9/7/2018 komal_knn1

In [33]: import pandas as pd

import numpy as np

from sklearn.model_selection import train_test_split

from sklearn import metrics

from sklearn.neighbors import KNeighborsClassifier

import seaborn as sns

sns.set(font_scale=1.5)
sns.set(style='white',color_codes=True)

import matplotlib.pyplot as plt

In [7]: location="D:\komal\SIMPLILEARN\MY COURSES\IN PROGRESS\DATA SCIENCE WITH PYTHON

\Live class downloads\Aug 11 Sat - Sep 15 Sat - Attending\datasets\iris.csv"

In [9]: df_training=pd.read_csv(location)

In [10]: df_training.head()

Out[10]:
sepal_length sepal_width petal_length petal_width class

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

file:///D:/komal/SIMPLILEARN/MY%20COURSES/IN%20PROGRESS/My%20Codes_ML_DS/codes%20in%20pdf/komal_knn1.html 1/4
9/7/2018 komal_knn1

In [17]: sns.pairplot(df_training,hue = 'class',size = 2)

Out[17]: <seaborn.axisgrid.PairGrid at 0x1a2114e2a58>

In [18]: X = df_training[['sepal_length','sepal_width','petal_length','petal_width']]

In [19]: y = df_training[['class']]

In [20]: X_train,X_test,y_train,y_test= train_test_split(X,y,test_size=0.3,random_state

=0)

In [21]: knn = KNeighborsClassifier(n_neighbors=5)

In [22]: knn

Out[22]: KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',

metric_params=None, n_jobs=1, n_neighbors=5, p=2,
weights='uniform')

file:///D:/komal/SIMPLILEARN/MY%20COURSES/IN%20PROGRESS/My%20Codes_ML_DS/codes%20in%20pdf/komal_knn1.html 2/4
9/7/2018 komal_knn1

In [23]: knn.fit(X_train, y_train)

C:\Users\hariz\Anaconda3\lib\site-packages\ipykernel_launcher.py:1: DataConve
rsionWarning: A column-vector y was passed when a 1d array was expected. Plea
se change the shape of y to (n_samples, ), for example using ravel().
"""Entry point for launching an IPython kernel.
Out[23]: KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
metric_params=None, n_jobs=1, n_neighbors=5, p=2,
weights='uniform')

In [24]: y_pred = knn.predict(X_test)

In [25]: ModelPrediction_accuracy=metrics.accuracy_score(y_test,y_pred)

In [26]: print("The accuracy of the model prediction is:",ModelPrediction_accuracy)

The accuracy of the model prediction is: 0.9777777777777777

In [34]: conf = metrics.confusion_matrix(y_test,y_pred)

plt.imshow(conf, cmap='binary', interpolation='None')
plt.show()

In [31]: print(metrics.classification_report(y_test,y_pred))

precision recall f1-score support

Iris-setosa 1.00 1.00 1.00 16

Iris-versicolor 1.00 0.94 0.97 18
Iris-virginica 0.92 1.00 0.96 11

avg / total 0.98 0.98 0.98 45

In [91]: sample=[[2,4,1,5],[3,1,2,5]]

file:///D:/komal/SIMPLILEARN/MY%20COURSES/IN%20PROGRESS/My%20Codes_ML_DS/codes%20in%20pdf/komal_knn1.html 3/4
9/7/2018 komal_knn1

In [92]: predictions=knn.predict(sample)
predictions

Out[92]: array(['Iris-setosa', 'Iris-versicolor'], dtype=object)

file:///D:/komal/SIMPLILEARN/MY%20COURSES/IN%20PROGRESS/My%20Codes_ML_DS/codes%20in%20pdf/komal_knn1.html 4/4