pyspark -ML Pipelines

参考地址：

1、http://spark.apache.org/docs/latest/ml-guide.html

2、https://github.com/apache/spark/tree/v2.2.0

3、http://spark.apache.org/docs/latest/ml-pipeline.html

Code examples

Example: Estimator, Transformer, and Param

from pyspark.ml.linalg import Vectors
from pyspark.ml.classification import LogisticRegression

# Prepare training data from a list of (label, features) tuples.
training = spark.createDataFrame([
    (1.0, Vectors.dense([0.0, 1.1, 0.1])),
    (0.0, Vectors.dense([2.0, 1.0, -1.0])),
    (0.0, Vectors.dense([2.0, 1.3, 1.0])),
    (1.0, Vectors.dense([0.0, 1.2, -0.5]))], ["label", "features"])

# Create a LogisticRegression instance. This instance is an Estimator.
lr = LogisticRegression(maxIter=10, regParam=0.01)
# Print out the parameters, documentation, and any default values.
print("LogisticRegression parameters:\n" + lr.explainParams() + "\n")

# Learn a LogisticRegression model. This uses the parameters stored in lr.
model1 = lr.fit(training)

# Since model1 is a Model (i.e., a transformer produced by an Estimator),
# we can view the parameters it used during fit().
# This prints the parameter (name: value) pairs, where names are unique IDs for this
# LogisticRegression instance.
print("Model 1 was fit using parameters: ")
print(model1.extractParamMap())

# We may alternatively specify parameters using a Python dictionary as a paramMap
paramMap = {lr.maxIter: 20}
paramMap[lr.maxIter] = 30  # Specify 1 Param, overwriting the original maxIter.
paramMap.update({lr.regParam: 0.1, lr.threshold: 0.55})  # Specify multiple Params.

# You can combine paramMaps, which are python dictionaries.
paramMap2 = {lr.probabilityCol: "myProbability"}  # Change output column name
paramMapCombined = paramMap.copy()
paramMapCombined.update(paramMap2)

# Now learn a new model using the paramMapCombined parameters.
# paramMapCombined overrides all parameters set earlier via lr.set* methods.
model2 = lr.fit(training, paramMapCombined)
print("Model 2 was fit using parameters: ")
print(model2.extractParamMap())

# Prepare test data
test = spark.createDataFrame([
    (1.0, Vectors.dense([-1.0, 1.5, 1.3])),
    (0.0, Vectors.dense([3.0, 2.0, -0.1])),
    (1.0, Vectors.dense([0.0, 2.2, -1.5]))], ["label", "features"])

# Make predictions on test data using the Transformer.transform() method.
# LogisticRegression.transform will only use the 'features' column.
# Note that model2.transform() outputs a "myProbability" column instead of the usual
# 'probability' column since we renamed the lr.probabilityCol parameter previously.
prediction = model2.transform(test)
result = prediction.select("features", "label", "myProbability", "prediction") \
    .collect()

for row in result:
    print("features=%s, label=%s -> prob=%s, prediction=%s"
          % (row.features, row.label, row.myProbability, row.prediction))

Example: Pipeline

from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer

# Prepare training documents from a list of (id, text, label) tuples.
training = spark.createDataFrame([
    (0, "a b c d e spark", 1.0),
    (1, "b d", 0.0),
    (2, "spark f g h", 1.0),
    (3, "hadoop mapreduce", 0.0)
], ["id", "text", "label"])

# Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
tokenizer = Tokenizer(inputCol="text", outputCol="words")
hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features")
lr = LogisticRegression(maxIter=10, regParam=0.001)
pipeline = Pipeline(stages=[tokenizer, hashingTF, lr])

# Fit the pipeline to training documents.
model = pipeline.fit(training)

# Prepare test documents, which are unlabeled (id, text) tuples.
test = spark.createDataFrame([
    (4, "spark i j k"),
    (5, "l m n"),
    (6, "spark hadoop spark"),
    (7, "apache hadoop")
], ["id", "text"])

# Make predictions on test documents and print columns of interest.
prediction = model.transform(test)
selected = prediction.select("id", "text", "probability", "prediction")
for row in selected.collect():
    rid, text, prob, prediction = row
    print("(%d, %s) --> prob=%s, prediction=%f" % (rid, text, str(prob), prediction))