Remove a bunch of Python2-related warts (#2315)

* remove all of the "from __future__" imports

* remove the first batch of rdkit.six imports/uses

* next step of rdkit.six removal

* removing xrange, range, and some maps

* next round of removals

* next round of cleanups

* fix inchi test

* last bits of "from rdkit.six" are gone

* and the last of the six stuff is gone

* strange importlib problem

Contrib/AtomAtomSimilarity/AtomAtomPathSimilarity.py

@@ -1,4 +1,4 @@
-from __future__ import print_function
+
 import numpy
 import time
 import unittest

Contrib/Glare/glare.py

@@ -1,4 +1,4 @@
-from __future__ import print_function
+
 import random, operator, itertools, math
 
 """

Contrib/LEF/AddLabels.py

@@ -29,10 +29,10 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Greg Landrum and Anna Vulpetti, March 2009
-from __future__ import print_function
+
 from rdkit import Chem
 from rdkit.Chem import BRICS
-import sys, cPickle, re
+import sys, pickle, re
 
 inF = file(sys.argv[1], 'r')
 inLs = inF.readlines()

Contrib/LEF/ClusterFps.py

@@ -29,10 +29,10 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Greg Landrum and Anna Vulpetti, March 2009
-from __future__ import print_function
+
 from rdkit.ML.Cluster import Butina
 from rdkit import DataStructs
-import sys, cPickle
+import sys, pickle
 
 # sims is the list of similarity thresholds used to generate clusters
 sims = [.9, .8, .7, .6]
@@ -42,8 +42,8 @@ uFps = []
 
 for fileN in sys.argv[1:]:
   inF = file(sys.argv[1], 'r')
-  cols = cPickle.load(inF)
-  fps = cPickle.load(inF)
+  cols = pickle.load(inF)
+  fps = pickle.load(inF)
 
   for row in fps:
     nm, smi, fp = row[:3]

Contrib/LEF/CreateFps.py

@@ -29,12 +29,12 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Greg Landrum and Anna Vulpetti, March 2009
-from __future__ import print_function
+
 
 from rdkit import Chem
 from rdkit.Chem import AllChem
 from rdkit.Chem.AtomPairs import Pairs, Torsions
-import sys, cPickle
+import sys, pickle
 
 # maxPathLength is the maximum path length in atoms
 # maxPathLength=6 corresponds to F-FP-5
@@ -92,8 +92,8 @@ if __name__ == '__main__':
     nm = mol.GetProp(nameField)
     fps.append([nm, smi, fp] + queryMatches)
   colNames = ['name', 'smiles', 'fp'] + [x for x, y in extraQueries]
-  cPickle.dump(colNames, outF)
-  cPickle.dump(fps, outF)
+  pickle.dump(colNames, outF)
+  pickle.dump(fps, outF)
 
   print('name1 smiles1 name2 smiles2 name12 smiles12 environment_id ' + ' '.join(
     [x for x, y in extraQueries]))

Contrib/M_Kossner/Frames.py

@@ -17,7 +17,7 @@
 #    - sd files containing all molecules belonging to one frame (1.sdf, 2.sdf etc)
 #    - frames.smi containing the (caninical) smiles and count of occurrence
 #
-from __future__ import print_function
+
 
 import os, sys
 from Chem import AllChem as Chem

Contrib/NP_Score/npscorer.py

@@ -13,7 +13,7 @@
 # peter ertl, august 2015
 #
 
-from __future__ import print_function
+
 from rdkit import Chem
 from rdkit.Chem import rdMolDescriptors
 import sys, math, gzip, pickle

Contrib/RxnRoleAssignment/identifyReactants.py

@@ -32,7 +32,7 @@
 
 
 
-from __future__ import print_function
+
 from rdkit import Chem
 from rdkit.Chem import AllChem
 from rdkit.Chem import rdqueries

Contrib/SA_Score/UnitTestSAScore.py

@@ -1,4 +1,4 @@
-from __future__ import print_function
+
 from rdkit import RDConfig
 from rdkit import Chem
 import unittest, os.path

Contrib/SA_Score/sascorer.py

@@ -15,12 +15,11 @@
 #
 # peter ertl & greg landrum, september 2013
 #
-from __future__ import print_function
+
 
 from rdkit import Chem
 from rdkit.Chem import rdMolDescriptors
-from rdkit.six.moves import cPickle
-from rdkit.six import iteritems
+import pickle
 
 import math
 from collections import defaultdict
@@ -31,132 +30,133 @@ _fscores = None
 
 
 def readFragmentScores(name='fpscores'):
-  import gzip
-  global _fscores
-  # generate the full path filename:
-  if name == "fpscores":
-    name = op.join(op.dirname(__file__), name)
-  _fscores = cPickle.load(gzip.open('%s.pkl.gz' % name))
-  outDict = {}
-  for i in _fscores:
-    for j in range(1, len(i)):
-      outDict[i[j]] = float(i[0])
-  _fscores = outDict
+    import gzip
+    global _fscores
+    # generate the full path filename:
+    if name == "fpscores":
+        name = op.join(op.dirname(__file__), name)
+    _fscores = pickle.load(gzip.open('%s.pkl.gz' % name))
+    outDict = {}
+    for i in _fscores:
+        for j in range(1, len(i)):
+            outDict[i[j]] = float(i[0])
+    _fscores = outDict
 
 
 def numBridgeheadsAndSpiro(mol, ri=None):
-  nSpiro = rdMolDescriptors.CalcNumSpiroAtoms(mol)
-  nBridgehead = rdMolDescriptors.CalcNumBridgeheadAtoms(mol)
-  return nBridgehead, nSpiro
+    nSpiro = rdMolDescriptors.CalcNumSpiroAtoms(mol)
+    nBridgehead = rdMolDescriptors.CalcNumBridgeheadAtoms(mol)
+    return nBridgehead, nSpiro
 
 
 def calculateScore(m):
-  if _fscores is None:
-    readFragmentScores()
+    if _fscores is None:
+        readFragmentScores()
 
-  # fragment score
-  fp = rdMolDescriptors.GetMorganFingerprint(m,
-                                             2)  #<- 2 is the *radius* of the circular fingerprint
-  fps = fp.GetNonzeroElements()
-  score1 = 0.
-  nf = 0
-  for bitId, v in iteritems(fps):
-    nf += v
-    sfp = bitId
-    score1 += _fscores.get(sfp, -4) * v
-  score1 /= nf
+    # fragment score
+    fp = rdMolDescriptors.GetMorganFingerprint(m,
+                                               2)  # <- 2 is the *radius* of the circular fingerprint
+    fps = fp.GetNonzeroElements()
+    score1 = 0.
+    nf = 0
+    for bitId, v in fps.items():
+        nf += v
+        sfp = bitId
+        score1 += _fscores.get(sfp, -4) * v
+    score1 /= nf
 
-  # features score
-  nAtoms = m.GetNumAtoms()
-  nChiralCenters = len(Chem.FindMolChiralCenters(m, includeUnassigned=True))
-  ri = m.GetRingInfo()
-  nBridgeheads, nSpiro = numBridgeheadsAndSpiro(m, ri)
-  nMacrocycles = 0
-  for x in ri.AtomRings():
-    if len(x) > 8:
-      nMacrocycles += 1
+    # features score
+    nAtoms = m.GetNumAtoms()
+    nChiralCenters = len(Chem.FindMolChiralCenters(m, includeUnassigned=True))
+    ri = m.GetRingInfo()
+    nBridgeheads, nSpiro = numBridgeheadsAndSpiro(m, ri)
+    nMacrocycles = 0
+    for x in ri.AtomRings():
+        if len(x) > 8:
+            nMacrocycles += 1
 
-  sizePenalty = nAtoms**1.005 - nAtoms
-  stereoPenalty = math.log10(nChiralCenters + 1)
-  spiroPenalty = math.log10(nSpiro + 1)
-  bridgePenalty = math.log10(nBridgeheads + 1)
-  macrocyclePenalty = 0.
-  # ---------------------------------------
-  # This differs from the paper, which defines:
-  #  macrocyclePenalty = math.log10(nMacrocycles+1)
-  # This form generates better results when 2 or more macrocycles are present
-  if nMacrocycles > 0:
-    macrocyclePenalty = math.log10(2)
+    sizePenalty = nAtoms**1.005 - nAtoms
+    stereoPenalty = math.log10(nChiralCenters + 1)
+    spiroPenalty = math.log10(nSpiro + 1)
+    bridgePenalty = math.log10(nBridgeheads + 1)
+    macrocyclePenalty = 0.
+    # ---------------------------------------
+    # This differs from the paper, which defines:
+    #  macrocyclePenalty = math.log10(nMacrocycles+1)
+    # This form generates better results when 2 or more macrocycles are present
+    if nMacrocycles > 0:
+        macrocyclePenalty = math.log10(2)
 
-  score2 = 0. - sizePenalty - stereoPenalty - spiroPenalty - bridgePenalty - macrocyclePenalty
+    score2 = 0. - sizePenalty - stereoPenalty - spiroPenalty - bridgePenalty - macrocyclePenalty
 
-  # correction for the fingerprint density
-  # not in the original publication, added in version 1.1
-  # to make highly symmetrical molecules easier to synthetise
-  score3 = 0.
-  if nAtoms > len(fps):
-    score3 = math.log(float(nAtoms) / len(fps)) * .5
+    # correction for the fingerprint density
+    # not in the original publication, added in version 1.1
+    # to make highly symmetrical molecules easier to synthetise
+    score3 = 0.
+    if nAtoms > len(fps):
+        score3 = math.log(float(nAtoms) / len(fps)) * .5
 
-  sascore = score1 + score2 + score3
+    sascore = score1 + score2 + score3
 
-  # need to transform "raw" value into scale between 1 and 10
-  min = -4.0
-  max = 2.5
-  sascore = 11. - (sascore - min + 1) / (max - min) * 9.
-  # smooth the 10-end
-  if sascore > 8.:
-    sascore = 8. + math.log(sascore + 1. - 9.)
-  if sascore > 10.:
-    sascore = 10.0
-  elif sascore < 1.:
-    sascore = 1.0
+    # need to transform "raw" value into scale between 1 and 10
+    min = -4.0
+    max = 2.5
+    sascore = 11. - (sascore - min + 1) / (max - min) * 9.
+    # smooth the 10-end
+    if sascore > 8.:
+        sascore = 8. + math.log(sascore + 1. - 9.)
+    if sascore > 10.:
+        sascore = 10.0
+    elif sascore < 1.:
+        sascore = 1.0
 
-  return sascore
+    return sascore
 
 
 def processMols(mols):
-  print('smiles\tName\tsa_score')
-  for i, m in enumerate(mols):
-    if m is None:
-      continue
+    print('smiles\tName\tsa_score')
+    for i, m in enumerate(mols):
+        if m is None:
+            continue
 
-    s = calculateScore(m)
+        s = calculateScore(m)
 
-    smiles = Chem.MolToSmiles(m)
-    print(smiles + "\t" + m.GetProp('_Name') + "\t%3f" % s)
+        smiles = Chem.MolToSmiles(m)
+        print(smiles + "\t" + m.GetProp('_Name') + "\t%3f" % s)
 
 
 if __name__ == '__main__':
-  import sys, time
+    import sys
+    import time
 
-  t1 = time.time()
-  readFragmentScores("fpscores")
-  t2 = time.time()
+    t1 = time.time()
+    readFragmentScores("fpscores")
+    t2 = time.time()
 
-  suppl = Chem.SmilesMolSupplier(sys.argv[1])
-  t3 = time.time()
-  processMols(suppl)
-  t4 = time.time()
+    suppl = Chem.SmilesMolSupplier(sys.argv[1])
+    t3 = time.time()
+    processMols(suppl)
+    t4 = time.time()
 
-  print('Reading took %.2f seconds. Calculating took %.2f seconds' % ((t2 - t1), (t4 - t3)),
-        file=sys.stderr)
+    print('Reading took %.2f seconds. Calculating took %.2f seconds' % ((t2 - t1), (t4 - t3)),
+          file=sys.stderr)
 
 #
 #  Copyright (c) 2013, Novartis Institutes for BioMedical Research Inc.
 #  All rights reserved.
-# 
+#
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are
-# met: 
+# met:
 #
-#     * Redistributions of source code must retain the above copyright 
+#     * Redistributions of source code must retain the above copyright
 #       notice, this list of conditions and the following disclaimer.
 #     * Redistributions in binary form must reproduce the above
-#       copyright notice, this list of conditions and the following 
-#       disclaimer in the documentation and/or other materials provided 
+#       copyright notice, this list of conditions and the following
+#       disclaimer in the documentation and/or other materials provided
 #       with the distribution.
-#     * Neither the name of Novartis Institutes for BioMedical Research Inc. 
-#       nor the names of its contributors may be used to endorse or promote 
+#     * Neither the name of Novartis Institutes for BioMedical Research Inc.
+#       nor the names of its contributors may be used to endorse or promote
 #       products derived from this software without specific prior written permission.
 #
 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

Contrib/fraggle/atomcontrib.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, May 2013
-from __future__ import print_function
+
 import sys
 from optparse import OptionParser
 from rdkit import Chem

Contrib/fraggle/cxn_tversky.py

@@ -31,7 +31,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, July 2013
-from __future__ import print_function
+
 
 import sys
 import re

Contrib/fraggle/fraggle.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, May 2013
-from __future__ import print_function
+
 from rdkit import Chem
 from rdkit.Chem.Fraggle import FraggleSim
 

Contrib/fraggle/rdkit_tversky.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, October 2013
-from __future__ import print_function
+
 import sys
 import re
 from optparse import OptionParser

Contrib/mmpa/cansmirk.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, September 2012
-from __future__ import print_function
+
 import sys
 import re
 from rdkit import Chem

Contrib/mmpa/indexing.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, September 2012
-from __future__ import print_function
+
 import sys
 import re
 from rdkit import Chem

Contrib/mmpa/mol_transform.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, July 2013
-from __future__ import print_function
+
 import sys
 import re
 from optparse import OptionParser

Contrib/mmpa/rfrag.py

@@ -32,7 +32,7 @@
 #
 # Modifications and optimizations by Greg Landrum, July 2015
 #
-from __future__ import print_function
+
 import sys
 import re
 from rdkit import Chem

Contrib/mmpa/search_mmp_db.py

@@ -29,7 +29,7 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # Created by Jameed Hussain, July 2013
-from __future__ import print_function
+
 import sys
 import os
 import re

Contrib/pzc/p_con.py

@@ -1,6 +1,6 @@
 # coding=utf-8
 # Copyright (c) 2014 Merck KGaA
-from __future__ import print_function
+
 import os, re, gzip, json, requests, sys, optparse, csv
 from rdkit import Chem
 from rdkit.Chem import AllChem
@@ -16,7 +16,7 @@ from sklearn.cross_validation import train_test_split
 from sklearn.metrics import roc_curve, auc
 from sklearn.metrics import precision_score, recall_score
 from sklearn import preprocessing
-import cPickle
+import pickle
 from pickle import Unpickler
 import numpy as np
 import math
@@ -1207,8 +1207,8 @@ table th[class*="col-"] {
     return
 
   def save_model(self, outfile, model_number=0):
-    """save Model to file using cPickle.dump"""
-    cPickle.dump(self.model[model_number], file(outfile, "wb+"))
+    """save Model to file using pickle.dump"""
+    pickle.dump(self.model[model_number], file(outfile, "wb+"))
     return
 
   def load_models(self, model_files):