import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import StandardScaler
iris = sns.load_dataset('iris')
scaler = StandardScaler()
scaled = scaler.fit_transform(
iris[['sepal_length', 'sepal_width', 'petal_length', 'petal_width']].values
)
covariance_matrix = np.cov(scaled.T)
covariance_matrix
sns.pairplot(iris)
sns.jointplot(x= iris['petal_length'], y=iris['petal_width'])
sns.jointplot(x = scaled[:, 2], y = scaled[:,3])
eigen_values, eigen_vectors = np.linalg.eig(covariance_matrix)
eigen_values
eigen_vectors
variance_explained = []
for i in eigen_values:
variance_explained.append((i/sum(eigen_values))*100)
print(variance_explained)
[72.9624454132999, 22.850761786701725, 3.6689218892828612, 0.5178709107154993]
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
pca.fit(scaled)
pca.explained_variance_ratio_
reduced_scaled = pca.transform(scaled)
iris['pca_1'] = scaled[:,0]
iris['pca_2'] = scaled[:,1]
sns.jointplot(iris['pca_1'], iris['pca_2'], hue = iris['species'])
/shared-libs/python3.7/py/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
FutureWarning