Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/6601#discussion_r31591940
--- Diff: python/pyspark/sql/context.py ---
@@ -378,39 +378,12 @@ def parquetFile(self, *paths):
jdf = self._ssql_ctx.parquetFile(jpaths)
return DataFrame(jdf, self)
- @since(1.0)
def jsonFile(self, path, schema=None, samplingRatio=1.0):
"""Loads a text file storing one JSON object per line as a
:class:`DataFrame`.
- If the schema is provided, applies the given schema to this JSON
dataset.
- Otherwise, it samples the dataset with ratio ``samplingRatio`` to
determine the schema.
-
- >>> import tempfile, shutil
- >>> jsonFile = tempfile.mkdtemp()
- >>> shutil.rmtree(jsonFile)
- >>> with open(jsonFile, 'w') as f:
- ... f.writelines(jsonStrings)
- >>> df1 = sqlContext.jsonFile(jsonFile)
- >>> df1.printSchema()
- root
- |-- field1: long (nullable = true)
- |-- field2: string (nullable = true)
- |-- field3: struct (nullable = true)
- | |-- field4: long (nullable = true)
-
- >>> from pyspark.sql.types import *
- >>> schema = StructType([
- ... StructField("field2", StringType()),
- ... StructField("field3",
- ... StructType([StructField("field5",
ArrayType(IntegerType()))]))])
- >>> df2 = sqlContext.jsonFile(jsonFile, schema)
- >>> df2.printSchema()
- root
- |-- field2: string (nullable = true)
- |-- field3: struct (nullable = true)
- | |-- field5: array (nullable = true)
- | | |-- element: integer (containsNull = true)
+ .. note:: Deprecated in 1.4, use :func:`DataFrameReader.json`
instead.
--- End diff --
Same as parquetFile().
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
