一、boston房价预测
from sklearn.datasets import load_boston boston = load_boston() boston.keys()
#划分训练集与测试集 from sklearn.model_selection import train_test_split x_train,x_test,y_train,y_test=train_test_split(boston.data,boston.target,test_size=0.3) print(x_train.shape,y_train.shape)
#一元线性回归模型 from sklearn.linear_model import LinearRegression LineR = LinearRegression() LineR.fit(x_train,y_train) print("系数:",LineR.coef_) #系数 print("截距:",LineR.intercept_) #截距
#检测模型好坏 from sklearn.metrics import regression y_pred = LineR.predict(x_test) #预测 n = regression.mean_squared_error(y_test,y_pred) #预测模型均方误差 print("线性回归均方误差：",n) a = regression.mean_absolute_error(y_test,y_pred) print("线性回归平均绝对误差",a) s = LineR.score(x_test,y_test) #模型分数 print("线性回归模型分数：",s)
#多元多项式回归模型 from sklearn.preprocessing import PolynomialFeatures poly = PolynomialFeatures(degree = 2) x_poly_train= poly.fit_transform(x_train) #多项式化 x_poly_test = poly.transform(x_test) #建立模型 LineR2 = LinearRegression() LineR2.fit(x_poly_train,y_train) y_pred2 =LineR2.predict(x_poly_test)#预测
#检测模型好坏 n2 = regression.mean_squared_error(y_test,y_pred2) print("多项式回归均方误差：",n2) a2 = regression.mean_absolute_error(y_test,y_pred2) print("多项式回归平均绝对误差",a2) s2 = LineR2.score(x_poly_test,y_test) print("多项式回归模型分数：",s2)
#比较线性模型与非线性模型的性能，并说明原因 非线性模型功能强，因为多项式模型是曲线，更符合与样本点的分布，而且多项式回归模型误差更小。
二、中文文本分类
import os import numpy as np import sys from datetime import datetime import gc path = 'E:\258' list = os.listdir(path) list
def list_all_files(rootdir):
import os
_files = []
list = os.listdir(rootdir) #列出文件夹下所有的目录与文件
for i in range(0,len(list)):
path = os.path.join(rootdir,list[i])
if os.path.isdir(path):
_files.extend(list_all_files(path))
if os.path.isfile(path):
_files.append(path)
return _files
_fs = list_all_files('E:\258')
#所有文件遍历出来
_fs
!pip install jieba
import jieba
with open(r'E:\stopsCN.txt',encoding='utf-8') as f:
stopwords = f.read().split('
')
import jieba
def processing(tokens):
tokens = "".join([char for char in tokens if char.isalpha()])# 去掉非字母汉字的字符
tokens = [token for token in jieba.cut(tokens,cut_all=True) if len(token) >=2]# 结巴分词
tokens = " ".join([token for token in tokens if token not in stopwords])# 去掉停用词
return tokens
tokenList = []
targetList = []
for root,dirs,files in os.walk(path):#拼接路径，再打开文件
for f in files:
filePath = os.path.join(root,f)
with open(filePath,encoding='utf-8') as f:
content = f.read()
target = filePath.split('\')[-2]
targetList.append(target)
tokenList.append(processing(content))
# 划分训练集测试集
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB,MultinomialNB
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
x_train,x_test,y_train,y_test = train_test_split(tokenList,targetList,test_size=0.3,stratify=targetList)
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)
#多项式朴素贝叶斯
from sklearn.naive_bayes import MultinomialNB
mnb = MultinomialNB()
module = mnb.fit(X_train,y_train)
y_predict = module.predict(X_test)#预测
scores=cross_val_score(mnb,X_test,y_test,cv=5)
print("Accuracy:%.3f"%scores.mean())
print("classification_report:
",classification_report(y_predict,y_test))
targetList.append(target)
print(targetList[0:10])
tokenList.append(processing(content))
tokenList[0:10]
# 统计测试集和预测集的各类新闻个数
testCount = collections.Counter(y_test)
predCount = collections.Counter(y_predict)
print('实际：',testCount,'
', '预测', predCount)
# 建立标签列表，实际结果列表，预测结果列表
nameList = list(testCount.keys())
testList = list(testCount.values())
predictList = list(predCount.values())
x = list(range(len(nameList)))
print("新闻类别：",nameList,'
',"实际：",testList,'
',"预测：",predictList)
