FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #1
Practical 1 : Implement Naive Bayes algorithm using sample data.
Output:-
#Displaying iris dataset
Suryakant Kumar (92301703051) 1
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #1
#Displaying X_test dataset
Suryakant Kumar (92301703051) 2
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #1
#Model name
#Printing accuracy
Code:-
#importing libraries
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score
#load datasets
iris=datasets.load_iris()
iris
#assigning dataset to variable
X=iris.data
y=iris.target
#split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=1)
Suryakant Kumar (92301703051) 3
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #1
#displaying X_test
X_test
#intialize gaussian naive bayes classifier and assign it to the variable
nb=GaussianNB()
#train model
nb.fit(X_train,y_train)
#using predict method to predict and storing in variable
y_pre=nb.predict(X_test)
#printing accuracy
accuracy=accuracy_score(y_test,y_pre)
print(accuracy)
Suryakant Kumar (92301703051) 4
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #2
Practical 2:- Implement Random Forest and ensemble learning techniques.
Output:-
#Displaying iris dataset
#Model Name
Suryakant Kumar (92301703051) 5
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #2
#Printing accuracy
Code:-
#importing libraries
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
# Load and displaying the iris dataset
iris = datasets.load_iris()
iris
X = iris.data
y = iris.target
# Split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=1)
# Create the Random Forest classifier
rf = RandomForestClassifier(n_estimators=100, random_state=1)
# Train the model
rf.fit(X_train, y_train)
# Predict
y_pred = rf.predict(X_test)
#Printing accuracy
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Suryakant Kumar (92301703051) 6
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #3
Practical 3:- Using a dataset implement SVM classifier.
Output:
#Displaying bank-full dataset
#Display basic information
Suryakant Kumar(92301703051) 7
(5EC4)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #3
#Display statistical summary of numeric columns
#Display first few rows of dataset(df.head(5))
#Display last few rows of dataset(df.tail(5))
#Check for null (missing) values in the column
Suryakant Kumar(92301703051) 8
(5EC4)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #3
#Check whether all values in the column are unique
#Count total number of missing values in each column of the dataset
#Encode all categorical (object-type) columns into numeric using LabelEncoder
#Model Name
#Printing Accuracy
Suryakant Kumar(92301703051) 9
(5EC4)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #3
Code:-
#Importing libraries
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import LabelEncoder
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
# Read the CSV file and displaying bank-full dataset
df = pd.read_csv('/content/bank-full.csv')
df
#Display basic information about the dataset
df.info()
#Display statistical summary of numeric columns
df.describe()
# Display the first few rows of the Dataset
display(df.head())
#Display last few rows of Dataset
display(df.tail())
#Check for null (missing) values in the column
df['loan'].isnull()
#Check whether all values in the column are unique
df['loan'].is_unique
#Count total number of missing values in each column of the dataset
df.isnull().sum()
Suryakant Kumar (92301703051) 10
(5EC5)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #3
#Encode all categorical (object-type) columns into numeric using LabelEncoder
for i in df.columns:
if df[i].dtype==object:
df[i]=LabelEncoder().fit_transform(df[i])
df.head()
#Separate features and target variable — remove 'Target' from features
x = df.drop('Target',axis=1)
y=df['Target']
#Split the data
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=42)
#Normalize the feature data using StandardScaler for better SVM performance
scaler = StandardScaler()
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test)
#Initialize the Support Vector Classifier (SVC) model
svm=SVC()
#Train the model
svm.fit(x_train,y_train)
#Make predictions using the trained SVM model on the test dataset
y_pre=svm.predict(x_test)
#Printing Accuracy
accuracy=accuracy_score(y_test,y_pre)
print(accuracy)
Suryakant Kumar (92301703051) 11
(5EC5)
Practical 4:Implement classification techniques evaluation parameters
using sample dataset
Output:
#Rows represent individual transaction records.
# Drop the Nameorig and nameDest
Suryakant Kumar (92301703051) 12
(5EC5)
#It converts the categorical values in the type
column in numerical labels
#Define features and target
#It trains a Decision Tree model on the training
data X_train and y_train.
Suryakant Kumar (92301703051) 13
(5EC5)
#It prints the performance metrics (precision,
recall, f1-score) and the confusion matrix of the
Decision Tree model on the test data.
Suryakant Kumar (92301703051) 14
(5EC5)
Code :
# Import required libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report, confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt
df=pd.read_csv("/content/transactions.csv")
df
df = df.drop(['nameOrig', 'nameDest'], axis=1)
df
le = LabelEncoder()
df['type'] = le.fit_transform(df['type'])
df
# Step 4: Define features and target
X = df.drop('isFraud', axis=1)
y = df['isFraud']
Y
#It trains a Decision Tree model
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42,
stratify=y)
dt_model = DecisionTreeClassifier(random_state=42)
dt_model.fit(X_train, y_train)
y_pred = dt_model.predict(X_test)
print("=== Decision Tree Classification Report ===")
print(classification_report(y_test, y_pred))
print("=== Confusion Matrix ===") print(confusion
matrix(y_test, y_pred))
Suryakant Kumar (92301703051) 15
(5EC5)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #2
Practical 5:- Develop a cost function of linear regression using sample
dataset.
Output:-
#Displaying graph of cost function history
#Displaying Graph of Linear Regression
Suryakant Kumar (92301703051) 2
(5EC5)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #2
#Printing optimized parameters
Code:-
#importing libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# Step 1: Load the Salary Data CSV file
# Assuming the CSV file has columns 'YearsExperience' and 'Salary'
df=pd.read_csv('/content/Salary_Data.csv')
# Step 2: Extract the input (x) and output (y) data
x = df['YearsExperience'].values # Years of experience
y = df['Salary'].values # Salary
# Step 3: Number of data points
m = len(x)
# Step 4: Prepare the data (add column of ones for intercept term)
X = np.c_[np.ones(m), x] # Adds a column of 1s for theta_0 (intercept term)
Suryakant Kumar (92301703051) 2
(5EC5)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #2
# Step 5: Initialize parameters (theta_0 and theta_1)
theta = np.zeros(2) # [theta_0, theta_1]
# Step 6: Learning rate and number of iterations for gradient descent
learning_rate = 0.01
iterations = 1000
# Step 7: Define the cost function (Mean Squared Error)
def cost_function(X, y, theta):
predictions = X.dot(theta)
cost = (1/(2*m)) * np.sum((predictions - y) ** 2)
return cost
# Step 8: Gradient descent function to optimize theta
def gradient_descent(X, y, theta, learning_rate, iterations):
cost_history = []
for _ in range(iterations):
predictions = X.dot(theta)
errors = predictions - y
gradient = (1/m) * X.T.dot(errors) # Gradient of the cost function
theta -= learning_rate * gradient # Update the parameters
cost_history.append(cost_function(X, y, theta)) # Record cost for each iteration
return theta, cost_history
# Step 9: Run gradient descent to fit the model
theta_optimized, cost_history = gradient_descent(X, y, theta, learning_rate, iterations)
# Step 10: Output optimized parameters
print(f"Optimized parameters: theta_0 = {theta_optimized[0]}, theta_1 =
{theta_optimized[1]}")
Suryakant Kumar (92301703051) 2
(5EC5)
FACULTY OF ENGINEERING AND
TECHNOLOGY
Department of Computer Engineering
01CE0524 – Machine Learning – Lab #2
# Step 11: Plot the cost function history
plt.plot(range(iterations), cost_history)
plt.xlabel('Iterations')
plt.ylabel('Cost (J)')
plt.title('Cost Function History during Gradient Descent')
plt.show()
# Step 12: Plotting the data and the regression line
plt.scatter(x, y, color='red', label='Data points')
plt.plot(x, X.dot(theta_optimized), label='Regression Line', color='blue')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.title('Linear Regression: Experience vs Salary')
plt.legend()
plt.show()
Suryakant Kumar (92301703051) 2
(5EC5)
