[go: up one dir, main page]
Scribd
Upload
47 views10 pages

For Assignment-8 (Logistic Regression)

The document provides an overview of Logistic Regression, a classification method that predicts probabilities using the sigmoid function. It discusses the Iris dataset, which contains 150 samples of three flower species and outlines steps for loading the dataset in Python, splitting it for training and testing, and applying feature scaling. Additionally, it explains how to train a Logistic Regression model using a One-vs-Rest strategy and evaluate its predictions with accuracy metrics.

Uploaded by

skaushal1be23
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
47 views10 pages

For Assignment-8 (Logistic Regression)

The document provides an overview of Logistic Regression, a classification method that predicts probabilities using the sigmoid function. It discusses the Iris dataset, which contains 150 samples of three flower species and outlines steps for loading the dataset in Python, splitting it for training and testing, and applying feature scaling. Additionally, it explains how to train a Logistic Regression model using a One-vs-Rest strategy and evaluate its predictions with accuracy metrics.

Uploaded by

skaushal1be23
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

Cognitive Computing UCS420

Logistic Regression
What is Logistic Regression?
• Logistic regression is used for classification problems.
• Unlike linear regression, it predicts probabilities (values
between 0 and 1).
• Uses the sigmoid function to map predictions.
Understanding the Iris Dataset
• The Iris dataset is widely used in ML.
• It contains 150 samples of 3 flower species (Setosa,
Versicolor, Virginica).
• Each sample has 4 features: Sepal Length, Sepal Width,
Petal Length, Petal Width.
Understanding the Iris Dataset
• The Iris dataset is widely used in ML.
• It contains 150 samples of 3 flower species (Setosa,
Versicolor, Virginica).
• Each sample has 4 features: Sepal Length, Sepal Width,
Petal Length, Petal Width.
Loading the Iris Dataset in Python
• Import datasets from sklearn and load the dataset.
• from sklearn import datasets
• iris = datasets.load_iris()
• X = iris.data
• y = iris.target
• X contains features, y contains target labels (0, 1, 2).
Splitting the Dataset
 Why do we split the data? To train and test separately.

 Answer-We split the data into training and testing sets to ensure that our
model learns from one part of the data and is evaluated on another, unseen
part.

 Code:

from sklearn.model_selection import train_test_split

 80% training, 20% testing.


Feature Scaling (Standardization)
Feature Scaling- Why? To normalize data for better model performance.

from sklearn.preprocessing import StandardScaler

• scaler = StandardScaler()
Training the Logistic Regression Model
 We use LogisticRegression from sklearn.

 from sklearn.linear_model import LogisticRegression

 multi_class='ovr' means One-vs-Rest classification.


 ulti_class='ovr' (One-vs-Rest) is a strategy used in multi-class classification
problems where logistic regression is inherently designed for binary
classification.
Training the Logistic Regression Model
• How does it work?
• If there are N classes, the model trains N binary classifiers.
• Each classifier treats one class as positive (1) and the rest as negative (0).
• During prediction, the model assigns the sample to the class with the
highest probability.
• Example (Iris Dataset with 3 classes: 0, 1, 2)
• First classifier: Classifies class 0 vs. (class 1 and 2 together).
• Second classifier: Classifies class 1 vs. (class 0 and 2 together).
• Third classifier: Classifies class 2 vs. (class 0 and 1 together).
Making Predictions and Model Evaluation
Metrics
 Use model.predict() to classify test samples.

y_pred = model.predict(X_test)

 Predictions will be class labels (0, 1, or 2).

 Accuracy Score: Measures overall correctness

You might also like