Python 101 - Python Libraries for Data Analysis - Numpy and

Pandas

May 29, 2025

1 TASK #1: DEFINE SINGLE AND MULTI-DIMENSIONAL

NUMPY ARRAYS
[20]: # NumPy is a Linear Algebra Library used for multidimensional arrays
# NumPy brings the best of two worlds: (1) C/Fortran computational efficiency,␣
↪(2) Python language easy syntax

import numpy as np

# Let's define a one-dimensional array

list_1 = [50, 60, 80, 100, 200, 300, 500, 600,]
list_1

[20]: [50, 60, 80, 100, 200, 300, 500, 600]

[21]: # Let's create a numpy array from the list "my_list"

my_numpy_array = np.array(list_1)
my_numpy_array

[21]: array([ 50, 60, 80, 100, 200, 300, 500, 600])

[5]: type(my_numpy_array)

[5]: numpy.ndarray

Multi-dimensional (Matrix definition)

[6]: my_matrix = np.array([[2, 5, 8], [7, 3, 6]])
my_matrix

[6]: array([[2, 5, 8],

[7, 3, 6]])

MINI CHALLENGE #1: - Write a code that creates the following 2x4 numpy array
[[3 7 9 3]
[4 3 2 2]]

1
[3]: x = np.array([[3, 7, 9, 3],
[4, 3, 2, 1]])
x

[3]: array([[3, 7, 9, 3],

[4, 3, 2, 1]])

[ ]:

2 TASK #2: LEVERAGE NUMPY BUILT-IN METHODS AND

FUNCTIONS
[8]: # "rand()" uniform distribution between 0 and 1: génére une valeur aléatoire
x = np.random.rand(20)
x

[8]: array([0.14056323, 0.53908128, 0.29549647, 0.03517011, 0.89102171,

0.05271959, 0.3741947 , 0.2051953 , 0.16712427, 0.65044685,
0.68705185, 0.26958268, 0.13184144, 0.36498677, 0.67224159,
0.42635753, 0.75119414, 0.82521819, 0.09219216, 0.85630017])

[9]: # you can create a matrix of random number as well

x = np.random.rand(3, 3)
x

[9]: array([[0.75189542, 0.8534315 , 0.58733699],

[0.10275586, 0.36892311, 0.54795311],
[0.55516788, 0.91208212, 0.45541749]])

[10]: # "randint" is used to generate random integers between upper and lower bounds

x = np.random.randint(1,50)
x

[10]: 22

[11]: # "randint" can be used to generate a certain number of random itegers as␣
↪follows

x = np.random.randint(1, 100, 15)

x

[11]: array([77, 80, 61, 59, 73, 97, 19, 22, 82, 78, 49, 97, 75, 69, 84])

[12]: # np.arange creates an evenly spaced values within a given interval

x = np.arange(1, 50)
x

2
[12]: array([ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,
18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34,
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49])

[13]: # create a diagonal of ones and zeros everywhere else

x = np.eye(7)
x

[13]: array([[1., 0., 0., 0., 0., 0., 0.],

[0., 1., 0., 0., 0., 0., 0.],
[0., 0., 1., 0., 0., 0., 0.],
[0., 0., 0., 1., 0., 0., 0.],
[0., 0., 0., 0., 1., 0., 0.],
[0., 0., 0., 0., 0., 1., 0.],
[0., 0., 0., 0., 0., 0., 1.]])

[14]: # Matrix of ones

x = np.ones((7, 7))
x

[14]: array([[1., 1., 1., 1., 1., 1., 1.],

[1., 1., 1., 1., 1., 1., 1.],
[1., 1., 1., 1., 1., 1., 1.],
[1., 1., 1., 1., 1., 1., 1.],
[1., 1., 1., 1., 1., 1., 1.],
[1., 1., 1., 1., 1., 1., 1.],
[1., 1., 1., 1., 1., 1., 1.]])

[15]: # Array of zeros

x = np.zeros(8)
x

[15]: array([0., 0., 0., 0., 0., 0., 0., 0.])

MINI CHALLENGE #2: - Write a code that takes in a positive integer “x” from the user and
creates a 1x10 array with random numbers ranging from 0 to “x”
[22]: #ask user to inter a positive interger
x = int(input("please enter a positive integer value"))
#verification
if x <= 0:
print("please enter a positif integer")
else:
#create table 1X10
array = np.random.randint(0, x, size=(1, 10))
print("generated table:")
print(array)

3
 please enter a positive integer value6
generated table:
[[5 3 2 4 4 1 4 4 3 2]]

[ ]:

3 TASK #3: PERFORM MATHEMATICAL OPERATIONS IN

NUMPY
[17]: # np.arange() returns an evenly spaced values within a given interval
x = np.arange(1, 10)
x

[17]: array([1, 2, 3, 4, 5, 6, 7, 8, 9])

[18]: y = np.arange(1, 10)

y

[18]: array([1, 2, 3, 4, 5, 6, 7, 8, 9])

[19]: # Add 2 numpy arrays together

sum = x + y
sum

[19]: array([ 2, 4, 6, 8, 10, 12, 14, 16, 18])

[20]: squared = x**2

squared

[20]: array([ 1, 4, 9, 16, 25, 36, 49, 64, 81])

[21]: sqrt = np.sqrt(squared)

sqrt

[21]: array([1., 2., 3., 4., 5., 6., 7., 8., 9.])

[22]: z = np.exp(y)
z

[22]: array([2.71828183e+00, 7.38905610e+00, 2.00855369e+01, 5.45981500e+01,

1.48413159e+02, 4.03428793e+02, 1.09663316e+03, 2.98095799e+03,
8.10308393e+03])

MINI CHALLENGE #3: - Given the X and Y values below, obtain the distance between them
X = [5, 7, 20]
Y = [9, 15, 4]

4
[23]: x = np.array([5, 7, 20])
y = np.array([9, 15, 4])

d = np.sqrt(x**2 + y**2)
d

[23]: array([10.29563014, 16.55294536, 20.39607805])

4 TASK #4: PERFORM ARRAYS SLICING AND INDEXING

[5]: my_numpy_array = np.array([3, 5, 6, 2, 8, 10, 20, 50])
my_numpy_array

[5]: array([ 3, 5, 6, 2, 8, 10, 20, 50])

[6]: # Access specific index from the numpy array

my_numpy_array[-1]

[6]: 50

[7]: # Starting from the first index 0 up until and NOT including the last element
my_numpy_array[0:3]

[7]: array([3, 5, 6])

[8]: # Broadcasting, altering several values in a numpy array at once

my_numpy_array[0:4] = 7
my_numpy_array

[8]: array([ 7, 7, 7, 7, 8, 10, 20, 50])

[9]: # Let's define a two dimensional numpy array

matrix = np.random.randint(1, 10,(4,4))
matrix

[9]: array([[8, 6, 8, 4],

[5, 4, 9, 9],
[7, 6, 4, 1],
[1, 4, 2, 1]])

[10]: # Get a row from a mtrix

matrix[-1]

[10]: array([1, 4, 2, 1])

5
[11]: # Get one element
matrix[0][0]

[11]: 8

MINI CHALLENGE #4: - In the following matrix, replace the last row with 0
X = [2 30 20 -2 -4] [3 4 40 -3 -2] [-3 4 -6 90 10] [25 45 34 22 12] [13 24 22 32 37]

[13]: X = np.array([[2, 30, 20,-2 ,-4],

[3, 4, 40 ,-3 ,-2],
[-3, 4,-6, 90, 10],
[25, 45,34, 22, 12],
[13, 24,22, 32, 37]])
X

[13]: array([[ 2, 30, 20, -2, -4],

[ 3, 4, 40, -3, -2],
[-3, 4, -6, 90, 10],
[25, 45, 34, 22, 12],
[13, 24, 22, 32, 37]])

[30]: X[4] = 0
X

[30]: array([[ 2, 30, 20, 0, 0],

[ 0, 4, 40, 0, 0],
[ 0, 4, 0, 90, 10],
[ 0, 0, 34, 22, 12],
[ 0, 0, 0, 0, 0]])

[ ]:

[ ]:

5 TASK #5: PERFORM ELEMENTS SELECTION (CONDI-

TIONAL)
[33]: matrix = np.random.randint(1, 10, (5, 5))
matrix

[33]: array([[8, 1, 5, 1, 6],

[2, 9, 8, 5, 9],
[4, 8, 4, 9, 2],
[2, 8, 8, 3, 6],
[4, 6, 9, 5, 8]])

6
[46]: new_matrix = matrix[ matrix > 7 ]
new_matrix

[46]: array([8, 9, 8, 9, 8, 9, 8, 8, 9, 8])

[47]: # Obtain odd elements only

new_matrix = matrix[ matrix % 2 == 1]
new_matrix

[47]: array([1, 5, 1, 9, 5, 9, 9, 3, 9, 5])

MINI CHALLENGE #5: - In the following matrix, replace negative elements by 0 and replace odd
elements with -2
X = [2 30 20 -2 -4]
[3 4 40 -3 -2]
[-3 4 -6 90 10]
[25 45 34 22 12]
[13 24 22 32 37]
[4]: X = np.array([[2, 30, 20, -2, -4],
[3, 4, 40, -3, -2],
[-3, 4, -6, 90, 10],
[25, 45, 34, 22, 12],
[13, 24, 22, 32, 37]])
X

[4]: array([[ 2, 30, 20, -2, -4],

[ 3, 4, 40, -3, -2],
[-3, 4, -6, 90, 10],
[25, 45, 34, 22, 12],
[13, 24, 22, 32, 37]])

[23]: X[ X < 0 ]= 0
X[ X % 2 == 1] = -2
X

[23]: array([[ 2, 30, 20, 0, 0],

[ 0, 4, 40, 0, 0],
[ 0, 4, 0, 90, 10],
[ 0, 0, 34, 22, 12],
[ 0, 24, 22, 32, 0]])

7
 6 TASK #6: UNDERSTAND PANDAS FUNDAMENTALS
[35]: # Pandas is a data manipulation and analysis tool that is built on Numpy.
# Pandas uses a data structure known as DataFrame (think of it as Microsoft␣
↪excel in Python).

# DataFrames empower programmers to store and manipulate data in a tabular␣

↪fashion (rows and columns).

# Series Vs. DataFrame? Series is considered a single column of a DataFrame.

[1]: import pandas as pd

[25]: # Let's define a two-dimensional Pandas DataFrame

# Note that you can create a pandas dataframe from a python dictionary
bank_client_df = pd.DataFrame({'Bank Client ID':[111, 222, 333, 444],
'Bank Client Name':['Chanel', 'Steve', 'Mitch',␣
↪'Ryan'],

'Net Worth [$]':[3500, 29000, 10000, 2000],

'Years with bank':[3, 4, 9, 5]})
bank_client_df

[25]: Bank Client ID Bank Client Name Net Worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
2 333 Mitch 10000 9
3 444 Ryan 2000 5

[26]: # Let's obtain the data type

type(bank_client_df)

[26]: pandas.core.frame.DataFrame

[28]: # you can only view the first couple of rows using .head()
bank_client_df.head(2)

[28]: Bank Client ID Bank Client Name Net Worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4

[29]: # you can only view the last couple of rows using .tail()
bank_client_df.tail(2)

[29]: Bank Client ID Bank Client Name Net Worth [$] Years with bank
2 333 Mitch 10000 9
3 444 Ryan 2000 5

MINI CHALLENGE #6: - A porfolio contains a collection of securities such as stocks, bonds and
ETFs. Define a dataframe named ‘portfolio_df’ that holds 3 different stock ticker symbols, number

8
 of shares, and price per share (feel free to choose any stocks) - Calculate the total value of the
porfolio including all stocks
[44]: portfolio_df = pd.DataFrame({'stock ticker symbol':['AAPL', 'AMZN', 'T'],
'price per share [$]':[3500, 200, 40],
'Number of stocks': [3, 4, 9]})
portfolio_df

[44]: stock ticker symbol price per share [$] Number of stocks
0 AAPL 3500 3
1 AMZN 200 4
2 T 40 9

[46]: stocks_dollar_value = portfolio_df['price per share [$]'] *␣

↪portfolio_df['Number of stocks']

stocks_dollar_value.sum()

[46]: 11660

[ ]:

7 TASK #7: PANDAS WITH CSV AND HTML DATA

[47]: # Pandas is used to read a csv file and store data in a DataFrame
house_price_df = pd.read_html('https://www.livingin-canada.com/
↪house-prices-canada.html')

house_price_df[0]

[47]: City \
0 Vancouver, BC
1 Toronto, Ont
2 Ottawa, Ont
3 Calgary, Alb
4 Montreal, Que
5 Halifax, NS
6 Regina, Sask
7 Fredericton, NB
8 (adsbygoogle = window.adsbygoogle || []).push(…

Average House Price \

0 $1,036,000
1 $870,000
2 $479,000
3 $410,000
4 $435,000
5 $331,000

9
 6 $254,000
7 $198,000
8 (adsbygoogle = window.adsbygoogle || []).push(…

12 Month Change
0 + 2.63 %
1 +10.2 %
2 + 15.4 %
3 – 1.5 %
4 + 9.3 %
5 + 3.6 %
6 – 3.9 %
7 – 4.3 %
8 (adsbygoogle = window.adsbygoogle || []).push(…

[48]: house_price_df[1]

[48]: Province \
0 British Columbia
1 Ontario
2 Alberta
3 Quebec
4 Manitoba
5 Saskatchewan
6 Nova Scotia
7 Prince Edward Island
8 Newfoundland / Labrador
9 New Brunswick
10 Canadian Average
11 (adsbygoogle = window.adsbygoogle || []).push(…

Average House Price \

0 $736,000
1 $594,000
2 $353,000
3 $340,000
4 $295,000
5 $271,000
6 $266,000
7 $243,000
8 $236,000
9 $183,000
10 $488,000
11 (adsbygoogle = window.adsbygoogle || []).push(…

12 Month Change
0 + 7.6 %

10
 1 – 3.2 %
2 – 7.5 %
3 + 7.6 %
4 – 1.4 %
5 – 3.8 %
6 + 3.5 %
7 + 3.0 %
8 – 1.6 %
9 – 2.2 %
10 – 1.3 %
11 (adsbygoogle = window.adsbygoogle || []).push(…

[41]: # Read tabular data using read_html

[ ]:

[ ]:

MINI CHALLENGE #7: - Write a code that uses Pandas to read tabular US retirement data -
You can use data from here: https://www.ssa.gov/oact/progdata/nra.html

[ ]: retirement_df = pd.read_html('https://www.ssa.gov/oact/progdata/nra.html')
retirement_df[0]

8 TASK #8: PANDAS OPERATIONS

[58]: # Let's define a dataframe as follows:
bank_client_df = pd.DataFrame({'Bank Client ID':[111, 222, 333, 444],
'Bank Client Name':['Chanel', 'Steve', 'Mitch',␣
↪'Ryan'],

'Net Worth [$]':[3500, 29000, 10000, 2000],

'Years with bank':[3, 4, 9, 5]})
bank_client_df

[58]: Bank Client ID Bank Client Name Net Worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
2 333 Mitch 10000 9
3 444 Ryan 2000 5

[59]: # Pick certain rows that satisfy a certain criteria

df_loyal = bank_client_df[ bank_client_df['Years with bank'] >=5]
df_loyal

[59]: Bank Client ID Bank Client Name Net Worth [$] Years with bank
2 333 Mitch 10000 9

11
 3 444 Ryan 2000 5

[60]: # Delete a column from a DataFrame

del bank_client_df['Bank Client ID']

bank_client_df

[60]: Bank Client Name Net Worth [$] Years with bank
0 Chanel 3500 3
1 Steve 29000 4
2 Mitch 10000 9
3 Ryan 2000 5

MINI CHALLENGE #8: - Using “bank_client_df” DataFrame, leverage pandas operations to

only select high networth individuals with minimum $5000 - What is the combined networth for
all customers with 5000+ networth?
[62]: df_high_networth = bank_client_df[ bank_client_df['Net Worth [$]'] >=5000]
df_high_networth

[62]: Bank Client Name Net Worth [$] Years with bank
1 Steve 29000 4
2 Mitch 10000 9

9 TASK #9: PANDAS WITH FUNCTIONS

[4]: # Let's define a dataframe as follows:
bank_client_df = pd.DataFrame({'Bank client ID':[111, 222, 333, 444],
'Bank Client Name':['Chanel', 'Steve', 'Mitch',␣
↪'Ryan'],

'Net worth [$]':[3500, 29000, 10000, 2000],

'Years with bank':[3, 4, 9, 5]})
bank_client_df

[4]: Bank client ID Bank Client Name Net worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
2 333 Mitch 10000 9
3 444 Ryan 2000 5

[2]: # Define a function that increases all clients networth (stocks) by a fixed␣
↪value of 20% (for simplicity sake)

def networth_update(balance):
return balance * 1.2

12
[5]: # You can apply a function to the DataFrame
bank_client_df['Net worth [$]'].apply(networth_update)

[5]: 0 4200.0
1 34800.0
2 12000.0
3 2400.0
Name: Net worth [$], dtype: float64

[ ]:

MINI CHALLENGE #9: - Define a function that triples the stock prices and adds $200 - Apply
the function to the DataFrame - Calculate the updated total networth of all clients combined
[8]: def networth_update(balance):
return balance *3 + 200

[11]: results= bank_client_df['Net worth [$]'].apply(networth_update)

results

[11]: 0 10700
1 87200
2 30200
3 6200
Name: Net worth [$], dtype: int64

[ ]:

10 TASK #10: PERFORM SORTING AND ORDERING IN

PANDAS
[12]: # Let's define a dataframe as follows:
bank_client_df = pd.DataFrame({'Bank client ID':[111, 222, 333, 444],
'Bank Client Name':['Chanel', 'Steve', 'Mitch',␣
↪'Ryan'],

'Net worth [$]':[3500, 29000, 10000, 2000],

'Years with bank':[3, 4, 9, 5]})
bank_client_df

[12]: Bank client ID Bank Client Name Net worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
2 333 Mitch 10000 9
3 444 Ryan 2000 5

13
[14]: # You can sort the values in the dataframe according to number of years with␣
↪bank

bank_client_df.sort_values(by = 'Years with bank')

[14]: Bank client ID Bank Client Name Net worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
3 444 Ryan 2000 5
2 333 Mitch 10000 9

[15]: # Note that nothing changed in memory! you have to make sure that inplace is␣
↪set to True

bank_client_df

[15]: Bank client ID Bank Client Name Net worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
2 333 Mitch 10000 9
3 444 Ryan 2000 5

[ ]: # Set inplace = True to ensure that change has taken place in memory
bank_client_df.sort_values(by = 'Years with bank', inplace = True)

[16]: # Note that now the change (ordering) took place

bank_client_df

[16]: Bank client ID Bank Client Name Net worth [$] Years with bank
0 111 Chanel 3500 3
1 222 Steve 29000 4
2 333 Mitch 10000 9
3 444 Ryan 2000 5

11 TASK #11: PERFORM CONCATENATING AND MERG-

ING WITH PANDAS
[ ]: # Check this out: https://pandas.pydata.org/pandas-docs/stable/user_guide/
↪merging.html

[24]: df1 = pd.DataFrame({'A':['A0', 'A1', 'A2', 'A3'],

'B':['B0', 'B1', 'B2', 'B3'],
'C':['C0', 'C1', 'C2', 'C3'],
'D':['D0', 'D1', 'D2', 'D3']},
index = [0, 1, 2, 3])
df1

14
[24]: A B C D
0 A0 B0 C0 D0
1 A1 B1 C1 D1
2 A2 B2 C2 D2
3 A3 B3 C3 D3

[25]: df1

[25]: A B C D
0 A0 B0 C0 D0
1 A1 B1 C1 D1
2 A2 B2 C2 D2
3 A3 B3 C3 D3

[27]: df2 = pd.DataFrame({'A':['A4', 'A5', 'A6', 'A7'],

'B':['B4', 'B5', 'B6', 'B7'],
'C':['C4', 'C5', 'C6', 'C7'],
'D':['D4', 'D5', 'D6', 'D7']},
index = [4, 5, 6, 7])

[28]: df2

[28]: A B C D
4 A4 B4 C4 D4
5 A5 B5 C5 D5
6 A6 B6 C6 D6
7 A7 B7 C7 D7

[29]: df3 = pd.DataFrame({'A':['A8', 'A9', 'A10', 'A11'],

'B':['B8', 'B9', 'B10', 'B11'],
'C':['C8', 'C9', 'C10', 'C11'],
'D':['D8', 'D9', 'D10', 'D11']},
index = [8, 9, 10, 11])

[30]: df3

[30]: A B C D
8 A8 B8 C8 D8
9 A9 B9 C9 D9
10 A10 B10 C10 D10
11 A11 B11 C11 D11

[31]: pd.concat([df1, df2, df3])

[31]: A B C D
0 A0 B0 C0 D0
1 A1 B1 C1 D1

15
 2 A2 B2 C2 D2
3 A3 B3 C3 D3
4 A4 B4 C4 D4
5 A5 B5 C5 D5
6 A6 B6 C6 D6
7 A7 B7 C7 D7
8 A8 B8 C8 D8
9 A9 B9 C9 D9
10 A10 B10 C10 D10
11 A11 B11 C11 D11

12 TASK #12: PROJECT AND CONCLUDING REMARKS

• Define a dataframe named ‘Bank_df_1’ that contains the first and last names for 5 bank
clients with IDs = 1, 2, 3, 4, 5
• Assume that the bank got 5 new clients, define another dataframe named ‘Bank_df_2’ that
contains a new clients with IDs = 6, 7, 8, 9, 10
• Let’s assume we obtained additional information (Annual Salary) about all our bank cus-
tomers (10 customers)
• Concatenate both ‘bank_df_1’ and ‘bank_df_2’ dataframes
• Merge client names and their newly added salary information using the ‘Bank Client ID’
• Let’s assume that you became a new client to the bank
• Define a new DataFrame that contains your information such as client ID (choose 11), first
name, last name, and annual salary.
• Add this new dataframe to the original dataframe ‘bank_df_all’.
[41]: raw_data ={ 'Bank Client ID':['1', '2', '3', '4', '5'],
'First Name':['ElMalick', 'Ibra', 'Fallou', 'Idiatou', 'Rassoul'],
'Last Name':['Ndiaye', 'Dione', 'Diop', 'Bah', 'Fall']}

Bank_df_1 = pd.DataFrame(raw_data, columns = ['Bank Client ID', 'First Name',␣

↪'Last Name'])

Bank_df_1

[41]: Bank Client ID First Name Last Name

0 1 ElMalick Ndiaye
1 2 Ibra Dione
2 3 Fallou Diop
3 4 Idiatou Bah
4 5 Rassoul Fall

[42]: raw_data = { 'Bank Client ID': ['6', '7', '8', '9', '10'],
'First Name':['Babacar', 'Ibrahima', 'Assane', 'Youssoufa',␣
↪'alphonse'],

'Last Name':['Kane', 'Ndior', 'Diakhoumpa', 'Sy', 'Mbengue']}

16
 Bank_df_2 = pd.DataFrame(raw_data, columns = ['Bank Client ID', 'First Name',␣
↪'Last Name'])

Bank_df_2

[42]: Bank Client ID First Name Last Name

0 6 Babacar Kane
1 7 Ibrahima Ndior
2 8 Assane Diakhoumpa
3 9 Youssoufa Sy
4 10 alphonse Mbengue

[51]: raw_data ={'Bank Client ID':[1, 2, 3, 4, 5, 6, 7, 8, 9, 10],

'Annual Salary[$/year]':[25000, 35000, 45000, 48000, 49000, 32000,␣
↪33000, 34000, 23000, 22000]}

bank_df_salary = pd.DataFrame(raw_data, columns = [ 'Bank Client ID', 'Annual␣

↪Salary[$/year]']).astype(int)

bank_df_salary

[51]: Bank Client ID Annual Salary[$/year]

0 1 25000
1 2 35000
2 3 45000
3 4 48000
4 5 49000
5 6 32000
6 7 33000
7 8 34000
8 9 23000
9 10 22000

[55]: bank_df_all = pd.concat([Bank_df_1, Bank_df_2])

bank_df_all

[55]: Bank Client ID First Name Last Name

0 1 ElMalick Ndiaye
1 2 Ibra Dione
2 3 Fallou Diop
3 4 Idiatou Bah
4 5 Rassoul Fall
0 6 Babacar Kane
1 7 Ibrahima Ndior
2 8 Assane Diakhoumpa
3 9 Youssoufa Sy
4 10 alphonse Mbengue

17
[58]: bank_df_all['Bank Client ID'] = bank_df_all['Bank Client ID'].astype(int)
bank_df_salary['Bank Client ID'] = bank_df_salary['Bank Client ID'].astype(int)

[59]: bank_df_all = pd.merge(bank_df_all, bank_df_salary, on='Bank Client ID')

bank_df_all

[59]: Bank Client ID First Name Last Name Annual Salary[$/year]

0 1 ElMalick Ndiaye 25000
1 2 Ibra Dione 35000
2 3 Fallou Diop 45000
3 4 Idiatou Bah 48000
4 5 Rassoul Fall 49000
5 6 Babacar Kane 32000
6 7 Ibrahima Ndior 33000
7 8 Assane Diakhoumpa 34000
8 9 Youssoufa Sy 23000
9 10 alphonse Mbengue 22000

[84]: new_client = {'Bank Client ID':['11'],

'First Name':['Cheikh'],
'Last Name':['Thiame'],
'Annual Salary[$/year]':[5000]}
new_client_df = pd.DataFrame(new_client, columns = ['Bank Client ID', 'First␣
↪Name', 'Last Name', 'Annual Salary [$/year]'])

new_client_df

[84]: Bank Client ID First Name Last Name Annual Salary [$/year]
0 11 Cheikh Thiame NaN

[ ]:

[ ]:

[ ]:

13 EXCELLENT JOB!

14 MINI CHALLENGES SOLUTIONS

MINI CHALLENGE #1 SOLUTION: - Write a code that creates the following 2x4 numpy array
[[3 7 9 3]
[4 3 2 2]]
[ ]: x = np.array([[[3, 7, 9, 3] , [4, 3, 2, 2]]])
x

18
 MINI CHALLENGE #2 SOLUTION: - Write a code that takes in a positive integer “x” from the
user and creates a 1x10 array with random numbers ranging from 0 to “x”
[ ]: x = int(input("Please enter a positive integer value: "))
x = np.random.randint(1, x, 10)
x

[ ]:

MINI CHALLENGE #3 SOLUTION: - Given the X and Y values below, obtain the distance
between them
X = [5, 7, 20]
Y = [9, 15, 4]
[ ]: X = np.array([5, 7, 20])
Y = np.array([9, 15, 4])
Z = np.sqrt(X**2 + Y**2)
Z

MINI CHALLENGE #4 SOLUTION: - In the following matrix, replace the last row with 0
X = [2 30 20 -2 -4]
[3 4 40 -3 -2]
[-3 4 -6 90 10]
[25 45 34 22 12]
[13 24 22 32 37]
[ ]: X = np.array([[2, 30, 20, -2, -4],
[3, 4, 40, -3, -2],
[-3, 4, -6, 90, 10],
[25, 45, 34, 22, 12],
[13, 24, 22, 32, 37]])

[ ]: X[4] = 0
X

MINI CHALLENGE #5 SOLUTION: - In the following matrix, replace negative elements by 0 and
replace odd elements with -2
X = [2 30 20 -2 -4]
[3 4 40 -3 -2]
[-3 4 -6 90 10]
[25 45 34 22 12]
[13 24 22 32 37]
[ ]: X = np.array([[2, 30, 20, -2, -4],
[3, 4, 40, -3, -2],
[-3, 4, -6, 90, 10],
[25, 45, 34, 22, 12],

19
 [13, 24, 22, 32, 37]])

X[X<0] = 0
X[X%2==1] = -2
X

MINI CHALLENGE #6 SOLUTION: - A porfolio contains a collection of securities such as stocks,

bonds and ETFs. Define a dataframe named ‘portfolio_df’ that holds 3 different stock ticker
symbols, number of shares, and price per share (feel free to choose any stocks) - Calculate the total
value of the porfolio including all stocks
[ ]: portfolio_df = pd.DataFrame({'stock ticker symbols':['AAPL', 'AMZN', 'T'],
'price per share [$]':[3500, 200, 40],
'Number of stocks':[3, 4, 9]})
portfolio_df

[ ]: stocks_dollar_value = portfolio_df['price per share [$]'] *␣

↪portfolio_df['Number of stocks']

print(stocks_dollar_value)
print('Total portfolio value = {}'.format(stocks_dollar_value.sum()))

MINI CHALLENGE #7 SOLUTION: - Write a code that uses Pandas to read tabular US retirement
data - You can use data from here: https://www.ssa.gov/oact/progdata/nra.html

[ ]: # Read tabular data using read_html

retirement_age_df = pd.read_html('https://www.ssa.gov/oact/progdata/nra.html')
retirement_age_df

MINI CHALLENGE #8 SOLUTION: - Using “bank_client_df” DataFrame, leverage pandas op-

erations to only select high networth individuals with minimum $5000 - What is the combined
networth for all customers with 5000+ networth?
[ ]: df_high_networth = bank_client_df[ (bank_client_df['Net worth [$]'] >= 5000) ]
df_high_networth

[ ]: df_high_networth['Net worth [$]'].sum()

MINI CHALLENGE #9 SOLUTION: - Define a function that triples the stock prices and adds
$200 - Apply the function to the DataFrame - Calculate the updated total networth of all clients
combined
[ ]: def networth_update(balance):
return balance * 3 + 200

[ ]: # You can apply a function to the DataFrame

results = bank_client_df['Net worth [$]'].apply(networth_update)
results

20
[ ]: results.sum()

PROJECT SOLUTION:
[ ]: # Creating a dataframe from a dictionary
# Let's define a dataframe with a list of bank clients with IDs = 1, 2, 3, 4, 5

raw_data = {'Bank Client ID': ['1', '2', '3', '4', '5'],

'First Name': ['Nancy', 'Alex', 'Shep', 'Max', 'Allen'],
'Last Name': ['Rob', 'Ali', 'George', 'Mitch', 'Steve']}

Bank_df_1 = pd.DataFrame(raw_data, columns = ['Bank Client ID', 'First Name',␣

↪'Last Name'])

Bank_df_1

# Let's define another dataframe for a separate list of clients (IDs = 6, 7, 8,␣
↪9, 10)

raw_data = {
'Bank Client ID': ['6', '7', '8', '9', '10'],
'First Name': ['Bill', 'Dina', 'Sarah', 'Heather', 'Holly'],
'Last Name': ['Christian', 'Mo', 'Steve', 'Bob', 'Michelle']}
Bank_df_2 = pd.DataFrame(raw_data, columns = ['Bank Client ID', 'First Name',␣
↪'Last Name'])

Bank_df_2

# Let's assume we obtained additional information (Annual Salary) about our␣

↪bank customers

# Note that data obtained is for all clients with IDs 1 to 10

raw_data = {
'Bank Client ID': ['1', '2', '3', '4', '5', '6', '7', '8', '9', '10'],
'Annual Salary [$/year]': [25000, 35000, 45000, 48000, 49000, 32000,␣
↪33000, 34000, 23000, 22000]}

bank_df_salary = pd.DataFrame(raw_data, columns = ['Bank Client ID','Annual␣

↪Salary [$/year]'])

bank_df_salary

# Let's concatenate both dataframes #1 and #2

# Note that we now have client IDs from 1 to 10
bank_df_all = pd.concat([Bank_df_1, Bank_df_2])
bank_df_all

# Let's merge all data on 'Bank Client ID'

bank_df_all = pd.merge(bank_df_all, bank_df_salary, on = 'Bank Client ID')

21
 bank_df_all

[ ]: new_client = {
'Bank Client ID': ['11'],
'First Name': ['Ry'],
'Last Name': ['Aly'],
'Annual Salary [$/year]' : [1000]}
new_client_df = pd.DataFrame(new_client, columns = ['Bank Client ID', 'First␣
↪Name', 'Last Name', 'Annual Salary [$/year]'])

new_client_df

[70]: new_df = pd.concat([bank_df_all, new_client_df], axis = 0)

new_df

[70]: Bank Client ID First Name Last Name Annual Salary[$/year] \

0 1 ElMalick Ndiaye 25000.0
1 2 Ibra Dione 35000.0
2 3 Fallou Diop 45000.0
3 4 Idiatou Bah 48000.0
4 5 Rassoul Fall 49000.0
5 6 Babacar Kane 32000.0
6 7 Ibrahima Ndior 33000.0
7 8 Assane Diakhoumpa 34000.0
8 9 Youssoufa Sy 23000.0
9 10 alphonse Mbengue 22000.0
0 11 Cheikh Thiame NaN

Annual Salary [$/year]

0 NaN
1 NaN
2 NaN
3 NaN
4 NaN
5 NaN
6 NaN
7 NaN
8 NaN
9 NaN
0 5000.0

[ ]:

22