From 44cb41112b215e2d763e3234b00504e6c203effc Mon Sep 17 00:00:00 2001
From: PARIKSHIT SINGH <parikshit2111@gmail.com>
Date: Sat, 1 Mar 2025 09:47:53 +0530
Subject: [PATCH 1/3] feat: Implement Principal Component Analysis (PCA)

- Added a Python implementation of PCA using NumPy and scikit-learn
- Standardizes the dataset before applying PCA for better performance
- Computes principal components and explained variance ratio
- Uses the Iris dataset as a sample for demonstration
- Provides a modular structure for easy extension and dataset modification
---
 .../principle_component_analysis.py           | 66 +++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100644 machine_learning/principle_component_analysis.py

diff --git a/machine_learning/principle_component_analysis.py b/machine_learning/principle_component_analysis.py
new file mode 100644
index 000000000000..fb06e12dacea
--- /dev/null
+++ b/machine_learning/principle_component_analysis.py
@@ -0,0 +1,66 @@
+"""
+Principal Component Analysis (PCA) is a dimensionality reduction technique 
+commonly used in machine learning. It transforms high-dimensional data into 
+lower dimensions while retaining most of the information.
+
+Here,we use a dataset (Iris dataset) and apply PCA to reduce the 
+dimensionality. We compute the principal components and transform the dataset 
+into a lower-dimensional space.
+
+We reduce the number of columns form 4 to 2 
+
+"""
+
+import numpy as np
+import requests
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+from sklearn.datasets import load_iris
+
+
+def collect_dataset():
+    """Collect dataset (Iris dataset)
+    :return: Feature matrix and target values
+    """
+    data = load_iris()
+    return np.array(data.data), np.array(data.target)
+
+
+def apply_pca(data_x, n_components):
+    """Apply Principal Component Analysis (PCA)
+    :param data_x: Original dataset
+    :param n_components: Number of principal components
+    :return: Transformed dataset and explained variance
+    """
+    # Standardizing the features
+    scaler = StandardScaler()
+    data_x_scaled = scaler.fit_transform(data_x)
+
+    # Applying PCA
+    pca = PCA(n_components=n_components)
+    principal_components = pca.fit_transform(data_x_scaled)
+
+    # Explained variance ratio
+    explained_variance = pca.explained_variance_ratio_
+
+    return principal_components, explained_variance
+
+
+def main():
+    """Driver function"""
+    data_x, data_y = collect_dataset()
+    # Set number of principal components
+    n_components = 3
+
+    # Apply PCA
+    transformed_data, variance_ratio = apply_pca(data_x, n_components)
+
+    print("Transformed Dataset (First 5 rows):")
+    print(transformed_data[:5])
+
+    print("\nExplained Variance Ratio:")
+    print(variance_ratio)
+
+
+if __name__ == "__main__":
+    main()

From ac605b512e35ef23f6fc5aa61c1cff499c69dce7 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 1 Mar 2025 04:28:50 +0000
Subject: [PATCH 2/3] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/principle_component_analysis.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/machine_learning/principle_component_analysis.py b/machine_learning/principle_component_analysis.py
index fb06e12dacea..96f64cb7b3e0 100644
--- a/machine_learning/principle_component_analysis.py
+++ b/machine_learning/principle_component_analysis.py
@@ -1,13 +1,13 @@
 """
-Principal Component Analysis (PCA) is a dimensionality reduction technique 
-commonly used in machine learning. It transforms high-dimensional data into 
+Principal Component Analysis (PCA) is a dimensionality reduction technique
+commonly used in machine learning. It transforms high-dimensional data into
 lower dimensions while retaining most of the information.
 
-Here,we use a dataset (Iris dataset) and apply PCA to reduce the 
-dimensionality. We compute the principal components and transform the dataset 
+Here,we use a dataset (Iris dataset) and apply PCA to reduce the
+dimensionality. We compute the principal components and transform the dataset
 into a lower-dimensional space.
 
-We reduce the number of columns form 4 to 2 
+We reduce the number of columns form 4 to 2
 
 """
 

From e735cbe5ed7a47caac788233d3b8fe43d89d3a32 Mon Sep 17 00:00:00 2001
From: PARIKSHIT SINGH <parikshit2111@gmail.com>
Date: Sat, 1 Mar 2025 10:02:51 +0530
Subject: [PATCH 3/3] refactor:Removed requests from imports

---
 machine_learning/principle_component_analysis.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/machine_learning/principle_component_analysis.py b/machine_learning/principle_component_analysis.py
index fb06e12dacea..5d9b15e3649d 100644
--- a/machine_learning/principle_component_analysis.py
+++ b/machine_learning/principle_component_analysis.py
@@ -12,7 +12,6 @@
 """
 
 import numpy as np
-import requests
 from sklearn.decomposition import PCA
 from sklearn.preprocessing import StandardScaler
 from sklearn.datasets import load_iris