CLN: Newer syntax, unicode, iterator range, zip, etc

Use new syntax ('except as', print as function, new raise syntax, next
function rather than method, next and __next__ defined throughout,
switchout xrange, etc.)

Now range is always equivalent to 2.X xrange throughout (but need to
import range from py3compat to use it). Also remove range fixer from
setup.py. + compatible long and string types, etc.

Author: jtratner

bench/alignment.py

@@ -1,13 +1,14 @@
 # Setup
+from pandas.util.py3compat import range
 import numpy as np
 import pandas
 import la
 N = 1000
 K = 50
 arr1 = np.random.randn(N, K)
 arr2 = np.random.randn(N, K)
-idx1 = range(N)
-idx2 = range(K)
+idx1 = list(range(N))
+idx2 = list(range(K))
 
 # pandas
 dma1 = pandas.DataFrame(arr1, idx1, idx2)

bench/bench_get_put_value.py

@@ -1,12 +1,13 @@
 from pandas import *
 from pandas.util.testing import rands
+from pandas.util.py3compat import range
 
 N = 1000
 K = 50
 
 
 def _random_index(howmany):
-    return Index([rands(10) for _ in xrange(howmany)])
+    return Index([rands(10) for _ in range(howmany)])
 
 df = DataFrame(np.random.randn(N, K), index=_random_index(N),
                columns=_random_index(K))

bench/bench_groupby.py

@@ -1,13 +1,14 @@
 from pandas import *
 from pandas.util.testing import rands
+from pandas.util.py3compat import range
 
 import string
 import random
 
 k = 20000
 n = 10
 
-foo = np.tile(np.array([rands(10) for _ in xrange(k)], dtype='O'), n)
+foo = np.tile(np.array([rands(10) for _ in range(k)], dtype='O'), n)
 foo2 = list(foo)
 random.shuffle(foo)
 random.shuffle(foo2)

bench/bench_join_panel.py

@@ -35,7 +35,7 @@ def reindex_on_axis(panels, axis, axis_reindex):
         # concatenate values
         try:
                 values = np.concatenate([p.values for p in panels], axis=1)
-        except (Exception), detail:
+        except Exception as detail:
                 raise Exception("cannot append values that dont' match dimensions! -> [%s] %s"
                                 % (','.join(["%s" % p for p in panels]), str(detail)))
         # pm('append - create_panel')

bench/bench_khash_dict.py

@@ -1,12 +1,14 @@
 """
 Some comparisons of khash.h to Python dict
 """
+from __future__ import print_function
 
 import numpy as np
 import os
 
 from vbench.api import Benchmark
 from pandas.util.testing import rands
+from pandas.util.py3compat import range
 import pandas._tseries as lib
 import pandas._sandbox as sbx
 import time
@@ -22,7 +24,7 @@ def object_test_data(n):
 
 
 def string_test_data(n):
-    return np.array([rands(10) for _ in xrange(n)], dtype='O')
+    return np.array([rands(10) for _ in range(n)], dtype='O')
 
 
 def int_test_data(n):
@@ -50,7 +52,7 @@ def f():
 
 def _timeit(f, iterations=10):
     start = time.time()
-    for _ in xrange(iterations):
+    for _ in range(iterations):
         foo = f()
     elapsed = time.time() - start
     return elapsed
@@ -73,8 +75,8 @@ def lookup_khash(values):
 
 
 def leak(values):
-    for _ in xrange(100):
-        print proc.get_memory_info()
+    for _ in range(100):
+        print(proc.get_memory_info())
         table = lookup_khash(values)
         # table.destroy()
 

bench/bench_merge.py

@@ -1,13 +1,14 @@
 from pandas import *
 from pandas.util.testing import rands
+from pandas.util.py3compat import range
 import random
 
 N = 10000
 ngroups = 10
 
 
 def get_test_data(ngroups=100, n=N):
-    unique_groups = range(ngroups)
+    unique_groups = list(range(ngroups))
     arr = np.asarray(np.tile(unique_groups, n / ngroups), dtype=object)
 
     if len(arr) < n:
@@ -34,8 +35,8 @@ def get_test_data(ngroups=100, n=N):
 from pandas.util.testing import rands
 N = 10000
 
-indices = np.array([rands(10) for _ in xrange(N)], dtype='O')
-indices2 = np.array([rands(10) for _ in xrange(N)], dtype='O')
+indices = np.array([rands(10) for _ in range(N)], dtype='O')
+indices2 = np.array([rands(10) for _ in range(N)], dtype='O')
 key = np.tile(indices[:8000], 10)
 key2 = np.tile(indices2[:8000], 10)
 
@@ -55,7 +56,7 @@ def get_test_data(ngroups=100, n=N):
         f = lambda: merge(left, right, how=join_method, sort=sort)
         gc.disable()
         start = time.time()
-        for _ in xrange(niter):
+        for _ in range(niter):
             f()
         elapsed = (time.time() - start) / niter
         gc.enable()
@@ -65,7 +66,7 @@ def get_test_data(ngroups=100, n=N):
 
 
 # R results
-from StringIO import StringIO
+from pandas.util.py3compat import StringIO
 # many to one
 r_results = read_table(StringIO("""      base::merge   plyr data.table
 inner      0.2475 0.1183     0.1100
@@ -93,7 +94,7 @@ def get_test_data(ngroups=100, n=N):
 
 # many to many
 
-from StringIO import StringIO
+from pandas.util.py3compat import StringIO
 # many to one
 r_results = read_table(StringIO("""base::merge   plyr data.table
 inner      0.4610 0.1276     0.1269

bench/bench_merge_sqlite.py

@@ -4,12 +4,14 @@
 import time
 from pandas import DataFrame
 from pandas.util.testing import rands
+from pandas.util.py3compat import range
+from six.moves import zip
 import random
 
 N = 10000
 
-indices = np.array([rands(10) for _ in xrange(N)], dtype='O')
-indices2 = np.array([rands(10) for _ in xrange(N)], dtype='O')
+indices = np.array([rands(10) for _ in range(N)], dtype='O')
+indices2 = np.array([rands(10) for _ in range(N)], dtype='O')
 key = np.tile(indices[:8000], 10)
 key2 = np.tile(indices2[:8000], 10)
 
@@ -67,7 +69,7 @@
         g = lambda: conn.execute(sql)  # list fetches results
         gc.disable()
         start = time.time()
-        # for _ in xrange(niter):
+        # for _ in range(niter):
         g()
         elapsed = (time.time() - start) / niter
         gc.enable()

bench/bench_sparse.py

@@ -3,6 +3,7 @@
 
 from pandas import *
 import pandas.core.sparse as spm
+import pandas.util.compat as compat
 reload(spm)
 from pandas.core.sparse import *
 
@@ -41,7 +42,7 @@
 
 def new_data_like(sdf):
     new_data = {}
-    for col, series in sdf.iteritems():
+    for col, series in compat.iteritems(sdf):
         new_data[col] = SparseSeries(np.random.randn(len(series.sp_values)),
                                      index=sdf.index,
                                      sparse_index=series.sp_index,

bench/bench_take_indexing.py

@@ -1,10 +1,12 @@
+from __future__ import print_function
 import numpy as np
 
 from pandas import *
 import pandas._tseries as lib
 
 from pandas import DataFrame
 import timeit
+from six.moves import zip
 
 setup = """
 from pandas import Series
@@ -35,7 +37,7 @@ def _timeit(stmt, size, k=5, iters=1000):
     return timer.timeit(n) / n
 
 for sz, its in zip(sizes, iters):
-    print sz
+    print(sz)
     fancy_2d.append(_timeit('arr[indexer]', sz, iters=its))
     take_2d.append(_timeit('arr.take(indexer, axis=0)', sz, iters=its))
     cython_2d.append(_timeit('lib.take_axis0(arr, indexer)', sz, iters=its))
@@ -44,7 +46,7 @@ def _timeit(stmt, size, k=5, iters=1000):
                 'take': take_2d,
                 'cython': cython_2d})
 
-print df
+print(df)
 
 from pandas.rpy.common import r
 r('mat <- matrix(rnorm(50000), nrow=10000, ncol=5)')

bench/bench_unique.py

@@ -1,14 +1,17 @@
+from __future__ import print_function
 from pandas import *
 from pandas.util.testing import rands
+from pandas.util.py3compat import range
+from six.moves import zip
 import pandas._tseries as lib
 import numpy as np
 import matplotlib.pyplot as plt
 
 N = 50000
 K = 10000
 
-groups = np.array([rands(10) for _ in xrange(K)], dtype='O')
-groups2 = np.array([rands(10) for _ in xrange(K)], dtype='O')
+groups = np.array([rands(10) for _ in range(K)], dtype='O')
+groups2 = np.array([rands(10) for _ in range(K)], dtype='O')
 
 labels = np.tile(groups, N // K)
 labels2 = np.tile(groups2, N // K)
@@ -20,7 +23,7 @@ def timeit(f, niter):
     import time
     gc.disable()
     start = time.time()
-    for _ in xrange(niter):
+    for _ in range(niter):
         f()
     elapsed = (time.time() - start) / niter
     gc.enable()
@@ -75,9 +78,8 @@ def algo3_sort():
 
 
 def f():
-    from itertools import izip
     # groupby sum
-    for k, v in izip(x, data):
+    for k, v in zip(x, data):
         try:
             counts[k] += v
         except KeyError:
@@ -128,7 +130,7 @@ def algo4():
 # N = 10000000
 # K = 500000
 
-# groups = np.array([rands(10) for _ in xrange(K)], dtype='O')
+# groups = np.array([rands(10) for _ in range(K)], dtype='O')
 
 # labels = np.tile(groups, N // K)
 data = np.random.randn(N)
@@ -232,11 +234,11 @@ def hash_bench():
     khash_hint = []
     khash_nohint = []
     for K in Ks:
-        print K
-        # groups = np.array([rands(10) for _ in xrange(K)])
+        print(K)
+        # groups = np.array([rands(10) for _ in range(K)])
         # labels = np.tile(groups, N // K).astype('O')
 
-        groups = np.random.randint(0, 100000000000L, size=K)
+        groups = np.random.randint(0, long(100000000000), size=K)
         labels = np.tile(groups, N // K)
         dict_based.append(timeit(lambda: dict_unique(labels, K), 20))
         khash_nohint.append(timeit(lambda: khash_unique_int64(labels, K), 20))
@@ -245,11 +247,11 @@ def hash_bench():
 
         # memory, hard to get
         # dict_based.append(np.mean([dict_unique(labels, K, memory=True)
-        #                            for _ in xrange(10)]))
+        #                            for _ in range(10)]))
         # khash_nohint.append(np.mean([khash_unique(labels, K, memory=True)
-        #                              for _ in xrange(10)]))
+        #                              for _ in range(10)]))
         # khash_hint.append(np.mean([khash_unique(labels, K, size_hint=True, memory=True)
-        #                            for _ in xrange(10)]))
+        #                            for _ in range(10)]))
 
         # dict_based_sort.append(timeit(lambda: dict_unique(labels, K,
         #                                                   sort=True), 10))

bench/better_unique.py

@@ -1,9 +1,13 @@
+from __future__ import print_function
 from pandas import DataFrame
+from pandas.util.py3compat import range
+from six.moves import zip
 import timeit
 
 setup = """
 from pandas import Series
 import pandas._tseries as _tseries
+from pandas.util.py3compat import range
 import random
 import numpy as np
 
@@ -48,11 +52,11 @@ def get_test_data(ngroups=100, n=tot):
     numpy_timer = timeit.Timer(stmt='np.unique(arr)',
                                setup=setup % sz)
 
-    print n
+    print(n)
     numpy_result = numpy_timer.timeit(number=n) / n
     wes_result = wes_timer.timeit(number=n) / n
 
-    print 'Groups: %d, NumPy: %s, Wes: %s' % (sz, numpy_result, wes_result)
+    print('Groups: %d, NumPy: %s, Wes: %s' % (sz, numpy_result, wes_result))
 
     wes.append(wes_result)
     numpy.append(numpy_result)

bench/io_roundtrip.py

@@ -1,16 +1,18 @@
+from __future__ import print_function
 import time
 import os
 import numpy as np
 
 import la
 import pandas
+from pandas.util.py3compat import range
 from pandas import datetools, DateRange
 
 
 def timeit(f, iterations):
     start = time.clock()
 
-    for i in xrange(iterations):
+    for i in range(iterations):
         f()
 
     return time.clock() - start
@@ -54,11 +56,11 @@ def rountrip_archive(N, K=50, iterations=10):
 
     pandas_f = lambda: pandas_roundtrip(filename_pandas, dma, dma)
     pandas_time = timeit(pandas_f, iterations) / iterations
-    print 'pandas (HDF5) %7.4f seconds' % pandas_time
+    print('pandas (HDF5) %7.4f seconds' % pandas_time)
 
     pickle_f = lambda: pandas_roundtrip(filename_pandas, dma, dma)
     pickle_time = timeit(pickle_f, iterations) / iterations
-    print 'pandas (pickle) %7.4f seconds' % pickle_time
+    print('pandas (pickle) %7.4f seconds' % pickle_time)
 
     # print 'Numpy (npz)   %7.4f seconds' % numpy_time
     # print 'larry (HDF5)  %7.4f seconds' % larry_time