# to load and to do operations on the data( Data Handling )
import pandas as pd
import numpy as np

# for the preprocessing the data 
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
import category_encoders as ce

#for visualization
import matplotlib.pyplot as plt
import seaborn as sns

# This is for to find the correaltion between categorial attributes
from scipy.stats import chi2_contingency,pointbiserialr, f_oneway,pearsonr

# for models
from sklearn.model_selection import cross_val_score , KFold , train_test_split
from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB 
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
import xgboost as xgb
from xgboost import XGBClassifier

#Evaluation for the model
from sklearn.metrics import  f1_score
from sklearn.metrics import accuracy_score, classification_report ,confusion_matrix , make_scorer, precision_score,recall_score 

Colon_Cancer_Classification.zip