From e9f4436f4766ac1a989b7bf1f6e920717ac78cdb Mon Sep 17 00:00:00 2001
From: Chun Jiang Zhu <chun_jiang.zhu@uconn.edu>
Date: Fri, 19 Jun 2020 19:02:23 -0400
Subject: [PATCH] Delete nmslib_sparse.py

---
 ann_benchmarks/algorithms/nmslib_sparse.py | 95 ----------------------
 1 file changed, 95 deletions(-)
 delete mode 100644 ann_benchmarks/algorithms/nmslib_sparse.py

diff --git a/ann_benchmarks/algorithms/nmslib_sparse.py b/ann_benchmarks/algorithms/nmslib_sparse.py
deleted file mode 100644
index 58af969..0000000
--- a/ann_benchmarks/algorithms/nmslib_sparse.py
+++ /dev/null
@@ -1,95 +0,0 @@
-from __future__ import absolute_import
-import os
-import nmslib
-from ann_benchmarks.constants import INDEX_DIR
-from ann_benchmarks.algorithms.base import BaseANN
-from scipy.sparse import csr_matrix
-import numpy
-
-
-class NmslibSparseReuseIndex(BaseANN):
-    @staticmethod
-    def encode(d):
-        return ["%s=%s" % (a, b) for (a, b) in d.iteritems()]
-
-    # For each entry in the sparse matrix, extract a list of IDs and
-    # convert them to a string. Return a list of such strings.
-    @staticmethod
-    def matrToStrArray(sparseMatr):
-        res = []
-        indptr = sparseMatr.indptr
-        indices = sparseMatr.indices
-        for row in range(sparseMatr.shape[0]):
-            arr = [k for k in indices[indptr[row]: indptr[row + 1]]]
-            arr.sort()
-            res.append(' '.join([str(k) for k in arr]))
-        return res
-
-    def __init__(self, metric, method_name, index_param, query_param):
-        self._nmslib_metric = {'angular': 'cosinesimil', 'euclidean': 'l2', 'jaccard': 'jaccard_sparse'}[metric]
-        self._method_name = method_name
-        self._save_index = False
-        self._index_param = NmslibSparseReuseIndex.encode(index_param)
-        if query_param!=False:
-            self._query_param = NmslibSparseReuseIndex.encode(query_param)
-            self.name = 'Nmslib(method_name=%s, index_param=%s, query_param=%s)' % (
-            self._method_name, self._index_param, self._query_param)
-        else:
-            self._query_param = None
-            self.name = 'Nmslib(method_name=%s, index_param=%s)' % (
-            self._method_name, self._index_param)
-
-        self._index_name = os.path.join(INDEX_DIR, "nmslib_%s_%s_%s" % (self._method_name, metric, '_'.join(self._index_param)))
-
-        d = os.path.dirname(self._index_name)
-        if not os.path.exists(d):
-            os.makedirs(d)
-
-    def fit(self, X):
-        if self._method_name == 'vptree':
-            # To avoid this issue:
-            # terminate called after throwing an instance of 'std::runtime_error'
-            # what():  The data size is too small or the bucket size is too big. Select the parameters so that <total # of records> is NOT less than <bucket size> * 1000
-            # Aborted (core dumped)
-            self._index_param.append('bucketSize=%d' % min(int(X.shape[0] * 0.0005), 1000))
-
-        # Chunjiang modified it to "if" for jaccard
-        if self._nmslib_metric == 'jaccard_sparse':
-            X_trans = NmslibSparseReuseIndex.matrToStrArray(X)
-            self._index = nmslib.init(space=self._nmslib_metric, method=self._method_name, data_type=nmslib.DataType.OBJECT_AS_STRING)
-            self._index.addDataPointBatch(X_trans)
-        else:
-            self._index = nmslib.init(space=self._nmslib_metric, method=self._method_name)
-            self._index.addDataPointBatch(X)
-
-        if os.path.exists(self._index_name):
-            print('Loading index from file')
-            self._index.loadIndex(self._index_name)
-        else:
-            self._index.createIndex(self._index_param)
-            if self._save_index:
-                self._index.saveIndex(self._index_name)
-        if self._query_param is not None:
-            self._index.setQueryTimeParams(self._query_param)
-
-    def set_query_arguments(self, ef):
-        if self._method_name == 'hnsw' or self._method_name == 'sw-graph':
-            self._index.setQueryTimeParams(["efSearch=%s"%(ef)])
-
-    def query(self, v, n):
-        # Chunjiang modified
-        if self._nmslib_metric == 'jaccard_sparse':
-            nz = numpy.nonzero(v)[0]
-            v = ' '.join([str(k) for k in nz])
-        ids, distances = self._index.knnQuery(v, n)
-        return ids
-
-    def batch_query(self, X, n):
-        # Chunjiang modified
-        if self._nmslib_metric == 'jaccard_sparse':
-            X = NmslibSparseReuseIndex.matrToStrArray(csr_matrix(X))
-        self.res = self._index.knnQueryBatch(X, n)
-
-    def get_batch_results(self):
-        return [x for x, _ in self.res]
-