import numpy as np
import math
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import classification_report
from tqdm import tqdm_notebook 
import seaborn as sns
import time
from IPython.display import HTML
import warnings
warnings.filterwarnings('ignore')
from sklearn.preprocessing import OneHotEncoder
import torch

df = pd.read_csv('/content/drive/My Drive/Dataset/BreastCancer/Breast_cancer_wisconsin.csv')
df.head(5)

df.drop(['Unnamed: 32',"id"], axis=1, inplace=True)
df.diagnosis = [1 if each == "M" else 0 for each in df.diagnosis]
labels = df.diagnosis.values
data = df.drop(['diagnosis'], axis=1).to_numpy()

X_train, X_test, Y_train, Y_test = train_test_split(data, labels, stratify=labels, random_state=0)
print(X_train.shape, X_test.shape, labels.shape)