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

# #MULTI CLASS CLASSIFICATION

# In[1]:


# Data Imports
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

# Plot imports
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')

get_ipython().run_line_magic('matplotlib', 'inline')


# In[2]:


from sklearn import linear_model
from sklearn.datasets import load_iris


# In[3]:


iris = load_iris()


# In[4]:


X = iris.data

Y = iris.target


# In[5]:


print iris.DESCR


# In[6]:


iris_data = DataFrame(X,columns=['Sepal Length','Sepal Width','Petal Length','Petal Width'])


# In[7]:


iris_target = DataFrame(Y,columns=['Species'])


# In[10]:


def flower(num):
    if num == 0:
        return 'Setosa'
    elif num == 1:
        return 'Versicolour'
    else:
        return 'Virginica'


# In[11]:


iris_target['Species'] =  iris_target['Species'].apply(flower)


# In[13]:


iris_target.tail()


# In[14]:


iris = pd.concat([iris_data,iris_target],axis=1)


# In[15]:


iris.head()


# In[16]:


sns.pairplot(iris,hue='Species',size=2)


# In[17]:


sns.factorplot('Petal Length',data=iris,hue='Species',size=10)


# In[19]:


from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import train_test_split


# In[20]:


logreg = LogisticRegression()

X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size = 0.4,random_state=3)


# In[21]:


logreg.fit(X_train,Y_train)


# In[22]:


from sklearn import metrics


# In[23]:


Y_pred = logreg.predict(X_test)


# In[24]:


print metrics.accuracy_score(Y_test,Y_pred)


# In[25]:


from sklearn.neighbors import KNeighborsClassifier


# In[27]:


knn = KNeighborsClassifier(n_neighbors = 6)


# In[28]:


knn.fit(X_train,Y_train)


# In[29]:


Y_pred = knn.predict(X_test)


# In[30]:


print metrics.accuracy_score(Y_test,Y_pred)


# In[31]:


knn = KNeighborsClassifier(n_neighbors=1)


# In[32]:


knn.fit(X_train,Y_train)


# In[33]:


Y_pred = knn.predict(X_test)


# In[34]:


print metrics.accuracy_score(Y_test,Y_pred)


# In[35]:


k_range = range(1,21)

accuracy = []


# In[36]:


for k in k_range:
    
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train,Y_train)
    Y_pred = knn.predict(X_test)
    
    accuracy.append(metrics.accuracy_score(Y_test,Y_pred))


# In[37]:


plt.plot(k_range,accuracy)
plt.xlabel('K value')
plt.ylabel('Testing Accuracy')


# In[ ]: