一、实验目的与要求
掌握常见关联规则、时序摸式方法
二、实验任务
1.理解常用关联规则算法。
2.掌握Apriori算法。
3.了解时序模式，掌握时间序列的常用算法。
三、预习与准备
1. python基本语法。
2. 熟悉pycharm的开发环境。
四、实验内容
1.实现Apriori算法调用代码。
2.实现ARIMA模型代码。
3.实现离散点检测代码。
五、实验过程
1.实现Apriori算法调用代码：
#-*- coding: utf-8 -*-from __future__ import print_functionimport pandas as pdfrom Apriori import *inputfile='E://PycharmProjects/data/menu_orders.xls'outputfile='E://PycharmProjects/tmp/apriori_rules.xls'data=pd.read_excel(inputfile,header=None)
print(u'\n转换原始数据至0-1矩阵...')ct=lambda x:pd.Series(1,index=x[pd.notnull(x)])
b=map(ct,data.as_matrix())data=pd.DataFrame(list(b)).fillna(0)print(u'转换完毕。')del bsupport=0.2confidence=0.5ms='---'find_rule(data,support,confidence,ms).to_excel(outputfile)
Ariori.py
# -*- coding: utf-8 -*-from __future__ import print_functionimport pandas as pddef connect_string(x, ms): x = list(map(lambda i: sorted(i.split(ms)), x)) l = len(x[0]) r = [] for i in range(len(x)): for j in range(i, len(x)): if x[i][:l - 1] == x[j][:l - 1] and x[i][l - 1] != x[j][l - 1]: r.append(x[i][:l - 1] + sorted([x[j][l - 1], x[i][l - 1]])) return rdef find_rule(d, support, confidence, ms=u'--'): result = pd.DataFrame(index=['support', 'confidence']) # 定义输出结果 support_series = 1.0 * d.sum() / len(d) # 支持度序列 column = list(support_series[support_series > support].index) k = 0 while len(column) > 1: k = k + 1 print(u'\n正在进行第%s次搜索...' % k) column = connect_string(column, ms) print(u'数目：%s...' % len(column)) sf = lambda i: d[i].prod(axis=1, numeric_only=True) d_2 = pd.DataFrame(list(map(sf, column)), index=[ms.join(i)
for i in column]).T support_series_2 = 1.0 * d_2[[ms.join(i) for i in column]].sum() /len(d) column = list(support_series_2[support_series_2 > support].index) support_series = support_series.append(support_series_2) column2 = [] for i in column: i = i.split(ms) for j in range(len(i)): column2.append(i[:j] + i[j + 1:] + i[j:j + 1]) cofidence_series = pd.Series(index=[ms.join(i) for i in column2]) for i in column2: # 计算置信度序列 cofidence_series[ms.join(i)] = support_series[ms.join(sorted(i))] / support_series[ms.join(i[:len(i) - 1])] for i in cofidence_series[cofidence_series > confidence].index: result[i] = 0.0
result[i]['confidence'] = cofidence_series[i]
result[i]['support'] = support_series[ms.join(sorted(i.split(ms)))]result = result.T.sort_values(['confidence', 'support'], ascending=False) print(u'\n结果为：')print(result)
2. 实现ARIMA模型代码：
#-*- coding: utf-8 -*-import pandas as pddiscfile='E://PycharmProjects/data/arima_data.xls'forecastnum=5data=pd.read_excel(discfile,index_col=u'日期')import matplotlib.pyplot as pltplt.rcParams['font.sans-serif']=['SimHei']plt.rcParams['axes.unicode_minus']=Falsedata.plot()plt.show()from statsmodels.graphics.tsaplots import plot_acfplot_acf(data).show()from statsmodels.tsa.stattools import adfuller as ADFprint(u'原始序列的ADF检验结果为：',ADF(data[u'销量']))D_data=data.diff().dropna()D_data=data.columns=[u'销量']D_data.plot()plt.show()plot_acf(D_data).show()from statsmodels.graphics.tsaplots import plot_pacfplot_pacf(D_data).show()print(u'差分序列的ADF检验结果为：',ADF(D_data[u'销量']))from statsmodels.stats.diagnostic import acorr_ljungboxprint(u'差分序列的白噪声检验结果为：',acorr_ljungbox(D_data,lags=1))from statsmodels.tsa.arima_model import ARIMA
pmax=int(len(D_data)/10)qmax=int(len(D_data)/10)bic_matrix=[]
for p in range(pmax+1): tmp=[] for q in range(qmax+1): try: tmp.append(ARIMA(data,(p,1,q)).fit().bic) except: tmp.append(None) bic_matrix.append(tmp)
3.实现离散点检测代码：
# -*- coding: utf-8 -*-import numpy as npimport pandas as pdif __name__ == '__main__': inputfile = 'E://PycharmProjects/data/consumption_data.xls' k = 3 threshold = 2 iteration = 500 data = pd.read_excel(inputfile, index_col='Id') data_zs = 1.0 * (data - data.mean()) / data.std() from sklearn.cluster import KMeans model = KMeans(n_clusters=k, n_jobs=4, max_iter=iteration) model.fit(data_zs) r = pd.concat([data_zs, pd.Series(model.labels_, index=data.index)], axis=1) r.columns = list(data.columns) + [u'聚类类别'] norm = [] for i in range(k): norm_tmp = r[['R', 'F', 'M']][r[u'聚类类别'] == i] - model.cluster_centers_[i] norm_tmp = norm_tmp.apply(np.linalg.norm, axis=1) norm.append(norm_tmp / norm_tmp.median()) norm = pd.concat(norm) import matplotlib.pyplot as plt plt.rcParams['font.sans-serif'] = ['SimHei'] plt.rcParams['axes.unicode_minus'] = False norm[norm <= threshold].plot(style='go') discrete_points = norm[norm > threshold] discrete_points.plot(style='ro') for i in range(len(discrete_points)): id = discrete_points.index[i] n = discrete_points.iloc[i] plt.annotate('(%s, %0.2f)' % (id, n), xy=(id, n), xytext=(id, n)) plt.xlabel(u'编号') plt.ylabel(u'相对距离') plt.show()
实验效果
1. 实现Apriori算法调用代码:
2. 实现ARIMA模型代码:
3.实现离散点检测代码：
六、实验总结与体会
通过这次的实验，我学会了Python中的挖掘建模的基本操作，通过pandas来读取Excel表格文件中的数据，通过outputfile来指定输出数据路径，然后通过data.to_excel(outputfile)输出结果，写入文件，通过matplotlib.pyplot来导入图像库，从而生成图像，更加直观的表达数据分析结果，通过这次的实验操作，让我对Python语言有了更深刻的认识，语言的简单明了，当时功能却很强大，在今后的学习当中，我一定要上课认真听老师讲解，仔细研读代码，分析代码，然后自己动手敲写代码，及时发现错误，自己尝试解决错误，实在无法解决的问题，要积极与老师和同学交流探讨，只有这样，我们才能更好的学习这门课程。
