Untitled

import pandas as pd
import seaborn as sb
import numpy as np


iris_data = pd.read_csv("iris.data")
colums_name = ['Sepal length', 'Sepal width', 'Petal length', 'Petal width', 'class'] 
iris_data.columns = colums_name 
# iris_data.head()

# iris_data.isnull().sum()
# iris_data.value_counts("class")

# sb.countplot(x="class", data = iris_data)


fig = sb.scatterplot(x="Sepal length", y="Sepal width", hue="class", data=iris_data)

fig.set(title="Sepal Length and Width")


features = iris_data.iloc[:, 0:4] 
label = iris_data.iloc[:, 4] 
print("Features : ") 
print(features) 
print("Label : ") 
print(label)

from sklearn.model_selection import train_test_split 
X_train, X_test, y_train, y_test = train_test_split( features, label, test_size=0.2, random_state=0) 
print('Number of train data' ,X_train.shape[0]) 
print('Number of data test', y_test.shape[0])

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=8, weights="uniform")
knn.fit(X_train, y_train)
train_acc = knn.score(X_train, y_train)
print("The accuracy Of KNN classifier on training data is : {:.3f}".format(train_acc))