fix more samples

Author: tswast

bigframes/dataframe.py

@@ -4247,7 +4247,7 @@ def _resample(
 
         **Examples:**
 
-
+        >>> import bigframes.pandas as bpd
         >>> data = {
         ...     "timestamp_col": pd.date_range(
         ...         start="2021-01-01 13:00:00", periods=30, freq="1s"

bigframes/operations/strings.py

@@ -67,7 +67,7 @@ def reverse(self) -> series.Series:
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series(["apple", "banana", "", pd.NA])
             >>> s.str.reverse()
             0     elppa

bigframes/series.py

@@ -2416,7 +2416,7 @@ def _resample(
 
         **Examples:**
 
-
+        >>> import bigframes.pandas as bpd
         >>> data = {
         ...     "timestamp_col": pd.date_range(
         ...         start="2021-01-01 13:00:00", periods=30, freq="1s"

bigframes/session/__init__.py

@@ -617,9 +617,9 @@ def read_gbq_query(
 
         **Examples:**
 
-
         Simple query input:
 
+            >>> import bigframes.pandas as bpd
             >>> df = bpd.read_gbq_query('''
             ...    SELECT
             ...       pitcherFirstName,
@@ -771,9 +771,9 @@ def read_gbq_table(
 
         **Examples:**
 
-
         Read a whole table, with arbitrary ordering or ordering corresponding to the primary key(s).
 
+            >>> import bigframes.pandas as bpd
             >>> df = bpd.read_gbq_table("bigquery-public-data.ml_datasets.penguins")
 
         See also: :meth:`Session.read_gbq`.
@@ -875,9 +875,9 @@ def read_gbq_model(self, model_name: str):
 
         **Examples:**
 
-
         Read an existing BigQuery ML model.
 
+            >>> import bigframes.pandas as bpd
             >>> model_name = "bigframes-dev.bqml_tutorial.penguins_model"
             >>> model = bpd.read_gbq_model(model_name)
 
@@ -1872,7 +1872,7 @@ def udf(
         You can clean-up the BigQuery functions created above using the BigQuery
         client from the BigQuery DataFrames session:
 
-            >>> session = bpd.get_global_session()
+            >>> session = bpd.get_global_session()  # doctest: +SKIP
             >>> session.bqclient.delete_routine(minutes_to_hours.bigframes_bigquery_function)  # doctest: +SKIP
             >>> session.bqclient.delete_routine(get_hash.bigframes_bigquery_function)  # doctest: +SKIP
 
@@ -1980,10 +1980,10 @@ def read_gbq_function(
 
         **Examples:**
 
-
         Use the [cw_lower_case_ascii_only](https://github.com/GoogleCloudPlatform/bigquery-utils/blob/master/udfs/community/README.md#cw_lower_case_ascii_onlystr-string)
         function from Community UDFs.
 
+            >>> import bigframes.pandas as bpd
             >>> func = bpd.read_gbq_function("bqutil.fn.cw_lower_case_ascii_only")
 
         You can run it on scalar input. Usually you would do so to verify that
@@ -2043,13 +2043,13 @@ def read_gbq_function(
         Another use case is to define your own remote function and use it later.
         For example, define the remote function:
 
-            >>> @bpd.remote_function(cloud_function_service_account="default")
+            >>> @bpd.remote_function(cloud_function_service_account="default")  # doctest: +SKIP
             ... def tenfold(num: int) -> float:
             ...     return num * 10
 
         Then, read back the deployed BQ remote function:
 
-            >>> tenfold_ref = bpd.read_gbq_function(
+            >>> tenfold_ref = bpd.read_gbq_function(  # doctest: +SKIP
             ...     tenfold.bigframes_remote_function,
             ... )
 
@@ -2061,7 +2061,7 @@ def read_gbq_function(
             <BLANKLINE>
             [2 rows x 3 columns]
 
-            >>> df['a'].apply(tenfold_ref)
+            >>> df['a'].apply(tenfold_ref)  # doctest: +SKIP
             0    10.0
             1    20.0
             Name: a, dtype: Float64
@@ -2070,11 +2070,11 @@ def read_gbq_function(
         note, row processor implies that the function has only one input
         parameter.
 
-            >>> @bpd.remote_function(cloud_function_service_account="default")
+            >>> @bpd.remote_function(cloud_function_service_account="default")  # doctest: +SKIP
             ... def row_sum(s: pd.Series) -> float:
             ...     return s['a'] + s['b'] + s['c']
 
-            >>> row_sum_ref = bpd.read_gbq_function(
+            >>> row_sum_ref = bpd.read_gbq_function(  # doctest: +SKIP
             ...     row_sum.bigframes_remote_function,
             ...     is_row_processor=True,
             ... )
@@ -2087,7 +2087,7 @@ def read_gbq_function(
             <BLANKLINE>
             [2 rows x 3 columns]
 
-            >>> df.apply(row_sum_ref, axis=1)
+            >>> df.apply(row_sum_ref, axis=1)  # doctest: +SKIP
             0     9.0
             1    12.0
             dtype: Float64

third_party/bigframes_vendored/pandas/core/config_init.py

@@ -19,6 +19,7 @@
 
 Define Repr mode to "deferred" will prevent job execution in repr.
 
+    >>> import bigframes.pandas as bpd
     >>> df = bpd.read_gbq("bigquery-public-data.ml_datasets.penguins")
 
     >>> bpd.options.display.repr_mode = "deferred"

third_party/bigframes_vendored/pandas/core/series.py

@@ -986,9 +986,9 @@ def drop_duplicates(
 
         **Examples:**
 
-
         Generate a Series with duplicated entries.
 
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series(['llama', 'cow', 'llama', 'beetle', 'llama', 'hippo'],
             ...                name='animal')
             >>> s
@@ -1176,7 +1176,7 @@ def round(self, decimals: int = 0) -> Series:
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series([0.1, 1.3, 2.7])
             >>> s.round()
             0    0.0
@@ -1283,17 +1283,17 @@ def autocorr(self, lag: int = 1) -> float:
 
 
             >>> s = bpd.Series([0.25, 0.5, 0.2, -0.05])
-            >>> s.autocorr()  # doctest: +ELLIPSIS
-            np.float64(0.10355263309024067)
+            >>> s.autocorr()
+            0.10355263309024065
 
             >>> s.autocorr(lag=2)
-            np.float64(-1.0)
+            -1.0
 
         If the Pearson correlation is not well defined, then 'NaN' is returned.
 
             >>> s = bpd.Series([1, 0, 0, 0])
             >>> s.autocorr()
-            np.float64(nan)
+            nan
 
         Args:
             lag (int, default 1):
@@ -1927,10 +1927,10 @@ def combine(
 
         **Examples:**
 
-
         Consider 2 Datasets ``s1`` and ``s2`` containing
         highest clocked speeds of different birds.
 
+            >>> import bigframes.pandas as bpd
             >>> s1 = bpd.Series({'falcon': 330.0, 'eagle': 160.0})
             >>> s1
             falcon    330.0
@@ -2376,7 +2376,7 @@ def replace(
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series([1, 2, 3, 4, 5])
             >>> s
             0    1
@@ -2684,7 +2684,7 @@ def cumprod(self):
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series([2, np.nan, 5, -1, 0])
             >>> s
             0     2.0
@@ -3973,7 +3973,7 @@ def pow(self, other) -> Series:
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> a = bpd.Series([1, 1, 1, np.nan], index=['a', 'b', 'c', 'd'])
             >>> a
             a     1.0
@@ -4006,6 +4006,7 @@ def pow(self, other) -> Series:
                 The result of the operation.
 
         """
+        # TODO(b/452366836): adjust sample if needed to match pyarrow semantics.
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
     def __pow__(self, other):
@@ -4055,7 +4056,7 @@ def rpow(self, other) -> Series:
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> a = bpd.Series([1, 1, 1, np.nan], index=['a', 'b', 'c', 'd'])
             >>> a
             a     1.0
@@ -4610,7 +4611,7 @@ def quantile(
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series([1, 2, 3, 4])
             >>> s.quantile(.5)
             np.float64(2.5)
@@ -5290,7 +5291,7 @@ def str(self):
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> s = bpd.Series(["A_Str_Series"])
             >>> s
             0    A_Str_Series
@@ -5317,7 +5318,7 @@ def plot(self):
 
         **Examples:**
 
-
+            >>> import bigframes.pandas as bpd
             >>> ser = bpd.Series([1, 2, 3, 3])
             >>> plot = ser.plot(kind='hist', title="My plot")
             >>> plot

third_party/bigframes_vendored/pandas/core/tools/timedeltas.py

@@ -54,9 +54,9 @@ def to_timedelta(
 
     **Examples:**
 
-
     Converting a Scalar to timedelta
 
+        >>> import bigframes.pandas as bpd
         >>> scalar = 2
         >>> bpd.to_timedelta(scalar, unit='s')
         Timedelta('0 days 00:00:02')