Merge pull request #31 from dzhwinter/model_ltr2

Add the example for pairwise and listwise LTR.

ltr/lambdaRank.py

@@ -0,0 +1,124 @@
+import os, sys
+import gzip
+import paddle.v2 as paddle
+import numpy as np
+import functools
+
+#lambdaRank is listwise learning to rank model
+
+
+def lambdaRank(input_dim):
+    """
+    lambdaRank is a ListWise Rank Model, input data and label must be sequence
+    https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf
+    parameters :
+      input_dim, one document's dense feature vector dimension
+
+    dense_vector_sequence format
+    [[f, ...], [f, ...], ...], f is represent for an float or int number
+    """
+    label = paddle.layer.data("label",
+                              paddle.data_type.dense_vector_sequence(1))
+    data = paddle.layer.data("data",
+                             paddle.data_type.dense_vector_sequence(input_dim))
+
+    # hidden layer
+    hd1 = paddle.layer.fc(
+        input=data,
+        size=128,
+        act=paddle.activation.Tanh(),
+        param_attr=paddle.attr.Param(initial_std=0.01))
+
+    hd2 = paddle.layer.fc(
+        input=hd1,
+        size=10,
+        act=paddle.activation.Tanh(),
+        param_attr=paddle.attr.Param(initial_std=0.01))
+    output = paddle.layer.fc(
+        input=hd2,
+        size=1,
+        act=paddle.activation.Linear(),
+        param_attr=paddle.attr.Param(initial_std=0.01))
+
+    # evaluator
+    evaluator = paddle.evaluator.auc(input=output, label=label)
+    # cost layer
+    cost = paddle.layer.lambda_cost(
+        input=output, score=label, NDCG_num=6, max_sort_size=-1)
+    return cost, output
+
+
+def train_lambdaRank(num_passes):
+    # listwise input sequence
+    fill_default_train = functools.partial(
+        paddle.dataset.mq2007.train, format="listwise")
+    fill_default_test = functools.partial(
+        paddle.dataset.mq2007.test, format="listwise")
+    train_reader = paddle.batch(
+        paddle.reader.shuffle(fill_default_train, buf_size=100), batch_size=32)
+    test_reader = paddle.batch(fill_default_test, batch_size=32)
+
+    # mq2007 input_dim = 46, dense format
+    input_dim = 46
+    cost, output = lambdaRank(input_dim)
+    parameters = paddle.parameters.create(cost)
+
+    trainer = paddle.trainer.SGD(
+        cost=cost,
+        parameters=parameters,
+        update_equation=paddle.optimizer.Adam(learning_rate=1e-4))
+
+    #  Define end batch and end pass event handler
+    def event_handler(event):
+        if isinstance(event, paddle.event.EndIteration):
+            print "Pass %d Batch %d Cost %.9f" % (event.pass_id, event.batch_id,
+                                                  event.cost)
+        if isinstance(event, paddle.event.EndPass):
+            result = trainer.test(reader=test_reader, feeding=feeding)
+            print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
+            with gzip.open("lambdaRank_params_%d.tar.gz" % (event.pass_id),
+                           "w") as f:
+                parameters.to_tar(f)
+
+    feeding = {"label": 0, "data": 1}
+    trainer.train(
+        reader=train_reader,
+        event_handler=event_handler,
+        feeding=feeding,
+        num_passes=num_passes)
+
+
+def lambdaRank_infer(pass_id):
+    """
+  lambdaRank model inference interface
+  parameters:
+    pass_id : inference model in pass_id
+  """
+    print "Begin to Infer..."
+    input_dim = 46
+    output = lambdaRank(input_dim)
+    parameters = paddle.parameters.Parameters.from_tar(
+        gzip.open("lambdaRank_params_%d.tar.gz" % (pass_id - 1)))
+
+    infer_query_id = None
+    infer_data = []
+    infer_data_num = 1
+    fill_default_test = functools.partial(
+        paddle.dataset.mq2007.test, format="listwise")
+    for label, querylist in fill_default_test():
+        infer_data.append(querylist)
+        if len(infer_data) == infer_data_num:
+            break
+
+    # predict score of infer_data document. Re-sort the document base on predict score
+    # in descending order. then we build the ranking documents
+    predicitons = paddle.infer(
+        output_layer=output, parameters=parameters, input=infer_data)
+    for i, score in enumerate(predicitons):
+        print i, score
+
+
+if __name__ == '__main__':
+    paddle.init(use_gpu=False, trainer_count=4)
+    train_lambdaRank(2)
+    lambdaRank_infer(pass_id=1)

ltr/metrics.py

@@ -0,0 +1,42 @@
+import numpy as np
+import unittest
+
+
+def ndcg(score_list):
+    """
+    measure the ndcg score of order list
+    https://en.wikipedia.org/wiki/Discounted_cumulative_gain
+    parameter:
+        score_list: np.array, shape=(sample_num,1)
+
+    e.g. predict rank score list :
+    >>> scores =  [3, 2, 3, 0, 1, 2] 
+    >>> ndcg_score = ndcg(scores)
+    
+    """
+
+    def dcg(score_list):
+        n = len(score_list)
+        cost = .0
+        for i in range(n):
+            cost += float(score_list[i]) / np.log((i + 1) + 1)
+        return cost
+
+    dcg_cost = dcg(score_list)
+    score_ranking = sorted(score_list, reverse=True)
+    ideal_cost = dcg(score_ranking)
+    return dcg_cost / ideal_cost
+
+
+class NdcgTest(unittest.TestCase):
+    def __init__(self):
+        pass
+
+    def runcase(self):
+        a = [3, 2, 3, 0, 1, 2]
+        value = ndcg(a)
+        self.assertAlmostEqual(0.961, value, places=3)
+
+
+if __name__ == '__main__':
+    unittest.main()

ltr/ranknet.py

@@ -0,0 +1,135 @@
+import os
+import sys
+import gzip
+import functools
+import paddle.v2 as paddle
+import numpy as np
+from metrics import ndcg
+
+# ranknet is the classic pairwise learning to rank algorithm
+# http://icml.cc/2015/wp-content/uploads/2015/06/icml_ranking.pdf
+
+
+def half_ranknet(name_prefix, input_dim):
+    """
+  parameter in same name will be shared in paddle framework,
+  these parameters in ranknet can be used in shared state, e.g. left network and right network
+  shared parameters in detail
+  https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/api.md
+  """
+    # data layer
+    data = paddle.layer.data(name_prefix + "/data",
+                             paddle.data_type.dense_vector(input_dim))
+
+    # hidden layer
+    hd1 = paddle.layer.fc(
+        input=data,
+        size=10,
+        act=paddle.activation.Tanh(),
+        param_attr=paddle.attr.Param(initial_std=0.01, name="hidden_w1"))
+    # fully connect layer/ output layer
+    output = paddle.layer.fc(
+        input=hd1,
+        size=1,
+        act=paddle.activation.Linear(),
+        param_attr=paddle.attr.Param(initial_std=0.01, name="output"))
+    return output
+
+
+def ranknet(input_dim):
+    # label layer
+    label = paddle.layer.data("label", paddle.data_type.dense_vector(1))
+
+    # reuse the parameter in half_ranknet
+    output_left = half_ranknet("left", input_dim)
+    output_right = half_ranknet("right", input_dim)
+
+    evaluator = paddle.evaluator.auc(input=output_left, label=label)
+    # rankcost layer
+    cost = paddle.layer.rank_cost(
+        name="cost", left=output_left, right=output_right, label=label)
+    return cost
+
+
+def train_ranknet(num_passes):
+    train_reader = paddle.batch(
+        paddle.reader.shuffle(paddle.dataset.mq2007.train, buf_size=100),
+        batch_size=100)
+    test_reader = paddle.batch(paddle.dataset.mq2007.test, batch_size=100)
+
+    # mq2007 feature_dim = 46, dense format
+    # fc hidden_dim = 128
+    feature_dim = 46
+    cost = ranknet(feature_dim)
+    parameters = paddle.parameters.create(cost)
+
+    trainer = paddle.trainer.SGD(
+        cost=cost,
+        parameters=parameters,
+        update_equation=paddle.optimizer.Adam(learning_rate=2e-4))
+
+    # Define the input data order
+    feeding = {"label": 0, "left/data": 1, "right/data": 2}
+
+    #  Define end batch and end pass event handler
+    def event_handler(event):
+        if isinstance(event, paddle.event.EndIteration):
+            if event.batch_id % 100 == 0:
+                print "Pass %d Batch %d Cost %.9f" % (
+                    event.pass_id, event.batch_id, event.cost)
+            else:
+                sys.stdout.write(".")
+                sys.stdout.flush()
+        if isinstance(event, paddle.event.EndPass):
+            result = trainer.test(reader=test_reader, feeding=feeding)
+            print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
+            with gzip.open("ranknet_params_%d.tar.gz" % (event.pass_id),
+                           "w") as f:
+                parameters.to_tar(f)
+
+    trainer.train(
+        reader=train_reader,
+        event_handler=event_handler,
+        feeding=feeding,
+        num_passes=num_passes)
+
+
+def ranknet_infer(pass_id):
+    """
+  load the trained model. And predict with plain txt input
+  """
+    print "Begin to Infer..."
+    feature_dim = 46
+
+    # we just need half_ranknet to predict a rank score, which can be used in sort documents
+    output = half_ranknet("left", feature_dim)
+    parameters = paddle.parameters.Parameters.from_tar(
+        gzip.open("ranknet_params_%d.tar.gz" % (pass_id - 1)))
+
+    # load data of same query and relevance documents, need ranknet to rank these candidates
+    infer_query_id = []
+    infer_data = []
+    infer_doc_index = []
+
+    # convert to mq2007 built-in data format
+    # <query_id> <relevance_score> <feature_vector>
+    plain_txt_test = functools.partial(
+        paddle.dataset.mq2007.test, format="plain_txt")
+
+    for query_id, relevance_score, feature_vector in plain_txt_test():
+        infer_query_id.append(query_id)
+        infer_data.append(feature_vector)
+
+    # predict score of infer_data document. Re-sort the document base on predict score
+    # in descending order. then we build the ranking documents
+    scores = paddle.infer(
+        output_layer=output, parameters=parameters, input=infer_data)
+    for query_id, score in zip(infer_query_id, scores):
+        print "query_id : ", query_id, " ranknet rank document order : ", score
+
+
+if __name__ == '__main__':
+    paddle.init(use_gpu=False, trainer_count=4)
+    pass_num = 2
+    train_ranknet(pass_num)
+    ranknet_infer(pass_id=pass_num - 1)