Sourcery refactored master branch

Accelerators/GANs/gan.py

@@ -122,7 +122,7 @@ def train(output_path, max_epoch, to_restore):
 
         for i in range(sess.run(global_step), max_epoch):
             for j in range(int(60000 // batch_size)):
-                print("epoch:%s, iter:%s" % (i, j))
+                print(f"epoch:{i}, iter:{j}")
                 x_value, _ = mnist.train.next_batch(batch_size)
                 x_value = 2 * x_value.astype(np.float32) - 1
                 z_value = generate_prior(batch_size, z_size)

C/Tree_2k/examples/visualization/visualization.py

@@ -13,7 +13,7 @@ def compute_segments(line):
     if len(data) != 4:
         print("### error: can only plot 2D data", file=sys.stderr)
         sys.exit(1)
-    center = data[0:2]
+    center = data[:2]
     extent = data[2:4]
     ur = (center[0] + extent[0], center[1] + extent[1])
     ul = (center[0] - extent[0], center[1] + extent[1])

CPlusPlus/Tbb/Tree/format_timings.py

@@ -17,10 +17,10 @@
             for line in file:
                 match = re.match(r'^time: ([^s]+)\s+s$', line)
                 if match is not None:
-                    time_avg = float(match.group(1))
+                    time_avg = float(match[1])
                     nr_timings += 1
                     continue
                 match = re.match('^procs: (\d+)$', line)
                 if match is not None:
-                    nr_procs = int(match.group(1))
+                    nr_procs = int(match[1])
             print('{0:d} {1:.6f}'.format(nr_procs, time_avg/nr_timings))

DataStorage/NetCDF/PythonSamples/write_netcdf.py

@@ -17,10 +17,7 @@
     arg_parser.add_argument('-v', dest='version', choices=['3', '4'],
                             default='3', help='NetCDF version to create')
     options = arg_parser.parse_args()
-    if options.version == '3':
-        version = 'NETCDF3_CLASSIC'
-    else:
-        version = 'NETCDF4'
+    version = 'NETCDF3_CLASSIC' if options.version == '3' else 'NETCDF4'
     rootgrp = Dataset(options.file, 'w', format='NETCDF3_CLASSIC')
     x_dim = rootgrp.createDimension('x', options.x)
     y_dim = rootgrp.createDimension('y', options.y)

Debugging/Arithmetic/dna_generator.py

@@ -10,8 +10,7 @@ def available_nucl(nucl_left):
 
 def get_nucl(nucl_left):
     while True:
-        avail_nucls = available_nucl(nucl_left)
-        if avail_nucls:
+        if avail_nucls := available_nucl(nucl_left):
             nucl = random.choice(avail_nucls)
             nucl_left[nucl] -= 1
             yield nucl

Debugging/CompilerFlags/FloatEqual/on_circle_driver.py

@@ -13,8 +13,8 @@ def compute_y(x, radius):
     [0.0, 0.0,  2.0,  1.0,       compute_y(1.0, 2.0)],
 ]
 
+cmd = './on_circle_c.exe'
 for case in cases:
-    cmd = './on_circle_c.exe'
     args = ['{0:.15f}'.format(x) for x in case]
     print(cmd, ' '.join(args))
     output = check_output([cmd, *args])

Python/Biopython/align_seqs.py

@@ -17,9 +17,10 @@
     arg_parser.add_argument('--show', action='store_true',
                             help='show MUSCLE output')
     options = arg_parser.parse_args()
-    seqs = {}
-    for seq_record in SeqIO.parse(options.file, options.format):
-        seqs[seq_record.id] = seq_record.seq
+    seqs = {
+        seq_record.id: seq_record.seq
+        for seq_record in SeqIO.parse(options.file, options.format)
+    }
     if options.alignment:
         with open(options.alignment, 'r') as alignment_file:
             stdout = alignment_file.read()

Python/Biopython/entrez_db_info.py

@@ -18,8 +18,8 @@
             record = Entrez.read(handle)
             db_info = record['DbInfo']
             print(db_info['Description'])
-            print('Count: {}'.format(db_info['Count']))
-            print('Last update: {}'.format(db_info['LastUpdate']))
+            print(f"Count: {db_info['Count']}")
+            print(f"Last update: {db_info['LastUpdate']}")
             if options.fields:
                 print('Fields:')
                 fmt_str = '{Name} ({FullName}): {Description}'

Python/Biopython/read_seq.py

@@ -23,9 +23,10 @@ def compute_stats(seq):
     arg_parser.add_argument('file', help='sequence file to parse')
     arg_parser.add_argument('--format', default='fasta', help='file format')
     options = arg_parser.parse_args()
-    seqs = {}
-    for seq_record in SeqIO.parse(options.file, options.format):
-        seqs[seq_record.id] = seq_record.seq
+    seqs = {
+        seq_record.id: seq_record.seq
+        for seq_record in SeqIO.parse(options.file, options.format)
+    }
     fmt_str = ('id: {id}\n\t'
                'length: {stats.length}\n\t'
                'gc: {stats.gc}\n\t'

Python/Biopython/search_entrez.py

@@ -26,9 +26,9 @@
         if options.summary:
             handle = Entrez.esummary(db='nucleotide', id=seq_id)
             summary = Entrez.read(handle)
-            print('ID {}:'.format(seq_id))
-            print('  {}'.format(summary[0]['Title']))
-            print('  Updated: {}'.format(summary[0]['UpdateDate']))
+            print(f'ID {seq_id}:')
+            print(f"  {summary[0]['Title']}")
+            print(f"  Updated: {summary[0]['UpdateDate']}")
         else:
             file_name = os.path.join('Data', '{0}.gbk'.format(seq_id))
             if not os.path.isfile(file_name):

Python/Biopython/seq_info.py

@@ -5,7 +5,7 @@
 import textwrap
 
 def print_seq_record(seq_record, indent_with='  ', indent=''):
-    print('Sequence ID: {}'.format(seq_record.id))
+    print(f'Sequence ID: {seq_record.id}')
     indent += indent_with
     print('{0}Name: {1}'.format(indent, seq_record.name))
     print('{0}Description: {1}'.format(indent, seq_record.description))

Python/Birdsong/create_signal.py

@@ -42,9 +42,7 @@ def normalize(signal, ampl):
     arg_parser.add_argument('--out', action='store_true',
                             help='print signal to standard output')
     options = arg_parser.parse_args()
-    if options.specs_file:
-        pass
-    else:
+    if not options.specs_file:
         if len(options.freqs) != len(options.ampls):
             msg = '# error: {0:d} frequencies for {1:d} amplitudes\n'
             sys.stderr.write(msg.format(len(options.freqs),

Python/CodeCoverage/functions.py

@@ -1,8 +1,5 @@
 def fac_r(n):
-    if n < 2:
-        return 1
-    else:
-        return n*fac_r(n - 1)
+    return 1 if n < 2 else n*fac_r(n - 1)
 
 def fac_i(n):
     result = 1

Python/CodeEvaluation/fac.py

@@ -1,5 +1,2 @@
 def fac(n):
-    if n < 2:
-        return 1
-    else:
-        return n*fac(n-1)
+    return 1 if n < 2 else n*fac(n-1)

Python/CodeEvaluation/fib.py

@@ -1,5 +1,2 @@
 def fib(n):
-    if n == 0 or n == 1:
-        return 1
-    else:
-        return fib(n-1) + fib(n-2)
+    return 1 if n in [0, 1] else fib(n-1) + fib(n-2)

Python/CodeTesting/Asserts/fac.py

@@ -4,10 +4,7 @@ def fac(n):
     '''compute the factorial of given number'''
     assert type(n) == int, 'argument must be integer'
     assert n >= 0, 'argument must be positive'
-    if n > 1:
-        return n*fac(n - 1)
-    else:
-        return 1
+    return n*fac(n - 1) if n > 1 else 1
 
 if __name__ == '__main__':
     for i in range(5):

Python/CodeTesting/constant_db.py

@@ -41,11 +41,10 @@ def get_value(self, name):
                               WHERE name = ?''', (name, ))
         rows = cursor.fetchall()
         cursor.close()
-        if not rows:
-            msg = "constant '{0}' is undefined".format(name)
-            raise UnknownConstantError(msg)
-        else:
+        if rows:
             return rows[0][0]
+        msg = "constant '{0}' is undefined".format(name)
+        raise UnknownConstantError(msg)
 
     def get_names(self):
         cursor = self._conn.cursor()

Python/CommandLineArgs/ArgParse/partial_parse.py

@@ -19,5 +19,5 @@
                                         options.resoure_specs))
         print('resources: ' + ', '.join(specs))
     if options.account:
-        print('account: ' + options.account)
+        print(f'account: {options.account}')
     print('unparsed: ' + ', '.join(unparsed))

Python/CommandLineArgs/ArgParse/two_stage_parse.py

@@ -7,7 +7,7 @@
 
 
 def parse_job_script(file_name):
-    args = list()
+    args = []
     with open(file_name) as file:
         for line in file:
             if line.lstrip().startswith('#PBS '):

Python/ConfigParser/config_reader.py

@@ -5,10 +5,7 @@
 
 
 def main():
-    if len(sys.argv) > 1:
-        cfg_file = sys.argv[1]
-    else:
-        cfg_file = 'defaults.conf'
+    cfg_file = sys.argv[1] if len(sys.argv) > 1 else 'defaults.conf'
     cfg_parser = SafeConfigParser()
     cfg_parser.read(cfg_file)
     print('Sections:')

Python/ContextManager/context.py

@@ -37,10 +37,9 @@ def main():
         print('in context {0}'.format(c2._context_nr))
     with label('foo') as foo, label('bar') as bar:
         print(foo, bar)
-    with ContextTest(1) as c1, ContextTest(2) as c2:
+    with (ContextTest(1) as c1, ContextTest(2) as c2):
         print('in context {0}'.format(c1._context_nr))
         raise Exception()
-        print('in context {0}'.format(c2._context_nr))
     return 0
 
 if __name__ == '__main__':

Python/Coroutines/stats.py

@@ -26,15 +26,12 @@ def process_line(line, mode=float):
     if not line:
         return None
     items = [item.strip() for item in line.split(',')]
-    if mode == float:
-        return [float(item) for item in items]
-    else:
-        return items
+    return [float(item) for item in items] if mode == float else items
 
 if __name__ == '__main__':
     line = sys.stdin.readline()
     names = process_line(line, mode='text')
-    averagers = [stats() for name in names]
+    averagers = [stats() for _ in names]
     for averager in averagers:
         next(averager)
     for line in sys.stdin:

Python/Cython/Numpy/compute_sums.py

@@ -25,7 +25,7 @@ def py_sum(a):
     for func in [array_sum, np.sum, py_sum]:
         total = 0.0
         start_time = timeit.default_timer()
-        for iter_nr in range(options.iter):
+        for _ in range(options.iter):
             total += func(a)
         total_time = timeit.default_timer() - start_time
         print('{0:s}: {1:.6f} s ({2})'.format(func.__name__, total_time,

Python/Cython/Primes/primes_vanilla.py

@@ -4,17 +4,16 @@
 def primes(kmax):
     p = array('i', [0]*1000)
     result = []
-    if kmax > 1000:
-        kmax = 1000
+    kmax = min(kmax, 1000)
     k = 0
     n = 2
     while k < kmax:
         i = 0
         while i < k and n % p[i] != 0:
-            i = i + 1
+            i += 1
         if i == k:
             p[k] = n
-            k = k + 1
+            k += 1
             result.append(n)
         n = n + 1
     return result

Python/Dask/create_csv_data.py

@@ -10,8 +10,10 @@
 
 def write_file(args):
     file_name, rows, curr_time, delta_time, curr_vals, delta_val = args
-    fieldnames = ['timestamp']
-    fieldnames.extend(['C{0:d}'.format(i + 1) for i in range(len(curr_vals))])
+    fieldnames = [
+        'timestamp',
+        *['C{0:d}'.format(i + 1) for i in range(len(curr_vals))],
+    ]
     with open(file_name, 'w', newline='') as csv_file:
         writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
         writer.writeheader()

Python/Dask/dask_distr_test.py

@@ -39,7 +39,7 @@ def get_hostname(i):
     if options.verbose:
         print('task placement:')
         print('\t' + '\n\t'.join(process_locations))
-    count = dict()
+    count = {}
     for process_location in process_locations:
         _, _, hostname = process_location.split()
         if hostname not in count:

Python/DataFormats/Vcd/vcd_parser.py

@@ -15,7 +15,7 @@ def parse_config_line(meta_data, line):
         meta_data[symbol] = demangle_name(name)
 
 def parse_config(vcd_file):
-    meta_data = dict()
+    meta_data = {}
     for line in vcd_file:
         line = line.strip()
         if line == '$end':
@@ -37,16 +37,15 @@ def update_buffer(buffer, line, meta_data):
     buffer[key] = value
 
 def init_data(meta_data):
-    data = dict()
-    data['time'] = list()
+    data = {'time': []}
     for var in meta_data:
-        data[meta_data[var]] = list()
+        data[meta_data[var]] = []
     return data
 
 def parse_data(vcd_file, meta_data):
     data = init_data(meta_data)
     time_stamp = None
-    buffer = dict()
+    buffer = {}
     for line in vcd_file:
         line = line.strip()
         if line.startswith('#'):
@@ -68,9 +67,7 @@ def write_vcd_data_structure(out_file, data, sep=' '):
     columns = list(data.keys())
     out_file.write(sep.join(columns) + '\n')
     for time_step in range(len(data['time'])):
-        data_line = list()
-        for var in columns:
-            data_line.append(data[var][time_step])
+        data_line = [data[var][time_step] for var in columns]
         out_file.write(sep.join(str(data_item) for data_item in data_line))
         out_file.write('\n')
 

Python/DataFormats/agt_parser.py

@@ -106,7 +106,7 @@ def _parse_data(self, agt_file):
         if not match:
             msg = "line {0:d}: invalid number of measurements '{1}'"
             raise AgtDataError(msg.format(self._current_line, nr_lines_str))
-        nr_lines = int(match.group(1))
+        nr_lines = int(match[1])
         self._current_line += 1
 # ignore header line
         agt_file.readline()

Python/DataFormats/data_generator.py

@@ -47,11 +47,10 @@ def __iter__(self):
         return self
 
     def __next__(self):
-        if self._current < self.n:
-            self._current += 1
-            return self._distr(*self._params)
-        else:
+        if self._current >= self.n:
             raise StopIteration()
+        self._current += 1
+        return self._distr(*self._params)
 
 
 class DistributionCreator(object):
@@ -108,9 +107,9 @@ def __init__(self, file_name, table_name, col_defs):
         self._row = self._table.row
 
     def _create_table(self, table_name, col_defs):
-        description = {}
-        for col_def in col_defs:
-            description[col_def['name']] = self._typemap[col_def['type']]
+        description = {
+            col_def['name']: self._typemap[col_def['type']] for col_def in col_defs
+        }
         return self._file.create_table('/', table_name, description)
 
     def set_headers(self, headers):

Python/DataFormats/read_csv.py

@@ -21,7 +21,7 @@ def main():
             print('{name} --- {weight}'.format(name=row['name'],
                                                weight=row['weight']))
             sum += float(row['weight'])
-        print('sum = {}'.format(sum))
+        print(f'sum = {sum}')
 
 if __name__ == '__main__':
     main()

Python/DataFormats/read_variable_length_array.py

@@ -13,10 +13,8 @@ def read_array(data_file, length):
     arg_parser.add_argument('file', help='binary file to read')
     options = arg_parser.parse_args()
     with open(options.file, 'rb') as data_file:
-        buffer = data_file.read(4);
-        while buffer:
+        while buffer := data_file.read(4):
             length = unpack('I', buffer)[0]
             values = read_array(data_file, length)
             value_str = ' '.join(f'{x:.2f}' for x in values)
             print(f'{length:d}: {value_str:s}')
-            buffer = data_file.read(4)