一、boston房价预测
1. 读取数据集
2. 训练集与测试集划分
from sklearn.datasets import load_boston from sklearn.model_selection import train_test_split data = load_boston() x_train,x_test,y_train,y_test = train_test_split(data.data,data.target,test_size=0.3) print(x_train.shape,y_train.shape)
3. 线性回归模型:建立13个变量与房价之间的预测模型,并检测模型好坏。
from sklearn.linear_model import LinearRegression mlr = LinearRegression() mlr.fit(x_train,y_train) print('系数',mlr.coef_,"\n截距",mlr.intercept_) from sklearn.metrics import regression y_predict = mlr.predict(x_test) print("预测的均方误差:", regression.mean_squared_error(y_test,y_predict)) print("预测的平均绝对误差:", regression.mean_absolute_error(y_test,y_predict)) print("模型的分数:",mlr.score(x_test, y_test))
4. 多项式回归模型:建立13个变量与房价之间的预测模型,并检测模型好坏。
from sklearn.preprocessing import PolynomialFeatures a = PolynomialFeatures(degree=2) x_poly_train = a.fit_transform(x_train) x_poly_test = a.transform(x_test) mlrp = LinearRegression() mlrp.fit(x_poly_train, y_train) y_predict2 = mlrp.predict(x_poly_test) print("预测的均方误差:", regression.mean_squared_error(y_test,y_predict2)) print("预测的平均绝对误差:", regression.mean_absolute_error(y_test,y_predict2)) print("模型的分数:",mlrp.score(x_poly_test, y_test))
5. 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,即多项回归模型更好一些,其误差控制的更小。线性模型作为一条回归分析线,误差控制肯定不如非线性模型。
按学号未位下载相应数据集。
147:财经、彩票、房产、股票、
258:家居、教育、科技、社会、时尚、
0369:时政、体育、星座、游戏、娱乐
分别建立中文文本分类模型,实现对文本的分类。基本步骤如下:
1.各种获取文件,写文件
2.除去噪声,如:格式转换,去掉符号,整体规范化
3.遍历每个个文件夹下的每个文本文件。
4.使用jieba分词将中文文本切割。
中文分词就是将一句话拆分为各个词语,因为中文分词在不同的语境中歧义较大,所以分词极其重要。
可以用jieba.add_word('word')增加词,用jieba.load_userdict('wordDict.txt')导入词库。
维护自定义词库
5.去掉停用词。
维护停用词表
6.对处理之后的文本开始用TF-IDF算法进行单词权值的计算
7.贝叶斯预测种类
8.模型评价
9.新文本类别预测
import os path = 'H:\大三上大作业\python大作业\date' import jieba with open(r'H:\大三上大作业\python大作业\stopsCN.txt', encoding='utf-8') as f: stopwords = f.read().split('\n') #print(stopwords.shape)#查看停用的字符数量 # for w in stopwords:#查看stopwords文件数据 # print(w) #文本预处理 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]#分词 tokens = " ".join([token for token in tokens if token not in stopwords])# 去掉停用词 return tokens tokenList = []#存放新闻的内容 targetList = []#存放新闻的类别
for root, dirs, files in os.walk(path): # print(root)#地址 # print(dirs)#子目录 # print(files)#详细文件名 for f in files: filePath = os.path.join(root, f)#地址拼接 with open(filePath, encoding='utf-8') as f: content = f.read() target = filePath.split('\\')[-2] targetList.append(target) tokenList.append(processing(content))
#建模 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) from sklearn.naive_bayes import MultinomialNB mnb = MultinomialNB() module = mnb.fit(X_train, y_train) y_predict = module.predict(X_test) scores = cross_val_score(mnb, X_test, y_test, cv=5) print("验证结果:%.3f" % scores.mean()) print("分类结果:\n", classification_report(y_predict, y_test)) import collections # 测试集和预测集的各类新闻数量 testCount = collections.Counter(y_test) predCount = collections.Counter(y_predict) print('实际:', testCount, '\n', '预测', predCount) # 建立标签列表,实际结果与预测结果 nameList = list(testCount.keys()) testList = list(testCount.values()) predictList = list(predCount.values()) x = list(range(len(nameList))) print("类别:", nameList, '\n', "实际:", testList, '\n', "预测:", predictList) # 画图 import matplotlib.pyplot as plt from pylab import mpl mpl.rcParams['font.sans-serif'] = ['FangSong'] # 指定字体 plt.figure(figsize=(7,5)) total_width, n = 0.6, 2 width = total_width / n plt.bar(x, testList, width=width,label='实际',fc = 'black') for i in range(len(x)): x[i] = x[i] + width plt.bar(x, predictList,width=width,label='预测',tick_label = nameList,fc='r') plt.grid() plt.title('实际和预测对比图',fontsize=17) plt.xlabel('新闻类别',fontsize=17) plt.ylabel('频数',fontsize=17) plt.legend(fontsize =17) plt.tick_params(labelsize=15) plt.show()