CSV 文件

# spark is from the previous example
sc = spark.sparkContext

# A CSV dataset is pointed to by path.
# The path can be either a single CSV file or a directory of CSV files
path = "examples/src/main/resources/people.csv"

df = spark.read.csv(path)
df.show()
# +------------------+
# |               _c0|
# +------------------+
# |      name;age;job|
# |Jorge;30;Developer|
# |  Bob;32;Developer|
# +------------------+

# Read a csv with delimiter, the default delimiter is ","
df2 = spark.read.option("delimiter", ";").csv(path)
df2.show()
# +-----+---+---------+
# |  _c0|_c1|      _c2|
# +-----+---+---------+
# | name|age|      job|
# |Jorge| 30|Developer|
# |  Bob| 32|Developer|
# +-----+---+---------+

# Read a csv with delimiter and a header
df3 = spark.read.option("delimiter", ";").option("header", True).csv(path)
df3.show()
# +-----+---+---------+
# | name|age|      job|
# +-----+---+---------+
# |Jorge| 30|Developer|
# |  Bob| 32|Developer|
# +-----+---+---------+

# You can also use options() to use multiple options
df4 = spark.read.options(delimiter=";", header=True).csv(path)

# "output" is a folder which contains multiple csv files and a _SUCCESS file.
df3.write.csv("output")

# Read all files in a folder, please make sure only CSV files should present in the folder.
folderPath = "examples/src/main/resources"
df5 = spark.read.csv(folderPath)
df5.show()
# Wrong schema because non-CSV files are read
# +-----------+
# |        _c0|
# +-----------+
# |238val_238|
# |  86val_86|
# |311val_311|
# |  27val_27|
# |165val_165|
# +-----------+

// A CSV dataset is pointed to by path.
// The path can be either a single CSV file or a directory of CSV files
val path = "examples/src/main/resources/people.csv"

val df = spark.read.csv(path)
df.show()
// +------------------+
// |               _c0|
// +------------------+
// |      name;age;job|
// |Jorge;30;Developer|
// |  Bob;32;Developer|
// +------------------+

// Read a csv with delimiter, the default delimiter is ","
val df2 = spark.read.option("delimiter", ";").csv(path)
df2.show()
// +-----+---+---------+
// |  _c0|_c1|      _c2|
// +-----+---+---------+
// | name|age|      job|
// |Jorge| 30|Developer|
// |  Bob| 32|Developer|
// +-----+---+---------+

// Read a csv with delimiter and a header
val df3 = spark.read.option("delimiter", ";").option("header", "true").csv(path)
df3.show()
// +-----+---+---------+
// | name|age|      job|
// +-----+---+---------+
// |Jorge| 30|Developer|
// |  Bob| 32|Developer|
// +-----+---+---------+

// You can also use options() to use multiple options
val df4 = spark.read.options(Map("delimiter"->";", "header"->"true")).csv(path)

// "output" is a folder which contains multiple csv files and a _SUCCESS file.
df3.write.csv("output")

// Read all files in a folder, please make sure only CSV files should present in the folder.
val folderPath = "examples/src/main/resources";
val df5 = spark.read.csv(folderPath);
df5.show();
// Wrong schema because non-CSV files are read
// +-----------+
// |        _c0|
// +-----------+
// |238val_238|
// |  86val_86|
// |311val_311|
// |  27val_27|
// |165val_165|
// +-----------+

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

// A CSV dataset is pointed to by path.
// The path can be either a single CSV file or a directory of CSV files
String path = "examples/src/main/resources/people.csv";

Dataset<Row> df = spark.read().csv(path);
df.show();
// +------------------+
// |               _c0|
// +------------------+
// |      name;age;job|
// |Jorge;30;Developer|
// |  Bob;32;Developer|
// +------------------+

// Read a csv with delimiter, the default delimiter is ","
Dataset<Row> df2 = spark.read().option("delimiter", ";").csv(path);
df2.show();
// +-----+---+---------+
// |  _c0|_c1|      _c2|
// +-----+---+---------+
// | name|age|      job|
// |Jorge| 30|Developer|
// |  Bob| 32|Developer|
// +-----+---+---------+

// Read a csv with delimiter and a header
Dataset<Row> df3 = spark.read().option("delimiter", ";").option("header", "true").csv(path);
df3.show();
// +-----+---+---------+
// | name|age|      job|
// +-----+---+---------+
// |Jorge| 30|Developer|
// |  Bob| 32|Developer|
// +-----+---+---------+

// You can also use options() to use multiple options
java.util.Map<String, String> optionsMap = new java.util.HashMap<String, String>();
optionsMap.put("delimiter",";");
optionsMap.put("header","true");
Dataset<Row> df4 = spark.read().options(optionsMap).csv(path);

// "output" is a folder which contains multiple csv files and a _SUCCESS file.
df3.write().csv("output");

// Read all files in a folder, please make sure only CSV files should present in the folder.
String folderPath = "examples/src/main/resources";
Dataset<Row> df5 = spark.read().csv(folderPath);
df5.show();
// Wrong schema because non-CSV files are read
// +-----------+
// |        _c0|
// +-----------+
// |238val_238|
// |  86val_86|
// |311val_311|
// |  27val_27|
// |165val_165|
// +-----------+