18it078_ds_prac3.py

# -*- coding: utf-8 -*-
"""18IT078_DS_PRAC3.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1KgsPR3kkWQEdmlCUg5OICHdOu9DQMFLA
"""

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler

url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"

df = pd.read_csv(url, names=['sepal length','sepal width','petal length','petal width','target'])



df.head()

feature = ['sepal length', 'sepal width', 'petal length', 'petal width']


x = df.loc[:,feature]

y = df.loc[:,'target']

x = StandardScaler().fit_transform(x)

from sklearn.decomposition import PCA

pca = PCA(n_components=2)

pct = pca.fit_transform(x)

principal_df = pd.DataFrame(pct,columns=['pc1','pc2'])

finaldf= pd.concat([principal_df,df[['target']]],axis=1)

finaldf.head()

fig = plt.figure(figsize = (8,8))
ax = fig.add_subplot(1,1,1) 
ax.set_xlabel('Principal Component 1', fontsize = 15)
ax.set_ylabel('Principal Component 2', fontsize = 15)
ax.set_title('2 component PCA', fontsize = 20)
targets = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
colors = ['r', 'g', 'b']
for target, color in zip(targets,colors):
    indicesToKeep = finaldf['target'] == target
    ax.scatter(finaldf.loc[indicesToKeep, 'pc1']
               , finaldf.loc[indicesToKeep, 'pc2']
               , c = color
               , s = 50)
ax.legend(targets)
ax.grid()

pca.explained_variance_ratio_