Python_Termwork

AI and ML Lab using Python — PCS253

Graphic Era (Deemed to be University), Dehradun
Department of Computer Science and Engineering | Semester II

---

📘 Course Information

Field	Details
Subject Code	PCS253
Course Title	AI and ML Lab using Python
Credits	1
Contact Hours	P: 2

---

🎯 Course Outcomes

CO	Description
CO1	Design and develop programs to visualize data and perform Exploratory Data Analysis
CO2	Design and develop graph search algorithms such as BFS, DFS, and A* using heuristics
CO3	Design and develop Machine Learning models (Linear Regression, Logistic Regression, KNN, Decision Tree)
CO4	Analyze and evaluate ML models using metrics (Confusion Matrix, F1 Score, Precision, Recall, Accuracy), clustering, and association rule mining

---

🧪 Lab Programs

🔹 Exploratory Data Analysis & Visualization

| # | Program | Key Concepts |

| 1 | EDA on Student Dataset | Shape, null values, line graphs, scatter plots, boxplots, IQR & Z-score outlier removal | | 2 | BMI Analysis | DataFrame operations, CSV I/O, histograms, aggregation, filtering | | 3 | Data Cleaning — Medical Records | Merging datasets, imputation, regex, group-by, value consistency |

🔹 AI Overview & Search Algorithms

| # | Program | Key Concepts |

| 4 | Depth-First Search (DFS) | Graph traversal, static & dynamic graphs, path finding | | 5 | Breadth-First Search (BFS) | Shortest path, level-order traversal | | 6 | A* Search Algorithm | Heuristics, f(n) = g(n) + h(n), optimal path cost |

🔹 Machine Learning & Preprocessing

| # | Program | Key Concepts | | 7 | Normalization | Min-Max Scaler, Standard Scaler, visualization | | 8 | Feature Selection | Forward Feature Selection, Backward Elimination, Linear Regression, KNN | | 9 | PCA | Dimensionality reduction, variance retention, before/after visualization |

🔹 Regression Analysis

| # | Program | Key Concepts | | 10 | Simple Linear Regression | Slope, intercept, regression line, MSE, R² | | 11 | Multiple Linear Regression | Coefficients, 70:30 / 60:40 / 80:20 splits, actual vs predicted |

🔹 Classification

| # | Program | Key Concepts | | 12 | Logistic Regression | Binary classification, confusion matrix, accuracy | | 13 | K-Nearest Neighbours (KNN) | Optimal K, precision, recall, F1 score | | 14 | Decision Tree | Loan approval prediction, classification metrics |

🔹 Clustering & Association Rule Mining

| # | Program | Key Concepts | | 15 | K-Means Clustering | Elbow method, silhouette score, cluster visualization | | 16 | Apriori Algorithm | Frequent itemsets, association rules, support & confidence |

---

🛠️ Requirements

Install all dependencies using:

pip install -r requirements.txt

requirements.txt

numpy
pandas
matplotlib
seaborn
scikit-learn
mlxtend
scipy

---

📚 References

• Russell, S. & Norvig, P. — Artificial Intelligence: A Modern Approach, 4th Ed., Pearson, 2021
• Alpaydin, E. — Introduction to Machine Learning, 4th Ed., MIT Press, 2020
• Géron, A. — Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 3rd Ed., O'Reilly, 2022

---

👤 Author

SAtyam Kumar
Roll No: 2028488 B.Tech CSE | Semester II
Graphic Era (Deemed to be University), Dehradun