Updating Python code from python2 to python3

code/A_Gentle_Introduction_to_Spark-Chapter_3_A_Tour_of_Sparks_Toolset.py

@@ -128,7 +128,7 @@
 from pyspark.ml.clustering import KMeans
 kmeans = KMeans()\
   .setK(20)\
-  .setSeed(1L)
+  .setSeed(1)
 
 
 # COMMAND ----------

code/Advanced_Analytics_and_Machine_Learning-Chapter_24_Advanced_Analytics_and_Machine_Learning.py

@@ -38,7 +38,7 @@
 
 # COMMAND ----------
 
-print lr.explainParams()
+print(lr.explainParams())
 
 
 # COMMAND ----------

code/Advanced_Analytics_and_Machine_Learning-Chapter_26_Classification.py

@@ -6,20 +6,20 @@
 
 from pyspark.ml.classification import LogisticRegression
 lr = LogisticRegression()
-print lr.explainParams() # see all parameters
+print(lr.explainParams()) # see all parameters
 lrModel = lr.fit(bInput)
 
 
 # COMMAND ----------
 
-print lrModel.coefficients
-print lrModel.intercept
+print(lrModel.coefficients)
+print(lrModel.intercept)
 
 
 # COMMAND ----------
 
 summary = lrModel.summary
-print summary.areaUnderROC
+print(summary.areaUnderROC)
 summary.roc.show()
 summary.pr.show()
 
@@ -33,31 +33,31 @@
 
 from pyspark.ml.classification import DecisionTreeClassifier
 dt = DecisionTreeClassifier()
-print dt.explainParams()
+print(dt.explainParams())
 dtModel = dt.fit(bInput)
 
 
 # COMMAND ----------
 
 from pyspark.ml.classification import RandomForestClassifier
 rfClassifier = RandomForestClassifier()
-print rfClassifier.explainParams()
+print(rfClassifier.explainParams())
 trainedModel = rfClassifier.fit(bInput)
 
 
 # COMMAND ----------
 
 from pyspark.ml.classification import GBTClassifier
 gbtClassifier = GBTClassifier()
-print gbtClassifier.explainParams()
+print(gbtClassifier.explainParams())
 trainedModel = gbtClassifier.fit(bInput)
 
 
 # COMMAND ----------
 
 from pyspark.ml.classification import NaiveBayes
 nb = NaiveBayes()
-print nb.explainParams()
+print(nb.explainParams())
 trainedModel = nb.fit(bInput.where("label != 0"))
 
 
@@ -72,9 +72,9 @@
 
 # COMMAND ----------
 
-print metrics.areaUnderPR
-print metrics.areaUnderROC
-print "Receiver Operating Characteristic"
+print(metrics.areaUnderPR)
+print(metrics.areaUnderROC)
+print("Receiver Operating Characteristic")
 metrics.roc.toDF().show()
 
 

code/Advanced_Analytics_and_Machine_Learning-Chapter_27_Regression.py

@@ -5,18 +5,18 @@
 
 from pyspark.ml.regression import LinearRegression
 lr = LinearRegression().setMaxIter(10).setRegParam(0.3).setElasticNetParam(0.8)
-print lr.explainParams()
+print(lr.explainParams())
 lrModel = lr.fit(df)
 
 
 # COMMAND ----------
 
 summary = lrModel.summary
 summary.residuals.show()
-print summary.totalIterations
-print summary.objectiveHistory
-print summary.rootMeanSquaredError
-print summary.r2
+print(summary.totalIterations)
+print(summary.objectiveHistory)
+print(summary.rootMeanSquaredError)
+print(summary.r2)
 
 
 # COMMAND ----------
@@ -28,15 +28,15 @@
   .setMaxIter(10)\
   .setRegParam(0.3)\
   .setLinkPredictionCol("linkOut")
-print glr.explainParams()
+print(glr.explainParams())
 glrModel = glr.fit(df)
 
 
 # COMMAND ----------
 
 from pyspark.ml.regression import DecisionTreeRegressor
 dtr = DecisionTreeRegressor()
-print dtr.explainParams()
+print(dtr.explainParams())
 dtrModel = dtr.fit(df)
 
 
@@ -45,10 +45,10 @@
 from pyspark.ml.regression import RandomForestRegressor
 from pyspark.ml.regression import GBTRegressor
 rf =  RandomForestRegressor()
-print rf.explainParams()
+print(rf.explainParams())
 rfModel = rf.fit(df)
 gbt = GBTRegressor()
-print gbt.explainParams()
+print(gbt.explainParams())
 gbtModel = gbt.fit(df)
 
 
@@ -79,11 +79,11 @@
 out = model.transform(df)\
   .select("prediction", "label").rdd.map(lambda x: (float(x[0]), float(x[1])))
 metrics = RegressionMetrics(out)
-print "MSE: " + str(metrics.meanSquaredError)
-print "RMSE: " + str(metrics.rootMeanSquaredError)
-print "R-squared: " + str(metrics.r2)
-print "MAE: " + str(metrics.meanAbsoluteError)
-print "Explained variance: " + str(metrics.explainedVariance)
+print("MSE: " + str(metrics.meanSquaredError))
+print("RMSE: " + str(metrics.rootMeanSquaredError))
+print("R-squared: " + str(metrics.r2))
+print("MAE: " + str(metrics.meanAbsoluteError))
+print("Explained variance: " + str(metrics.explainedVariance))
 
 
 # COMMAND ----------

code/Advanced_Analytics_and_Machine_Learning-Chapter_28_Recommendation.py

@@ -15,7 +15,7 @@
   .setUserCol("userId")\
   .setItemCol("movieId")\
   .setRatingCol("rating")
-print als.explainParams()
+print(als.explainParams())
 alsModel = als.fit(training)
 predictions = alsModel.transform(test)
 

code/Advanced_Analytics_and_Machine_Learning-Chapter_29_Unsupervised_Learning.py

@@ -18,14 +18,14 @@
 
 from pyspark.ml.clustering import KMeans
 km = KMeans().setK(5)
-print km.explainParams()
+print(km.explainParams())
 kmModel = km.fit(sales)
 
 
 # COMMAND ----------
 
 summary = kmModel.summary
-print summary.clusterSizes # number of points
+print(summary.clusterSizes) # number of points
 kmModel.computeCost(sales)
 centers = kmModel.clusterCenters()
 print("Cluster Centers: ")
@@ -43,7 +43,7 @@
 # COMMAND ----------
 
 summary = bkmModel.summary
-print summary.clusterSizes # number of points
+print(summary.clusterSizes) # number of points
 kmModel.computeCost(sales)
 centers = kmModel.clusterCenters()
 print("Cluster Centers: ")
@@ -55,14 +55,14 @@
 
 from pyspark.ml.clustering import GaussianMixture
 gmm = GaussianMixture().setK(5)
-print gmm.explainParams()
+print(gmm.explainParams())
 model = gmm.fit(sales)
 
 
 # COMMAND ----------
 
 summary = model.summary
-print model.weights
+print(model.weights)
 model.gaussiansDF.show()
 summary.cluster.show()
 summary.clusterSizes
@@ -89,7 +89,7 @@
 
 from pyspark.ml.clustering import LDA
 lda = LDA().setK(10).setMaxIter(5)
-print lda.explainParams()
+print(lda.explainParams())
 model = lda.fit(prepped)
 
 

code/Advanced_Analytics_and_Machine_Learning-Chapter_30_Graph_Analysis.py

@@ -21,9 +21,9 @@
 
 # COMMAND ----------
 
-print "Total Number of Stations: " + str(stationGraph.vertices.count())
-print "Total Number of Trips in Graph: " + str(stationGraph.edges.count())
-print "Total Number of Trips in Original Data: " + str(tripData.count())
+print("Total Number of Stations: " + str(stationGraph.vertices.count()))
+print("Total Number of Trips in Graph: " + str(stationGraph.edges.count()))
+print("Total Number of Trips in Original Data: " + str(tripData.count()))
 
 
 # COMMAND ----------

code/Production_Applications-Chapter_16_Spark_Applications.py

@@ -1,4 +1,4 @@
-from __future__ import print_function
+
 if __name__ == '__main__':
     from pyspark.sql import SparkSession
     spark = SparkSession.builder \

code/Structured_APIs-Chapter_5_Basic_Structured_Operations.py

@@ -190,8 +190,8 @@
 from pyspark.sql import Row
 schema = df.schema
 newRows = [
-  Row("New Country", "Other Country", 5L),
-  Row("New Country 2", "Other Country 3", 1L)
+  Row("New Country", "Other Country", 5),
+  Row("New Country 2", "Other Country 3", 1)
 ]
 parallelizedRows = spark.sparkContext.parallelize(newRows)
 newDF = spark.createDataFrame(parallelizedRows, schema)

code/Structured_APIs-Chapter_9_Data_Sources.py

@@ -112,8 +112,8 @@
 # COMMAND ----------
 
 colName = "count"
-lowerBound = 0L
-upperBound = 348113L # this is the max count in our database
+lowerBound = 0
+upperBound = 348113 # this is the max count in our database
 numPartitions = 10