%run talktools.py

import string
dir(string)

s = "HeLLo tHEre MY FriEND"

s.upper()

s.lower()

s.title()

s.capitalize()

s.swapcase()

s.split()

L = s.capitalize().split()
L

s = '_'.join(L)
s

s.split('_')

''.join(s.split('_'))

s = "    Too many spaces!    "
s.strip()

s = "*~*~*~*Super!!**~*~**~*~**~"
s.strip('*~')

s.rstrip('*~')

s.lstrip('*~')

s.replace('*', '')

s.replace('*', '').replace('~', '')

s = "The quick brown fox jumped"
s.find("fox")

s[16:]

s.find('booyah')

s.startswith('The')

s.endswith('jumped')

s.endswith('fox')

'1234'.isdigit()

'123.45'.isdigit()

'ABC'.isalpha()

'ABC123'.isalpha()

"ABC123".isalnum()

'ABC easy as 123'.isalnum()

'hello'.islower()

'HELLO'.isupper()

'Hello'.istitle()

'   '.isspace()

from math import pi
"my favorite integer is %d, but my favorite float is %f." % (42, pi)

"in exponential notation it's %e" % pi

"to choose smartly if exponential is needed: %g" % pi

"or with a bigger number: %g" % 123456787654321.0

"rounded to three decimal places it's %.3f" % pi

"an integer padded with spaces: %10d" % 42

"an integer padded on the right: %-10d" % 42

"an integer padded with zeros: %010d" % 42

"we can also name our arguments: %(value)d" % dict(value=3)

"Escape the percent sign with an extra symbol: the %d%%" % 99

"{}{}".format("ABC", 123)

"{0}{1}".format("ABC", 123)

"{0}{0}".format("ABC", 123)

"{1}{0}".format("ABC", 123)

("%.2f" % 3.14159) ==  "{:.2f}".format(3.14159)

"{0:d} is an integer; {1:.3f} is a float".format(42, pi)

"{the_answer:010d} is an integer; {pi:.5g} is a float".format(the_answer=42,
                                                              pi=pi)

'{desire} to {place}'.format(desire='Fly me',
                             place='The Moon')

# using a pre-defined dictionary
f = {"desire": "Won't you take me",
     "place": "funky town?"}

'{desire} to {place}'.format(**f)

# format also supports binary numbers
"int: {0:d};  hex: {0:x};  oct: {0:o};  bin: {0:b}".format(42)

%%file inout.dat
Here is a nice file
with a couple lines of text
it is a haiku

f = open('inout.dat')
print(f.read())
f.close()

f = open('inout.dat')
print(f.readlines())
f.close()

for line in open('inout.dat'):
    print(line.split())

# write() is the opposite of read()
contents = open('inout.dat').read()
out = open('my_output.dat', 'w')
out.write(contents.replace(' ', '_'))
out.close()

!cat my_output.dat

# writelines() is the opposite of readlines()
lines = open('inout.dat').readlines()
out = open('my_output.dat', 'w')
out.writelines(lines)
out.close()

!cat my_output.dat

# Don't modify this: it simply writes the example file
f = open('messy_data.dat', 'w')
import random
for i in range(100):
    for j in range(5):
        f.write(' ' * random.randint(0, 6))
        f.write('%0*.*g' % (random.randint(8, 12),
                            random.randint(5, 10),
                            100 * random.random()))
        if j != 4:
            f.write(',')
    f.write('\n')
f.close()

# Look at the first four lines of the file:
!head -4 messy_data.dat

# your solution here



import numpy as np
data = np.loadtxt("messy_data.dat", delimiter=',')
np.savetxt("clean_data.dat", data,
           delimiter=',', fmt="%8.4f")

!head -5 clean_data.dat