Introduction:
Naive bayes is a supervised machine learning algorithm that can be used to solve classification problem, it is a probabilistic classifier that means it predicts on the basis of probability of an object. Let's breakdown the meaning the name.
Naive: It is called naive because of assumption that all the attribute are independent from eachother.
Bayes: It is called bayes because it is based on the principle of bayes theorem.
Some Uniques features of Naive Bayes Algo:
1. Classification Focused: Naive Bayes is a supervised learning algorithm specifically designed for classification problems. It excels at categorizing new data points into predefined classes based on their features.
2. Built on Bayes' Theorem: The algorithm leverages Bayes' theorem, a powerful tool in probability theory, to calculate the conditional probability of a data point belonging to a particular class.
3. Conditional Feature Independence: The "naive" part of Naive Bayes comes from its core assumption: that the features (attributes) used for classification are conditionally independent of each other given the class label. In simpler terms, the presence of one feature doesn't influence the presence of another feature, considering the class.
4. Efficient for High-Dimensional Data: Unlike some complex algorithms, Naive Bayes works well with high-dimensional data, where there are many features. This makes it a good choice for text classification tasks where each word can be considered a feature.
5. Fast and Scalable: The relatively simple calculations involved in Naive Bayes make it a fast and computationally efficient algorithm. This allows for quick predictions and easy implementation in various applications.
6. Handles Various Data Types: Naive Bayes can handle both discrete data (like text categories) and continuous data (like numerical values) with appropriate adjustments.
7. Strong for Multi-Class Problems: While it works for binary classification (two classes), Naive Bayes often shines in multi-class scenarios (more than two classes) due to its efficient handling of multiple class probabilities.
Advantages of Bayes Algo:
Simple and Easy to Implement: Naive Bayes is known for its user-friendly nature, making it a great choice for beginners in machine learning.
Efficient for Large Datasets: Due to its reliance on simple calculations, Naive Bayes excels at handling large datasets and making predictions quickly.
Works Well with Less Training Data: Compared to other algorithms, Naive Bayes can perform well even with limited training data.
Effective for Multi-Class Problems: Naive Bayes handles multiple classes efficiently, making it a good fit for tasks with various classification options.
Code:
from sklearn.naive_bayes import GaussianNB
X = [[3, 5], [4, 8], [1, 1], [2, 3], [5, 7]]
y = ["spam", "spam", "ham", "ham", "spam"]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = GaussianNB()
model.fit(X_train, y_train)
new_email = [2, 7]
predicted_class = model.predict([new_email])[0]
print("Predicted class:", predicted_class)
This is a very basic code regarding naive bayes algorithm you can tweak this and make a model that works better for your sample data.
KEEP LEARNING!!