| #!/usr/bin/python | |
| """ pr( ... x= y= ... ), probj() for testing """ | |
| # must be thousands such | |
| # use with https://docs.python.org/2.7/library/logging.html ? | |
| from __future__ import division | |
| import numpy as np | |
| __version__ = "2016-03-06 mar denis" | |
| #............................................................................... | |
| def pr( *args, **kwargs ): | |
| """ pr( "stage 42:", ntop=ntop, df=df ... ) | |
| probj each arg / kwarg, summary line / ndarray | |
| apply liberally | |
| """ | |
| print "" | |
| for arg in args: | |
| probj( arg ) | |
| for key, val in sorted( kwargs.items() ): | |
| # sorted, else random not caller's order | |
| probj( val, key ) | |
| # print "" | |
| #............................................................................... | |
| def probj( x, nm="" ): | |
| """ print any ? obj: | |
| string scalar list tuple dict: 1 summary line "nm: list len 42" | |
| pandas head() tail() with pd.set_option | |
| numpy ndarray with user's np.set_printoptions | |
| """ | |
| # sure to be buggy | |
| if nm: | |
| print "-- %s:" % nm , | |
| if x is None or _isstr( x ): | |
| print x | |
| return | |
| if np.isscalar( x ) \ | |
| or (hasattr( x, "ndim" ) and x.ndim == 0): # np.array( 3 ) | |
| print "%.6g" % x | |
| return | |
| if hasattr( x, "name" ) and x.name is not None: # pandas | |
| print x.name , | |
| # type / classname, shape / len -- | |
| t = getattr( x, "__class__", type(x) ) | |
| print t.__name__ , | |
| if hasattr( x, "shape" ): | |
| print x.shape | |
| n = x.shape[0] | |
| else: | |
| try: | |
| n = len(x) | |
| print "len %d" % n | |
| except (TypeError, AttributeError): # len() of unsized object ? | |
| n = np.NaN | |
| print "" | |
| if isinstance( x, (tuple, list) ): | |
| return | |
| if isinstance( x, dict ): | |
| print " keys:", sorted( x.keys() [:10] ) | |
| return | |
| # pandas DataFrame, Series etc. | |
| # (to print as ndarray, pr( df.values )) | |
| if hasattr( x, "head" ): | |
| if n <= 10: | |
| print x.head( n ) # with user's pd.set_option( max_rows max_cols ... ) | |
| else: | |
| print x.head( 3 ) | |
| print "..." | |
| print x.tail( 3 ) | |
| print "" | |
| return | |
| if hasattr( x, "values" ): | |
| x = x.values | |
| if hasattr( x, "dtype" ): # np array kind O ? | |
| print x # with user's np.set_printoptions | |
| print "" | |
| def _isstr( x ): | |
| """ basestring or np.array( "str" ) """ | |
| return isinstance( x, basestring ) \ | |
| or np.issubdtype( getattr( x, "dtype", "i4"), np.string_ ) # ? | |
| #............................................................................... | |
| if __name__ == "__main__": | |
| from collections import namedtuple | |
| np.set_printoptions( threshold=100, edgeitems=10, linewidth=140, | |
| formatter = dict( float = lambda x: "%.2g" % x )) # float arrays %.2g | |
| # pd.set_option( "display.width", 140, "display.precision", 2 ) | |
| class C: | |
| pass | |
| c = C() | |
| Namedtuple = namedtuple( "Namedtuple", "x y" ) | |
| pr( | |
| adict = { 1:2, 3:4 }, | |
| alist = [1, 2], | |
| array0d = np.array( 3 ), | |
| none = None, | |
| arraynone = [None], | |
| arraystr = np.array("string"), | |
| array2 = np.array([ "string", 3 ]), | |
| eye = np.eye( 3 ) * np.pi, | |
| pi = np.pi, | |
| arraypi = np.array( np.pi ), | |
| s = "string", | |
| C=C, | |
| c=c, | |
| Namedtuple = Namedtuple, | |
| anamedtuple = Namedtuple( 1, 2 ), | |
| ) | |
Purpose: generate "print ..." to help follow code.
print_gen.py expands lines like
p var = expr
-->
print( '''>> var = expr''' )
var = expr
pr( var )
pr() can be pr = print, or a custom printer such as pr.py .
Example: groupby.p --> groupby.py .
Keywords: software testing, print statements, generate, preprocessor, python
| #!/usr/bin/env python | |
| """ expand lines "p var = expr" --> | |
| print( '''>> var = expr''' ) | |
| var = expr | |
| pr( var ) | |
| Purpose: generate "print ..." to help follow code. | |
| `pr()` can be `pr = print`, or a custom printer such as `pr.py` . | |
| """ | |
| # odd, useful ? 4 possiblities | |
| import re # http://docs.python.org/2.7/library/re.html | |
| __version__ = "2016-03-06 mar denis" | |
| p_var_eq_expr_pat = re.compile( | |
| r"(\s*)p \s+ (.+) \s+ = \s+ (.*)", re.X ) | |
| # p lhs = anything | |
| #............................................................................... | |
| def pline( line ): | |
| """ lines "p var = expr" --> print, var = expr, pr() """ | |
| m = p_var_eq_expr_pat.match( line ) | |
| if not m: | |
| return line | |
| space, var, expr = m.groups() | |
| return \ | |
| """%sprint( '''\\n>> %s = %s''' ) | |
| %s%s = %s | |
| %spr( %s ) | |
| """ % ( | |
| space, var, expr, | |
| space, var, expr, | |
| space, var ) | |
| #............................................................................... | |
| def plines( lines ): | |
| """ plines( filename ) | |
| plines( lines list or iter ) e.g. f.readlines() | |
| """ | |
| if not isinstance( lines, basestring ): | |
| for line in lines: | |
| print pline( line ) , # lines with \n | |
| else: | |
| with open( lines, 'r' ) as lines: | |
| for line in lines: | |
| print pline( line ) , | |
| #............................................................................... | |
| if __name__ == "__main__": | |
| import sys | |
| if len(sys.argv) > 1: | |
| for filename in sys.argv[1:]: | |
| plines( filename ) | |
| else: | |
| lines = """ | |
| p var = expr | |
| p var = expr | |
| p = 0 | |
| p, q = 1, 2 | |
| """ | |
| plines([ line + "\n" | |
| for line in lines.split("\n") ]) | |
| """ simple examples of pandas groupby """ | |
| # p-py: this.p -> this.py | |
| from __future__ import division | |
| import sys | |
| import numpy as np | |
| import pandas as pd | |
| from bz.etc.pr import pr | |
| np.set_printoptions( threshold=20, edgeitems=10, linewidth=140, | |
| formatter = dict( float = lambda x: "%.2g" % x )) # float arrays %.2g | |
| pd.set_option( "display.width", 140, | |
| "display.max_rows", 20, | |
| "display.precision", 2 ) | |
| print "\n", 80 * "-" | |
| n = 10 | |
| seed = 0 | |
| # to change these params in sh or ipython, run this.py a=1 b=None c=[3,4] ... | |
| for arg in sys.argv[1:]: | |
| exec( arg ) | |
| np.random.seed( seed ) | |
| #............................................................................... | |
| A = np.random.randint( 0, 2+1, n ) | |
| B = np.random.exponential( size=n ) | |
| X = np.array([ "x", "y", "z" ]) [np.random.randint( 0, 2+1, n )] | |
| p df = pd.DataFrame( dict( A=A, B=B, X=X )) .sort_values( by=["A", "B"] ) | |
| p Agr = df.groupby( "A" ) # pr() head(3) confusing | |
| print "\ngroups:", Agr.groups | |
| print "\nindices:", Agr.indices | |
| p Acount = Agr.count() | |
| p Ahead = Agr.head(1) | |
| p ABcount = Agr .B .count() | |
| p ABsum = Agr .B .sum() | |
| p Atrans = Agr .transform( np.sum ) # ? | |
| p Btrans = Agr .B .transform( np.sum ) | |
| p agg = Agr.agg( np.sum ) # num cols only | |
| """ simple examples of pandas groupby """ | |
| # p-py: this.p -> this.py | |
| from __future__ import division | |
| import sys | |
| import numpy as np | |
| import pandas as pd | |
| from bz.etc.pr import pr | |
| np.set_printoptions( threshold=20, edgeitems=10, linewidth=140, | |
| formatter = dict( float = lambda x: "%.2g" % x )) # float arrays %.2g | |
| pd.set_option( "display.width", 140, | |
| "display.max_rows", 20, | |
| "display.precision", 2 ) | |
| print "\n", 80 * "-" | |
| n = 10 | |
| seed = 0 | |
| # to change these params in sh or ipython, run this.py a=1 b=None c=[3,4] ... | |
| for arg in sys.argv[1:]: | |
| exec( arg ) | |
| np.random.seed( seed ) | |
| #............................................................................... | |
| A = np.random.randint( 0, 2+1, n ) | |
| B = np.random.exponential( size=n ) | |
| X = np.array([ "x", "y", "z" ]) [np.random.randint( 0, 2+1, n )] | |
| print( '''\n>> df = pd.DataFrame( dict( A=A, B=B, X=X )) .sort_values( by=["A", "B"] )''' ) | |
| df = pd.DataFrame( dict( A=A, B=B, X=X )) .sort_values( by=["A", "B"] ) | |
| pr( df ) | |
| print( '''\n>> Agr = df.groupby( "A" ) # pr() head(3) confusing''' ) | |
| Agr = df.groupby( "A" ) # pr() head(3) confusing | |
| pr( Agr ) | |
| print "\ngroups:", Agr.groups | |
| print "\nindices:", Agr.indices | |
| print( '''\n>> Acount = Agr.count()''' ) | |
| Acount = Agr.count() | |
| pr( Acount ) | |
| print( '''\n>> Ahead = Agr.head(1)''' ) | |
| Ahead = Agr.head(1) | |
| pr( Ahead ) | |
| print( '''\n>> ABcount = Agr .B .count()''' ) | |
| ABcount = Agr .B .count() | |
| pr( ABcount ) | |
| print( '''\n>> ABsum = Agr .B .sum()''' ) | |
| ABsum = Agr .B .sum() | |
| pr( ABsum ) | |
| print( '''\n>> Atrans = Agr .transform( np.sum ) # ?''' ) | |
| Atrans = Agr .transform( np.sum ) # ? | |
| pr( Atrans ) | |
| print( '''\n>> Btrans = Agr .B .transform( np.sum )''' ) | |
| Btrans = Agr .B .transform( np.sum ) | |
| pr( Btrans ) | |
| print( '''\n>> agg = Agr.agg( np.sum ) # num cols only''' ) | |
| agg = Agr.agg( np.sum ) # num cols only | |
| pr( agg ) | |