import pandas as pd

data1=pd.read_csv('/home/jovyan/work/seeds_dataset.csv')

data1.isnull().sum()

data1.head(10)

x=data1[['area','perimeter','compactness','lengthOfKernel','widthOfKernel','asymmetryCoefficient','lengthOfKernelGroove']] y=data1['seedType']

from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 0)

from sklearn.tree import DecisionTreeClassifier classifier = DecisionTreeClassifier(criterion = 'gini', random_state = 42) classifier.fit(X_train, y_train)

y_pred = classifier.predict(X_test)

from sklearn.metrics import accuracy_score accuracy_score(y_test, y_pred)