Lab Exam ... Roll No 24cs4103

Logistic Regression
Implement the logistic regression in Python using the dataset available in

Kaggel or UCI. You must submit two programs with and without using the
inbuilt function (from sklearn.linear_model import Linear Regression ).
1. Logistic Regression Using Scikit-Learn
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
# Load the Iris dataset

iris = datasets.load_iris()
X = iris.data[:, :2] # Using only the first two features for 2D plotting
y = iris.target
# Create a DataFrame for better visualization

iris_df = pd.DataFrame(data=X, columns=iris.feature_names[:2])
iris_df['target'] = y
# Split the dataset into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create and train the logistic regression model

model = LogisticRegression(multi_class='multinomial', solver='lbfgs', max_iter=200)
model.fit(X_train, y_train)
# Plot the original data points

plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plt.scatter(X[:, 0], X[:, 1], c=y, edgecolors='k', cmap=plt.cm.Set1)
plt.title('Iris Dataset: Original Data Points')
plt.xlabel(iris.feature_names[0])
plt.ylabel(iris.feature_names[1])
plt.grid()
# Plotting decision boundaries

x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),
np.arange(y_min, y_max, 0.01))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, alpha=0.8, cmap=plt.cm.Set1)
plt.scatter(X[:, 0], X[:, 1], c=y, marker='o', label='Data Points')
plt.scatter(X_test[:, 0], X_test[:, 1], c='black', marker='x', label='Test Data')
plt.title('Logistic Regression Decision Boundary')
plt.legend()
plt.grid()
plt.tight_layout()
plt.show()
2. Logistic Regression Without Using Inbuilt Functions
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
# Load the Iris dataset

iris = datasets.load_iris()
X = iris.data[:, :2] # Using only the first two features for 2D plotting
y = iris.target
# Split the dataset into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
class LogisticRegressionScratch:
def __init__(self, learning_rate=0.01, num_iterations=1000):
self.learning_rate = learning_rate
self.num_iterations = num_iterations
self.weights = None
self.bias = None
def softmax(self, z):

exp_z = np.exp(z - np.max(z, axis=1, keepdims=True)) # Stability improvement
return exp_z / np.sum(exp_z, axis=1, keepdims=True)
def fit(self, X, y):

num_samples, num_features = X.shape
num_classes = len(np.unique(y))
self.weights = np.zeros((num_features, num_classes))
self.bias = np.zeros(num_classes)
for _ in range(self.num_iterations):
# Linear model
linear_model = np.dot(X, self.weights) + self.bias
probabilities = self.softmax(linear_model)
# One-hot encode the target

y_one_hot = np.zeros((num_samples, num_classes))
y_one_hot[np.arange(num_samples), y] = 1
# Compute gradients
dw = (1 / num_samples) * np.dot(X.T, (probabilities - y_one_hot))
db = (1 / num_samples) * np.sum(probabilities - y_one_hot, axis=0)
# Update weights and bias

self.weights -= self.learning_rate * dw
self.bias -= self.learning_rate * db
def predict(self, X):

linear_model = np.dot(X, self.weights) + self.bias
probabilities = self.softmax(linear_model)
return np.argmax(probabilities, axis=1)
# Create and train the logistic regression model

model = LogisticRegressionScratch(learning_rate=0.1, num_iterations=1000)
model.fit(X_train, y_train)
# Plot the original data points
plt.figure(figsize=(12, 6))
plt.scatter(X[:, 0], X[:, 1], c=y, edgecolors='k', cmap=plt.cm.Set1)
plt.title('Iris Dataset: Original Data Points')
plt.grid()
# Plotting decision boundaries

x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),
np.arange(y_min, y_max, 0.01))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, alpha=0.8, cmap=plt.cm.Set1)
plt.scatter(X[:, 0], X[:, 1], c=y, marker='o', label='Data Points')
plt.scatter(X_test[:, 0], X_test[:, 1], c='black', marker='x', label='Test Data')
plt.title('Logistic Regression Decision Boundary')
plt.legend()
plt.grid()
plt.tight_layout()
plt.show()

Lab Exam ... Roll No 24cs4103

Uploaded by

Document Informationclick to expand document information

Document Informationclick to expand document information

Copyright:

Available Formats

Lab Exam ... Roll No 24cs4103

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lab Exam ... Roll No 24cs4103

Uploaded by

Copyright:

Available Formats

Logistic Regression

Implement the logistic regression in Python using the dataset available in

1. Logistic Regression Using Scikit-Learn

# Load the Iris dataset

# Create a DataFrame for better visualization

# Split the dataset into training and testing sets

# Create and train the logistic regression model

# Plot the original data points

# Plotting decision boundaries

# Load the Iris dataset

# Split the dataset into training and testing sets

def softmax(self, z):

def fit(self, X, y):

# One-hot encode the target

# Update weights and bias

def predict(self, X):

# Create and train the logistic regression model

# Plotting decision boundaries

You might also like