本文主要简述如何通过sklearn模块来进行预测和学习,最后再以图表这种更加直观的方式展现出来
学习数据
预测数据
因为我们打开我们的的学习数据集,最后一项是我们的真实数值,看过小唐上一篇的人都知道,老规矩先进行拆分,前面的特征放一块,后面的真实值放一块,同时由于数据没有列名,我们选择使用iloc[]来实现分离
def shuju(tr_path,ts_path,sep='\t'):
train=pd.read_csv(tr_path,sep=sep)
test=pd.read_csv(ts_path,sep=sep)
#特征和结果分离
train_features=train.iloc[:,:-1].values
train_labels=train.iloc[:,-1].values
test_features = test.iloc[:, :-1].values
test_labels = test.iloc[:, -1].values
return train_features,test_features,train_labels,test_labels
我们在这里直接使用sklearn函数,通过选择模型,然后直接生成其识别规则
#训练数据
def train_tree(*data):
x_train, x_test, y_train, y_test=data
clf=DecisionTreeClassifier()
clf.fit(x_train,y_train)
print("学习模型预测成绩:{:.4f}".format(clf.score(x_train, y_train)))
print("实际模型预测成绩:{:.4f}".format(clf.score(x_test, y_test)))
#返回学习模型
return clf
为了让我们的观察更加直观,我们还可以使用matplotlib来进行观测
def plot_imafe(test,test_labels,preds):
plt.ion()
plt.show()
for i in range(50):
label,pred=test_labels[i],preds[i]
title='实际值:{},predict{}'.format(label,pred)
img=test[i].reshape(28,28)
plt.imshow(img,cmap="binary")
plt.title(title)
plt.show()
print('done')
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt
def shuju(tr_path,ts_path,sep='\t'):
train=pd.read_csv(tr_path,sep=sep)
test=pd.read_csv(ts_path,sep=sep)
#特征和结果分离
train_features=train.iloc[:,:-1].values
train_labels=train.iloc[:,-1].values
test_features = test.iloc[:, :-1].values
test_labels = test.iloc[:, -1].values
return train_features,test_features,train_labels,test_labels
#训练数据
def train_tree(*data):
x_train, x_test, y_train, y_test=data
clf=DecisionTreeClassifier()
clf.fit(x_train,y_train)
print("学习模型预测成绩:{:.4f}".format(clf.score(x_train, y_train)))
print("实际模型预测成绩:{:.4f}".format(clf.score(x_test, y_test)))
#返回学习模型
return clf
def plot_imafe(test,test_labels,preds):
plt.ion()
plt.show()
for i in range(50):
label,pred=test_labels[i],preds[i]
title='实际值:{},predict{}'.format(label,pred)
img=test[i].reshape(28,28)
plt.imshow(img,cmap="binary")
plt.title(title)
plt.show()
print('done')
train_features,test_features,train_labels,test_labels=shuju(r"C:\Users\twy\PycharmProjects\1\train_images.csv",r"C:\Users\twy\PycharmProjects\1\test_images.csv")
clf=train_tree(train_features,test_features,train_labels,test_labels)
preds=clf.predict(test_features)
plot_imafe(test_features,test_labels,preds)