Convert to Python3

coretracker/FisherExact/Fisher.py

@@ -1,9 +1,9 @@
 import scipy.stats as ss
 from scipy.special import gammaln as lgamma
-import statlib.fexact as f
-from statlib.fexact import fisher_exact as f_exact
-from statlib.asa159 import rcont2
-from statlib.asa205 import enum as rcont
+from . import statlib.fexact as f
+from .statlib.fexact import fisher_exact as f_exact
+from .statlib.asa159 import rcont2
+from .statlib.asa205 import enum as rcont
 import numpy as np
 import logging
 import os
@@ -220,19 +220,19 @@ def _fisher_sim(c, replicate, seed=None):
     results = np.zeros(replicate)
 
     fact = np.zeros(n + 1)
-    for i in xrange(2, n + 1):
+    for i in range(2, n + 1):
         fact[i] = fact[i - 1] + np.log(i)
 
     observed = np.zeros((nr, nc), dtype="int32", order='F')
-    for it in xrange(replicate):
+    for it in range(replicate):
         rcont2(nrow=nr, ncol=nc, nrowt=sr, ncolt=sc, key=key,
                seed=seed, matrix=observed, ierror=ierror)
         # if we do not have an error, make spcial action
         ans = 0.
         tmp_observed = observed.ravel()
         if ierror[0] != 0:
             raise ValueError("Fortran subroutine rcont2 return an error !")
-        for j in xrange(nc):
+        for j in range(nc):
             i = 0
             ii = j * nr
             while(i < nr):
@@ -268,7 +268,7 @@ def _midp(c):
     global result
     result = []
     logfact = np.zeros(n + 1)
-    for i in xrange(2, n + 1):
+    for i in range(2, n + 1):
         logfact[i] = logfact[i - 1] + np.log(i)
 
     def callback(iflag, table, m, n, rowsum, colsum, prob, mult):

coretracker/FisherExact/__init__.py

@@ -1,2 +1,2 @@
-from Fisher import fisher_exact
+from .Fisher import fisher_exact
 __all__ = [fisher_exact]

coretracker/classifier/__init__.py

@@ -11,7 +11,7 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-from classifier import Classifier, getDataFromFeatures, read_from_json
+from .classifier import Classifier, getDataFromFeatures, read_from_json
 import os
 this_dir, this_filename = os.path.split(__file__)
 MODELPATH = os.path.join(this_dir, "models", '%s/classifier.pkl.z')

coretracker/classifier/classifier.py

@@ -1,4 +1,4 @@
-from __future__ import division
+
 
 import itertools
 import json
@@ -55,7 +55,7 @@ def load_from_file(clc, loadfile):
             clf = joblib.load(loadfile)
             return clf
         except IOError:
-            print('Problem with file %s, can not open it' % loadfile)
+            print(('Problem with file %s, can not open it' % loadfile))
         except Exception as e:
             raise e
         return None
@@ -112,11 +112,11 @@ def feature_importance(self, outfile="importance.png", features_list=[]):
                 [tree.feature_importances_ for tree in self.clf.estimators_], axis=0)
             plt.figure()
             plt.title("Feature importances")
-            plt.bar(range(n_feats), importances[
+            plt.bar(list(range(n_feats)), importances[
                     indices], width=0.5, color="b", yerr=std[indices], align="center")
             if len(features_list) > 0:
                 features_list = np.asarray(features_list)[indices]
-                plt.xticks(range(n_feats), features_list, rotation='vertical')
+                plt.xticks(list(range(n_feats)), features_list, rotation='vertical')
             plt.xlim([-1, n_feats])
             plt.margins(0.2)
 
@@ -176,21 +176,21 @@ def get_stat(self, X_test, y_test):
                 (prob_pos.max() - prob_pos.min())
 
         clf_score = brier_score_loss(y_test, prob_pos)
-        print("%s:" % self.method)
-        print("\tBrier: %1.3f" % (clf_score))
-        print("\tPrecision: %1.3f" % precision_score(y_test, y_pred))
-        print("\tRecall: %1.3f" % recall_score(y_test, y_pred))
-        print("\tF1: %1.3f" % f1_score(y_test, y_pred))
-        print("\tROC AUC score: %1.3f\n" % roc_auc_score(y_test, prob_pos))
+        print(("%s:" % self.method))
+        print(("\tBrier: %1.3f" % (clf_score)))
+        print(("\tPrecision: %1.3f" % precision_score(y_test, y_pred)))
+        print(("\tRecall: %1.3f" % recall_score(y_test, y_pred)))
+        print(("\tF1: %1.3f" % f1_score(y_test, y_pred)))
+        print(("\tROC AUC score: %1.3f\n" % roc_auc_score(y_test, prob_pos)))
 
 
 def read_from_json(data, labels=None, use_global=True, use_pvalue=True):
     """Parse X array from data"""
-    if isinstance(data, basestring):
+    if isinstance(data, str):
         with open(data) as jfile:
             data = json.load(jfile)
 
-    if labels and isinstance(labels, basestring):
+    if labels and isinstance(labels, str):
         with open(labels) as jfile2:
             labels = json.load(jfile2)
     # matrice format
@@ -209,9 +209,9 @@ def read_from_json(data, labels=None, use_global=True, use_pvalue=True):
     # each entry format :
     # [fitch, suspected, gene_frac, rea_frac, used_frac, subs_count, codon_lik_for_rea_aa]
 
-    for aa2, val in data['aa'].items():
-        for aa1, glist in val.items():
-            for genome, gdata in glist.items():
+    for aa2, val in list(data['aa'].items()):
+        for aa1, glist in list(val.items()):
+            for genome, gdata in list(glist.items()):
                 type_check = gdata[dtype]
                 codon_total = gdata['codons'][dtype]
                 fitch = gdata['fitch']
@@ -221,10 +221,10 @@ def read_from_json(data, labels=None, use_global=True, use_pvalue=True):
                 used_codon = type_check['used_codon']
                 # gene_in_genome = data['genes'][genome]
                 was_lost = gdata['lost'][fisher_type]
-                total_aa = np.sum(codon_total.values())
+                total_aa = np.sum(list(codon_total.values()))
                 # mixte_codon = type_check['mixte_codon']
                 subs_count = type_check['count']
-                for codon in codon_total.keys():
+                for codon in list(codon_total.keys()):
                     gene_count = 0
                     total_gene_count = 0
                     try:
@@ -320,7 +320,7 @@ def get_2D_distinct(Xdata, Xlabel, y, etiquette, outfile="2Dcompare.png", featur
     ncomp = len(features)
     if ncomp == 0 or ncomp > len(etiquette):
         ncomp = len(etiquette)
-        features = range(len(etiquette))
+        features = list(range(len(etiquette)))
     else:
         Xdata = Xdata[:, features]
 
@@ -331,8 +331,8 @@ def get_2D_distinct(Xdata, Xlabel, y, etiquette, outfile="2Dcompare.png", featur
 
     plt.close('all')
     f, axarr = plt.subplots(i, j)
-    for xax in xrange(ncomp):
-        for yax in xrange(xax + 1, ncomp):
+    for xax in range(ncomp):
+        for yax in range(xax + 1, ncomp):
             total_size -= 1
             i, j = np.unravel_index(total_size, axarr.shape)
             axarr[i, j].scatter(Xdata[:, xax], Xdata[:, yax], c=color)
@@ -385,8 +385,8 @@ def draw_pca_data(X_features, Xlabel, y, outfile="PCA.png"):
     plt.close('all')
     f, axarr = plt.subplots(i, j)
     if total_size > 1:
-        for xax in xrange(ncomp):
-            for yax in xrange(xax + 1, ncomp):
+        for xax in range(ncomp):
+            for yax in range(xax + 1, ncomp):
                 total_size -= 1
                 i, j = np.unravel_index(total_size, axarr.shape)
                 axarr[i, j].scatter(X_features[:, xax],
@@ -413,11 +413,11 @@ def print_data(X, X_label, Y, etiquette=None):
                      "N. used", "Cod. count", "Sub. count", "G. len", "codon_lik", "N. mixte", "id"]
     etiquette = list(etiquette)
 
-    print("\n" + "\t".join(["genome", "codon",
-                            "ori_aa", "rea_aa"] + etiquette))
-    for i in xrange(len(X_label)):
+    print(("\n" + "\t".join(["genome", "codon",
+                            "ori_aa", "rea_aa"] + etiquette)))
+    for i in range(len(X_label)):
         if Y[i] == 1:
-            print("\t".join(list(X_label[i]) + [str(x) for x in X[i]]))
+            print(("\t".join(list(X_label[i]) + [str(x) for x in X[i]])))
 
 
 def getDataFromFeatures(Xdata, etiquette, feats=[]):
@@ -434,7 +434,7 @@ def get_sensibility_and_precision(pred_y, true_y, X_labels=None, X=None, log=Tru
     assert nel == len(pred_y), 'Vector should be the same size\n'
     true_pos, true_neg, false_pos, false_neg = 0.0, 0.0, 0.0, 0.0
     false_neg_list, false_pos_list = [], []
-    for i in xrange(len(pred_y)):
+    for i in range(len(pred_y)):
         if pred_y[i] == 0 and true_y[i] == 1:
             false_neg += 1
             false_neg_list.append(i)
@@ -446,30 +446,30 @@ def get_sensibility_and_precision(pred_y, true_y, X_labels=None, X=None, log=Tru
         elif pred_y[i] == 0 and true_y[i] == 0:
             true_neg += 1
 
-    print("Test size is: %d\nTrue Positive is: %d\nTrue negative is: \
+    print(("Test size is: %d\nTrue Positive is: %d\nTrue negative is: \
           %d\nFalse positive is: %d\nFalse negative is:%d" % (
-        nel, true_pos, true_neg, false_pos, false_neg))
+        nel, true_pos, true_neg, false_pos, false_neg)))
     print('-------------------------------------------')
-    print("Sensibility is %f" % (true_pos / (true_pos + false_neg)
-                                 if (true_pos + false_neg) > 0 else 1))
-    print("Specificity is %f" % (true_neg / (true_neg + false_pos)
-                                 if (true_neg + false_pos) > 0 else 1))
-    print("Accuracy is %f" % ((true_neg + true_pos) / nel))
-    print("Precision is %f\n\n" %
-          (true_pos / (true_pos + false_pos) if (true_pos + false_pos) > 0 else 1))
+    print(("Sensibility is %f" % (true_pos / (true_pos + false_neg)
+                                 if (true_pos + false_neg) > 0 else 1)))
+    print(("Specificity is %f" % (true_neg / (true_neg + false_pos)
+                                 if (true_neg + false_pos) > 0 else 1)))
+    print(("Accuracy is %f" % ((true_neg + true_pos) / nel)))
+    print(("Precision is %f\n\n" %
+          (true_pos / (true_pos + false_pos) if (true_pos + false_pos) > 0 else 1)))
     if log:
         if X_labels is not None and X is not None:
             if len(false_neg_list) > 0:
                 print("List of false negatives")
                 for i in false_neg_list:
-                    print("\t".join(X_labels[i]))
-                    print("\t".join([str(x) for x in X[i]]))
+                    print(("\t".join(X_labels[i])))
+                    print(("\t".join([str(x) for x in X[i]])))
 
             if len(false_pos_list) > 0:
                 print("\nList of False positives")
                 for i in false_pos_list:
-                    print("\t".join(X_labels[i]))
-                    print("\t".join([str(x) for x in X[i]]))
+                    print(("\t".join(X_labels[i])))
+                    print(("\t".join([str(x) for x in X[i]])))
 
 
 def split_zeros_pos(L, X, Y, split_size=300):
@@ -493,7 +493,7 @@ def get_aa_cross_val(L, X, Y, AA, tsize=None, rstate=-1):
     """Get test data from dataset"""
     test_position = []
     aa_y = np.zeros(Y.shape)
-    for i in xrange(len(Y)):
+    for i in range(len(Y)):
         if L[i][-1] == AA:
             aa_y[i] = 1
             test_position.append(i)
@@ -510,7 +510,7 @@ def get_aa_cross_val(L, X, Y, AA, tsize=None, rstate=-1):
     test_position = np.random.permutation(test_position)
     mask = np.ones(Y.shape, dtype=bool)
     mask[test_position] = False
-    train_position = np.array(range(len(mask)))[mask]
+    train_position = np.array(list(range(len(mask))))[mask]
 
     if rstate > 0:
         return shuffle(train_position, random_state=rstate), shuffle(test_position, random_state=rstate)

coretracker/classifier/models/__init__.py

@@ -23,15 +23,15 @@ class ModelType(object):
     default_sfeat = {'1': mod1, '2': mod2, '3': mod3}
 
     def __init__(self, m, etiquette, sfeat=[], encode=False):
-        if m not in self.default_sfeat.keys():
+        if m not in list(self.default_sfeat.keys()):
             raise ValueError('Selected model do not exist')
         self.model = str(m)
         self.etiquette = etiquette
         if not sfeat:
             try:
                 self.sfeat = self.default_sfeat[self.model]
             except:
-                self.sfeat = range(len(etiquette))
+                self.sfeat = list(range(len(etiquette)))
         else:
             self.sfeat = sfeat
         self.encode = encode

coretracker/coreutils/AncestralRecon.py

@@ -1,22 +1,20 @@
 from abc import ABCMeta, abstractmethod
-import utils
+from . import utils
 from collections import defaultdict, Counter
 import numpy as np
 import operator
-from letterconfig import *
+from .letterconfig import *
 
 
 def init_back_table(dct):
     """Get back table for the current genetic code"""
     back_table = defaultdict(list)
-    for aa, codon in zip(dct.forward_table.values(), dct.forward_table.keys()):
+    for aa, codon in zip(list(dct.forward_table.values()), list(dct.forward_table.keys())):
         back_table[aa].append(codon)
     return back_table
 
 
-class AbsAncest:
-    __metaclass__ = ABCMeta
-
+class AbsAncest(metaclass=ABCMeta):
     def __init__(self, tree, nodestates):
         self.tree = tree
         self.nodestates = nodestates
@@ -55,8 +53,8 @@ def flip_rea_forward(clc, nodestates):
         """Flip rea data dict"""
         new_dt = utils.makehash(1, set)
         state_map = defaultdict(set)
-        for (genome, aarea) in nodestates.items():
-            nl = [(c, aa) for aa, codons in aarea.items() for c in codons]
+        for (genome, aarea) in list(nodestates.items()):
+            nl = [(c, aa) for aa, codons in list(aarea.items()) for c in codons]
             for (c, aa) in nl:
                 new_dt[genome][c].add(aa)
                 state_map[c].add(aa)
@@ -149,13 +147,13 @@ def __const_term_state(self, term_list, smat, char_states, nullstate):
 
         # sort, whether by total number
         if self.enforce_order:
-            return [(x, is_valid_for_c[x]) for x in char_states if x in is_valid_for_c.keys()]
+            return [(x, is_valid_for_c[x]) for x in char_states if x in list(is_valid_for_c.keys())]
         if self.sort_by_size:
-            possible_order = sorted([(x, np.count_nonzero(y)) for x, y in is_valid_for_c.items(
-            )], key=operator.itemgetter(1), reverse=True)
+            possible_order = sorted([(x, np.count_nonzero(y)) for x, y in list(is_valid_for_c.items(
+            ))], key=operator.itemgetter(1), reverse=True)
         else:
             # here we sort by subtree weight, ignoring excluded subgroup
-            possible_order = sorted([(x, y[-1]) for x, y in is_valid_for_c.items()],
+            possible_order = sorted([(x, y[-1]) for x, y in list(is_valid_for_c.items())],
                                     key=operator.itemgetter(1), reverse=True)
         return possible_order
 
@@ -263,7 +261,7 @@ def __init__(self, tree, reassigned, ori_aa, dest_aa, dct, codon_rea=(None, None
         self.dct = dct
         self.back_table = init_back_table(dct)
         codon_list = self.back_table[aa_letters_3to1[ori_aa]]
-        self.colors = dict(zip(codon_list, colors))
+        self.colors = dict(list(zip(codon_list, colors)))
         for leaf in tree:
             if leaf.name in reassigned:
                 leaf.add_features(reassigned={1})

coretracker/coreutils/Faces.py

@@ -94,12 +94,12 @@
 
 def _get_codon_fgcolors(codontable, cible_aa):
     """Get colon foreground color"""
-    return dict((k, (_aafgcolors[v] if v != cible_aa else '#FFFFFF')) for (k, v) in codontable.items())
+    return dict((k, (_aafgcolors[v] if v != cible_aa else '#FFFFFF')) for (k, v) in list(codontable.items()))
 
 
 def _get_codon_bgcolors(codontable, cible_aa, spec_codon_col):
     """Get colon background color"""
-    return dict((k, spec_codon_col.get(k, ("#FFFFFF" if v != cible_aa else '#000000'))) for (k, v) in codontable.items())
+    return dict((k, spec_codon_col.get(k, ("#FFFFFF" if v != cible_aa else '#000000'))) for (k, v) in list(codontable.items()))
 
 
 class PPieChartFace(faces.StaticItemFace):
@@ -120,7 +120,7 @@ def __init__(self, percents, width, height, colors=None, line_color=None, label_
 
         if not is_percent:
             s = sum(percents)
-            percents = map(lambda x: x * 100. / s, percents)
+            percents = [x * 100. / s for x in percents]
 
         if round(sum(percents)) > 100:
             raise ValueError("PPieChartItem: percentage values > 100")
@@ -271,7 +271,7 @@ def __init__(self, seq, cible_aa, seqtype="aa", fsize=10,
             self.col_w *= 3
             if not isinstance(self.seq, list):
                 # only consider the position where 3 nuc can be obtained
-                self.seq = [self.seq[i:i + 3] for i in xrange(0,
+                self.seq = [self.seq[i:i + 3] for i in range(0,
                                                               len(self.seq) - len(self.seq) % 3, 3)]
             if not fg_colors:
                 fg_colors = _get_codon_fgcolors(codontable, cible_aa)
@@ -421,7 +421,7 @@ def __init__(self, aalist, readict, is_leaf=True, spacer=1, height=12,
 
         def _init_colors(bgtype=True, fgcolor='#000000'):
             color = {}
-            for aa in readict.keys():
+            for aa in list(readict.keys()):
                 c = _aabgcolors[aa.upper()] if bgtype else fgcolor
                 color[aa.upper()] = QBrush(QColor(c))
             return color
@@ -431,7 +431,7 @@ def _init_colors(bgtype=True, fgcolor='#000000'):
     def update_items(self):
         try:
             max_codons = math.ceil(
-                max([len(x) for x in self.readict.values()]) / 2.0) * 2
+                max([len(x) for x in list(self.readict.values())]) / 2.0) * 2
         except:
             max_codons = 1
         if self.maxcodon: