Daily Report
Daily Report
2023)
Overview: This report highlights the daily activities, progress, and key achievements
throughout the internship, which focused on machine learning, data science tools, and
the EMS (Energy Management System) use case. The internship provided hands-on
experience with various data science techniques, including data cleaning, feature
engineering, model building, evaluation, and optimization.
October 3:
• Internship commenced with orientation. Set up Python, Jupyter notebooks, and relevant
data science libraries.
• An overview of the EMS use case and its datasets was provided.
October 4:
October 5-6:
• Continued with the bootcamp, learning about machine learning algorithms like
Decision Trees and Logistic Regression.
• Gained proficiency with scikit-learn for building and evaluating models.
• Began exploring exploratory data analysis (EDA) using Matplotlib and Seaborn for
data visualization.
October 7-9:
• Enhanced Python data analysis skills by mastering techniques for data cleaning and
preprocessing.
• Started working on a classification project and applied Logistic Regression.
• Evaluated model performance with metrics like accuracy, precision, and recall.
• Reviewed feedback from mentors and started exploring additional classification models,
including Random Forests and k-Nearest Neighbors.
October 10:
October 11:
• Refined the classification project based on mentor feedback, improving evaluation with
various metrics like accuracy, precision, recall, and F1-score.
October 12-13:
October 14-16:
• Applied initial machine learning models to the EMS dataset, including linear regression
and decision trees.
• Addressed data imbalance in the EMS dataset using techniques like SMOTE (Synthetic
Minority Over-sampling Technique).
• Tuned hyperparameters to enhance model performance and participated in team
discussions for model improvements.
October 17-18:
• Tested advanced models such as Gradient Boosting Machines (GBM) and Random
Forests on the EMS use case.
• Analyzed model outputs and prepared preliminary results for feedback.
October 19-23:
• Refined the EMS model outputs based on feedback and finalized the machine learning
pipeline.
• Implemented final adjustments to the EMS model and tested it on unseen data.
• Optimized the model and collaborated with teammates to finalize features.
October 24-25:
• Participated in team discussions on different machine learning models and the next
steps for improving future models.
• Finalized the dataset and code for the EMS use case.
October 26-27:
October 28-29:
October 30-31:
• Finalized and submitted all code related to the EMS use case.
• Completed final assessments, reviewed the internship experience, and participated in
feedback sessions with the team.
• Concluded the internship with a wrap-up meeting, receiving positive feedback for
contributions.
November 1-2: