exam-sub 1.0.0

package/README.md

@@ -0,0 +1,19 @@
+# exam-sub
+
+A simple CLI tool for accessing college subject study materials directly from the terminal.
+
+## Features
+
+- AIOP study material
+- DIV - Data Interface & Visualization
+- Big Data & Hadoop
+- MLF - Machine Learning Fundamentals
+- Interactive subject selection
+- Direct subject commands
+
+## Installation
+
+Install globally using npm:
+
+```bash
+npm install -g exam-sub

package/bin/cli.js

@@ -0,0 +1,121 @@
+#!/usr/bin/env node
+
+const fs = require("fs");
+const path = require("path");
+const { select } = require("@inquirer/prompts");
+
+const dataPath = path.join(__dirname, "..", "data");
+
+const subjects = {
+  aiop: {
+    name: "AIOP",
+    file: "aiop.txt"
+  },
+
+  div: {
+    name: "DIV - Data Interface & Visualization",
+    file: "div.txt"
+  },
+
+  bdh: {
+    name: "Big Data & Hadoop",
+    file: "bdh.txt"
+  },
+
+  mlf: {
+    name: "MLF - Machine Learning Fundamentals",
+    file: "mlf.txt"
+  }
+};
+
+
+// Show subject data
+function showSubject(subjectKey) {
+  const subject = subjects[subjectKey];
+
+  if (!subject) {
+    console.log("Subject not found.");
+    return;
+  }
+
+  const filePath = path.join(dataPath, subject.file);
+
+  console.clear();
+
+  console.log("========================================");
+  console.log(`          ${subject.name}`);
+  console.log("========================================");
+  console.log("");
+
+  if (!fs.existsSync(filePath)) {
+    console.log("Data file not found:");
+    console.log(filePath);
+    return;
+  }
+
+  const data = fs.readFileSync(filePath, "utf8");
+
+  console.log(data);
+
+  console.log("");
+  console.log("========================================");
+  console.log("              END OF DATA");
+  console.log("========================================");
+}
+
+
+// Main menu
+async function main() {
+  console.clear();
+
+  console.log("========================================");
+  console.log("           EXAM SUBJECTS CLI");
+  console.log("========================================");
+  console.log("");
+
+  const selectedSubject = await select({
+    message: "Select a subject:",
+    choices: [
+      {
+        name: "AIOP",
+        value: "aiop"
+      },
+      {
+        name: "DIV - Data Interface & Visualization",
+        value: "div"
+      },
+      {
+        name: "Big Data & Hadoop",
+        value: "bdh"
+      },
+      {
+        name: "MLF - Machine Learning Fundamentals",
+        value: "mlf"
+      }
+    ]
+  });
+
+  showSubject(selectedSubject);
+}
+
+
+// Direct command support
+const command = process.argv[2];
+
+if (command) {
+  const commandName = command.toLowerCase();
+
+  if (subjects[commandName]) {
+    showSubject(commandName);
+  } else {
+    console.log(`Unknown subject: ${command}`);
+    console.log("");
+    console.log("Available subjects:");
+    console.log("  aiop");
+    console.log("  div");
+    console.log("  bdh");
+    console.log("  mlf");
+  }
+} else {
+  main();
+}

package/data/aiop.txt

@@ -0,0 +1,162 @@
+Q1. Implement AI Problem-Solving Techniques using Python
+Aim: To implement a simple AI problem-solving technique using Breadth First Search (BFS).
+Python Program:
+from collections import deque
+graph = {
+    'A': ['B', 'C'],
+    'B': ['D', 'E'],
+    'C': ['F'],
+    'D': [],
+    'E': ['F'],
+    'F': []
+}
+def bfs(start, goal):
+    queue = deque([[start]])
+    visited = set()
+    while queue:
+        path = queue.popleft()
+        node = path[-1]
+        if node == goal:
+            return path
+        if node not in visited:
+            visited.add(node)
+            for neighbour in graph[node]:
+                new_path = path + [neighbour]
+                queue.append(new_path)
+print("Path:", bfs('A', 'F'))
+Example Output:
+Path: ['A', 'C', 'F']
+Explanation: - BFS searches level by level.
+- It starts from node A.
+- It checks neighbouring nodes.
+- It finds the path from A to F.
+
+Q3. Develop a Context-Aware Rule-Based Chatbot using Python
+Aim: To create a chatbot that responds according to the context of the conversation.
+Python Program:
+context = ""
+while True:
+    user = input("You: ").lower()
+    if user == "bye":
+        print("Bot: Goodbye!")
+        break
+    if "hello" in user or "hi" in user:
+        print("Bot: Hello! How can I help you?")
+    elif "my name is" in user:
+        context = user.split("my name is")[-1].strip()
+        print("Bot: Nice to meet you, " + context)
+    elif "what is my name" in user:
+        if context:
+            print("Bot: Your name is " + context)
+        else:
+            print("Bot: I don't know your name yet.")
+    elif "course" in user:
+        print("Bot: Which course are you studying?")
+    else:
+        print("Bot: Please tell me more.")
+Example Output:
+You: hi
+Bot: Hello! How can I help you?
+You: my name is Sunny
+Bot: Nice to meet you, sunny
+You: what is my name
+Bot: Your name is sunny
+Explanation: The chatbot stores information in the context variable and uses it in later conversations.
+
+Q4. Implement an Intent-Based Chatbot using Rule Matching and Pattern
+Processing
+Aim: To identify the user's intent using simple keyword/pattern matching.
+Python Program:
+import re
+patterns = {
+    "greeting": r"\b(hi|hello|hey)\b",
+    "courses": r"\b(course|courses|subjects)\b",
+    "fees": r"\b(fees|fee|payment)\b",
+    "bye": r"\b(bye|goodbye)\b"
+}
+def get_intent(message):
+    for intent, pattern in patterns.items():
+        if re.search(pattern, message.lower()):
+            return intent
+    return "unknown"
+while True:
+    user = input("You: ")
+    intent = get_intent(user)
+    if intent == "greeting":
+        print("Bot: Hello! How can I help you?")
+    elif intent == "courses":
+        print("Bot: We offer Computer Science and IT courses.")
+    elif intent == "fees":
+        print("Bot: Please contact the college office for fee details.")
+    elif intent == "bye":
+        print("Bot: Goodbye!")
+        break
+    else:
+        print("Bot: Sorry, I don't understand.")
+Example Output:
+You: Hello
+Bot: Hello! How can I help you?
+You: Tell me about courses
+Bot: We offer Computer Science and IT courses.
+You: What are the fees?
+Bot: Please contact the college office for fee details.
+Explanation: - Intent means what the user wants.
+- Regular expressions (re) identify patterns.
+- The chatbot gives a response according to the detected intent.
+
+Q5. Implement a Rule-Based Recommendation Chatbot using Forward
+Chaining
+Aim: To recommend a course using rules and forward chaining.
+Python Program:
+facts = set()
+print("Answer with yes or no.")
+python = input("Do you like Python? ").lower()
+web = input("Do you like Web Development? ").lower()
+data = input("Do you like Data Analysis? ").lower()
+if python == "yes":
+    facts.add("python")
+if web == "yes":
+    facts.add("web")
+if data == "yes":
+    facts.add("data")
+# Forward chaining rules
+if "python" in facts and "data" in facts:
+    print("Recommendation: Machine Learning / Data Science")
+elif "web" in facts and "python" in facts:
+    print("Recommendation: Python Full Stack Development")
+elif "web" in facts:
+    print("Recommendation: Web Development")
+elif "python" in facts:
+    print("Recommendation: Python Programming")
+else:
+    print("Recommendation: Explore basic computer courses.")
+Example Output:
+Do you like Python? yes
+Do you like Web Development? no
+Do you like Data Analysis? yes
+Recommendation: Machine Learning / Data Science
+Explanation: Forward chaining starts with known facts and applies rules to reach a conclusion.
+Python + Data Analysis → Machine Learning
+
+Q6. Develop an Intelligent Academic-Assistance Chatbot using Python
+Aim: To create a chatbot that helps students with common academic queries.
+Python Program:
+while True:
+    user = input("Student: ").lower()
+    if "hello" in user or "hi" in user:
+        print("Bot: Hello! How can I help you?")
+    elif "exam" in user:
+        print("Bot: Prepare important topics and practice previous papers.")
+    elif "assignment" in user:
+        print("Bot: Complete your assignment before the submission date.")
+    elif "attendance" in user:
+        print("Bot: Please check your attendance with the college portal.")
+    elif "study" in user or "study plan" in user:
+        print("Bot: Study 2-3 hours daily and revise important topics.")
+    elif "python" in user:
+        print("Bot: Practice Python basics, functions, lists and OOP.")
+    elif "bye" in user:
+        print("Bot: Good luck with your studies!")
+        break
+    else:
+        print("Bot: Sorry, I don't have information about that.")

package/data/bdh.txt

@@ -0,0 +1,157 @@
+University and Hospital database questions using TEXTFILE storage format.
+Question 9 – University Database
+-- ==========================================
+-- Q9: UNIVERSITY
+-- ==========================================
+-- Create Database
+CREATE DATABASE university_db;
+-- Select Database
+USE university_db;
+-- Create Table
+CREATE TABLE students (
+    student_id INT,
+    name STRING,
+    course STRING,
+    marks FLOAT
+)
+STORED AS TEXTFILE;
+-- Insert Sample Values
+INSERT INTO students VALUES
+(101, 'John', 'Computer Science', 85),
+(102, 'Alice', 'Mathematics', 72),
+(103, 'Bob', 'Physics', 45),
+(104, 'Charlie', 'Mathematics', 65);
+-- 1. Retrieve Computer Science students
+SELECT *
+FROM students
+WHERE course = 'Computer Science';
+-- 2. Delete students whose marks are below 50
+DELETE FROM students
+WHERE marks < 50;
+-- 3. Add 10 bonus marks to Mathematics students
+UPDATE students
+SET marks = marks + 10
+WHERE course = 'Mathematics';
+-- 4. Delete student whose student_id is 102
+DELETE FROM students
+WHERE student_id = 102;
+Question 11 – Hospital Database
+-- ==========================================
+-- Q11: HOSPITAL
+-- ==========================================
+-- Create Database
+CREATE DATABASE hospital_db;
+-- Select Database
+USE hospital_db;
+-- Create Table
+CREATE TABLE patients (
+    patient_id INT,
+    patient_name STRING,
+    age INT,
+    disease STRING
+)
+STORED AS TEXTFILE;
+-- Insert Sample Values
+INSERT INTO patients VALUES
+(1, 'Rahul', 45, 'Diabetes'),
+(2, 'Amit', 30, 'Hypertension'),
+(3, 'Priya', 16, 'Fever'),
+(4, 'Neha', 55, 'Diabetes'),
+(8, 'Raj', 40, 'Hypertension');
+-- 1. Retrieve patients with Diabetes
+SELECT *
+FROM patients
+WHERE disease = 'Diabetes';
+-- 2. Delete patients whose age is below 18
+DELETE FROM patients
+WHERE age < 18;
+-- 3. Change Hypertension to Chronic Hypertension
+UPDATE patients
+SET disease = 'Chronic Hypertension'
+WHERE disease = 'Hypertension';
+-- 4. Delete patient whose patient_id is 8
+DELETE FROM patients
+WHERE patient_id = 8;
+
+
+Complete Hive code for the University (Q9) and Hospital (Q11) database questions, including database creation,
+table creation, sample data, SELECT, DELETE and UPDATE operations.
+Question 9 – University Database
+-- ==========================================
+-- Q9: UNIVERSITY
+-- ==========================================
+-- Create Database
+CREATE DATABASE university_db;
+-- Select Database
+USE university_db;
+-- Create Table
+CREATE TABLE students (
+    student_id INT,
+    name STRING,
+    course STRING,
+    marks FLOAT
+)
+STORED AS ORC
+TBLPROPERTIES ('transactional'='true');
+-- Insert Sample Values
+INSERT INTO students VALUES
+(101, 'John', 'Computer Science', 85),
+(102, 'Alice', 'Mathematics', 72),
+(103, 'Bob', 'Physics', 45),
+(104, 'Charlie', 'Mathematics', 65);
+-- 1. Retrieve Computer Science students
+SELECT *
+FROM students
+WHERE course = 'Computer Science';
+-- 2. Delete students whose marks are below 50
+DELETE FROM students
+WHERE marks < 50;
+-- 3. Add 10 bonus marks to Mathematics students
+UPDATE students
+SET marks = marks + 10
+WHERE course = 'Mathematics';
+-- 4. Delete student whose student_id is 102
+DELETE FROM students
+WHERE student_id = 102;
+Question 11 – Hospital Database
+-- ==========================================
+-- Q11: HOSPITAL
+-- ==========================================
+-- Create Database
+CREATE DATABASE hospital_db;
+-- Select Database
+USE hospital_db;
+-- Create Table
+CREATE TABLE patients (
+    patient_id INT,
+    patient_name STRING,
+    age INT,
+    disease STRING
+)
+STORED AS ORC
+TBLPROPERTIES ('transactional'='true');
+-- Insert Sample Values
+INSERT INTO patients VALUES
+(1, 'Rahul', 45, 'Diabetes'),
+(2, 'Amit', 30, 'Hypertension'),
+(3, 'Priya', 16, 'Fever'),
+(4, 'Neha', 55, 'Diabetes'),
+(8, 'Raj', 40, 'Hypertension');
+-- 1. Retrieve patients with Diabetes
+SELECT *
+FROM patients
+WHERE disease = 'Diabetes';
+-- 2. Delete patients whose age is below 18
+DELETE FROM patients
+WHERE age < 18;
+-- 3. Change Hypertension to Chronic Hypertension
+UPDATE patients
+SET disease = 'Chronic Hypertension'
+WHERE disease = 'Hypertension';
+-- 4. Delete patient whose patient_id is 8
+DELETE FROM patients
+WHERE patient_id = 8;
+Note: These examples use ORC transactional tables so that Hive UPDATE and DELETE operations can be
+performed. If your college specifically requires TEXTFILE syntax, replace the storage clause as instructed by your
+lab/teacher.
+ 

package/data/div.txt

@@ -0,0 +1,83 @@
+MongoDB CRUD Operations – CollegeDB
+Complete practical code for Questions 1–3 using one MongoDB database with separate collections: employees,
+students, and books.
+Complete Code
+// Create / Select Database
+use collegeDB
+// ==========================================
+// Q1: EMPLOYEES
+// ==========================================
+// Create Collection
+db.createCollection("employees")
+// Insert Values
+db.employees.insertMany([
+  {name:"Alice", position:"Manager", salary:70000},
+  {name:"Bob", position:"Developer", salary:55000},
+  {name:"Charlie", position:"HR", salary:45000}
+])
+// Read - Salary greater than 50000
+db.employees.find({salary:{$gt:50000}})
+// Update - Increase Developer salary by 10%
+db.employees.updateMany(
+  {position:"Developer"},
+  {$mul:{salary:1.10}}
+)
+// Delete - Remove Charlie
+db.employees.deleteOne({name:"Charlie"})
+// ==========================================
+// Q2: STUDENTS
+// ==========================================
+// Create Collection
+db.createCollection("students")
+// Insert Values
+db.students.insertOne({
+  name:"John Doe",
+  age:22,
+  course:"Computer Science"
+})
+// Read - Age greater than 20
+db.students.find({age:{$gt:20}})
+// Update - Change course
+db.students.updateOne(
+  {name:"John Doe"},
+  {$set:{course:"Data Science"}}
+)
+// Delete - Age less than 21
+db.students.deleteMany({age:{$lt:21}})
+// ==========================================
+// Q3: BOOKS
+// ==========================================
+// Create Collection
+db.createCollection("books")
+// Insert Values
+db.books.insertOne({
+  title:"The Alchemist",
+  author:"Paulo Coelho",
+  publishedYear:1988,
+  copiesSold:65000000
+})
+// Read - Books published before 2000
+db.books.find({publishedYear:{$lt:2000}})
+// Update - Add rating
+db.books.updateOne(
+  {title:"The Alchemist"},
+  {$set:{rating:4.8}}
+)
+// Delete - Books with copies sold less than 1 million
+db.books.deleteMany({copiesSold:{$lt:1000000}})
+Fresh Run / Reset Database Collections
+If you run the practical multiple times, existing collections and data may cause duplicate records or collection-exists
+errors. Use the following commands first when you want a clean run.
+use collegeDB
+db.employees.drop()
+db.students.drop()
+db.books.drop()
+Important MongoDB Note
+MongoDB does not use tables like MySQL. MongoDB stores data in collections. For this practical, employees,
+students, and books are collections inside the same collegeDB database.
+CRUD Summary
+Create: createCollection(), insertOne(), insertMany()
+Read: find()
+Update: updateOne(), updateMany()
+Delete: deleteOne(), deleteMany()
+ 

package/data/mlf.txt

@@ -0,0 +1,347 @@
+ Q1 to Q6: Short, Simple and Easy-to-Understand Solutions
+Question 1: Sales Data EDA
+Aim: Perform Exploratory Data Analysis on sales data to understand patterns, missing values and unusual transactions.
+1. Import libraries and load data
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+df = pd.read_csv("sales_data.csv")
+print(df.head())
+print(df.shape)
+print(df.info())
+
+2. Convert Date
+df['Date'] = pd.to_datetime(df['Date'])
+print(df['Date'].dtype)
+
+3. Identify variable types
+print(df.dtypes)
+Typical types: Order_ID – integer/object; Date – DateTime; Product, Category, Region, Customer_Type – categorical;
+Quantity, Unit_Price, Discount, Sales – numerical.
+
+4. Check and 5. Handle missing values
+print(df.isnull().sum())
+df['Quantity'] = df['Quantity'].fillna(df['Quantity'].median())
+df['Unit_Price'] = df['Unit_Price'].fillna(df['Unit_Price'].median())
+df['Discount'] = df['Discount'].fillna(df['Discount'].median())
+df['Sales'] = df['Sales'].fillna(df['Sales'].median())
+df['Region'] = df['Region'].fillna(df['Region'].mode()[0])
+df['Category'] = df['Category'].fillna(df['Category'].mode()[0])
+
+6. Univariate analysis
+sns.histplot(df['Sales'], kde=True)
+plt.title("Sales Distribution")
+plt.show()
+sns.histplot(df['Quantity'], kde=True)
+plt.title("Quantity Distribution")
+plt.show()
+
+7. Bivariate analysis
+# Quantity vs Sales
+sns.scatterplot(x='Quantity', y='Sales', data=df)
+plt.show()
+# Discount vs Sales
+sns.scatterplot(x='Discount', y='Sales', data=df)
+plt.show()
+# Region vs Sales
+sns.boxplot(x='Region', y='Sales', data=df)
+plt.show()
+
+8. Multivariate analysis
+sns.pairplot(df[['Quantity', 'Unit_Price', 'Discount', 'Sales']])
+plt.show()
+
+9. Detect sales outliers using IQR
+
+Q1 = df['Sales'].quantile(0.25)
+Q3 = df['Sales'].quantile(0.75)
+IQR = Q3 - Q1
+lower = Q1 - 1.5 * IQR
+upper = Q3 + 1.5 * IQR
+outliers = df[(df['Sales'] < lower) | (df['Sales'] > upper)]
+print("Number of outliers:", len(outliers))
+print(outliers)
+
+10. Handle outliers and 11. plot final distribution
+df_clean = df[(df['Sales'] >= lower) & (df['Sales'] <= upper)]
+sns.histplot(df_clean['Sales'], kde=True)
+plt.title("Sales Distribution After Outlier Removal")
+plt.show()
+Conclusion: EDA helps understand sales distribution, relationships, regional patterns, missing values and unusual
+transactions. IQR is used to detect sales outliers.
+Question 2: Automated EDA and Statistical Relationship Analysis
+Aim: Analyze student academic performance and relationships between study habits, attendance, assignments and
+marks.
+A. Data Loading and Basic Analysis
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+df = pd.read_csv("student_performance.csv")
+print(df.head())
+print(df.tail())
+print("Shape:", df.shape)
+print("Columns:", df.columns)
+print("Data Types:")
+print(df.dtypes)
+print("Statistical Summary:")
+print(df.describe())
+print("Missing values:")
+print(df.isnull().sum())
+print("Duplicates:", df.duplicated().sum())
+print("Unique values:")
+print(df.nunique())
+Handle missing and duplicate values:
+df = df.fillna(df.median(numeric_only=True))
+df = df.drop_duplicates()
+B1. D-Tale
+# Install once in terminal:
+# pip install dtale
+import dtale
+dtale.show(df)
+D-Tale provides an interactive overview, column statistics, missing values, correlations, histograms, scatter plots and
+outlier information.
+B2. YData Profiling / Pandas Profiling
+# Install once:
+# pip install ydata-profiling
+from ydata_profiling import ProfileReport
+profile = ProfileReport(df, title="Student Performance Report")
+profile.to_file("student_profile.html")
+The HTML report contains dataset overview, variable statistics, missing values, correlations, distributions, duplicates and
+warnings.
+B3. Sweetviz
+# Install once:
+# pip install sweetviz
+import sweetviz as sv
+report = sv.analyze(df)
+report.show_html("sweetviz_report.html")
+Sweetviz automatically shows distributions, associations, correlations, missing values and summary statistics.
+B4. AutoViz
+# Install once:
+# pip install autoviz
+from autoviz.AutoViz_Class import AutoViz_Class
+AV = AutoViz_Class()
+AV.AutoViz("student_performance.csv")
+AutoViz automatically creates visualizations and helps identify important relationships.
+C. Covariance and Correlation
+num_cols = [
+    'Study_Hours',
+    'Attendance',
+    'Assignment_Marks',
+    'Internal_Marks',
+    'Final_Marks'
+]
+covariance = df[num_cols].cov()
+print(covariance)
+correlation = df[num_cols].corr()
+print(correlation)
+plt.figure(figsize=(8, 6))
+sns.heatmap(correlation, annot=True, cmap='coolwarm')
+plt.title("Correlation Matrix")
+plt.show()
+Correlation ranges from -1 to +1. +1 means strong positive relationship, 0 means no linear relationship, and -1 means
+strong negative relationship. The strongest positive correlation with Final_Marks is the variable whose correlation value
+with Final_Marks is closest to +1. Weak variables have correlation values close to 0. Highly correlated independent
+variables have values close to +1 or -1.
+Conclusion: Automated EDA makes analysis faster by generating statistics, graphs, correlations, missing-value
+information and warnings.
+Question 3: Student Performance Prediction
+Aim: Predict Final_Marks using Linear Regression.
+Task 1. Load and preprocess
+import pandas as pd
+import numpy as np
+df = pd.read_csv("student_performance.csv")
+print(df.head())
+print(df.shape)
+print(df.dtypes)
+print(df.describe())
+print(df.isnull().sum())
+df = df.fillna(df.median(numeric_only=True))
+df = df.drop_duplicates()
+Task 2. Apply Linear Regression
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+X = df[
+    [
+        'Study_Hours',
+        'Attendance',
+        'Assignment_Score',
+        'Internal_Marks',
+        'Previous_Sem_Marks'
+    ]
+]
+y = df['Final_Marks']
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.20, random_state=42
+)
+model = LinearRegression()
+model.fit(X_train, y_train)
+print("Intercept:", model.intercept_)
+for col, coef in zip(X.columns, model.coef_):
+    print(col, ":", coef)
+y_pred = model.predict(X_test)
+print("Predicted Final Marks:")
+print(y_pred)
+Task 3. Evaluate Linear Regression
+from sklearn.metrics import r2_score, mean_squared_error
+r2 = r2_score(y_test, y_pred)
+mse = mean_squared_error(y_test, y_pred)
+rmse = np.sqrt(mse)
+residuals = y_test - y_pred
+RSS = np.sum(residuals ** 2)
+print("R2:", r2)
+print("MSE:", mse)
+print("RMSE:", rmse)
+print("Residuals:")
+print(residuals)
+print("RSS:", RSS)
+plt.scatter(y_test, y_pred)
+plt.xlabel("Actual Final Marks")
+plt.ylabel("Predicted Final Marks")
+plt.title("Actual vs Predicted Final Marks")
+plt.show()
+Interpretation: Higher R² generally means the model explains more variation in Final_Marks. Lower MSE and RMSE mean
+smaller prediction errors. Residual = Actual − Predicted.
+Question 4: Sales Data Analysis Using Python
+Aim: Load, clean, transform, analyze and visualize sales data.
+1. Load and inspect
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+df = pd.read_csv("sales_data.csv")
+print(df.head())
+print(df.columns)
+print(df.dtypes)
+print(df.isnull().sum())
+2. Fill missing Price using average Price of its Product Category
+df['Price'] = df.groupby('Category')['Price'].transform(
+    lambda x: x.fillna(x.mean())
+)
+print(df['Price'].isnull().sum())
+3. Create TotalAmount
+df['TotalAmount'] = df['Quantity'] * df['Price']
+print(df.head())
+4. Data analysis
+# Highest total sales region
+region_sales = df.groupby('Region')['TotalAmount'].sum()
+print(region_sales)
+print("Highest Sales Region:", region_sales.idxmax())
+# Total Electronics revenue
+electronics_sales = df[
+    df['Category'] == 'Electronics'
+]['TotalAmount'].sum()
+print("Electronics Revenue:", electronics_sales)
+# Highest quantity in a single invoice
+highest = df.loc[df['Quantity'].idxmax()]
+print(highest)
+
+5. Data visualization
+# Bar chart: sales by region
+region_sales.plot(kind='bar')
+plt.title("Total Sales by Region")
+plt.xlabel("Region")
+plt.ylabel("Sales")
+plt.show()
+# Pie chart: sales by category
+category_sales = df.groupby('Category')['TotalAmount'].sum()
+category_sales.plot(kind='pie', autopct='%1.1f%%')
+plt.title("Sales Distribution by Category")
+plt.ylabel("")
+plt.show()
+# Line chart: monthly sales
+df['Date'] = pd.to_datetime(df['Date'])
+monthly_sales = df.groupby(
+    df['Date'].dt.to_period('M')
+)['TotalAmount'].sum()
+monthly_sales.plot(kind='line', marker='o')
+plt.title("Monthly Sales")
+plt.xlabel("Month")
+plt.ylabel("Sales")
+plt.show()
+Conclusion: The dataset was loaded, cleaned and transformed. Regional sales, electronics revenue and highest quantity
+were calculated, followed by bar, pie and line charts.
+Question 5: Employee Promotion Prediction Using Logistic Regression
+Aim: Predict promotion probability from years of work experience.
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LogisticRegression
+experience = np.array([1,2,3,4,5,6,7,8,9,10])
+promotion = np.array([0,0,0,0,0,1,1,1,1,1])
+df = pd.DataFrame({
+    'Experience': experience,
+    'Promotion': promotion
+})
+X = experience.reshape(-1, 1)
+y = promotion
+model = LogisticRegression()
+model.fit(X, y)
+# Predicted probability
+probability = model.predict_proba(X)[:, 1]
+# Threshold 0.5
+predicted = (probability >= 0.5).astype(int)
+result = pd.DataFrame({
+    'Experience': experience,
+    'Actual': promotion,
+    'Probability': probability,
+    'Predicted': predicted
+})
+print(result)
+# Sigmoid curve
+x_curve = np.linspace(1, 10, 100).reshape(-1, 1)
+y_curve = model.predict_proba(x_curve)[:, 1]
+plt.scatter(experience, promotion)
+plt.plot(x_curve, y_curve)
+plt.axhline(0.5, linestyle='--')
+plt.xlabel("Years of Experience")
+plt.ylabel("Probability of Promotion")
+plt.title("Logistic Regression - Promotion")
+plt.show()
+Interpretation: Logistic Regression gives a probability between 0 and 1. If probability ≥ 0.5, the employee is classified as
+Promoted (1); otherwise Not Promoted (0). As experience increases, the predicted promotion probability generally
+increases for this dataset.
+Question 6: Loan Approval Prediction Using Logistic Regression
+Aim: Predict loan approval probability from monthly income.
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LogisticRegression
+income = np.array([15,18,20,22,25,28,30,35,40,45])
+loan_approved = np.array([0,0,0,0,1,1,1,1,1,1])
+df = pd.DataFrame({
+    'Income': income,
+    'Loan_Approved': loan_approved
+})
+X = income.reshape(-1, 1)
+y = loan_approved
+model = LogisticRegression()
+model.fit(X, y)
+# Predicted probability
+probability = model.predict_proba(X)[:, 1]
+# Threshold 0.5
+prediction = (probability >= 0.5).astype(int)
+result = pd.DataFrame({
+    'Income': income,
+    'Actual': loan_approved,
+    'Probability': probability,
+    'Prediction': prediction
+})
+print(result)
+# Logistic curve
+x_curve = np.linspace(15, 45, 100).reshape(-1, 1)
+y_curve = model.predict_proba(x_curve)[:, 1]
+plt.scatter(income, loan_approved)
+plt.plot(x_curve, y_curve)
+plt.axhline(0.5, linestyle='--')
+plt.xlabel("Monthly Income")
+plt.ylabel("Probability of Loan Approval")
+plt.title("Logistic Regression - Loan Approval")
+plt.show()
+# Decision boundary
+boundary = -model.intercept_[0] / model.coef_[0][0]
+print("Decision Boundary:", boundary)
+Interpretation: The model converts income into a probability of loan approval. Probability ≥ 0.5 is classified as Loan
+Approved (1), while probability < 0.5 is classified as Loan Rejected (0).
+Quick Revision for Viva

package/package.json

@@ -0,0 +1,28 @@
+{
+  "name": "exam-sub",
+  "version": "1.0.0",
+  "description": "A CLI for accessing college subject study materials from the terminal.",
+  "bin": {
+    "exam-sub": "bin/cli.js"
+  },
+  "files": [
+    "bin",
+    "data",
+    "README.md"
+  ],
+  "keywords": [
+    "college",
+    "study",
+    "cli",
+    "div",
+    "aiop",
+    "big-data",
+    "hadoop",
+    "mlf"
+  ],
+  "author": "wizard",
+  "license": "MIT",
+  "dependencies": {
+    "@inquirer/prompts": "^8.7.2"
+  }
+}