# libraries
from sklearn.tree import DecisionTreeClassifier
from sklearn.cluster import KMeans
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
from sklearn.model_selection import cross_val_score, KFold
from sklearn import metrics
from sklearn.utils import resample
from sklearn.ensemble import VotingClassifier
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

cancer_df = pd.read_csv("https://github.com/mpourhoma/CS4661/raw/master/Cancer.csv")
cancer_df.head()

#feature columns
feature_cols = ['Clump_Thickness','Uniformity_of_Cell_Size','Uniformity_of_Cell_Shape',
                'Marginal_Adhesion','Single_Epithelial_Cell_Size','Bare_Nuclei',
                'Bland_Chromatin','Normal_Nucleoli','Mitoses']
X = cancer_df[feature_cols] 
# label
y = cancer_df['Malignant_Cancer']
print(X.head())
print(y.head())

# splitting the original dataset into training set and testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.35, random_state=3)
# print size of test train data
print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)

# Creating instance for DTree Calssifier
my_decisiontree = DecisionTreeClassifier(random_state=3)
my_decisiontree.fit(X_train, y_train)
y_predict_dt = my_decisiontree.predict(X_test)
# Accuracy
print(classification_report(y_test, y_predict_dt))
# Print
print(y_predict_dt)