DATA SCIENCE LAB MANUAL

 

 Example 1: Linear Regression

PREDITING PRICE BASES ON AREA

import numpy as np

import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression

# 1. Example Data

# X = Input (Area of house)

# Y = Output (Price)

X = np.array([100, 200, 300, 400, 500]).reshape(-1, 1)

Y = np.array([10, 20, 30, 40, 50])

# 2. Create and train the model

model = LinearRegression()   # intercept is included by default

model.fit(X, Y)

# 3. Get slope and intercept

m = model.coef_[0]        # slope

b = model.intercept_      # intercept

# 4. Prediction

x_new = 350

y_pred = model.predict([[x_new]])

# 5. Plot the graph

X_line = np.linspace(100, 500, 100).reshape(-1, 1)

Y_line = model.predict(X_line)

plt.scatter(X, Y)          # original data points

plt.plot(X_line, Y_line)   # regression line

plt.scatter(x_new, y_pred) # predicted point

plt.xlabel("Area")

plt.ylabel("Price")

plt.title("Simple Linear Regression")

plt.show()

# 6. Print results

print("Slope (m):", m)

print("Intercept (b):", b)

print("Equation: Y =", m, "* X +", b)

print("Predicted Price for", x_new, ":", y_pred[0])

 Example 2: Linear Regression (Study Hours vs Marks)

👉 Problem Statement

Predict student marks based on study hours.

import numpy as np

import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression

# Data

X = np.array([1, 2, 3, 4, 5]).reshape(-1, 1)  # Study hours

Y = np.array([35, 40, 50, 60, 70])            # Marks

# Model

model = LinearRegression()

model.fit(X, Y)

# Slope and intercept

m = model.coef_[0]

b = model.intercept_

# Prediction

hours = 6

predicted_marks = model.predict([[hours]])

# Plot

X_line = np.linspace(1, 6, 100).reshape(-1, 1)

Y_line = model.predict(X_line)

plt.scatter(X, Y)

plt.plot(X_line, Y_line)

plt.scatter(hours, predicted_marks)

plt.xlabel("Study Hours")

plt.ylabel("Marks")

plt.title("Linear Regression: Study Hours vs Marks")

plt.show()

# Output

print("Slope (m):", m)

print("Intercept (b):", b)

print("Equation: Y =", m, "* X +", b)

print("Predicted Marks for", hours, "hours:", predicted_marks[0])

2. Logistic Regression code  

Program 1: Student Pass / Fail Prediction

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression

from sklearn.metrics import accuracy_score, confusion_matrix

# Dataset

data = {

    'Hours_Studied': [1,2,3,4,5,6,7,8],

    'Passed': [0,0,0,0,1,1,1,1]

}

df = pd.DataFrame(data)

# Features and target

X = df[['Hours_Studied']]

y = df['Passed']

# Train-test split

X_train, X_test, y_train, y_test = train_test_split(

    X, y, test_size=0.25, random_state=0

)

# Model

model = LogisticRegression()

model.fit(X_train, y_train)

# Prediction

y_pred = model.predict(X_test)

# Results

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

print("Intercept (β0):", model.intercept_)

print("Coefficient (β1):", model.coef_)  

OUTPUT 

Accuracy: 1.0 Confusion Matrix: [[1 0] [0 1]] Intercept (β0): [-4.4350521] Coefficient (β1): [[1.01750279]]

Program 2: Salary > 50K Prediction (Binary Classification)

# Logistic Regression – Example 2 (Salary Prediction)

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

# Dataset
data = {
    'Age': [22,25,30,35,40,45,50,55],
    'Experience': [0,1,3,5,7,10,15,20],
    'High_Salary': [0,0,0,1,1,1,1,1]
}

df = pd.DataFrame(data)

# Features and target
X = df[['Age', 'Experience']]
y = df['High_Salary']

# Train-test split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=1
)

# Model
model = LogisticRegression()
model.fit(X_train, y_train)

# Prediction
y_pred = model.predict(X_test)

# Results
print("Accuracy:", accuracy_score(y_test, y_pred))
print("Intercept (β0):", model.intercept_)
print("Coefficients (β1, β2):", model.coef_)

Accuracy: 0.6666666666666666
Intercept (β0): [-13.33988536]
Coefficients (β1, β2): [[0.45410297 0.17502853]]