import pandas as pd
import numpy as np
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import GridSearchCV
from sklearn import metrics
from sklearn.neighbors import KNeighborsRegressor,KNeighborsClassifier
from sklearn.metrics import mean_squared_error # 评价指标
import pandas as pd读取数据
df = pd.read_excel('internet.xlsx')
df.head()
数据清洗
df=df.drop(labels=['用户id', '投资理财类标志', '信托类标志','银行理财类标志'],axis=1)
data=df.values
# print(data)
for i,line in enumerate(data):
for j in range(len(data[i])):
# print(data[i,j])
if data[i,j]==('未逾期' or '有'):
data[i,j]=1
elif data[i,j]==('逾期'or '无'):
data[i,j]=0
print(data)
print(data[0])
构造训练数据：
data_x=[]
data_y=[]
for line in data:
data_y.append(line[0])
data_x.append(line[1:])
x_train,x_test,y_train,y_test = train_test_split(data_x,data_y,test_size=0.2)knn算法进行预测
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski',n_jobs=-1)
knn.fit(x_train, y_train)
test_pred=knn.predict(x_test) # 进行预测
print('f1分数:', metrics.f1_score(y_test,test_pred)) #二分类评价标准
print('准确率: %.2f' % metrics.accuracy_score(y_test,test_pred))
所有代码+数据
