exam-sub 1.0.0 → 1.0.2

package/data/div.txt

@@ -1,83 +1,265 @@
-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
+================================================================================
+MONGODB CRUD OPERATIONS – COLLEGE DB
+================================================================================
+
+AIM:
+To implement CRUD (Create, Read, Update, Delete) operations using MongoDB 
+queries across three collections: employees, students, and books inside a single 
+database named collegeDB.
+
+
+================================================================================
+OPTIONAL: RESET / CLEAN RUN COMMANDS
+================================================================================
+
+NOTE:
+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 start.
+
+JAVASCRIPT / MONGODB SHELL COMMANDS:
+--------------------------------------------------------------------------------
+// Select Database
 use collegeDB
-// ==========================================
-// Q1: EMPLOYEES
-// ==========================================
-// Create Collection
+
+// Drop Existing Collections
+db.employees.drop()
+db.students.drop()
+db.books.drop()
+--------------------------------------------------------------------------------
+
+
+================================================================================
+Q1: EMPLOYEES COLLECTION
+================================================================================
+
+JAVASCRIPT / MONGODB SHELL COMMANDS:
+--------------------------------------------------------------------------------
+// Select Database
+use collegeDB
+
+// Step 1: Create Collection
 db.createCollection("employees")
-// Insert Values
+
+// Step 2: Insert Multiple Documents
 db.employees.insertMany([
-  {name:"Alice", position:"Manager", salary:70000},
-  {name:"Bob", position:"Developer", salary:55000},
-  {name:"Charlie", position:"HR", salary:45000}
+  { 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%
+
+// Step 3: Read - Retrieve employees with salary greater than 50,000
+db.employees.find({ salary: { $gt: 50000 } })
+
+// Step 4: Update - Increase Developer salary by 10%
 db.employees.updateMany(
-  {position:"Developer"},
-  {$mul:{salary:1.10}}
+  { position: "Developer" },
+  { $mul: { salary: 1.10 } }
 )
-// Delete - Remove Charlie
-db.employees.deleteOne({name:"Charlie"})
-// ==========================================
-// Q2: STUDENTS
-// ==========================================
-// Create Collection
+
+// Step 5: Delete - Remove employee named Charlie
+db.employees.deleteOne({ name: "Charlie" })
+--------------------------------------------------------------------------------
+
+
+================================================================================
+Q2: STUDENTS COLLECTION
+================================================================================
+
+JAVASCRIPT / MONGODB SHELL COMMANDS:
+--------------------------------------------------------------------------------
+// Select Database
+use collegeDB
+
+// Step 1: Create Collection
 db.createCollection("students")
-// Insert Values
+
+// Step 2: Insert Single Document
 db.students.insertOne({
-  name:"John Doe",
-  age:22,
-  course:"Computer Science"
+  name: "John Doe",
+  age: 22,
+  course: "Computer Science"
 })
-// Read - Age greater than 20
-db.students.find({age:{$gt:20}})
-// Update - Change course
+
+// Step 3: Read - Retrieve students with age greater than 20
+db.students.find({ age: { $gt: 20 } })
+
+// Step 4: Update - Change course to Data Science
 db.students.updateOne(
-  {name:"John Doe"},
-  {$set:{course:"Data Science"}}
+  { name: "John Doe" },
+  { $set: { course: "Data Science" } }
 )
-// Delete - Age less than 21
-db.students.deleteMany({age:{$lt:21}})
-// ==========================================
-// Q3: BOOKS
-// ==========================================
-// Create Collection
+
+// Step 5: Delete - Remove students with age less than 21
+db.students.deleteMany({ age: { $lt: 21 } })
+--------------------------------------------------------------------------------
+
+
+================================================================================
+Q3: BOOKS COLLECTION
+================================================================================
+
+JAVASCRIPT / MONGODB SHELL COMMANDS:
+--------------------------------------------------------------------------------
+// Select Database
+use collegeDB
+
+// Step 1: Create Collection
 db.createCollection("books")
-// Insert Values
+
+// Step 2: Insert Single Document
 db.books.insertOne({
-  title:"The Alchemist",
-  author:"Paulo Coelho",
-  publishedYear:1988,
-  copiesSold:65000000
+  title: "The Alchemist",
+  author: "Paulo Coelho",
+  publishedYear: 1988,
+  copiesSold: 65000000
 })
-// Read - Books published before 2000
-db.books.find({publishedYear:{$lt:2000}})
-// Update - Add rating
+
+// Step 3: Read - Retrieve books published before the year 2000
+db.books.find({ publishedYear: { $lt: 2000 } })
+
+// Step 4: Update - Add rating field to 'The Alchemist'
 db.books.updateOne(
-  {title:"The Alchemist"},
-  {$set:{rating:4.8}}
+  { 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()
- 
+
+// Step 5: Delete - Remove books with copies sold less than 1 million
+db.books.deleteMany({ copiesSold: { $lt: 1000000 } })
+--------------------------------------------------------------------------------
+
+
+================================================================================
+IMPORTANT MONGODB CONCEPTS & SUMMARY
+================================================================================
+
+DATABASE CONCEPT:
+MongoDB does not use tables like relational databases (e.g., MySQL). Instead, 
+it stores JSON-like documents inside collections. In this practical, 
+'employees', 'students', and 'books' are separate collections stored inside 
+the single 'collegeDB' database.
+
+CRUD METHOD SUMMARY:
+--------------------------------------------------------------------------------
+Operation  | MongoDB Functions / Methods
+--------------------------------------------------------------------------------
+CREATE     | createCollection(), insertOne(), insertMany()
+READ       | find()
+UPDATE     | updateOne(), updateMany()
+DELETE     | deleteOne(), deleteMany()
+--------------------------------------------------------------------------------
+
+================================================================================
+THREADORA BOUTIQUE DATA ANALYSIS & MACHINE LEARNING PIPELINE
+================================================================================
+
+AIM:
+Perform data acquisition, preprocessing, normalization, exploratory data analysis, 
+visualization, and build both Linear and Logistic Regression models on the 
+Threadora Boutique dataset.
+
+PYTHON PROGRAM:
+--------------------------------------------------------------------------------
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression, LogisticRegression
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.metrics import (
+    r2_score,
+    mean_absolute_error,
+    mean_squared_error,
+    accuracy_score,
+    confusion_matrix,
+    classification_report
+)
+
+# 1. Data Acquisition
+df = pd.read_csv("threadora_boutique_data.csv")
+print("Shape:", df.shape)
+print("Missing Values:\n", df.isnull().sum())
+
+# 2. Data Pre-processing
+num_cols = ["Footfall", "Sales", "Ad_Spend", "Insta_Mentions", "Whatsapp_Inquiries"]
+for col in num_cols:
+    df[col] = df[col].fillna(df[col].median())
+
+df["Deal_Offered"] = df["Deal_Offered"].fillna(df["Deal_Offered"].mode()[0])
+df["Date"] = pd.to_datetime(df["Date"])
+df["Deal_Encoded"] = (df["Deal_Offered"].str.lower() == "yes").astype(int)
+
+# 3. Data Transformation - Min-Max Normalization
+scaler = MinMaxScaler()
+normalized = pd.DataFrame(scaler.fit_transform(df[num_cols]), columns=num_cols)
+print("Normalized Data:\n", normalized.head())
+
+# 4. EDA - Summary Statistics & Correlation Analysis
+print("Summary Statistics:\n", df[num_cols].describe())
+
+corr_cols = [
+    "Sales",
+    "Footfall",
+    "Ad_Spend",
+    "Insta_Mentions",
+    "Whatsapp_Inquiries",
+    "Deal_Encoded"
+]
+print("Correlation with Sales:\n", df[corr_cols].corr()["Sales"].sort_values(ascending=False))
+
+# 5. Data Visualization
+plt.figure(figsize=(10, 5))
+plt.plot(df["Date"], df["Sales"], label="Sales")
+plt.plot(df["Date"], df["Footfall"], label="Footfall")
+plt.title("Sales and Footfall Over Time")
+plt.xlabel("Date")
+plt.ylabel("Value")
+plt.xticks(rotation=45)
+plt.legend()
+plt.tight_layout()
+plt.show()
+
+# 6. Linear Regression (Sales Prediction)
+features = ["Ad_Spend", "Footfall", "Whatsapp_Inquiries", "Insta_Mentions"]
+X = df[features]
+y = df["Sales"]
+
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.20, random_state=42
+)
+
+linear_model = LinearRegression()
+linear_model.fit(X_train, y_train)
+
+y_pred = linear_model.predict(X_test)
+
+print("Linear Regression:")
+print("R2 =", r2_score(y_test, y_pred))
+print("MAE =", mean_absolute_error(y_test, y_pred))
+print("RMSE =", mean_squared_error(y_test, y_pred) ** 0.5)
+print("Coefficients:")
+for feature, coef in zip(features, linear_model.coef_):
+    print(feature, "=", coef)
+
+# 7. Logistic Regression (High Sales Day Classification)
+df["High_Sales_Day"] = (df["Sales"] > 5000).astype(int)
+
+X_cls = df[features]
+y_cls = df["High_Sales_Day"]
+
+Xc_train, Xc_test, yc_train, yc_test = train_test_split(
+    X_cls, y_cls, test_size=0.20, random_state=42, stratify=y_cls
+)
+
+log_model = LogisticRegression(max_iter=1000, class_weight="balanced")
+log_model.fit(Xc_train, yc_train)
+
+predictions = log_model.predict(Xc_test)
+
+print("Logistic Regression:")
+print("Accuracy =", accuracy_score(yc_test, predictions))
+print("Confusion Matrix:\n", confusion_matrix(yc_test, predictions))
+print("Classification Report:\n", classification_report(yc_test, predictions))
+--------------------------------------------------------------------------------
+
+