The training program on β€œMachine Learning in Python for Mechanical Engineers” is a part of a comprehensive approach to train students as a professional mechanical engineer. Keeping in mind the recent trends in the technological developments in mechanical engineering, this course was proposed by the Departmental faculty members and has been approved by the HOD, Department of Mechanical Engineering,MSIT. The objective of this program is to enhance the multidisciplinary knowledge and employment enhancement of the Mechanical Engineering students.

The main objective of the training program is to train our students in the field of artificial intelligence like Machine Learning (supervised & unsupervised). Mechanical engineering students having the domain knowledge as well as the AI model making definitely make them a complete understanding of the recent advancement of the field. Undergraduate students with a project on machine learning are definitely going to be benefited in the job market both in core industry as well as in IT industries.

Python has been selected as a programming language for learning this Data Science course and Google Colab was used as an online IDE. As such no prerequisites were there for this course. Python programming & important libraries were also part of this course.

Outcome of this course is that students will be able to handle big data. They will be able to learn the data exploration techniques to clean the raw data & select the suitable machine learning model with hyper-parameter tuning to effectively use the data analysis in the field of mechanical engineering.

Total 60 ME students were trained under Prof. Anirban Bose from 5th April to 30th April 2021 through an online course using Google Classroom and Google Colab platform. Out of sixty participants forty nine number of participants successfully completed the course.

Participants evaluate the training program to be very effective and informative. They have shown a great interest for such courses in future. Overall rating of the training is given around 4.5 in a scale from 1 to 5.


The training consisted of the following two Modules:

Python Basics & Python Libraries:

  • Lecture-1: Python Basics-1:

Anaconda Installation, Jupyter Notebook, google colab, Writing python code in jupyter notebook, python coding in colab, Basic python coding, variables, data types in python, extracting characters from string variable, mathematical operators, logical operators, relation operators in python, length of a string, split, replace in a string in python

  • Lecture-2: Python Basics-2:

Python Data Structures, List, Tuples, Dictionary, set, basic operations on list, dictionaries like append, extracting elements, remove elements, concatenate , update , sort, pop, if else in python, while loop in python, for loop in python, taking input from user in python

  • Lecture-3: Python Basics-3:

Python Functions, Lambda functions, filter, map, Object Oriented Programming, Class, Object, attributes, methods, constructor

  • Lecture-4 : Python Libraries-1:

Numpy, Pandas

  • Lecture-5 : Python Libraries-2:

Pandas, Matplotlib

Machine Learning Models:

  • Lecture-6 : Machine Learning in Python-1: Linear Regression-Single Variable

  • Lecture-7: Machine Learning in Python-2: Linear Regression-Multiple Variable

  • Lecture-8: Machine Learning in Python-3: One Hot Encoding & Train Test Split

  • Lecture-9: Machine Learning in Python 4: Logistic Regression-1- Binary Classification

  • Lecture-10: Machine Learning in Python 5: Logistic Regression-2- Multiclass Classification

  • Lecture-11: Machine Learning in Python-6:DecisionTree, RandomForest & SVM

  • Lecture-12: Machine Learning in Python-7: Naive Bayes Classifier

  • Lecture-13: Machine Learning in Python-8: K-MeansClustering, HyperparameterTuning, Pipeline, PCA, FeatureScaling