#genaral
C:\Python27\ python #cmd prompt sart
import os # import a module
dir(os) # list all parameters in os module
os.listdir("C:\users\iss") # list * files in a folder
help(modulename) #To get the docs on all the functions at once
import aa #import a method 1
aa.get_directory(aa.drive)
from aa import * #import a method 2
get_directory(drive)
#----------------------------------------------------------------
# String Formatting
name = "John"
age = 23
print "%s is %d years old." % (name, age)
mylist = [1,2,3]
print "A list: %s" % mylist # List print
%s - String (or any object with a string representation, like numbers)
%d - Integers
%f - Floating point numbers
%.
%x/%X - Integers in hex representation (lowercase/uppercase)
s = "Hey there! what should this string be?"
print "Length of s = %d" % len(s) # Length = 38
print "The first occurrence of the letter a = %d" % s.index("a") # First occurrence of "a" =13
print "a occurs %d times" % s.count("a") # Number of a's =1
# Slicing the string into bits
print "The first five characters are '%s'" % s[:5] # Start to 5
print "The next five characters are '%s'" % s[5:10] # 5 to 10
print "The twelfth character is '%s'" % s[12] # Just number 12
print "The last five characters are '%s'" % s[-5:] # 5th-from-last to end
print "String in uppercase: %s" % s.upper() # Convert everything to uppercase
print "String in lowercase: %s" % s.lower() # Convert everything to lowercase
# Check how a string starts
s = "Str Hey there! what should this string be? some"
if s.startswith("Str"):
print "String starts with 'Str'. Good!"
# Check how a string ends
if s.endswith("ome!"):
print "String ends with 'ome!'. Good!"
# Split the string into three separate strings
print "Split the words of the string: %s" % s.split(" ")
#Basic Operators-------------------------------------------------
number = 1 + 2 * 3 / 4.0
remainder = 11 % 3
squared = 7 ** 2
cubed = 2 ** 3
helloworld = "hello" + " " + "world"
lotsofhellos = "hello" * 10 # multiplying strings to form a string
even_numbers = [2,4,6,8]
odd_numbers = [1,3,5,7]
all_numbers = odd_numbers + even_numbers #Lists can be joined
print [1,2,3] * 3 #repeating sequence
#Conditions------------------------------------------------------
x = 2
print x == 2 # prints True
print x == 3 # prints False
print x < 3 # prints True
name = "John"
age = 23
if name == "John" and age == 23:
print "Your name is John, and you are also 23 years old."
if name == "John" or name == "Rick":
print "Your name is either John or Rick."
#Loop------------------------------------------------------------
#The "for" loop - Prints out the numbers 0,1,2,3,4
for x in xrange(5):
print x
# Prints out 3,4,5
for x in xrange(3,6):
print x
#"while" loops - Prints out 0,1,2,3,4
count = 0
while count < 5:
print count
count += 1
#break is used to exit a for loop or a while loop, whereas continue is used to skip the
#current block, and return to the "for" or "while"
count = 0
while True:
print count
if count > 5:
break
# Prints out only odd numbers - 1,3,5,7,9
for x in xrange(10):
# Check if x is even
if x % 2 == 0:
continue
print x
#Function---------------------------------------------------------
def func2(x, y, z, m):
print x+y+z+m
func2(1,2,3,4)
#function within fuunction
def wrapper1(func, *args): # with star
func(*args)
def wrapper2(func, args): # without star ..positional args
func(*args)
def func2(x, y, z, m):
print x+y+z+m
wrapper1(func2, 1, 2, 3, 4)
wrapper2(func2, [1, 2, 3, 4])
#multiple function argument
def foo(xxx, yyy, zzz, *mmm):
print "First: %s" % xxx
print "Second: %s" % yyy
print "Third: %s" % zzz
print "And all the rest... %s" % mmm
foo(1,2,3,4)
#classes and objects-----------------------------------------------
class MyClass:
variable = "blah" # define variable withing functtion
def function(self): # define variable
print "This is a message inside the class."
myobjectx = MyClass() # assign class to an object
print myobjectx.variable # access variable within class
print myobjectx.function() # access function within class
myobjecty = MyClass()
myobjecty.variable = "yackity"
print myobjecty.variable
#Dictionaries-------------------------------------------------------
#A dictionary is a data type similar to arrays, but works with keys and values instead of
#indexes. Each value stored in a dictionary can be accessed using a key, which is any type of
#object (a string, a number, a list, etc.) instead of using its index to address it
phonebook = {}
phonebook["John"] = 938477566
phonebook["Jack"] = 938377264
or
phonebook = {
"John" : 938477566,
"Jack" : 938377264
}
#dictionary, unlike a list, does not keep the order of the values stored in it.
for name, number in phonebook.iteritems():
print "Phone number of %s is %d" % (name, number)
#To remove a specified index, use either one of the following notations:
del phonebook["John"] or
phonebook.remove("John")
#Genaraters----------------------------------------------------------
#Generators are simple functions which return an iterable set of items, one at a time, in a special way.
import random
def lottery():
# returns 6 numbers between 1 and 40
for i in xrange(6):
yield random.randint(1, 40)
# returns a 7th number between 1 and 15
yield random.randint(1,15)
for random_number in lottery():
print "And the next number is... %d!" % random_number
#List Comprehensions--------------------------------------------------
#creates a new list based on another list, in a single, readable line
sentence = "the quick brown fox jumps over the lazy dog"
words = sentence.split()
word_lengths = [len(word) for word in words if word != "the"]
print words
print word_lengths
#regular expression----------------------------------------------------
#Search and Replace: Some of the most important re methods that use regular expressions is sub.
#re.sub(pattern, repl, string, max=0)
#replace all occurrences of the RE pattern in string with repl, substituting all occurrences unless max provided.
#This method would return modified string.
phone = "2004-959-559 #This is Phone Number"
num = re.sub(r'#.', "", phone) # replace "This" = 2004-959-559 #is Phone Number
num = re.sub(r'#.*$', "", phone) # replace All after # mark with "" = 2004-959-559
num = re.sub(r'\D', "", phone) # replace anything other than digits with "" = 2004959559
print "Phone Num : ", num
#http://www.tutorialspoint.com/python/python_reg_expressions.htm
#Pattern Description
#-----------------------------------------------------------------------------------------------------
^ Matches beginning of line.
$ Matches end of line.
. Matches any single character except newline. Using m option allows it to match newline as well.
[...] Matches any single character in brackets.
[^...] Matches any single character not in brackets
re* Matches 0 or more occurrences of preceding expression.
re+ Matches 1 or more occurrence of preceding expression.
re? Matches 0 or 1 occurrence of preceding expression.
re{ n} Matches exactly n number of occurrences of preceding expression.
re{ n,} Matches n or more occurrences of preceding expression.
re{ n, m} Matches at least n and at most m occurrences of preceding expression.
a| b Matches either a or b.
(re) Groups regular expressions and remembers matched text.
(?imx) Temporarily toggles on i, m, or x options within a regular expression. If in parentheses, only that area is affected.
(?-imx) Temporarily toggles off i, m, or x options within a regular expression. If in parentheses, only that area is affected.
(?: re) Groups regular expressions without remembering matched text.
(?imx: re) Temporarily toggles on i, m, or x options within parentheses.
(?-imx: re) Temporarily toggles off i, m, or x options within parentheses.
(?#...) Comment.
(?= re) Specifies position using a pattern. Doesn't have a range.
(?! re) Specifies position using pattern negation. Doesn't have a range.
(?> re) Matches independent pattern without backtracking.
\w Matches word characters.
\W Matches nonword characters.
\s Matches whitespace. Equivalent to [\t\n\r\f].
\S Matches nonwhitespace.
\d Matches digits. Equivalent to [0-9].
\D Matches nondigits.
\A Matches beginning of string.
\Z Matches end of string. If a newline exists, it matches just before newline.
\z Matches end of string.
\G Matches point where last match finished.
\b Matches word boundaries when outside brackets. Matches backspace (0x08) when inside brackets.
\B Matches nonword boundaries.
\n, \t, etc. Matches newlines, carriage returns, tabs, etc.
\1...\9 Matches nth grouped subexpression.
\10 Matches nth grouped subexpression if it matched already. Otherwise refers to the octal representation of a character code.
File handler and line counts
f = open('received/20000402172012MARK0OUT.DAT', 'r')
s = open('received/20000402172012MARK0.NA', 'r')
num_lines = sum(1 for line in f)
num_liness= sum(1 for line in s)
print num_lines + num_liness
