find_model_collaborative.py 文件源码

def howFarAreWe(model, against, sizeAgainst):
  # Ignore the rating column  
  againstNoRatings = against.map(lambda x: (int(x[0]), int(x[1])) )

  # Keep the rating to compare against
  againstWiRatings = against.map(lambda x: ((int(x[0]),int(x[1])), int(x[2])) )

  # Make a prediction and map it for later comparison
  # The map has to be ((user,product), rating) not ((product,user), rating)
  predictions = model.predictAll(againstNoRatings).map(lambda p: ( (p[0],p[1]), p[2]) )

  # Returns the pairs (prediction, rating)
  predictionsAndRatings = predictions.join(againstWiRatings).values()

  # Returns the variance
  return sqrt(predictionsAndRatings.map(lambda s: (s[0] - s[1]) ** 2).reduce(add) / float(sizeAgainst))
#[END how_far]

# Read the data from the Cloud SQL
# Create dataframes