Update API docs.

PiperOrigin-RevId: 236202555

Author: paulgc17

g3doc/api_docs/python/tfdv/GenerateStatistics.md

@@ -37,7 +37,7 @@ Initializes the transform.
 
 #### Args:
 
-* <b>`options`</b>: Options for generating data statistics.
+* <b>`options`</b>: <a href="../tfdv/StatsOptions.md"><code>tfdv.StatsOptions</code></a> for generating data statistics.
 
 
 #### Raises:

g3doc/api_docs/python/tfdv/StatsOptions.md

@@ -42,7 +42,8 @@ __init__(
     num_quantiles_histogram_buckets=10,
     epsilon=0.01,
     infer_type_from_schema=False,
-    desired_batch_size=None
+    desired_batch_size=None,
+    enable_semantic_domain_stats=False
 )
 ```
 
@@ -95,6 +96,8 @@ Initializes statistics options.
       on CSV data.
 * <b>`desired_batch_size`</b>: An optional number of examples to include in each
     batch that is passed to the statistics generators.
+* <b>`enable_semantic_domain_stats`</b>: If True statistics for semantic domains are
+    generated (e.g: image, text domains).
 
 
 

g3doc/api_docs/python/tfdv/generate_statistics_from_csv.md

@@ -37,7 +37,7 @@ PTransform API directly instead.
 * <b>`output_path`</b>: The file path to output data statistics result to. If None, we
     use a temporary directory. It will be a TFRecord file containing a single
     data statistics proto, and can be read with the 'load_statistics' API.
-* <b>`stats_options`</b>: Options for generating data statistics.
+* <b>`stats_options`</b>: <a href="../tfdv/StatsOptions.md"><code>tfdv.StatsOptions</code></a> for generating data statistics.
 * <b>`pipeline_options`</b>: Optional beam pipeline options. This allows users to
     specify various beam pipeline execution parameters like pipeline runner
     (DirectRunner or DataflowRunner), cloud dataflow service project id, etc.

g3doc/api_docs/python/tfdv/generate_statistics_from_dataframe.md

@@ -8,7 +8,8 @@
 ``` python
 tfdv.generate_statistics_from_dataframe(
     dataframe,
-    stats_options=options.StatsOptions()
+    stats_options=options.StatsOptions(),
+    n_jobs=1
 )
 ```
 
@@ -20,7 +21,9 @@ as a pandas DataFrame.
 #### Args:
 
 * <b>`dataframe`</b>: Input pandas DataFrame.
-* <b>`stats_options`</b>: Options for generating data statistics.
+* <b>`stats_options`</b>: <a href="../tfdv/StatsOptions.md"><code>tfdv.StatsOptions</code></a> for generating data statistics.
+* <b>`n_jobs`</b>: Number of processes to run (defaults to 1). If -1 is provided,
+    uses the same number of processes as the number of CPU cores.
 
 
 #### Returns:

g3doc/api_docs/python/tfdv/generate_statistics_from_tfrecord.md

@@ -30,7 +30,7 @@ PTransform API directly instead.
 * <b>`output_path`</b>: The file path to output data statistics result to. If None, we
     use a temporary directory. It will be a TFRecord file containing a single
     data statistics proto, and can be read with the 'load_statistics' API.
-* <b>`stats_options`</b>: Options for generating data statistics.
+* <b>`stats_options`</b>: <a href="../tfdv/StatsOptions.md"><code>tfdv.StatsOptions</code></a> for generating data statistics.
 * <b>`pipeline_options`</b>: Optional beam pipeline options. This allows users to
     specify various beam pipeline execution parameters like pipeline runner
     (DirectRunner or DataflowRunner), cloud dataflow service project id, etc.

g3doc/api_docs/python/tfdv/validate_instance.md

@@ -22,8 +22,8 @@ If an optional `environment` is specified, the schema is filtered using the
 
 * <b>`instance`</b>: A single example in the form of a dict mapping a feature name to a
     numpy array.
-* <b>`options`</b>: Options for generating data statistics. This must contain a
-    schema.
+* <b>`options`</b>: <a href="../tfdv/StatsOptions.md"><code>tfdv.StatsOptions</code></a> for generating data statistics. This must
+    contain a schema.
 * <b>`environment`</b>: An optional string denoting the validation environment. Must be
     one of the default environments specified in the schema. In some cases
     introducing slight schema variations is necessary, for instance features

tensorflow_data_validation/api/stats_api.py

@@ -83,7 +83,7 @@ def __init__(
     """Initializes the transform.
 
     Args:
-      options: Options for generating data statistics.
+      options: `tfdv.StatsOptions` for generating data statistics.
 
     Raises:
       TypeError: If options is not of the expected type.

tensorflow_data_validation/api/validation_api.py

@@ -276,8 +276,8 @@ def validate_instance(
   Args:
     instance: A single example in the form of a dict mapping a feature name to a
       numpy array.
-    options: Options for generating data statistics. This must contain a
-      schema.
+    options: `tfdv.StatsOptions` for generating data statistics. This must
+      contain a schema.
     environment: An optional string denoting the validation environment. Must be
       one of the default environments specified in the schema. In some cases
       introducing slight schema variations is necessary, for instance features

tensorflow_data_validation/utils/stats_gen_lib.py

@@ -65,7 +65,7 @@ def generate_statistics_from_tfrecord(
     output_path: The file path to output data statistics result to. If None, we
       use a temporary directory. It will be a TFRecord file containing a single
       data statistics proto, and can be read with the 'load_statistics' API.
-    stats_options: Options for generating data statistics.
+    stats_options: `tfdv.StatsOptions` for generating data statistics.
     pipeline_options: Optional beam pipeline options. This allows users to
       specify various beam pipeline execution parameters like pipeline runner
       (DirectRunner or DataflowRunner), cloud dataflow service project id, etc.
@@ -128,7 +128,7 @@ def generate_statistics_from_csv(
     output_path: The file path to output data statistics result to. If None, we
       use a temporary directory. It will be a TFRecord file containing a single
       data statistics proto, and can be read with the 'load_statistics' API.
-    stats_options: Options for generating data statistics.
+    stats_options: `tfdv.StatsOptions` for generating data statistics.
     pipeline_options: Optional beam pipeline options. This allows users to
       specify various beam pipeline execution parameters like pipeline runner
       (DirectRunner or DataflowRunner), cloud dataflow service project id, etc.
@@ -182,7 +182,7 @@ def generate_statistics_from_dataframe(
 
   Args:
     dataframe: Input pandas DataFrame.
-    stats_options: Options for generating data statistics.
+    stats_options: `tfdv.StatsOptions` for generating data statistics.
     n_jobs: Number of processes to run (defaults to 1). If -1 is provided,
       uses the same number of processes as the number of CPU cores.