3.3数据挖掘作业-财政收入影响因数分析及预测

 

#描述性统计分析
# 对各属性进行描述性统计分析
def statisticAnalysis():
    inputfile = '../data/data.csv'  # 输出的数据文件
    data = pd.read_csv(inputfile)  # 读数据
    # 最小值、最大值、均值、标准差
    description = [data.min(), data.max(), data.mean(), data.std()]

    # 将结果存入数据框
    description = pd.DataFrame(description, index=["Min", "Max", "Mean", "STD"]).T
    print("描述性统计结果：\n", np.round(description, 2))  # 保留两位 

# 求解原始数据的Pearson相关系数矩阵
def correlationCoefficientMatrix(data):
    inputfile = '../data/data.csv'  # 输出的数据文件
    data = pd.read_csv(inputfile)  # 读数据
    corr = data.corr(method='pearson')  # 计算相关系数矩阵
    print("相关系数矩阵为：\n", np.round(corr, 2))  # 保留两位
    return corr

# 绘制相关性热力图
def thermodynamic(corr):
    plt.rcParams['font.sans-serif'] = ['SimHei']  # 显示中文标签
    plt.rcParams['axes.unicode_minus']=False
    plt.subplots(figsize=(10, 10))
    sns.heatmap(corr, annot=True, vmax=1, square=True, cmap="Blues_r")
    plt.title("相关性热力图 3102")
    plt.show()
    plt.close()

#构建模型并预测
# 构建灰色预测模型并预测
def grey():
    sys.path.append("D:/作业/数据挖掘/tmp")

    inputfile1 = "../data/new_reg_data.csv"
    inputfile2 = "../data/data.csv"
    new_reg_data = pd.read_csv(inputfile1)
    data = pd.read_csv(inputfile2)
    new_reg_data.index = range(1994, 2014)
    new_reg_data.loc[2014] = None
    new_reg_data.loc[2015] = None
    cols = ['x1', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x13']
    for i in cols:
        f = GM11(new_reg_data.loc[range(1994, 2014), i].values)[0]
        new_reg_data.loc[2014, i] = f(len(new_reg_data)-1)   # 2014年预测结果
        new_reg_data.loc[2015, i] = f(len(new_reg_data))  # 2015年预测结果
        new_reg_data[i] = new_reg_data[i].round(2)

    outputfile = '../tmp/new_reg_data_GM11.xls'            # 灰色预测后保存路径
    y = list(data['y'].values)
    y.extend([np.nan, np.nan])
    new_reg_data['y'] = y
    new_reg_data.to_excel(outputfile)
    print("预测结果为：\n",new_reg_data.loc[2014:2015,:])

# 构建支持向量回归预测模型
def SVR():
    from sklearn.svm import LinearSVR

    inputfile = '../tmp/new_reg_data_GM11.xls'
    data = pd.read_excel(inputfile)
    feature = ['x1', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x13']
    data.index = range(1994, 2016)
    data_train = data.loc[range(1994, 2014)].copy()
    data_mean = data_train.mean()
    data_std = data_train.std()
    data_train = (data_train - data_mean)/data_std
    x_train = data_train[feature].to_numpy()
    y_train = data_train['y'].to_numpy()

    linearsvr = LinearSVR()
    linearsvr.fit(x_train, y_train)
    x = ((data[feature] - data_mean[feature])/data_std[feature]).to_numpy()

    data[u'y_pred'] = linearsvr.predict(x) * data_std['y'] + data_mean['y']
    # outputfile = '../tmp/new_reg_data_GM11_revenue.xls'
    # data.to_excel(outputfile)

    print("真实值与预测值分别为：\n",data[['y', 'y_pred']])

    plt.rcParams['font.sans-serif'] = ['SimHei']  # 显示中文标签
    plt.rcParams['axes.unicode_minus'] = False

    fig = data[['y', 'y_pred']].plot(subplots = True,style=['b-o', 'r-*'])
    plt.title("3102")
    plt.show()

#GM(1,1)
def GM11(x0):    # 自定义灰色预测函数
  import numpy as np
  x1 = x0.cumsum()    # 1-AGO序列
  z1 = (x1[:len(x1)-1] + x1[1:])/2.0   # 紧邻均值（MEAN）生成序列
  z1 = z1.reshape((len(z1),1))
  B = np.append(-z1, np.ones_like(z1), axis = 1)
  Yn = x0[1:].reshape((len(x0)-1, 1))
  [[a],[b]] = np.dot(np.dot(np.linalg.inv(np.dot(B.T, B)), B.T), Yn)   # 计算参数
  f = lambda k: (x0[0]-b/a)*np.exp(-a*(k-1))-(x0[0]-b/a)*np.exp(-a*(k-2))   # 还原值
  delta = np.abs(x0 - np.array([f(i) for i in range(1,len(x0)+1)]))
  C = delta.std()/x0.std()
  P = 1.0*(np.abs(delta - delta.mean()) < 0.6745*x0.std()).sum()/len(x0)
  return f, a, b, x0[0], C, P   # 返回灰色预测函数、a、b、首项、方差比、小残差概率