "ml_generate_embedding_statistics": "statistics",
+                "ml_generate_embedding_status": _ML_EMBED_TEXT_STATUS,
+            }
+        )
 
         if (df[_ML_EMBED_TEXT_STATUS] != "").any():
             warnings.warn(

bigframes/operations/_matplotlib/core.py

@@ -98,6 +98,12 @@ def __init__(self, data, **kwargs) -> None:
                 f"Only support a single color string or a column name/posision. {constants.FEEDBACK_LINK}"
             )
 
+        s = self.kwargs.get("s", None)
+        if self._is_sequence_arg(s):
+            raise NotImplementedError(
+                f"Only support a single color string or a column name/posision. {constants.FEEDBACK_LINK}"
+            )
+
     def _compute_plot_data(self):
         sample = self._compute_sample_data(self.data)
 

docs/templates/toc.yml

@@ -60,6 +60,11 @@
       name: Indexers
     - name: pandas
       uid: bigframes.pandas
+    - items:
+      - name: Plotting
+        uid: bigframes.operations.plotting
+      - name: PlotAccessor
+        uid: bigframes.operations.plotting.PlotAccessor
     - items:
       - name: Series
         uid: bigframes.series.Series

tests/system/small/ml/test_llm.py

@@ -261,8 +261,8 @@ def test_embedding_generator_predict_success(
 ):
     df = palm2_embedding_generator_model.predict(llm_text_df).to_pandas()
     assert df.shape == (3, 4)
-    assert "ml_generate_embedding_result" in df.columns
-    series = df["ml_generate_embedding_result"]
+    assert "text_embedding" in df.columns
+    series = df["text_embedding"]
     value = series[0]
     assert len(value) == 768
 
@@ -273,8 +273,8 @@ def test_embedding_generator_multilingual_predict_success(
 ):
     df = palm2_embedding_generator_multilingual_model.predict(llm_text_df).to_pandas()
     assert df.shape == (3, 4)
-    assert "ml_generate_embedding_result" in df.columns
-    series = df["ml_generate_embedding_result"]
+    assert "text_embedding" in df.columns
+    series = df["text_embedding"]
     value = series[0]
     assert len(value) == 768
 
@@ -285,8 +285,8 @@ def test_embedding_generator_predict_series_success(
 ):
     df = palm2_embedding_generator_model.predict(llm_text_df["prompt"]).to_pandas()
     assert df.shape == (3, 4)
-    assert "ml_generate_embedding_result" in df.columns
-    series = df["ml_generate_embedding_result"]
+    assert "text_embedding" in df.columns
+    series = df["text_embedding"]
     value = series[0]
     assert len(value) == 768
 

tests/system/small/operations/test_plotting.py

@@ -240,6 +240,22 @@ def test_scatter_args_c(c):
         )
 
 
+@pytest.mark.parametrize(
+    ("arg_name"),
+    [
+        pytest.param("c", marks=pytest.mark.xfail(raises=NotImplementedError)),
+        pytest.param("s", marks=pytest.mark.xfail(raises=NotImplementedError)),
+    ],
+)
+def test_scatter_sequence_arg(arg_name):
+    data = {
+        "a": [1, 2, 3],
+        "b": [1, 2, 3],
+    }
+    arg_value = [3, 3, 1]
+    bpd.DataFrame(data).plot.scatter(x="a", y="b", **{arg_name: arg_value})
+
+
 def test_sampling_plot_args_n():
     df = bpd.DataFrame(np.arange(bf_mpl.DEFAULT_SAMPLING_N * 10), columns=["one"])
     ax = df.plot.line()

third_party/bigframes_vendored/pandas/plotting/_core.py

@@ -257,9 +257,6 @@ def scatter(
 
                 - A string with the name of the column to be used for marker's size.
                 - A single scalar so all points have the same size.
-                - A sequence of scalars, which will be used for each point's size
-                  recursively. For instance, when passing [2,14] all points size
-                  will be either 2 or 14, alternatively.
 
             c (str, int or array-like, optional):
                 The color of each point. Possible values are: