#!/usr/bin/env python
# coding: utf-8

# In[1]:


import numpy as np
import matplotlib.pyplot as plt
import sklearn.datasets as dt
import sklearn.decomposition as dec
import sklearn.neighbors as ne
import sklearn.model_selection as ms


# In[3]:


#1 feature instead of 4 features:
IRIS = dt.load_iris()
x1 = IRIS.data
y = IRIS.target

DR = dec.PCA(n_components = 1)
DR.fit(x1)
x2 = DR.transform(x1)


# In[4]:


plt.subplot(2, 2, 1)
plt.scatter(x1[:, 0], x1[:, 1], s = 5, c = y)
plt.xlabel("X1")
plt.ylabel("X2")

plt.subplot(2, 2, 2)
plt.scatter(x2[:, 0], x2[:, 0], s = 5)
plt.xlabel("PC1")

plt.subplot(2, 2, 3)
plt.scatter(x1[:, 2], x1[:, 3], s = 5, c = y)
plt.xlabel("X3")
plt.ylabel("X4")

plt.subplot(2, 2, 4)
plt.scatter(x2[:, 0], x2[:, 0], s = 5)
plt.xlabel("PC1")

plt.tight_layout()


# In[5]:


xtr1, xte1, ytr1, yte1 = ms.train_test_split(x1, y, train_size = 0.7, random_state = 23)
xtr2, xte2, ytr2, yte2 = ms.train_test_split(x2, y, train_size = 0.7, random_state = 23)


# In[6]:


KNN1 = ne.KNeighborsClassifier(n_neighbors = 5)
KNN1.fit(xtr1, ytr1)
trACC1 = KNN1.score(xtr1, ytr1)
teACC1 = KNN1.score(xte1, yte1)

KNN2 = ne.KNeighborsClassifier(n_neighbors = 5)
KNN2.fit(xtr2, ytr2)
trACC2 = KNN2.score(xtr2, ytr2)
teACC2 = KNN2.score(xte2, yte2)


# In[7]:


print("Train Accuracy Change : ", trACC2 - trACC1)
print("Test Accuracy Change : ", teACC2 - teACC1)