Python Virtual Training For Arcesium - Module II

Oct 11-15, 2021 Vikrant Patil

These notes are available online at https://notes.pipal.in/2021/arcesium_finop_batch2/

© Pipal Academy LLP

Day 1

We will be using jupyter hub from https://lab2.pipal.in for this training.

create a notebook with name module2-day1

Recap

items = ["col1,col2,col2",
         "2,2,1,",
         "1,1,1,13",
         "1,1,31",
         "1,1,1,1,1,1,1343"]
max(items)

'col1,col2,col2'

def get_fields_count(line):
    fields = line.split(",") # split the the text data based on comma and make a list
    return len(fields)
    
max(items, key=get_fields_count)

'1,1,1,1,1,1,1343'

volume = ["1.2B",
         "2.3M",
         "3.4B",
         "1.2M",
         "0"]

def get_numeric_volume(v):
    if v.endswith("B"):
        return float(v[:-1])*10**9
    elif v.endswith("M"):
        return float(v[:-1])*10**6
    else:
        return float(v)
        
max(volume, key=get_numeric_volume)

'3.4B'

min(volume, key=get_numeric_volume)

'0'

sorted(volume, key=get_numeric_volume)

['0', '1.2M', '2.3M', '1.2B', '3.4B']

%%file add.py

def add(a, b):
    return a+b

Overwriting add.py

import add # module

add.add(3, 4)

7

%%file addapp.py
import sys

def add(x, y):
    return x+y



a = int(sys.argv[1])
b = int(sys.argv[2])
print(add(a,b))

Overwriting addapp.py

!python3 addapp.py 34 67

101

Iterations

items

['col1,col2,col2', '2,2,1,', '1,1,1,13', '1,1,31', '1,1,1,1,1,1,1343']

for line in items: # first pattern
    print(line)

col1,col2,col2
2,2,1,
1,1,1,13
1,1,31
1,1,1,1,1,1,1343

Patterns of iterations

for i in range(5):
    print(i)

0
1
2
3
4

for i in reversed(range(5)):
    print(i)

4
3
2
1
0

items

['col1,col2,col2', '2,2,1,', '1,1,1,13', '1,1,31', '1,1,1,1,1,1,1343']

for line in reversed(items):
    print(line)

1,1,1,1,1,1,1343
1,1,31
1,1,1,13
2,2,1,
col1,col2,col2

nums = [1, 2, 3, 4, 5]

for n in reversed(nums):
    print(5)

5
5
5
5
5

nums

[1, 2, 3, 4, 5]

print(reversed(nums))

<list_reverseiterator object at 0x7f5a2eab0d90>

colors = ("red", "green", "blue")

for c in reversed(colors):
    print(c)

blue
green
red

for char in reversed("this is text data"):
    print(char, end=",") # print by defaults adds new lineafter every print! we are telling it that instead print ,

a,t,a,d, ,t,x,e,t, ,s,i, ,s,i,h,t,

poem = """This is first line of my poem
and this is another
which is obvously fake poem
but I don't mind it
calling as a poem"""

poem.split() # words!

['This',
 'is',
 'first',
 'line',
 'of',
 'my',
 'poem',
 'and',
 'this',
 'is',
 'another',
 'which',
 'is',
 'obvously',
 'fake',
 'poem',
 'but',
 'I',
 "don't",
 'mind',
 'it',
 'calling',
 'as',
 'a',
 'poem']

poem.split("\n")

['This is first line of my poem',
 'and this is another',
 'which is obvously fake poem',
 "but I don't mind it",
 'calling as a poem']

lines = poem.split("\n")

for i, line in enumerate(lines):
    print(i, line)

0 This is first line of my poem
1 and this is another
2 which is obvously fake poem
3 but I don't mind it
4 calling as a poem

for i, line in enumerate(lines, start=1):
    print(i, line)

1 This is first line of my poem
2 and this is another
3 which is obvously fake poem
4 but I don't mind it
5 calling as a poem

firstnames = ["Alice","Elsa", "Alex", "Elisa", "Vikrant"]
lastnames = ["Wondergirl", "Frozen", "Lion", "Hacker", "Patil"]
for name, surname in zip(firstnames, lastnames):
    print(name, surname)

Alice Wondergirl
Elsa Frozen
Alex Lion
Elisa Hacker
Vikrant Patil

xs = ["x1","x2","x3"]
ys = ["y1","y2","y3","y4"]

for x,y in zip(xs, ys):
    print(x, y)

x1 y1
x2 y2
x3 y3

xs = ["x1","x2","x3"]
ys = ["y1","y2","y3","y4"]
zs = ["z1","z2","z3","z4"]

for x,y,z in zip(xs, ys, zs):
    print(x, y, z)

x1 y1 z1
x2 y2 z2
x3 y3 z3

nums

[1, 2, 3, 4, 5]

r = reversed(nums) # this is iterator and not a list

for item in r: # this can be done only once
    print(item)

5
4
3
2
1

for item in r: # r is already consumed in about for loop!
    print(item) # here this loop will be empty

for i in reversed(range(5)):
    print(i)

4
3
2
1
0

nums = [1, 2, 3, 4, 5]
r = reversed(nums)
for item in r: # this can be done only once
    print(r)

<list_reverseiterator object at 0x7f34d3533190>
<list_reverseiterator object at 0x7f34d3533190>
<list_reverseiterator object at 0x7f34d3533190>
<list_reverseiterator object at 0x7f34d3533190>
<list_reverseiterator object at 0x7f34d3533190>

nums = [1, 2, 3, 4, 5]
r_nums = reversed(nums)
for i in r_nums: # this can be done only once
    print(i)

5
4
3
2
1

Problems

• Write a function called vector_add, which does vector addition (component wise addition)

  >>> v1 = [1, 1, 1]
  >>> v2 = [3, 4, 5]
  >>> vector_add(v1, v2)
  [4, 5, 6]

• A matrix is called as unit matrix if diagnal elements are nothing but 1. and all off diagonal elements are zero. Write a function is_unit_matrix

  >>> m = [[1, 0 , 0],
         [0, 1, 0],
         [0, 0, 1]]
  >>> is_unit_matrix(m)
  True

• Write a function called invertprint which takes a poem as multiline text and prints in order such that last line is first ..and first line at last

  >>> poem = """This is first line of my poem
  and this is another
  which is obvously fake poem
  but I don't mind it
  calling as a poem"""
  >>> invertprint(poem)
  calling as a poem
  but I don't mind it
  which is obviously fake poem
  and this is another
  This is first line of my poem

v1 = [1, 2, 3]
v2 = [2, 3, 4]

v1 + v2 # addition for a list is nothing but concatenation

[1, 2, 3, 2, 3, 4]

zip(v1, v2)

<zip at 0x7f34d30a3c00>

zip(v1+v2)

<zip at 0x7f34d30a5900>

def vector_add(v1, v2):
    v3 = []
    for x,y in zip(v1, v2):
        v3.append(x+y)
    return v3
    

def vector_add(v1, v2):
    i = 0
    v3 = []
    for item in v1:
        v4 = v1[i] + v2[i]
        v3.append(v4)
        i = i + 1
    
    return v3

def vector_add(vector1, vector2):
    v = []
    for v1, v2 in zip(vector1, vector2):
        v4 = v1 + v2
        v.append(v4)
    
    return v

def vector_add(v1, v2):

    v3 = []
    for i, item in enumerate(v1):
        v4 = item + v2[i]
        v3.append(v4)
    
    return v3

vector1 = [1, 2, 3]
vector2 = [2, 3, 4]
vector3 = [2, 3, 4]
vector4 = [1, 2, 3]


for x, y, z, m in zip(vector1, vector2, vector3, vector4):
    

def add(x, y):
    return x+y

add(3, 4)

7

add(3, 5, 6)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-15-7ab0921c8354> in <module>
----> 1 add(3, 5, 6)

TypeError: add() takes 2 positional arguments but 3 were given

def myadd(*args):
    print(args)

myadd(2, 3)

(2, 3)

myadd(3, 4, 5)

(3, 4, 5)

def myadd(*args):
    s = 0
    for i in args:
        s += i
    return s

myadd(1, 2, 3, 5)

11

myadd(1, 2)

3

nums = [1, 2, 3, 4, 6, 7, 8, 8]
#myadd(nums[0], nums[1], )...
myadd(*nums)

39

vector1 = [1, 2, 3]
vector2 = [2, 3, 4]
vector3 = [2, 3, 4]
vector4 = [1, 2, 3]
vector5 = [1, 1, 1]

list_of_vectors = [vector1,
                  vector2,
                  vector3,
                  vector4,
                  vector5]
v = []
for components in zip(*list_of_vectors):
    v.append(sum(components))

print(v)

[7, 11, 15]

vector1 = [1, 0, 0]
vector2 = [0, 3, 0] # this is not allowed
vector3 = [4, 0, 0]
vector4 = [1, 2, 2]
vector5 = [1, 1, 1]

csvfile = """1,1,2
,1,
,,3
1,2,3
"""

for line in csvfile.split("\n"):
    print(line)

1,1,2
,1,
,,3
1,2,3

for line in csvfile.split("\n"):
    print(line.split(","))

['1', '1', '2']
['', '1', '']
['', '', '3']
['1', '2', '3']
['']

def handle_spaces(line):
    values = line.split(",")
    intvalues = []
    for v in values:
        if v == "":
            intvalues.append(0)
        else:
            intvalues.append(int(v))
    return intvalues


def populate_spaces_with_zeros(csvfiledata):

    finaldata = []
    for line in csvfiledata.split("\n"):
        intvalues = handle_spaces(line)
        finaldata.append(intvalues)
    return finaldata

populate_spaces_with_zeros(csvfile)

[[1, 1, 2], [0, 1, 0], [0, 0, 3], [1, 2, 3], [0]]

m = [[1, 0 , 0],
     [0, 1, 0],
     [0, 0, 1]]

def is_unit_matrix(matrix):
    
    for i, row in enumerate(matrix): # i is row index
        if row[i] != 1: # diagonal element
            return False
        for j, item in enumerate(row): # j is column index
            if i!=j and item!=0:
                return False
        
    return True

is_unit_matrix(m)

True

m1 = [[1, 2, 3],
     [1, 2, 3],
     [1, 2, 3]]

is_unit_matrix(m1)

False

def invertprint(data):
    for line in reversed(data.split("\n")):
        print(line)

invertprint(poem)

calling as a poem
but I don't mind it
which is obvously fake poem
and this is another
This is first line of my poem

List Comprehension

def findlens(words):
    lens = []
    for word in words:
        lens.append(len(word))
        
    return lens


def squares(nums):
    sqrs = []
    for n in nums:
        sqrs.append(n*n)
    return sqrs
    

import datetime

def trange(n):
    """generates next n dates startng from today
    """
    dates = []
    start = datetime.datetime.today()
    for i in range(n):
        nextdate = start + datetime.timedelta(days=i)
        dates.append(nextdate)
    return dates

findlens(["one", "twi", "three"])

[3, 3, 5]

squares([2, 3, 4, 4])

[4, 9, 16, 16]

new_list = []

for item in in old_list:
    newitem = do_some_operation(item)
    new_list.append(newitem)

[ do_some_operation(item) for item in old_list]

def findlens(words):
    lens = []
    for word in words:
        lens.append(len(word))
        
    return lens

words = "Hello these are some words".split()
[len(word) for word in words] 

[5, 5, 3, 4, 5]

def squares(nums):
    sqrs = []
    for n in nums:
        sqrs.append(n*n)
    return sqrs
    
[n*n for n in nums]

[1, 4, 9, 16, 36, 49, 64, 64]

import datetime

def trange(n):
    """generates next n dates startng from today
    """
    dates = []
    start = datetime.datetime.today()
    for i in range(n):
        nextdate = start + datetime.timedelta(days=i)
        dates.append(nextdate)
    return dates

[datetime.datetime.today() + datetime.timedelta(days=i) for i in range(5)]

[datetime.datetime(2021, 10, 11, 12, 24, 5, 129980),
 datetime.datetime(2021, 10, 12, 12, 24, 5, 130003),
 datetime.datetime(2021, 10, 13, 12, 24, 5, 130008),
 datetime.datetime(2021, 10, 14, 12, 24, 5, 130012),
 datetime.datetime(2021, 10, 15, 12, 24, 5, 130014)]

Filtering

def evens(nums):
    e = []
    for n in nums:
        if n%2==0:
            e.append(n)
    return e

evens([1, 1, 2, 3, 1, 3, 4, 4, 6, 8])

[2, 4, 4, 6, 8]

nums = [1, 1, 2, 3, 1, 3, 4, 4, 6, 8]
[n for n in nums if n%2==0]

[2, 4, 4, 6, 8]

[n*n for n in nums if n%2==0]

[4, 16, 16, 36, 64]

problems

• Write a function listpy which works eactly like lisdir ..but it give back list of only python files( with extention ".py"

  >>> import os
  >>> listpy(os.getcwd())
  ['add.py','square.py', ...]

• Find sum of all multiples of 11 or 13 below 1000

• Write a function factors which finds all fatctors of given number (1 and self included)
• Write a function is_prime which tells if given number is prime number or not.
• Write a list comprehension to generate prime numbers less than n!

import os

os.listdir()

['index.html',
 'module1-day5.html',
 'mymodule.py',
 'push',
 'module1-day5.ipynb',
 'square.py',
 '__pycache__',
 'Untitled.html',
 'index.ipynb',
 'module1-day1.html',
 'module1-day1.ipynb',
 'module1-day2.ipynb',
 'add.py',
 'module1-assignment.ipynb',
 'aad.py',
 'module2-day1.ipynb',
 'module1-day3.html',
 'module1-day2.html',
 'module1-day3.ipynb',
 'module1-assignment.html',
 'module1-day4.html',
 'Makefile',
 'module2-day1.html',
 '.ipynb_checkpoints',
 'mymodule1.py',
 'addapp.py',
 'module1-day4.ipynb']

def listpy(dirpath):
    files = os.listdir(dirpath)
    return [file for file in files if file.endswith(".py")]

listpy(os.getcwd())

['mymodule.py', 'square.py', 'add.py', 'aad.py', 'mymodule1.py', 'addapp.py']

listpy(".") # . means current directory

['mymodule.py', 'square.py', 'add.py', 'aad.py', 'mymodule1.py', 'addapp.py']

os.listdir()

['index.html',
 'module1-day5.html',
 'mymodule.py',
 'push',
 'module1-day5.ipynb',
 'square.py',
 '__pycache__',
 'Untitled.html',
 'index.ipynb',
 'module1-day1.html',
 'module1-day1.ipynb',
 'module1-day2.ipynb',
 'add.py',
 'module1-assignment.ipynb',
 'aad.py',
 'module2-day1.ipynb',
 'module1-day3.html',
 'module1-day2.html',
 'module1-day3.ipynb',
 'module1-assignment.html',
 'module1-day4.html',
 'Makefile',
 'module2-day1.html',
 '.ipynb_checkpoints',
 'mymodule1.py',
 'addapp.py',
 'module1-day4.ipynb']

def listpy(dirpath=None):
    if dirpath==None:
        dirpath = os.getcwd()
    files = os.listdir(dirpath)
    return [file for file in files if file.endswith(".py")]

listpy() #means dirpath argument will be taken as NOne

['mymodule.py', 'square.py', 'add.py', 'aad.py', 'mymodule1.py', 'addapp.py']

def listpy_(): # this will work only for current directoty
    dirpath = os.getcwd()
    files = os.listdir(dirpath)
    return [file for file in files if file.endswith(".py")]

listpy("../arcesium_finop_batch1/")

['bank1.py',
 'tail.py',
 'bank0.py',
 'unixcommand.py',
 'capitalize.py',
 'modulezyx.py',
 'mymodule.py',
 'hello.py',
 'grep.py',
 'square.py',
 'head.py',
 'head1.py',
 'mymathmodule.py',
 'cat.py',
 'just_another.py',
 'testmodule.py',
 'mymath.py',
 'testmodule1.py',
 'helloworld.py',
 'mymodule1.py']

def factors(n):
    return [f for f in range(1, n+1) if n%f==0]

factors(5)

[1, 5]

factors(12)

[1, 2, 3, 4, 6, 12]

factors(49)

[1, 7, 49]

def is_prime(n):
    return factors(n)==[1,n]

[p for p in range(50) if is_prime(p)]

[2, 3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37, 41, 43, 47]

EXAMPLE

COUNTIFS implement this excel function

import operator as op

def seperate_value_cond(condstr):
    "<40"
    "<>40"
    value = int("".join([c for c in condstr if c.isdigit()]))
    cond = "".join([c for c in condstr if not c.isdigit()])
    return cond, value
    
    
def COUNTIFS(condlist, condstr):
    funcmap = {">": op.gt,
              ">=": op.ge,
              "<": op.lt,
              "<=": op.le,
              "<>": op.ne,
              "":op.eq}
    
    cond, value = seperate_value_cond(condstr)
    return len([v for v in condlist if funcmap[cond](v, value)])
    

COUNTIFS([10, 20, 30, 40, 50, 40, 40, 50], "<40")

3

COUNTIFS([10, 20, 30, 40, 50, 40, 40, 50], ">=40")

5

    
def SUMIFS(sumlist, condlist, condstr):
    funcmap = {">": op.gt,
              ">=": op.ge,
              "<": op.lt,
              "<=": op.le,
              "<>": op.ne,
              "":op.eq}
    
    cond, value = seperate_value_cond(condstr)
    return sum([v for v,c in zip(sumlist, condlist) if funcmap[cond](c, value)])
    

SUMIFS([1, 2, 3, 4, 5, 4, 4, 5], [10, 20, 30, 40, 50, 40, 40, 50], "<40")

6