KNN with Iris

Libraries

import sklearn.neighbors as nei
import pandas as pd
import sklearn.model_selection as mod

Data

# Load the iris data set from a URL.
df = pd.read_csv("https://github.com/ianmcloughlin/datasets/raw/master/iris.csv")

df

	sepal_length	sepal_width	petal_length	petal_width	class
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa
...	...	...	...	...	...
145	6.7	3.0	5.2	2.3	virginica
146	6.3	2.5	5.0	1.9	virginica
147	6.5	3.0	5.2	2.0	virginica
148	6.2	3.4	5.4	2.3	virginica
149	5.9	3.0	5.1	1.8	virginica

150 rows × 5 columns

Visualise

# Load the seaborn package.
import seaborn as sns

# Plot the Iris data set with a pair plot.
sns.pairplot(df, hue="class")

<seaborn.axisgrid.PairGrid at 0x1e0de7d0988>

Inputs and outputs

inputs = df[['sepal_length', 'sepal_width', 'petal_length', 'petal_width']]
outputs = df['class']

Classifier

knn = nei.KNeighborsClassifier(n_neighbors=5)

Fit

knn.fit(inputs, outputs)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
                     metric_params=None, n_jobs=None, n_neighbors=5, p=2,
                     weights='uniform')

Predict

df.loc[121]

sepal_length          5.6
sepal_width           2.8
petal_length          4.9
petal_width             2
class           virginica
Name: 121, dtype: object

knn.predict([[5.6, 2.8, 4.9, 2.0]])

array(['virginica'], dtype=object)

Evaluate

(knn.predict(inputs) == outputs).sum()

145

inputs_train, inputs_test, outputs_train, outputs_test = mod.train_test_split(inputs, outputs, test_size=0.33)

knn = nei.KNeighborsClassifier(n_neighbors=5)
knn.fit(inputs_train, outputs_train)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
                     metric_params=None, n_jobs=None, n_neighbors=5, p=2,
                     weights='uniform')

(knn.predict(inputs_test) == outputs_test).sum()

48

End