Spark的简介&应用

pip install pysparkd.

text_file = sc.textFile("hdfs://...")
counts = text_file.flatMap(lambda line: line.split(" ")) \
             .map(lambda word: (word, 1)) \
             .reduceByKey(lambda a, b: a + b)
counts.saveAsTextFile("hdfs://...")

def inside(p):
    x, y = random.random(), random.random()
    return x*x + y*y < 1

count = sc.parallelize(xrange(0, NUM_SAMPLES)) \
             .filter(inside).count()
print "Pi is roughly %f" % (4.0 * count / NUM_SAMPLES)

extFile = sc.textFile("hdfs://...")

# Creates a DataFrame having a single column named "line"
df = textFile.map(lambda r: Row(r)).toDF(["line"])
errors = df.filter(col("line").like("%ERROR%"))
# Counts all the errors
errors.count()
# Counts errors mentioning MySQL
errors.filter(col("line").like("%MySQL%")).count()
# Fetches the MySQL errors as an array of strings
errors.filter(col("line").like("%MySQL%")).collect()

# Creates a DataFrame based on a table named "people"
# stored in a MySQL database.
url = \
  "jdbc:mysql://yourIP:yourPort/test?user=yourUsername;password=yourPassword"
df = sqlContext \
  .read \
  .format("jdbc") \
  .option("url", url) \
  .option("dbtable", "people") \
  .load()

# Looks the schema of this DataFrame.
df.printSchema()

# Counts people by age
countsByAge = df.groupBy("age").count()
countsByAge.show()

# Saves countsByAge to S3 in the JSON format.
countsByAge.write.format("json").save("s3a://...")

# Every record of this DataFrame contains the label and
# features represented by a vector.
df = sqlContext.createDataFrame(data, ["label", "features"])

# Set parameters for the algorithm.
# Here, we limit the number of iterations to 10.
lr = LogisticRegression(maxIter=10)

# Fit the model to the data.
model = lr.fit(df)

# Given a dataset, predict each point's label, and show the results.
model.transform(df).show()

from pyspark.mllib.regression import LabeledPoint, LinearRegressionWithSGD, LinearRegressionModel

# Load and parse the data
def parsePoint(line):
    values = [float(x) for x in line.replace(',', ' ').split(' ')]
    return LabeledPoint(values[0], values[1:])

data = sc.textFile("data/mllib/ridge-data/lpsa.data")
parsedData = data.map(parsePoint)

# Build the model
model = LinearRegressionWithSGD.train(parsedData, iterations=100, step=0.00000001)

# Evaluate the model on training data
valuesAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
MSE = valuesAndPreds \
    .map(lambda vp: (vp[0] - vp[1])**2) \
    .reduce(lambda x, y: x + y) / valuesAndPreds.count()
print("Mean Squared Error = " + str(MSE))

# Save and load model
model.save(sc, "target/tmp/pythonLinearRegressionWithSGDModel")
sameModel = LinearRegressionModel.load(sc, "target/tmp/pythonLinearRegressionWithSGDModel")

from pyspark.mllib.classification import LogisticRegressionWithLBFGS, LogisticRegressionModel
from pyspark.mllib.regression import LabeledPoint

# Load and parse the data
def parsePoint(line):
    values = [float(x) for x in line.split(' ')]
    return LabeledPoint(values[0], values[1:])

data = sc.textFile("data/mllib/sample_svm_data.txt")
parsedData = data.map(parsePoint)

# Build the model
model = LogisticRegressionWithLBFGS.train(parsedData)

# Evaluating the model on training data
labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda lp: lp[0] != lp[1]).count() / float(parsedData.count())
print("Training Error = " + str(trainErr))

# Save and load model
model.save(sc, "target/tmp/pythonLogisticRegressionWithLBFGSModel")
sameModel = LogisticRegressionModel.load(sc,
                                         "target/tmp/pythonLogisticRegressionWithLBFGSModel")