Snowpark Migration Accelerator : Codes de problème pour Python¶

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])

df.write.options(nullValue="myVal", sep=",").csv("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])
#EWI: SPRKPY1089 => The pyspark.sql.readwriter.DataFrameWriter.options values in Snowpark may be different, so required validation might be needed.
df.write.options(nullValue="myVal", sep=",").csv("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])
#EWI: SPRKPY1089 => The pyspark.sql.readwriter.DataFrameWriter.options values in Snowpark may be different, so required validation might be needed.
df.write.options(nullValue="myVal", sep=",").csv("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])

df.write.options(header=True, sep=",").csv("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])
#EWI: SPRKPY1089 => The pyspark.sql.readwriter.DataFrameWriter.options values in Snowpark may be different, so required validation might be needed.
df.write.options(header=True, sep=",").csv("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])
#EWI: SPRKPY1089 => The pyspark.sql.readwriter.DataFrameWriter.options values in Snowpark may be different, so required validation might be needed.
df.write.csv("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])

df.write.options(nullValue="myVal", sep=",").json("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])
#EWI: SPRKPY1089 => The pyspark.sql.readwriter.DataFrameWriter.options values in Snowpark may be different, so required validation might be needed.
df.write.options(nullValue="myVal", sep=",").json("some_path")

df = spark.createDataFrame([(1, "myVal")], [2, "myVal2"], [None, "myVal3" ])
#EWI: SPRKPY1089 => The pyspark.sql.readwriter.DataFrameWriter.options values in Snowpark may be different, so required validation might be needed.
df.write.json("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])

df.write.option("sep", ",").csv("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])
#EWI: SPRKPY1088 => The pyspark.sql.readwriter.DataFrameWriter.option values in Snowpark may be different, so required validation might be needed.
df.write.option("sep", ",").csv("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])
#EWI: SPRKPY1088 => The pyspark.sql.readwriter.DataFrameWriter.option values in Snowpark may be different, so required validation might be needed.
df.write.option("sep", ",").csv("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])

df.write.option("header", True).csv("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])
#EWI: SPRKPY1088 => The pyspark.sql.readwriter.DataFrameWriter.option values in Snowpark may be different, so required validation might be needed.
df.write.option("header", True).csv("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])
#EWI: SPRKPY1088 => The pyspark.sql.readwriter.DataFrameWriter.option values in Snowpark may be different, so required validation might be needed.
df.write.csv("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])

df.write.option("sep", ",").json("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])
#EWI: SPRKPY1088 => The pyspark.sql.readwriter.DataFrameWriter.option values in Snowpark may be different, so required validation might be needed.
df.write.option("sep", ",").json("some_path")

df = spark.createDataFrame([(100, "myVal")], ["ID", "Value"])
#EWI: SPRKPY1088 => The pyspark.sql.readwriter.DataFrameWriter.option values in Snowpark may be different, so required validation might be needed.
df.write.json("some_path")

df.write.csv(file_path, mode="overwrite")

df.write.csv(file_path, format_type_options = dict(compression = "None"), overwrite = True)

df.write.csv(file_path, mode=myVal)

#EWI: SPRKPY1070 => The 'mode' argument is transformed to 'overwrite', check the variable value and set the corresponding bool value.
df.write.csv(file_path, format_type_options = dict(compression = "None"), overwrite = myVal)

df.write.csv(file_path, format_type_options = dict(compression = "None"), overwrite = True)

path_csv_file = "/path/to/file.csv"

data = [
        ("John", 30, "New York"),
        ("Jane", 25, "San Francisco")
    ]

df = my_session.createDataFrame(data, schema=["Name", "Age", "City"])

df.write.save(path_csv_file, format="csv")
df.write.save(path_csv_file, format="csv", mode="overwrite")
df.write.save(path_csv_file, format="csv", mode="overwrite", lineSep="\r\n", dateFormat="YYYY/MM/DD")
df.write.save(path_csv_file, format="csv", mode="overwrite", partitionBy="City", lineSep="\r\n", dateFormat="YYYY/MM/DD")

path_csv_file = "/path/to/file.csv"

data = [
        ("John", 30, "New York"),
        ("Jane", 25, "San Francisco")
    ]

df = my_session.createDataFrame(data, schema=["Name", "Age", "City"])

#EWI: SPRKPY1083 => The pyspark.sql.readwriter.DataFrameWriter.save function is not supported. A workaround is to use Snowpark DataFrameWriter copy_into_location method instead.
df.write.save(path_csv_file, format="csv")
#EWI: SPRKPY1083 => The pyspark.sql.readwriter.DataFrameWriter.save function is not supported. A workaround is to use Snowpark DataFrameWriter copy_into_location method instead.
df.write.save(path_csv_file, format="csv", mode="overwrite")
#EWI: SPRKPY1083 => The pyspark.sql.readwriter.DataFrameWriter.save function is not supported. A workaround is to use Snowpark DataFrameWriter copy_into_location method instead.
df.write.save(path_csv_file, format="csv", mode="overwrite", lineSep="\r\n", dateFormat="YYYY/MM/DD")
#EWI: SPRKPY1083 => The pyspark.sql.readwriter.DataFrameWriter.save function is not supported. A workaround is to use Snowpark DataFrameWriter copy_into_location method instead.
df.write.save(path_csv_file, format="csv", mode="overwrite", partitionBy="City", lineSep="\r\n", dateFormat="YYYY/MM/DD")

data = [
        ("John", 30, "New York"),
        ("Jane", 25, "San Francisco")
    ]
df = spark.createDataFrame(data, schema=["Name", "Age", "City"])

## Stage creation

temp_stage = f'{Session.get_fully_qualified_current_schema()}.{_generate_prefix("TEMP_STAGE")}'
my_session.sql(f'CREATE TEMPORARY STAGE IF NOT EXISTS {temp_stage}').show()
my_session.file.put(f"file:///path/to/file.csv", f"@{temp_stage}")
stage_file_path = f"{temp_stage}file.csv"

## Using csv method
df.write.csv(stage_file_path)

## Using copy_into_location method
df.write.copy_into_location(stage_file_path, file_format_type="csv")

data = [
        ("John", 30, "New York"),
        ("Jane", 25, "San Francisco")
    ]
df = spark.createDataFrame(data, schema=["Name", "Age", "City"])

## Using csv method
df.write.mode("overwrite").csv(temp_stage)

## Using copy_into_location method
df.write.mode("overwrite").copy_into_location(temp_stage, file_format_type="csv")

data = [
        ("John", 30, "New York"),
        ("Jane", 25, "San Francisco")
    ]
df = spark.createDataFrame(data, schema=["Name", "Age", "City"])

## Using csv method
df.write.csv(temp_stage, partition_by="City")

## Using copy_into_location method
df.write.copy_into_location(temp_stage, file_format_type="csv", partition_by="City")

data = [
        ("John", 30, "New York"),
        ("Jane", 25, "San Francisco")
    ]
df = spark.createDataFrame(data, schema=["Name", "Age", "City"])
optionsParam = {"RECORD_DELIMITER": "\r\n", "DATE_FORMAT": "YYYY/MM/DD"}

## Using csv method
df.write.csv(stage, format_type_options=optionsParam)

## Using copy_into_location method
df.write.csv(stage, file_format_type="csv", format_type_options=optionsParam)

F.split('col', '\\|')

#EWI: SPRKPY1044 => pyspark.sql.functions.split has a workaround, see the documentation for more info
F.split('col', '\\|')

F.split('col', lit('\\|'))
## the result of lit will be sent to the split function

from pyspark.sql import SparkSession
spark = SparkSession.builder.getOrCreate()

df1 = spark.read.format('csv').load('/path/to/file')

from snowflake.snowpark import Session
spark = Session.builder.getOrCreate()

df1 = spark.read.csv('/path/to/file')

from snowflake.snowpark import Session
spark = Session.builder.getOrCreate()

df2 = spark.read.format('jdbc') \
    .option("driver", "com.mysql.cj.jdbc.Driver") \
    .option("url", "jdbc:mysql://localhost:3306/emp") \
    .option("dbtable", "employee") \
    .option("user", "root") \
    .option("password", "root") \
    .load()

from snowflake.snowpark import Session
spark = Session.builder.getOrCreate()

#EWI: SPRKPY1054 => pyspark.sql.readwriter.DataFrameReader.format with argument value "jdbc" is not supported.
#EWI: SPRKPY1002 => pyspark.sql.readwriter.DataFrameReader.load is not supported

df2 = spark.read.format('jdbc') \
    .option("driver", "com.mysql.cj.jdbc.Driver") \
    .option("url", "jdbc:mysql://localhost:3306/emp") \
    .option("dbtable", "employee") \
    .option("user", "root") \
    .option("password", "root") \
    .load()

from snowflake.snowpark import Session
spark = Session.builder.getOrCreate()

myFormat = 'csv'
df3 = spark.read.format(myFormat).load('/path/to/file')

from snowflake.snowpark import Session
spark = Session.builder.getOrCreate()

myFormat = 'csv'
#EWI: SPRKPY1054 => pyspark.sql.readwriter.DataFrameReader.format with argument value "" is not supported.
#EWI: SPRKPY1002 => pyspark.sql.readwriter.DataFrameReader.load is not supported
df3 = spark.read.format(myFormat).load('/path/to/file')

path_csv_file = "/path/to/file.csv"

schemaParam = StructType([
        StructField("Name", StringType(), True),
        StructField("Superhero", StringType(), True)
    ])

my_session.read.load(path_csv_file, "csv").show()
my_session.read.load(path_csv_file, "csv", schema=schemaParam).show()
my_session.read.load(path_csv_file, "csv", schema=schemaParam, lineSep="\r\n", dateFormat="YYYY/MM/DD").show()

path_csv_file = "/path/to/file.csv"

schemaParam = StructType([
        StructField("Name", StringType(), True),
        StructField("Superhero", StringType(), True)
    ])
#EWI: SPRKPY1082 => The pyspark.sql.readwriter.DataFrameReader.load function is not supported. A workaround is to use Snowpark DataFrameReader format specific method instead (avro csv, json, orc, parquet). The path parameter should be a stage location.

my_session.read.load(path_csv_file, "csv").show()
#EWI: SPRKPY1082 => The pyspark.sql.readwriter.DataFrameReader.load function is not supported. A workaround is to use Snowpark DataFrameReader format specific method instead (avro csv, json, orc, parquet). The path parameter should be a stage location.
my_session.read.load(path_csv_file, "csv", schema=schemaParam).show()
#EWI: The pyspark.sql.readwriter.DataFrameReader.load function is not supported. A workaround is to use Snowpark DataFrameReader format specific method instead (avro csv, json, orc, parquet). The path parameter should be a stage location.
my_session.read.load(path_csv_file, "csv", schema=schemaParam, lineSep="\r\n", dateFormat="YYYY/MM/DD").show()

path_csv_file = "/path/to/file.csv"

## Stage creation

temp_stage = f'{Session.get_fully_qualified_current_schema()}.{_generate_prefix("TEMP_STAGE")}'
my_session.sql(f'CREATE TEMPORARY STAGE IF NOT EXISTS {temp_stage}').show()
my_session.file.put(f"file:///path/to/file.csv", f"@{temp_stage}")
stage_file_path = f"{temp_stage}file.csv"

schemaParam = StructType([
        StructField("Name", StringType(), True),
        StructField("Superhero", StringType(), True)
    ])

my_session.read.csv(stage_file_path).show()

schemaParam = StructType([
        StructField("name", StringType(), True),
        StructField("city", StringType(), True)
    ])

df = my_session.read.schema(schemaParam).csv(temp_stage)

optionsParam = {"RECORD_DELIMITER": "\r\n", "DATE_FORMAT": "YYYY/MM/DD"}
df = my_session.read.options(optionsParam).csv(stage)