Python 2

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
Week 01
Thursday 26 August 2021
What we have done till now

Basic Data types
String Slicing
Conditionals
Lists, Tuples, Dict, Set
Agenda for today

Coding Exercise (Solutions)
User Defined Functions
Libraries in Python
Pandas
Coding Exercise Solutions

Assignment 01
Create a dictionary for the squares of the first 25 natural numbers
Get user input
Use the input as a dictionary key to get the square
In [1]: # Using lists and zip
number_list = []
sq_list = []
for i in range(1,25+1):
number_list.append(i)
sq_list.append(i**2)
sq_dict = dict(zip(number_list, sq_list))
sq_dict
Out[1]: {1: 1,
2: 4,
3: 9,
4: 16,
5: 25,
6: 36,
7: 49,
8: 64,
9: 81,
10: 100,
11: 121,
localhost:8888/nbconvert/html/Completed 004 2021-08-23 to 2021-09-10.ipynb?download=false 1/117

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
12: 144,
13: 169,
14: 196,
15: 225,
16: 256,
17: 289,
18: 324,
19: 361,
20: 400,
21: 441,
22: 484,
23: 529,
24: 576,
25: 625}
In [2]: # Appending to an empty dictionary
sq_dict2 = {}
for i in range(1,25+1):
sq_dict2.update({i : i**2})
sq_dict2
Out[2]: {1: 1,
2: 4,
3: 9,
4: 16,
5: 25,
6: 36,
7: 49,
8: 64,
9: 81,
10: 100,
11: 121,
12: 144,
13: 169,
14: 196,
15: 225,
16: 256,
17: 289,
18: 324,
19: 361,
20: 400,
21: 441,
22: 484,
23: 529,
24: 576,
25: 625}
In [3]: user_input = int(input("Enter a number "))
print(f"Square of {user_input} is {sq_dict.get(user_input, 'Not found')}") # Set a defa
Enter a number 12
Square of 12 is 144
Assignment 02
You are given a string that contains alphanumeric characters only. Your task is to sort the string in
the following manner:
All sorted lowercase letters are ahead of uppercase letters.

All sorted uppercase letters are ahead of digits.
9/8/2021 Completed 004 2021-08-23 to 2021-09-10
All sorted odd digits are ahead of sorted even digits.
Input : A single line of input contains the string
Output : Sorted string
In [4]: sample_str = 'Sorting1234'
lower_case = []
upper_case = []
odd_digits = []
even_digits = []
for c in sample_str:
# Separate the lower case characters
if c.islower():
lower_case.append(c)
# Separate the upper case characters
elif c.isupper():
upper_case.append(c)
# Check the numbers
elif c.isnumeric():
if int(c) % 2 == 0:
even_digits.append(c)
else:
odd_digits.append(c)
# Combine the individual lists
final_list = sorted(lower_case) + sorted(upper_case) + sorted(odd_digits) + sorted(even_

# Convert the list to string
final_str = ''
for list_item in final_list:
final_str = final_str + list_item
# Use join method
final_str2 = ''.join(final_list)
print(lower_case, upper_case)
print(odd_digits, even_digits)
print(final_list)
print(final_str)
print(final_str2)
['o', 'r', 't', 'i', 'n', 'g'] ['S']
['1', '3'] ['2', '4']
['g', 'i', 'n', 'o', 'r', 't', 'S', '1', '3', '2', '4']
ginortS1324
ginortS1324
User Defined Functions

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
Functions are used for
Readability
Reuse existing code
Creating the Prime Number Function
In [5]: def add_two_numbers(a, b):
print(a + b)
y =add_two_numbers(12, 50)
62
In [6]: print(y)
None
In [7]: def add_two_numbers_r(a, b):
return a + b
x = add_two_numbers_r(12, 50)
print(x)
62
In [8]: # Convert the code block in a function
def prime_number_check(num):
# Start of function block
if num == 1:
is_prime = False
else:
is_prime = True

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
for i in range(2, num):
# Start For Loop
if num % i == 0:
# Start if condition
is_prime = False
break
# End if condition
# End if loop
if is_prime:
return 'Prime Number'
else:
return 'Not a Prime Number'
# End of function block
user_num = int(input('Enter a Number '))
print(prime_number_check(user_num))
Enter a Number 12
Not a Prime Number
Function Definition
def (keyword to specify a function) (function name) (inputs or arguments):
Body of the function
return (any value to be returned by the function) - not necessary
In [9]: # Convert the code block in a function
def prime_number_check(num):
# Start of function block
if num == 1:
return "Not a Prime Number"
for i in range(2, num):
# Start For Loop
if num % i == 0:
# Start if condition
return "Not a Prime Number"
# End if condition
# End if loop
return 'Prime Number'
# End of function block
for i in range(20):
print(i, prime_number_check(i))
0 Prime Number
1 Not a Prime Number
2 Prime Number
3 Prime Number
5 Prime Number

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
7 Prime Number
11 Prime Number
13 Prime Number
17 Prime Number
19 Prime Number
In [ ]:
In [10]: # Returning Multiple Values
def mult_ops(a, b):
return (a + b), (a-b), (a*b)
out_vals = mult_ops(15, 6)
type(out_vals)
Out[10]: tuple
In [11]: out_vals
Out[11]: (21, 9, 90)
In [ ]:
In [12]: p, q, r = mult_ops(12, 8)
In [13]: p
Out[13]: 20
In [14]: q
Out[14]: 4
In [15]: r
Out[15]: 96
In [ ]:
Coding Exercise
The Fibonacci Series
F(n) is a mathematical series defined as
F(0) = 0
F(1) = 1
9/8/2021 Completed 004 2021-08-23 to 2021-09-10
F(n) = F(n-1) + F(n-2) for n > 1
Instructions
Ask the user to input a non negative integer (n)

Return the Fibonacci number corresponding to F(n)
Coding Exericise Solution

In [31]: def fib(num):
fib_list = [0,1]
for i in range(2, num+1):
# Start for loop
next_value = fib_list[i-1] + fib_list[i-2]
fib_list.append(next_value)
# fib_list = fib_list + [next_value]
# End for loop
return fib_list[num]
# Check values with Excel Sheet
for i in range(20):
print(f'{i}, fib({i}) = {fib(i)}')
0, fib(0) = 0
1, fib(1) = 1
2, fib(2) = 1
3, fib(3) = 2
4, fib(4) = 3
5, fib(5) = 5
6, fib(6) = 8
7, fib(7) = 13
8, fib(8) = 21
9, fib(9) = 34
10, fib(10) = 55
11, fib(11) = 89
12, fib(12) = 144
13, fib(13) = 233
14, fib(14) = 377
15, fib(15) = 610
16, fib(16) = 987
17, fib(17) = 1597
18, fib(18) = 2584
19, fib(19) = 4181
In [42]: fib(5000)
Out[42]: 3878968454388325633701916308325905312082127714646245106160597214895550139044037097010822
9164622106694792934528588829738134831020089549829403614301569114789383642165639441069102
1450563413370655865623825465670071252592990385493381392883637834751890876297071203333705
2923107693008518093849801803847813996748881765554653788291644268912980384613778969021502
2930824756663462249230718833248032803750391303529033045058427011476352422702109346376991
0400671417488329842289149127310405432875329804427367682297724498774987455569190770388063
7046832794811358973739993110106219308149018570815397854379195305617510761053075688783766
0336673554452588448862416192105534574936758978490279882343510235998446639348532564119522
2185956306047536464547076033090242080638258492915645287629157575914234380914230291749108
8984155209854432486594079793571316841692868039545309545388698114665082066862897420639323
4384884652409887423958738019769938203171742089322654688793640026307977800587591296713896
34214252579116872755600360311370547754724604639987588046985178408674382863125
Recursion
9/8/2021 Completed 004 2021-08-23 to 2021-09-10
A function calls itself
In [36]: def rec_fib(num):
print(f'Calculating for {num}')
if num == 0:
return 0
elif num == 1:
return 1
else:
print(f"Calculating for {num-1} + {num - 2}")
return rec_fib(num - 1) + rec_fib(num - 2)
rec_fib(0)
Calculating for 0
Out[36]: 0
In [33]: rec_fib(1)
Calculating for 1
Out[33]: 1
In [34]: rec_fib(2)
Calculating for 2
Calculating for 1
Calculating for 0
Out[34]: 1
In [37]: rec_fib(3)
Calculating for 3
Calculating for 2 + 1
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 1
Out[37]: 2
In [38]: rec_fib(7)
Calculating for 7
Calculating for 6
Calculating for 5
Calculating for 4
Calculating for 3
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 1
Calculating for 2
Calculating for 1

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
Calculating for 0
Calculating for 3
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 1
Calculating for 4
Calculating for 3
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 1
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 5
Calculating for 4
Calculating for 3
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 1
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 3
Calculating for 2
Calculating for 1
Calculating for 0
Calculating for 1
Out[38]: 13
In [39]: rec_fib(5000)
Calculating for 5000

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
---------------------------------------------------------------------------
RecursionError Traceback (most recent call last)
<ipython-input-39-978d0ba5a189> in <module>
----> 1 rec_fib(5000)
<ipython-input-36-92eee5791210> in rec_fib(num)
7 else:
8 print(f"Calculating for {num-1} + {num - 2}")
----> 9 return rec_fib(num - 1) + rec_fib(num - 2)
10
11 rec_fib(0)
... last 1 frames repeated, from the frame below ...
<ipython-input-36-92eee5791210> in rec_fib(num)
7 else:
8 print(f"Calculating for {num-1} + {num - 2}")
----> 9 return rec_fib(num - 1) + rec_fib(num - 2)
10
11 rec_fib(0)
RecursionError: maximum recursion depth exceeded while calling a Python object
In [ ]:
In [ ]:
Lambda Expressions
https://docs.python.org/3.8/reference/expressions.html#lambda

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
In [16]: add_vals_lambda = lambda a, b : a+b
add_vals_lambda(10,12)
Out[16]: 22
In [17]: add_vals_lambda(12, 50)
Out[17]: 62
In [18]: multiply_lambda = lambda x, y, z : x*z + y*z
In [19]: multiply_lambda(12,6,8)
Out[19]: 144
In [43]: # Fibonacci series as a lambda function
rec_lambda = lambda x : 1 if x == 1 else 0 if x == 0 else rec_lambda(x-1) + rec_lambda(

rec_lambda(10)
Out[43]: 55
In [ ]:
In [ ]:
Function Arguments in Python

Arguments = Inputs to the functions
Positional arguments are arguments that can be called by their position in the function
definition.
Keyword arguments are arguments that can be called by their name.
Required arguments are arguments that must passed to the function.
Optional arguments are argument that can need not passed to the function. In python
optional arguments are arguments that have a default value.
In [20]: def some_func(p, q, r, s):
print("p value is ", p)
print("q value is ", q)
print("r value is ", r)
print("s value is ", s)
print('--------------------------')
some_func(1,2,3,4) # Arguements by position
some_func(12, 23, 65, 1) # Arguements by position
p value is 1
q value is 2
r value is 3
s value is 4
--------------------------
p value is 12
q value is 23
r value is 65

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
s value is 1
--------------------------
In [21]: some_func(s = 12, p = 23, r = 65, q =1) # Keywords
p value is 23
q value is 1
r value is 65
s value is 12
--------------------------
In [22]: some_func(12, 15, s = 36, r = -2 ) # Both position and Keyword
p value is 12
q value is 15
r value is -2
s value is 36
--------------------------
In [23]: some_func(p = 12, 15, 36, r = -2 ) # Error because positional follows keyword
File "<ipython-input-23-720c696d83cc>", line 1
some_func(p = 12, 15, 36, r = -2 )
SyntaxError: positional argument follows keyword argument
In [24]: # You cannot have a positional arguement after a keyword arguement
some_func(12, 15, p = 36, s= -2 ) # Both position and Keyword
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-24-664dd3852deb> in <module>
1 # You cannot have a positional arguement after a keyword arguement
----> 2 some_func(12, 15, p = 36, s= -2 ) # Both position and Keyword
TypeError: some_func() got multiple values for argument 'p'
In [25]: # Another Function
# Default values for b and c
def another_func(a, d, b = -2, c = 50):
print("a value is ", a)
print("b value is ", b)
print("c value is ", c)
print("d value is ", d)
print('--------------------------')
In [26]: another_func(12, 20)
a value is 12
b value is -2
c value is 50
d value is 20
--------------------------
In [27]: another_func(12, 20, 55) # changes the default value of b (positional)
a value is 12
b value is 55
c value is 50
d value is 20
--------------------------

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
In [28]: another_func(12)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-28-73d7f6be72db> in <module>
----> 1 another_func(12)
TypeError: another_func() missing 1 required positional argument: 'd'
In [29]: another_func(11, 59, c = 23)
a value is 11
b value is -2
c value is 23
d value is 59
--------------------------
In [30]: another_func(11, 59, c = "Vivek")
a value is 11
b value is -2
c value is Vivek
d value is 59
--------------------------
In [ ]:
Python Libraries
Libraries developed for most common tasks
Vast resources
Documented
Forked to create your own libraries
Libraries that Data Scientists we will be dealing with on a regular

basis
Pandas (for tabular data)
Matplotlib (for visualization)
Seaborn (for visualization)
Numpy (for fast Math)
SciPy (for stats and Math)
Scikit Learn (for Machine Learning)
NLTK (for Natural Language Processing)
Beautiful Soup (for Web Scraping)
Requests (for Web Scraping)
Others
json (to read / write json files)

pickle (to save items)
os (OS based functions)
path (in conjuction with os)
9/8/2021 Completed 004 2021-08-23 to 2021-09-10
sys (system functions)

datetime (for date and time utilities)
Python Packages
https://pypi.org/
In [ ]:
Installing Libraries
using pip
In [44]: !pip install pandas
Requirement already satisfied: pandas in c:\programdata\anaconda3\lib\site-packages (1.

2.2)
Requirement already satisfied: pytz>=2017.3 in c:\programdata\anaconda3\lib\site-package

s (from pandas) (2019.3)
Requirement already satisfied: python-dateutil>=2.7.3 in c:\programdata\anaconda3\lib\si

te-packages (from pandas) (2.8.0)
Requirement already satisfied: numpy>=1.16.5 in c:\programdata\anaconda3\lib\site-packag

es (from pandas) (1.20.1)
Requirement already satisfied: six>=1.5 in c:\programdata\anaconda3\lib\site-packages (f

rom python-dateutil>=2.7.3->pandas) (1.12.0)
Pandas
Your Excel Sheet in Python
You are going to spend a lot of time with Pandas.
Master Pandas
https://pandas.pydata.org/docs/
In [45]: import pandas as pd # Alias
In [46]: dir(pd)
Out[46]: ['BooleanDtype',

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
'Categorical',
'CategoricalDtype',
'CategoricalIndex',
'DataFrame',
'DateOffset',
'DatetimeIndex',
'DatetimeTZDtype',
'ExcelFile',
'ExcelWriter',
'Flags',
'Float32Dtype',
'Float64Dtype',
'Float64Index',
'Grouper',
'HDFStore',
'Index',
'IndexSlice',
'Int16Dtype',
'Int32Dtype',
'Int64Dtype',
'Int64Index',
'Int8Dtype',
'Interval',
'IntervalDtype',
'IntervalIndex',
'MultiIndex',
'NA',
'NaT',
'NamedAgg',
'Period',
'PeriodDtype',
'PeriodIndex',
'RangeIndex',
'Series',
'SparseDtype',
'StringDtype',
'Timedelta',
'TimedeltaIndex',
'Timestamp',
'UInt16Dtype',
'UInt32Dtype',
'UInt64Dtype',
'UInt64Index',
'UInt8Dtype',
'__builtins__',
'__cached__',
'__doc__',
'__docformat__',
'__file__',
'__getattr__',
'__git_version__',
'__loader__',
'__name__',
'__package__',
'__path__',
'__spec__',
'__version__',
'_config',
'_hashtable',
'_is_numpy_dev',
'_lib',
'_libs',
'_np_version_under1p17',
'_np_version_under1p18',
'_testing',

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
'_tslib',
'_typing',
'_version',
'api',
'array',
'arrays',
'bdate_range',
'compat',
'concat',
'core',
'crosstab',
'cut',
'date_range',
'describe_option',
'errors',
'eval',
'factorize',
'get_dummies',
'get_option',
'infer_freq',
'interval_range',
'io',
'isna',
'isnull',
'json_normalize',
'lreshape',
'melt',
'merge',
'merge_asof',
'merge_ordered',
'notna',
'notnull',
'offsets',
'option_context',
'options',
'pandas',
'period_range',
'pivot',
'pivot_table',
'plotting',
'qcut',
'read_clipboard',
'read_csv',
'read_excel',
'read_feather',
'read_fwf',
'read_gbq',
'read_hdf',
'read_html',
'read_json',
'read_orc',
'read_parquet',
'read_pickle',
'read_sas',
'read_spss',
'read_sql',
'read_sql_query',
'read_sql_table',
'read_stata',
'read_table',
'reset_option',
'set_eng_float_format',
'set_option',
'show_versions',
'test',

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
'testing',
'timedelta_range',
'to_datetime',
'to_numeric',
'to_pickle',
'to_timedelta',
'tseries',
'unique',
'util',
'value_counts',
'wide_to_long']
In [ ]:
Data Frames
Creating Data Frames using Lists
In [47]: number = []
square = []
for i in range(1, 11):
number.append(i)
square.append(i**2)
number
Out[47]: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
In [48]: square
Out[48]: [1, 4, 9, 16, 25, 36, 49, 64, 81, 100]
In [49]: num_df = pd.DataFrame(number, columns = ['Number'])
num_df
Out[49]: Number
0 1
1 2
2 3
3 4
4 5
5 6
6 7
7 8
8 9
9 10
In [50]: num_df2 = pd.DataFrame(number, index = square) # No column name, the square list passed
num_df2
Out[50]:
9/8/2021 Completed 004 2021-08-23 to 2021-09-10
1 1
4 2
9 3
16 4
25 5
36 6
49 7
64 8
81 9
100 10
In [ ]:
Creating DataFrames using zip
In [51]: sq_list = list(zip(number, square))
sq_list
Out[51]: [(1, 1),
(2, 4),
(3, 9),
(4, 16),
(5, 25),
(6, 36),
(7, 49),
(8, 64),
(9, 81),
(10, 100)]
In [52]: sq_df = pd.DataFrame(sq_list, columns = ['Number', 'Square'])
sq_df
Out[52]: Number Square
0 1 1
1 2 4
2 3 9
3 4 16
4 5 25
5 6 36
6 7 49
7 8 64
8 9 81
9 10 100

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
In [ ]:
In [ ]:
Creating DataFrames using dict
In [53]: sq_dict = dict({'Number' : number, 'Square' : square})

sq_dict
Out[53]: {'Number': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'Square': [1, 4, 9, 16, 25, 36, 49, 64, 81, 100]}
In [54]: sq_df2 = pd.DataFrame(sq_dict)
sq_df2
Out[54]: Number Square
0 1 1
1 2 4
2 3 9
3 4 16
4 5 25
5 6 36
6 7 49
7 8 64
8 9 81
9 10 100
Read a File

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
image Source:
Data Source:
CSV file
read_csv
https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
In [55]: pokemon_df = pd.read_csv(r'C:\Vivek\Misc\Simplilearn\Pokemon.csv')
pokemon_df
Out[55]: Type Sp. Sp.

Name Type 1 Total HP Attack Defense Speed Generation Legenda
2 Atk Def
0 Bulbasaur Grass Poison 318 45 49 49 65 65 45 1 Fa
1 Ivysaur Grass Poison 405 60 62 63 80 80 60 1 Fa
2 Venusaur Grass Poison 525 80 82 83 100 100 80 1 Fa
VenusaurMega
3 Grass Poison 625 80 100 123 122 120 80 1 Fa
Venusaur
4 Charmander Fire NaN 309 39 52 43 60 50 65 1 Fa
... ... ... ... ... ... ... ... ... ... ... ...
795 Diancie Rock Fairy 600 50 100 150 100 150 50 6 T
DiancieMega
796 Rock Fairy 700 50 160 110 160 110 110 6 T
Diancie
HoopaHoopa
797 Psychic Ghost 600 80 110 60 150 130 70 6 T
Confined
HoopaHoopa
798 Psychic Dark 680 80 160 60 170 130 80 6 T
Unbound
799 Volcanion Fire Water 600 80 110 120 130 90 70 6 T

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
800 rows × 12 columns
In [ ]:
CSV file without headers
In [59]: pokemon_v2_df = pd.read_csv(r'C:\Vivek\Misc\Simplilearn\Pokemon v2.csv', header= None)
pokemon_v2_df
Out[59]: 0 1 2 3 4 5 6 7 8 9 10 11
0 Bulbasaur Grass Poison 318 45 49 49 65 65 45 1 False
1 Ivysaur Grass Poison 405 60 62 63 80 80 60 1 False
2 Venusaur Grass Poison 525 80 82 83 100 100 80 1 False
3 VenusaurMega Venusaur Grass Poison 625 80 100 123 122 120 80 1 False
4 Charmander Fire NaN 309 39 52 43 60 50 65 1 False
... ... ... ... ... ... ... ... ... ... ... ... ...
795 Diancie Rock Fairy 600 50 100 150 100 150 50 6 True
796 DiancieMega Diancie Rock Fairy 700 50 160 110 160 110 110 6 True
797 HoopaHoopa Confined Psychic Ghost 600 80 110 60 150 130 70 6 True
798 HoopaHoopa Unbound Psychic Dark 680 80 160 60 170 130 80 6 True
799 Volcanion Fire Water 600 80 110 120 130 90 70 6 True
Read only the first n rows - use the nrows arguement
In [60]: pokemon_v2_df = pd.read_csv(r'C:\Vivek\Misc\Simplilearn\Pokemon v2.csv', header = None,

pokemon_v2_df
Out[60]: 0 1 2 3 4 5 6 7 8 9 10 11
3 VenusaurMega Venusaur Grass Poison 625 80 100 123 122 120 80 1 False
... ... ... ... ... ... ... ... ... ... ... ... ...
95 Grimer Poison NaN 325 80 80 50 40 50 25 1 False
96 Muk Poison NaN 500 105 105 75 65 100 50 1 False
97 Shellder Water NaN 305 30 65 100 45 25 40 1 False
98 Cloyster Water Ice 525 50 95 180 85 45 70 1 False

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
0 1 2 3 4 5 6 7 8 9 10 11
99 Gastly Ghost Poison 310 30 35 30 100 35 80 1 False
In [ ]:
In [ ]:
Tab Separated file
In [62]: pokemon_txt_df = pd.read_csv('Pokemon.txt', delimiter = '\t')
pokemon_txt_df

2 Atk Def
VenusaurMega
3 Grass Poison 625 80 100 123 122 120 80 1 Fa
Venusaur
... ... ... ... ... ... ... ... ... ... ... ...
DiancieMega
796 Rock Fairy 700 50 160 110 160 110 110 6 T
Diancie
HoopaHoopa
797 Psychic Ghost 600 80 110 60 150 130 70 6 T
Confined
HoopaHoopa
798 Psychic Dark 680 80 160 60 170 130 80 6 T
Unbound
In [ ]:
In [ ]:
Excel File
read_excel
https://pandas.pydata.org/docs/reference/api/pandas.read_excel.html
In [63]: pokemon_excel_df = pd.read_excel('Pokemon.xlsx')

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
pokemon_excel_df

2 Atk Def
VenusaurMega
3 Grass Poison 625 80 100 123 122 120 80 1 Fa
Venusaur
... ... ... ... ... ... ... ... ... ... ... ...
DiancieMega
796 Rock Fairy 700 50 160 110 160 110 110 6 T
Diancie
HoopaHoopa
797 Psychic Ghost 600 80 110 60 150 130 70 6 T
Confined
HoopaHoopa
798 Psychic Dark 680 80 160 60 170 130 80 6 T
Unbound
In [ ]:
In [ ]:
In [ ]:
Basic Operations
Exploring the Data
info
In [64]: pokemon_df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 800 entries, 0 to 799
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Name 800 non-null object
1 Type 1 800 non-null object
2 Type 2 414 non-null object
3 Total 800 non-null int64
4 HP 800 non-null int64
5 Attack 800 non-null int64
6 Defense 800 non-null int64
7 Sp. Atk 800 non-null int64

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
8 Sp. Def 800 non-null int64
9 Speed 800 non-null int64
10 Generation 800 non-null int64
11 Legendary 800 non-null bool
dtypes: bool(1), int64(8), object(3)
memory usage: 69.7+ KB
In [ ]:
shape
In [65]: pokemon_df.shape
Out[65]: (800, 12)
describe
In [66]: pokemon_df.describe()
Out[66]: Total HP Attack Defense Sp. Atk Sp. Def Speed Generation
count 800.00000 800.000000 800.000000 800.000000 800.000000 800.000000 800.000000 800.00000
mean 435.10250 69.258750 79.001250 73.842500 72.820000 71.902500 68.277500 3.32375
std 119.96304 25.534669 32.457366 31.183501 32.722294 27.828916 29.060474 1.66129
min 180.00000 1.000000 5.000000 5.000000 10.000000 20.000000 5.000000 1.00000
25% 330.00000 50.000000 55.000000 50.000000 49.750000 50.000000 45.000000 2.00000
50% 450.00000 65.000000 75.000000 70.000000 65.000000 70.000000 65.000000 3.00000
75% 515.00000 80.000000 100.000000 90.000000 95.000000 90.000000 90.000000 5.00000
max 780.00000 255.000000 190.000000 230.000000 194.000000 230.000000 180.000000 6.00000
In [67]: pokemon_df.describe(include = 'all') # For all types of data
Out[67]: Type Type

Name Total HP Attack Defense Sp. Atk Sp. Def
1 2
count 800 800 414 800.00000 800.000000 800.000000 800.000000 800.000000 800.000000 80
unique 800 18 18 NaN NaN NaN NaN NaN NaN
top Cleffa Water Flying NaN NaN NaN NaN NaN NaN
freq 1 112 97 NaN NaN NaN NaN NaN NaN
mean NaN NaN NaN 435.10250 69.258750 79.001250 73.842500 72.820000 71.902500 6
std NaN NaN NaN 119.96304 25.534669 32.457366 31.183501 32.722294 27.828916 2
min NaN NaN NaN 180.00000 1.000000 5.000000 5.000000 10.000000 20.000000
25% NaN NaN NaN 330.00000 50.000000 55.000000 50.000000 49.750000 50.000000 4
50% NaN NaN NaN 450.00000 65.000000 75.000000 70.000000 65.000000 70.000000 6
75% NaN NaN NaN 515.00000 80.000000 100.000000 90.000000 95.000000 90.000000 9
max NaN NaN NaN 780.00000 255.000000 190.000000 230.000000 194.000000 230.000000 18

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
Head
In [68]: pokemon_df.head()
Out[68]: Type Type Sp. Sp.

Name Total HP Attack Defense Speed Generation Legendary
1 2 Atk Def
VenusaurMega
3 Grass Poison 625 80 100 123 122 120 80 1 False
Venusaur
In [69]: pokemon_df.head(20) # Top N default is 5

Name Type 2 Total HP Attack Defense Speed Generation Legendar
1 Atk Def
0 Bulbasaur Grass Poison 318 45 49 49 65 65 45 1 Fals
1 Ivysaur Grass Poison 405 60 62 63 80 80 60 1 Fals
2 Venusaur Grass Poison 525 80 82 83 100 100 80 1 Fals
VenusaurMega
3 Grass Poison 625 80 100 123 122 120 80 1 Fals
Venusaur
4 Charmander Fire NaN 309 39 52 43 60 50 65 1 Fals
5 Charmeleon Fire NaN 405 58 64 58 80 65 80 1 Fals
6 Charizard Fire Flying 534 78 84 78 109 85 100 1 Fals
CharizardMega
7 Fire Dragon 634 78 130 111 130 85 100 1 Fals
Charizard X
CharizardMega
8 Fire Flying 634 78 104 78 159 115 100 1 Fals
Charizard Y
9 Squirtle Water NaN 314 44 48 65 50 64 43 1 Fals
10 Wartortle Water NaN 405 59 63 80 65 80 58 1 Fals
11 Blastoise Water NaN 530 79 83 100 85 105 78 1 Fals
BlastoiseMega
12 Water NaN 630 79 103 120 135 115 78 1 Fals
Blastoise
13 Caterpie Bug NaN 195 45 30 35 20 20 45 1 Fals
14 Metapod Bug NaN 205 50 20 55 25 25 30 1 Fals
15 Butterfree Bug Flying 395 60 45 50 90 80 70 1 Fals
16 Weedle Bug Poison 195 40 35 30 20 20 50 1 Fals
17 Kakuna Bug Poison 205 45 25 50 25 25 35 1 Fals

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
Type Sp. Sp.

Name Type 2 Total HP Attack Defense Speed Generation Legendar
1 Atk Def
18 Beedrill Bug Poison 395 65 90 40 45 80 75 1 Fals
BeedrillMega
19 Bug Poison 495 65 150 40 15 80 145 1 Fals
Beedrill
In [ ]:
Tail
In [70]: pokemon_df.tail(10) # bottom N - default = 5
Out[70]: Sp. Sp.

Name Type 1 Type 2 Total HP Attack Defense Speed Generation Legend
Atk Def
790 Noibat Flying Dragon 245 40 30 35 45 40 55 6 Fa
791 Noivern Flying Dragon 535 85 70 80 97 80 123 6 Fa
792 Xerneas Fairy NaN 680 126 131 95 131 98 99 6 T
793 Yveltal Dark Flying 680 126 131 95 131 98 99 6 T
Zygarde50%
794 Dragon Ground 600 108 100 121 81 95 95 6 T
Forme
DiancieMega
796 Rock Fairy 700 50 160 110 160 110 110 6 T
Diancie
HoopaHoopa
797 Psychic Ghost 600 80 110 60 150 130 70 6 T
Confined
HoopaHoopa
798 Psychic Dark 680 80 160 60 170 130 80 6 T
Unbound
Column Names
In [71]: pokemon_df.columns
Out[71]: Index(['Name', 'Type 1', 'Type 2', 'Total', 'HP', 'Attack', 'Defense',
'Sp. Atk', 'Sp. Def', 'Speed', 'Generation', 'Legendary'],
dtype='object')
In [72]: pokemon_df.columns.to_list()
Out[72]: ['Name',
'Type 1',
'Type 2',
'Total',
'HP',
'Attack',
'Defense',
'Sp. Atk',

9/8/2021 Completed 004 2021-08-23 to 2021-09-10
'Sp. Def',
'Speed',
'Generation',
'Legendary']

Python 2

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Python 2

Uploaded by

Copyright:

Available Formats

9/8/2021 Completed 004 2021-08-23 to 2021-09-10

What we have done till now

Agenda for today

Coding Exercise Solutions

In [1]: # Using lists and zip

sq_dict = dict(zip(number_list, sq_list))

localhost:8888/nbconvert/html/Completed 004 2021-08-23 to 2021-09-10.ipynb?download=false 1/117

In [2]: # Appending to an empty dictionary

In [3]: user_input = int(input("Enter a number "))

print(f"Square of {user_input} is {sq_dict.get(user_input, 'Not found')}") # Set a defa

All sorted lowercase letters are ahead of uppercase letters.

All sorted odd digits are ahead of sorted even digits.

Input : A single line of input contains the string

Output : Sorted string

In [4]: sample_str = 'Sorting1234'

# Separate the lower case characters

# Separate the upper case characters

# Check the numbers

# Combine the individual lists

final_list = sorted(lower_case) + sorted(upper_case) + sorted(odd_digits) + sorted(even_

# Convert the list to string

for list_item in final_list:

final_str = final_str + list_item

# Use join method

['o', 'r', 't', 'i', 'n', 'g'] ['S']

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

User Defined Functions

localhost:8888/nbconvert/html/Completed 004 2021-08-23 to 2021-09-10.ipynb?download=false 3/117

Functions are used for

Creating the Prime Number Function

In [5]: def add_two_numbers(a, b):

In [7]: def add_two_numbers_r(a, b):

In [8]: # Convert the code block in a function

# Start of function block

localhost:8888/nbconvert/html/Completed 004 2021-08-23 to 2021-09-10.ipynb?download=false 4/117

# Start For Loop

return 'Prime Number'

return 'Not a Prime Number'

# End of function block

user_num = int(input('Enter a Number '))

Not a Prime Number

def (keyword to specify a function) (function name) (inputs or arguments):

Body of the function

return (any value to be returned by the function) - not necessary

In [9]: # Convert the code block in a function

# Start of function block

return "Not a Prime Number"

for i in range(2, num):

# Start For Loop

return "Not a Prime Number"

return 'Prime Number'

# End of function block

1 Not a Prime Number

4 Not a Prime Number

6 Not a Prime Number

localhost:8888/nbconvert/html/Completed 004 2021-08-23 to 2021-09-10.ipynb?download=false 5/117

8 Not a Prime Number

9 Not a Prime Number

10 Not a Prime Number

12 Not a Prime Number

14 Not a Prime Number

15 Not a Prime Number

16 Not a Prime Number