Scribd
Upload
5 views7 pages

EX-1

The document outlines various methods for building regression models, including Linear Regression using Least Squares, Gradient Descent, and Multiple Linear Regression with Scikit-learn and Statsmodels. It also covers the implementation of Bayesian Linear Regression and Logistic Regression for classification tasks, demonstrating the use of Python libraries such as pandas, matplotlib, and scikit-learn. Each section includes code snippets and outputs for model evaluation, specifically focusing on Mean Squared Error and accuracy metrics.

Uploaded by

953622104040
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
5 views7 pages

EX-1

The document outlines various methods for building regression models, including Linear Regression using Least Squares, Gradient Descent, and Multiple Linear Regression with Scikit-learn and Statsmodels. It also covers the implementation of Bayesian Linear Regression and Logistic Regression for classification tasks, demonstrating the use of Python libraries such as pandas, matplotlib, and scikit-learn. Each section includes code snippets and outputs for model evaluation, specifically focusing on Mean Squared Error and accuracy metrics.

Uploaded by

953622104040
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Name: Jeyasuriya K

RegNo: 953622104040

EX-1
1a. Build Linear Regression Model using Least Square.
#least regression

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data = pd.read_csv('data.csv')
X = data.iloc[:, 0]
Y = data.iloc[:, 1]
plt.scatter(X, Y)
plt.show()
n = len(X)
sum_x = sum(X)
sum_y = sum(Y)
sum_xy = 0
for i in range(n):
sum_xy = sum_xy + X[i] * Y[i]
sum_sq_x = 0
for i in range(n):
sum_sq_x = sum_sq_x + (X[i] * X[i])
m = (n * sum_xy - sum_x * sum_y) / (n * sum_sq_x - (sum_x) ** 2)
c = (sum_y - m * sum_x) / n
print("The intercept is:",m)
print("The coefficient is:",c)
y_pred = [m * x + c for x in X]
plt.scatter(X, Y)
plt.plot([min(X),max(X)],[min(y_pred),max(y_pred)],color='red')
plt.show()

OUTPUT:
Name: Jeyasuriya K
RegNo: 953622104040

1b. Build Linear Regression Model using Gradient Descent.


#gradiant
import numpy as np
import pandas as pd
import matplotlib .pyplot as plt
data = pd.read_csv('data.csv')
x=data.iloc[:,0]
y=data.iloc[:,1]
plt.scatter(x,y)
plt.show()
n=len(x)
m=5
c=1
l=0.0001
epoch=1000
for i in range(len(x)):
y_pred=m*x+c
dm=(-2/n)*sum(x*(y-y_pred))
dc=(-2/n)*sum(y*(y-y_pred))
m=m-l*dm
c=c-l*dc
print(m,c)
y_pred=m*x+c
mse = (1/n)*((sum(y-y_pred)) ** 2)
print("The mse is:",mse)
plt.scatter(x,y)
plt.scatter(x,y_pred)
plt.show()
Name: Jeyasuriya K
RegNo: 953622104040
Name: Jeyasuriya K
RegNo: 953622104040

1c. Build Multiple Linear Regression Model using Scikit learn and stats model.
#using statsmodels and Sklearn
import pandas as pd
import matplotlib.pyplot as plt
import statsmodels.api as sm
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
df = pd.read_csv("Advertising.csv")
x = df.drop('sales', axis=1)
y = df['sales']
x = sm.add_constant(x)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
model_ols = sm.OLS(y_train, x_train).fit()
intercept_ols = model_ols.params[0]
coefficients_ols = model_ols.params[1:]
print("Intercept:",intercept_ols)
print("Coefficient:",coefficients_ols)
y_pred_ols = model_ols.predict(x_test)
mse_ols = mean_squared_error(y_test, y_pred_ols)
print("Mean Squared Error using OLS:",mse_ols)
plt.scatter(y_test, y_pred_ols)
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], linestyle='--', color='red',
linewidth=2)
plt.xlabel("Actual Sales")
plt.ylabel("Predicted Sales")
plt.title("OLS Regression Results")
plt.show()

Output:
Name: Jeyasuriya K
RegNo: 953622104040

1d. Build Linear Regression Model using Pre-defined Packages with training and testing data.

# Predefined packages
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

df = pd.read_csv("Advertising.csv")
x = df.drop('sales', axis=1)
y = df['sales']
x = pd.get_dummies(x, drop_first=True)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
model = LinearRegression()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
mse = mean_squared_error(y_test, y_pred)
print("M:",model.intercept_)
print("C:",model.coef_)
print(f"Mean Squared Error: {mse}")
plt.scatter(y_test,y_pred)
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], linestyle='--', color='red',
linewidth=2)
plt.show()

Output:
Name: Jeyasuriya K
RegNo: 953622104040

1e. Build Bayesian Linear Regression Model.

# BayesianRidge
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import BayesianRidge
from sklearn.metrics import mean_squared_error

df = pd.read_csv("Advertising.csv")
x = df.drop('sales', axis=1)
y = df['sales']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
model = BayesianRidge()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
mse = mean_squared_error(y_test, y_pred)
print("Intercept:",model.intercept_)
print("Coefficient:",model.coef_)
print(f"Mean Squared Error: {mse}")
plt.scatter(y_test,y_pred)
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], linestyle='--', color='red',
linewidth=2)
plt.show()

Output:
Name: Jeyasuriya K
RegNo: 953622104040

1f. Build Logistic Regression Model.

#Logisitic Regression

import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import StandardScaler

df=pd.read_csv("breast_cancer.csv")
x = df.drop(['diagnosis'], axis=1)
y = df['diagnosis']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
scaler = StandardScaler()
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test)
model = LogisticRegression()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print('Accuracy:', accuracy)

Output:

You might also like