Scribd
Upload
16 views23 pages

Unit 2-Numpy Advanced

The document discusses the use of NumPy for data analytics in machine learning, focusing on linear algebra functions such as np.linalg.solve for solving systems of linear equations and np.dot for matrix multiplication. It provides examples related to predicting ad performance and student marks using these functions. Additionally, it highlights the differences between np.dot and np.matmul in handling 3D matrices.

Uploaded by

Rishit Gandha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views23 pages

Unit 2-Numpy Advanced

The document discusses the use of NumPy for data analytics in machine learning, focusing on linear algebra functions such as np.linalg.solve for solving systems of linear equations and np.dot for matrix multiplication. It provides examples related to predicting ad performance and student marks using these functions. Additionally, it highlights the differences between np.dot and np.matmul in handling 3D matrices.

Uploaded by

Rishit Gandha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 23

Python essentials for Machine learning

NumPy for Data Analytics


Mr. Vyankatesh Emche
Linear Algebra Functions
• np.linalg.solve is a NumPy function used to solve systems
of linear equations of the form:
𝐴𝑋=B
Where:
• 𝐴 is a square matrix (coefficients of equations).
• 𝑋 is the unknown variable matrix (solutions).
• B is the result matrix (constants on the right side).
• Solving a system of equations like
3𝑥+2𝑦=5
4x−y=2
To find the values of x and y
Example
• Scenario: Predicting Ad Performance
• We have 3 types of ad spend affecting total sales:
• TV Ads Spend
• Social Media Ads Spend
• YouTube Ads Spend
Given Past Data:
• 500𝑥1+200𝑥2+100𝑥3=700(Total Sales for Campaign 1)
• 400𝑥1+300𝑥2+150𝑥3=600(Total Sales for Campaign 2)
• 200𝑥1+400𝑥2+300𝑥3=500(Total Sales for Campaign 3)
• Here:
• 𝑥1,𝑥2,𝑥3 represent ad efficiency factors for TV, Social, and
YouTube Ads.
• We need to find 𝑥1,𝑥2,𝑥3
• 300𝑥1+200𝑥2+250𝑥3= ? (Total Sales for Campaign 4)
Np.dot
• The dot product is a simple multiplication of two vectors (1D
Arrays).
• .This function performs the dot product of two arrays.
• It is mainly used for:Matrix-vector multiplication (e.g., predictions in
linear regression)
• Vector-vector multiplication (e.g., weighted scores)
• Matrix-matrix multiplication (when one of them is a 2D array).
=
Students Data
• Consider dataset with 40 rows of student marks.
• We can use np.linalg.solve to calculate weights for
trim1_marks, trim2_marks, and trim3_marks to predict
trim4_marks.
• Then we can use np.dot to predict the trim4_marks for 10 new
students.
• Getting Square Matrix and relevant dependent
variable(multiplying both sides) value for passing it to
np.linalg.solve
Np.dot
Np.dot and np.matmul
• Both np.dot and np.matmul are used for matrix multiplication in NumPy,
but they behave differently in case of 3d Matrices(Tensors).
Any Queries?

You might also like