def map_annotations_cols(dataframe: DataFrame,
f,
columns: list,
output_column: str,
annotatyon_type: str,
output_type: DataType = Annotation.arrayType()):
return dataframe.withColumn(
output_column,
map_annotations_array(f, output_type)(array(*columns)).alias(
output_column, metadata={'annotatorType': annotatyon_type}))
def map_annotations_cols(dataframe: DataFrame,
f,
columns: list,
output_column: str,
annotatyon_type: str,
output_type: DataType = Annotation.arrayType()):
"""Creates a Spark UDF to map over multiple columns of Annotation results.
Parameters
----------
dataframe : DataFrame
Input DataFrame
f : function
Function to apply to the column
columns : list
Name of the input column
output_column : str
Name of the output column
annotatyon_type : str
Annotator type
output_type : DataType, optional
Output type, by default Annotation.arrayType()
Returns
-------
:class:`pyspark.sql.DataFrame`
Transformed DataFrame
Examples
--------
>>> from sparknlp.pretrained import PretrainedPipeline
>>> from sparknlp.functions import *
>>> explain_document_pipeline = PretrainedPipeline("explain_document_dl")
>>> data = spark.createDataFrame([["U.N. official Ekeus heads for Baghdad."]]).toDF("text")
>>> result = explain_document_pipeline.transform(data)
>>> chunks_df = map_annotations_cols(
... result,
... lambda x: [
... Annotation("tag", a.begin, a.end, a.result, a.metadata, a.embeddings)
... for a in x
... ],
... ["pos", "ner"],
... "tags",
... "chunk"
... )
>>> chunks_df.selectExpr("explode(tags)").show(truncate=False)
+-------------------------------------------+
|col |
+-------------------------------------------+
|[tag, 0, 2, NNP, [word -> U.N], []] |
|[tag, 3, 3, ., [word -> .], []] |
|[tag, 5, 12, JJ, [word -> official], []] |
|[tag, 14, 18, NNP, [word -> Epeus], []] |
|[tag, 20, 24, VBZ, [word -> heads], []] |
|[tag, 26, 28, IN, [word -> for], []] |
|[tag, 30, 36, NNP, [word -> Baghdad], []] |
|[tag, 37, 37, ., [word -> .], []] |
|[tag, 0, 2, B-ORG, [word -> U.N], []] |
|[tag, 3, 3, O, [word -> .], []] |
|[tag, 5, 12, O, [word -> official], []] |
|[tag, 14, 18, B-PER, [word -> Ekeus], []] |
|[tag, 20, 24, O, [word -> heads], []] |
|[tag, 26, 28, O, [word -> for], []] |
|[tag, 30, 36, B-LOC, [word -> Baghdad], []]|
|[tag, 37, 37, O, [word -> .], []] |
+-------------------------------------------+
"""
return dataframe.withColumn(
output_column,
map_annotations_array(f, output_type)(array(*columns)).alias(
output_column, metadata={'annotatorType': annotatyon_type}))
def map_annotations_col(dataframe: DataFrame,
f,
column: str,
output_column: str,
annotatyon_type: str,
output_type: DataType = Annotation.arrayType()):
"""Creates a Spark UDF to map over a column of Annotation results.
Parameters
----------
dataframe : DataFrame
Input DataFrame
f : function
Function to apply to the column
column : str
Name of the input column
output_column : str
Name of the output column
annotatyon_type : str
Annotator type
output_type : DataType, optional
Output type, by default Annotation.arrayType()
Returns
-------
:class:`pyspark.sql.DataFrame`
Transformed DataFrame
Examples
--------
>>> from sparknlp.pretrained import PretrainedPipeline
>>> from sparknlp.functions import *
>>> explain_document_pipeline = PretrainedPipeline("explain_document_dl")
>>> data = spark.createDataFrame([["U.N. official Ekeus heads for Baghdad."]]).toDF("text")
>>> result = explain_document_pipeline.transform(data)
>>> chunks_df = map_annotations_col(
... result,
... lambda x: [
... Annotation("chunk", a.begin, a.end, a.result, a.metadata, a.embeddings)
... for a in x
... ],
... "pos",
... "pos_chunk",
... "chunk",
... )
>>> chunks_df.selectExpr("explode(pos_chunk)").show()
+--------------------+
| col|
+--------------------+
|[chunk, 0, 2, NNP...|
|[chunk, 3, 3, ., ...|
|[chunk, 5, 12, JJ...|
|[chunk, 14, 18, N...|
|[chunk, 20, 24, V...|
|[chunk, 26, 28, I...|
|[chunk, 30, 36, N...|
|[chunk, 37, 37, ....|
+--------------------+
"""
return dataframe.withColumn(
output_column,
map_annotations(f, output_type)(column).alias(
output_column, metadata={'annotatorType': annotatyon_type}))