期末大作业

一、boston房价预测

1. 读取数据集

from sklearn.datasets import load_boston
boston = load_boston()
boston.keys()

print(boston.DESCR)

boston.data.shape

import pandas as pd
pd.DataFrame(boston.data)

2. 训练集与测试集划分

from sklearn.model_selection import train_test_split
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
lineR = LinearRegression()
lineR.fit(boston.data,y)
lineR.coef_

lineR.intercept_

import matplotlib.pyplot as plt
x= boston.data[:,12].reshape(-1,1)
y= boston.target
plt.figure(figsize=(10,6))
plt.scatter(x,y)
from sklearn.linear_model import LinearRegression
lineR = LinearRegression()
lineR.fit(x,y)
y_pred = lineR.predict(x)
plt.plot(x,y_pred)
print(lineR.coef_,lineR.intercept_)
plt.show()

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
poly = PolynomialFeatures(degree=2)
poly.fit_transform(x)
lrp = LinearRegression()
lineR.fit(x,y)
y_pred = lineR.predict(x)
plt.plot(x,y_pred)

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=2)
x_poly = poly.fit_transform(x)

lrp = LinearRegression()
lrp.fit(x_poly,y)
y_pred = lineR.predict(x)
plt.plot(x,y_pred)

x_poly

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=2)
x_poly = poly.fit_transform(x)

lrp = LinearRegression()
lrp.fit(x_poly,y)
y_poly_pred = lrp.predict(x_poly)
plt.scatter(x,y)
plt.scatter(x,y_pred)
plt.scatter(x,y_poly_pred)
plt.show()

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=2)
x_poly = poly.fit_transform(x)

lp = LinearRegression()
lp.fit(x_poly,y)
y_poly_pred = lp.predict(x_poly)

plt.scatter(x,y)
plt.plot(x,y_pred,'r')
plt.scatter(x,y_poly_pred,c='b')
plt.show()

5. 比较线性模型与非线性模型的性能，并说明原因。

如果模型是参数的线性函数，并且存在线性分类面，那么就是线性分类器，否则不是。线性分类器可解释性好，

计算复杂度较低，不足之处是模型拟合效果相对弱些。非线性分类器拟合能力较强，不足之处是数据量不足容易过拟合，计算复杂度高，可解释性不好。线性分类器有三大类：感知器准则函数，SVM，Fisher准则，而贝叶斯分类器不是线性分类器。

二、中文文本分类

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。

import os
data = []
target = []
fileList = os.listdir(path)
path = r'C:\Users\Administrator\Desktop\147\财经'
for f in fileList:
    file = os.path.join(path,f)
    print(file)

import jieba
with open(r'G:\杜云梅\stops.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')

 

5.去掉停用词。

def processing(tokens):
    
    tokens = "".join([char for char in tokens if char.isalpha()])
    
    tokens = [token for token in jieba.cut(tokens,cut_all=True) if len(token) >=2]
    
    tokens = " ".join([token for token in tokens if token not in stopwords])
    return tokens

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

tokenList = []
targetList = []

for root,dirs,files in os.walk(path):
    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))

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("Accuracy:%.3f"%scores.mean())
print("classification_report:\n",classification_report(y_predict,y_test))

 

 

9.新文本类别预测

targetList.append(target)
print(targetList[0:10])
tokenList.append(processing(content))
tokenList[0:10]