pyspark 广义线性回归

from pyspark.ml.regression import GeneralizedLinearRegression
from pyspark.sql import SparkSession

spark= SparkSession\
                .builder \
                .appName("dataFrame") \
                .getOrCreate()

# Load training data
dataset = spark.read.format("libsvm")\
    .load("/home/luogan/lg/softinstall/spark-2.2.0-bin-hadoop2.7/data/mllib/sample_linear_regression_data.txt")

glr = GeneralizedLinearRegression(family="gaussian", link="identity", maxIter=10, regParam=0.3)

# Fit the model
model = glr.fit(dataset)

# Print the coefficients and intercept for generalized linear regression model
print("Coefficients: " + str(model.coefficients))
print("Intercept: " + str(model.intercept))

# Summarize the model over the training set and print out some metrics
summary = model.summary
print("Coefficient Standard Errors: " + str(summary.coefficientStandardErrors))
print("T Values: " + str(summary.tValues))
print("P Values: " + str(summary.pValues))
print("Dispersion: " + str(summary.dispersion))
print("Null Deviance: " + str(summary.nullDeviance))
print("Residual Degree Of Freedom Null: " + str(summary.residualDegreeOfFreedomNull))
print("Deviance: " + str(summary.deviance))
print("Residual Degree Of Freedom: " + str(summary.residualDegreeOfFreedom))
print("AIC: " + str(summary.aic))
print("Deviance Residuals: ")
summary.residuals().show()

Coefficients: [0.010541828081257216,0.8003253100560949,-0.7845165541420371,2.3679887171421914,0.5010002089857577,1.1222351159753026,-0.2926824398623296,-0.49837174323213035,-0.6035797180675657,0.6725550067187461]
Intercept: 0.14592176145232041
Coefficient Standard Errors: [0.7950428434287478, 0.8049713176546897, 0.7975916824772489, 0.8312649247659919, 0.7945436200517938, 0.8118992572197593, 0.7919506385542777, 0.7973378214726764, 0.8300714999626418, 0.7771333489686802, 0.463930109648428]
T Values: [0.013259446542269243, 0.9942283563442594, -0.9836067393599172, 2.848657084633759, 0.6305509179635714, 1.382234441029355, -0.3695715687490668, -0.6250446546128238, -0.7271418403049983, 0.8654306337661122, 0.31453393176593286]
P Values: [0.989426199114056, 0.32060241580811044, 0.3257943227369877, 0.004575078538306521, 0.5286281628105467, 0.16752945248679119, 0.7118614002322872, 0.5322327097421431, 0.467486325282384, 0.3872259825794293, 0.753249430501097]
Dispersion: 105.60988356821714
Null Deviance: 53229.3654338832
Residual Degree Of Freedom Null: 500
Deviance: 51748.8429484264
Residual Degree Of Freedom: 490
AIC: 3769.1895871765314
Deviance Residuals: 
+-------------------+
|  devianceResiduals|
+-------------------+
|-10.974359174246889|
| 0.8872320138420559|
| -4.596541837478908|
|-20.411667435019638|
|-10.270419345342642|
|-6.0156058956799905|
|-10.663939415849267|
| 2.1153960525024713|
| 3.9807132379137675|
|-17.225218272069533|
| -4.611647633532147|
| 6.4176669407698546|
| 11.407137945300537|
| -20.70176540467664|
| -2.683748540510967|
|-16.755494794232536|
|  8.154668342638725|
|-1.4355057987358848|
|-0.6435058688185704|
|  -1.13802589316832|
+-------------------+
only showing top 20 rows