python: Write totals at different indentation levels

"""
ReportWithLevels
__author__ = 'Margery Harrison'
__license__ = "Public Domain"
__version__ = "1.0"
"""

import sys

class ReportWithLevels():

    def __init__(self):
        """
        Sets the default values for the class
        """
        self.fdout=sys.stdout  #default - writes report to stdout
        self.number_width=10
        self.level_indent=2
        self.total_width=30
        self.debug = True
        self.min_level = 1
        self.max_level = 4

        #levels before which to print a newline
        self.newline_before = [1]

    # open the input path as file to write to
    def open_outfile(self,path):
        try:
            self.fdout = open(path,'w')
        except IOError:
            msg="{0:s} Can't open and write to {1:s}".format(self.__class__.__name__,path)
            sys.stderr.write(msg)

    # print debug statement if debugging turned on
    def debugPrint(self,message):
        if self.debug:
            print(message)

    # Write a line out to the output file with newline at end
    def writeLine(self,message):
        self.fdout.write(message + '\n')

    # Print message and total with indentation set by input level
    def printLevel(self, level, message, total):
        lev=int(level)
        assert lev >= self.min_level and lev <= self.max_level,\
            "input level not within current limits"

        #skip a space before level 1 statements
        if lev in self.newline_before:
            self.writeLine('')

        #s1 and s2 are number of spaces for formatting
        s1 = lev * self.level_indent
        s2 = self.total_width - s1

        #initialize fstr to the correct number of spaces
        fstr='{{0:{0:d}s}} {{1:{1:d}s}}'.format(s1,s2)

        # Number format string is right justified within number_width
        number_format='{{2:-{0:d}d}}'.format(self.number_width)
        fstr+=number_format
        self.debugPrint('level {0:d} format str= {1:s}'.format(lev,fstr))

        self.writeLine(fstr.format(' ', message, int(total)))


if __name__ == '__main__':
    print "Testing ReportWithLevels.printLevel()"
    pl=ReportWithLevels()
    pl.open_outfile("testout.txt")
    pl.writeLine("This is my report")
    pl.number_width=12
    tot=7
    for level in [1,2,3,2,2,3,4,3,1]:  #range(1,4):
        msg='level {0:d} msg'.format(level)
        tot=tot * 12
        pl.printLevel(level,msg,tot)


    #pl.printLevel(8,"level 8 msg",88)  #test assert error


assert isinstance() not for file stream parameters?

I'm writing methods in PyCharm, and I'd like to follow its hints for the way I should be structuring my code. Here I'm passing in a parameter of type file stream, could be sys.out or a file descriptor. It prompted me to include an "assert isinstance()" for the input parameter. 

    def set_stream(self,fdout):
        """
        :param fdout: 
        """ 
        assert isinstance(fdout,...) 

I was looking up what type to call it for the purposes of isinstance() and I came across  http://dobesland.wordpress.com/2007/10/07/python-isinstance-considered-useful/:

The classic example of this is python’s famous “file-like objects”, which typically implement read and/or write in the same way and are accepted by various python functions.  I believe the DB API is another well-used example of this.  In both cases, there is no common base-class, so it’s impossible to use isinstance() to check whether a particular object is, in fact, file-like or a database object.

I guess I'll leave that assert() out. The code will break reliably enough when someone tries to write to an fdout that isn't the right sort of object.

python: CSV analysis using Counter and DictReader and format

Here is a simple CSV file:

name,color,size,shape,number
tom,red,big,square,3
mary,blue,big,triangle,5
sally,green,small,square,2
edith,blue,small,triangle,1
wally,red,big,square,7
jon,blue,small,triangle,3

This code reads in the simple CSV and reports on it:


import os.path 
import csv 
import collections


def printLevel(level, message, total):
""" Print message and totals, with spacing determined by level
   

    Keyword arguments:

    level   -- integer from 1 to 4

    message -- string, e.g. "Number of happy tomcats"

    total   -- for this version, should be an integer count 

"""
    lev=int(level)
        
    if lev==1:
        print("")
    #fstr1='{0:5s} {1:35s} {2:-3d}'
    #fstr2='{0:10s} {1:30s} {2:-3d}'
    s1=5*lev  #5 or 10
    s2=40-s1
    fstr='{{0:{0:d}s}} {{1:{1:d}s}}'.format(s1,s2)
    fstr+=' {2:-3d}'
    print fstr.format(' ', message, int(total))

def print_colors_shapes(c):
"""Prints report on number of shapes of different colors
    keyword argument:
    c -- collection that includes values in shape_list, color_list below
"""
    shape_list= ['square', 'triangle','circle']
    color_list= ['red', 'blue', 'green','yellow']
    #first print shapes
    for shape in shape_list:
        msg = 'Number of '+ shape + 's'
        tot=c.get(shape,"0")
        printLevel(1, msg,tot)
        if int(tot) > 0:
            for color in color_list:
                msg = "Number of " + color + " " + shape + 's'
                tot=c.get(color + '_' + shape,"0")
                printLevel(2, msg, tot)
    for color in color_list:
        msg = 'Total {0} shapes'.format(color)
        tot = c.get(color,'0')
        printLevel(1,msg,tot)


def count_color_shape(my_reader):
""" create counters for colors and shapes separate and combined
    keyword argument:
    my_reader -- of type csv.DictReader
"""
    c = collections.Counter()
    for row in my_reader:
        print row
        color = row['color']
        shape = row['shape']
        c[color] += 1
        c[shape] += 1
        c[color + '_' + shape] += 1
    return c


def read_dict(path):
    with open(path) as csv_file:
        my_reader = csv.DictReader(csv_file)
        print my_reader.fieldnames
        #now have the read_dict() method return the Counter datastructure
        c = count_color_shape(my_reader)
        print c
        print_colors_shapes(c)

def test_dict():
    datadir = "/Users/margery/Documents/pystuff/pyGotham/demo/data"
    csv_file = 'simpleCSV.txt'
    path = os.path.join(datadir, csv_file)
    print path
    read_dict(path)

test_dict()
 
Here is the output:
/usr/bin/python /Users/margery/PycharmProjects/proj3/TestDict1.py
/Users/margery/Documents/pystuff/pyGotham/demo/data/simpleCSV.txt
['name', 'color', 'size', 'shape', 'number']
{'color': 'red', 'shape': 'square', 'number': '3', 'name': 'tom', 'size': 'big'}
{'color': 'blue', 'shape': 'triangle', 'number': '5', 'name': 'mary', 'size': 'big'}
{'color': 'green', 'shape': 'square', 'number': '2', 'name': 'sally', 'size': 'small'}
{'color': 'blue', 'shape': 'triangle', 'number': '1', 'name': 'edith', 'size': 'small'}
{'color': 'red', 'shape': 'square', 'number': '7', 'name': 'wally', 'size': 'big'}
{'color': 'blue', 'shape': 'triangle', 'number': '3', 'name': 'jon', 'size': 'small'}
Counter({'blue': 3, 'square': 3, 'triangle': 3, 'blue_triangle': 3, 'red_square': 2, 'red': 2, 'green': 1, 'green_square': 1})

      Number of squares                     3
           Number of red squares            2
           Number of blue squares           0
           Number of green squares          1
           Number of yellow squares         0

      Number of triangles                   3
           Number of red triangles          0
           Number of blue triangles         3
           Number of green triangles        0
           Number of yellow triangles       0

      Number of circles                     0

      Total red shapes                      2

      Total blue shapes                     3

      Total green shapes                    1

      Total yellow shapes                   0


python: csv.dictreader - That's what I should have been using

I learned late Wednesday that I'm supposed to give a talk at PyGotham about my forays into python dictionary land. So I did some research. And what I really should have been using is a csv reader flavor called dictreader. This does exist in python 2.6, so being stuck there is no excuse.

There's a good explanation at http://pymotw.com/2/csv/#using-field-names

And great examples at:

http://www.youlikeprogramming.com/2013/11/python-csv-reader-dictreader-quick-reference/