import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
import pickle

df = pd.read_csv('Clean_cancer_dataset.csv')

x = df.drop(['diagnosis','Unnamed: 0'],axis=1)
y = df['diagnosis']

x_train , x_test , y_train , y_test = train_test_split(x,y,test_size=0.2,random_state=908)

model = DecisionTreeClassifier()
model.fit(x_train,y_train)

pickle.dump(model,open("model.pkl","wb"))