@Override public final double itemSimilarity(long itemID1, long itemID2) throws TasteException { PreferenceArray xPrefs = dataModel.getPreferencesForItem(itemID1); PreferenceArray yPrefs = dataModel.getPreferencesForItem(itemID2); int xLength = xPrefs.length(); int yLength = yPrefs.length(); if ((xLength == 0) || (yLength == 0)) { return Double.NaN; } long xIndex = xPrefs.getUserID(0); long yIndex = yPrefs.getUserID(0); int xPrefIndex = 0; int yPrefIndex = 0; double sumX = 0.0; double sumX2 = 0.0; double sumY = 0.0; double sumY2 = 0.0; double sumXY = 0.0; double sumXYdiff2 = 0.0; int count = 0; // No, pref inferrers and transforms don't appy here. I think. while (true) { int compare = xIndex < yIndex ? -1 : xIndex > yIndex ? 1 : 0; if (compare == 0) { // Both users expressed a preference for the item double x = xPrefs.getValue(xPrefIndex); double y = yPrefs.getValue(yPrefIndex); sumXY += x * y; sumX += x; sumX2 += x * x; sumY += y; sumY2 += y * y; double diff = x - y; sumXYdiff2 += diff * diff; count++; } if (compare <= 0) { if (++xPrefIndex == xLength) { break; } xIndex = xPrefs.getUserID(xPrefIndex); } if (compare >= 0) { if (++yPrefIndex == yLength) { break; } yIndex = yPrefs.getUserID(yPrefIndex); } } double result; if (centerData) { // See comments above on these computations double n = (double) count; double meanX = sumX / n; double meanY = sumY / n; // double centeredSumXY = sumXY - meanY * sumX - meanX * sumY + n * meanX * meanY; double centeredSumXY = sumXY - meanY * sumX; // double centeredSumX2 = sumX2 - 2.0 * meanX * sumX + n * meanX * meanX; double centeredSumX2 = sumX2 - meanX * sumX; // double centeredSumY2 = sumY2 - 2.0 * meanY * sumY + n * meanY * meanY; double centeredSumY2 = sumY2 - meanY * sumY; result = computeResult(count, centeredSumXY, centeredSumX2, centeredSumY2, sumXYdiff2); } else { result = computeResult(count, sumXY, sumX2, sumY2, sumXYdiff2); } if (similarityTransform != null) { result = similarityTransform.transformSimilarity(itemID1, itemID2, result); } if (!Double.isNaN(result)) { result = normalizeWeightResult(result, count, cachedNumUsers); } return result; }
@Override public double userSimilarity(long userID1, long userID2) throws TasteException { PreferenceArray xPrefs = dataModel.getPreferencesFromUser(userID1); PreferenceArray yPrefs = dataModel.getPreferencesFromUser(userID2); int xLength = xPrefs.length(); int yLength = yPrefs.length(); if ((xLength == 0) || (yLength == 0)) { return Double.NaN; } long xIndex = xPrefs.getItemID(0); long yIndex = yPrefs.getItemID(0); int xPrefIndex = 0; int yPrefIndex = 0; double sumX = 0.0; double sumX2 = 0.0; double sumY = 0.0; double sumY2 = 0.0; double sumXY = 0.0; double sumXYdiff2 = 0.0; int count = 0; boolean hasInferrer = inferrer != null; boolean hasPrefTransform = prefTransform != null; while (true) { int compare = xIndex < yIndex ? -1 : xIndex > yIndex ? 1 : 0; if (hasInferrer || compare == 0) { double x; double y; if (xIndex == yIndex) { // Both users expressed a preference for the item if (hasPrefTransform) { x = prefTransform.getTransformedValue(xPrefs.get(xPrefIndex)); y = prefTransform.getTransformedValue(yPrefs.get(yPrefIndex)); } else { x = xPrefs.getValue(xPrefIndex); y = yPrefs.getValue(yPrefIndex); } } else { // Only one user expressed a preference, but infer the other one's preference and tally // as if the other user expressed that preference if (compare < 0) { // X has a value; infer Y's x = hasPrefTransform ? prefTransform.getTransformedValue(xPrefs.get(xPrefIndex)) : xPrefs.getValue(xPrefIndex); y = inferrer.inferPreference(userID2, xIndex); } else { // compare > 0 // Y has a value; infer X's x = inferrer.inferPreference(userID1, yIndex); y = hasPrefTransform ? prefTransform.getTransformedValue(yPrefs.get(yPrefIndex)) : yPrefs.getValue(yPrefIndex); } } sumXY += x * y; sumX += x; sumX2 += x * x; sumY += y; sumY2 += y * y; double diff = x - y; sumXYdiff2 += diff * diff; count++; } if (compare <= 0) { if (++xPrefIndex >= xLength) { if (hasInferrer) { // Must count other Ys; pretend next X is far away if (yIndex == Long.MAX_VALUE) { // ... but stop if both are done! break; } xIndex = Long.MAX_VALUE; } else { break; } } else { xIndex = xPrefs.getItemID(xPrefIndex); } } if (compare >= 0) { if (++yPrefIndex >= yLength) { if (hasInferrer) { // Must count other Xs; pretend next Y is far away if (xIndex == Long.MAX_VALUE) { // ... but stop if both are done! break; } yIndex = Long.MAX_VALUE; } else { break; } } else { yIndex = yPrefs.getItemID(yPrefIndex); } } } // "Center" the data. If my math is correct, this'll do it. double result; if (centerData) { double n = count; double meanX = sumX / n; double meanY = sumY / n; // double centeredSumXY = sumXY - meanY * sumX - meanX * sumY + n * meanX * meanY; double centeredSumXY = sumXY - meanY * sumX; // double centeredSumX2 = sumX2 - 2.0 * meanX * sumX + n * meanX * meanX; double centeredSumX2 = sumX2 - meanX * sumX; // double centeredSumY2 = sumY2 - 2.0 * meanY * sumY + n * meanY * meanY; double centeredSumY2 = sumY2 - meanY * sumY; result = computeResult(count, centeredSumXY, centeredSumX2, centeredSumY2, sumXYdiff2); } else { result = computeResult(count, sumXY, sumX2, sumY2, sumXYdiff2); } if (similarityTransform != null) { result = similarityTransform.transformSimilarity(userID1, userID2, result); } if (!Double.isNaN(result)) { result = normalizeWeightResult(result, count, cachedNumItems); } return result; }