直接用决策树跑baseline

准确率是0.67，下一篇博客将去掉偏差大的特征。

import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

import seaborn as sns

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

df1=pd.read_csv('test.csv')

df=df.drop(['ID'],axis=1)

df=df.to_numpy()

feature=df[:,:-1]

label=df[:,-1]

from sklearn.model_selection import train_test_split

tfeature,ttest,tlabel,testlabel=train_test_split(feature,label,test_size=0.2)

from sklearn import tree

from sklearn.metrics import accuracy_score

from sklearn.model_selection import KFold

kf=KFold(n_splits=5,shuffle=False)

from sklearn import svm

from sklearn.model_selection import cross_val_score

for k in range(10):

    sum=0

    sum1=0

    i=0

    for train_index,test_index in kf.split(df):

        i=i+1

        tfeature=df[train_index,:-1]

        label=df[train_index,-1]

        clf=tree.DecisionTreeClassifier(criterion='gini',random_state=0,max_depth=k+1)    

        clf.fit(tfeature,tlabel)

        l=clf.predict(tfeature)

        ttest=df[test_index,:-1]

        testlabel=df[test_index,-1]

        l1=clf.predict(ttest)

        pr=accuracy_score(tlabel, l)

        pr1=accuracy_score(testlabel, l1)

        sum=sum+pr

        sum1=sum1+pr

    clf1=tree.DecisionTreeClassifier(criterion='gini',random_state=0,max_depth=k+1)

    scores = cross_val_score(clf, df[:,:-1], df[:,-1], cv=5)

    print(k,sum/i,sum1/i,scores.mean())

   

clf=tree.DecisionTreeClassifier(criterion='gini',random_state=0,max_depth=11)    

clf.fit(df[:,:-1],df[:,-1])

df1=df1.drop(['ID'],axis=1)

df1=df1.to_numpy()

y=clf.predict(df1[:,:])

out=pd.DataFrame(y)

out.columns = ['CLASS']

w=[]

for k in range(out.shape[0]):

    w.append(k+210)

out['ID']=np.reshape(w,(-1,1))

out[['ID','CLASS']].to_csv('out.csv',index=False)