dimensionality reduction on iris dataset

In [1]:

    

import matplotlib.pyplot as plt
import matplotlib.ticker
import mpl_toolkits.mplot3d
import numpy as np
import pandas as pd
import seaborn as sns
import sklearn.datasets
import sklearn.decomposition
import sklearn.manifold
import sklearn.preprocessing
sns.set(style='ticks')
sns.set_palette('husl')
mpl_toolkits.mplot3d.Axes3D
import warnings
warnings.filterwarnings("ignore")


    

In [2]:

    

%matplotlib inline
plt.rcParams["figure.figsize"] = (17, 17)
#sns.set(context="paper", font="monospace")


    

In [3]:

    

df = pd.read_csv(
    'iris.csv',
    header = None,
    names  = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species']
)
df.head()


    

    
Out[3]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
species
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
      
Iris-setosa
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
Iris-setosa
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
      
Iris-setosa
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
      
Iris-setosa
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
      
Iris-setosa
    
  

In [4]:

    

features = list(df.columns[:-1])
print(features)
X = df[features].values
y = df["species"].values


    

    




['sepal_length', 'sepal_width', 'petal_length', 'petal_width']

In [5]:

    

df["species"].unique()


    

    
Out[5]:





array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)

In [6]:

    

for point, label in zip(X, y):
    if label == 'Iris-setosa':
        plt.scatter(point[0], point[1], c="red", s=100)
    if label == 'Iris-versicolor':
        plt.scatter(point[0], point[1], c="blue", s=100)
    if label == 'Iris-virginica':
        plt.scatter(point[0], point[1], c="green", s=100)
    plt.axes().annotate(label, (point[0], point[1]), ha='center', size=15)


    

In [7]:

    

pca = sklearn.decomposition.PCA(n_components=2).fit_transform(X)
for point, label in zip(pca, y):
    if label == 'Iris-setosa':
        plt.scatter(point[0], point[1], c="red", s=100)
    if label == 'Iris-versicolor':
        plt.scatter(point[0], point[1], c="blue", s=100)
    if label == 'Iris-virginica':
        plt.scatter(point[0], point[1], c="green", s=100)
    plt.axes().annotate(label, (point[0], point[1]), ha='center', size=15)


    

In [9]:

    

Y = sklearn.manifold.TSNE(
    n_components = 2,
    init         = "pca",
    method       = "barnes_hut",
    perplexity   = 13
).fit_transform(X)

for point, label in zip(Y, y):
    if label == 'Iris-setosa':
        plt.scatter(point[0], point[1], c="red", s=100)
    if label == 'Iris-versicolor':
        plt.scatter(point[0], point[1], c="blue", s=100)
    if label == 'Iris-virginica':
        plt.scatter(point[0], point[1], c="green", s=100)
    plt.axes().annotate(label, (point[0], point[1]), ha='center', size=15)


    

In [ ]: