diff --git a/docs/mllib-collaborative-filtering.md b/docs/mllib-collaborative-filtering.md index 2094963392295b98050d3770ea9452e66be310a7..ef18cec9371d69489b9c926fe56eb169a7ca1cd8 100644 --- a/docs/mllib-collaborative-filtering.md +++ b/docs/mllib-collaborative-filtering.md @@ -192,12 +192,11 @@ We use the default ALS.train() method which assumes ratings are explicit. We eva recommendation by measuring the Mean Squared Error of rating prediction. {% highlight python %} -from pyspark.mllib.recommendation import ALS -from numpy import array +from pyspark.mllib.recommendation import ALS, Rating # Load and parse the data data = sc.textFile("data/mllib/als/test.data") -ratings = data.map(lambda line: array([float(x) for x in line.split(',')])) +ratings = data.map(lambda l: l.split(',')).map(lambda l: Rating(int(l[0]), int(l[1]), float(l[2]))) # Build the recommendation model using Alternating Least Squares rank = 10 @@ -205,10 +204,10 @@ numIterations = 20 model = ALS.train(ratings, rank, numIterations) # Evaluate the model on training data -testdata = ratings.map(lambda p: (int(p[0]), int(p[1]))) +testdata = ratings.map(lambda p: (p[0], p[1])) predictions = model.predictAll(testdata).map(lambda r: ((r[0], r[1]), r[2])) ratesAndPreds = ratings.map(lambda r: ((r[0], r[1]), r[2])).join(predictions) -MSE = ratesAndPreds.map(lambda r: (r[1][0] - r[1][1])**2).reduce(lambda x, y: x + y)/ratesAndPreds.count() +MSE = ratesAndPreds.map(lambda r: (r[1][0] - r[1][1])**2).reduce(lambda x, y: x + y) / ratesAndPreds.count() print("Mean Squared Error = " + str(MSE)) {% endhighlight %} @@ -217,7 +216,7 @@ signals), you can use the trainImplicit method to get better results. {% highlight python %} # Build the recommendation model using Alternating Least Squares based on implicit ratings -model = ALS.trainImplicit(ratings, rank, numIterations, alpha = 0.01) +model = ALS.trainImplicit(ratings, rank, numIterations, alpha=0.01) {% endhighlight %} </div>