################################### 报告内容 ################################## # 根据真实值分组,去掉最高最小预测值画图逻辑 # content.append(Graphs.draw_text('图示说明:')) # content.append(Graphs.draw_text('1. 将所有模型的预测结果进行分组,大于真实值的为一组,小于真实值的为一组,去掉最高的预测值,去掉最小的预测值')) # content.append(Graphs.draw_text('2. 确定通道上界:在大于真实值的分组中,取最大的预测值')) # content.append(Graphs.draw_text('3. 确定通道下界:在小于真实值的分组中,取第二小的预测值')) # content.append(Graphs.draw_text('4. 预测结果没有真实值作为参考依据,通道上界取近20个交易日内预测在上界值的模型对应的预测值,通道下界同理;')) # content.append(Graphs.draw_text('5. 预测结果选用近20个交易日内,最多接近真实值的模型的预测值对应的预测结果;')) # content.append(Graphs.draw_text('6. 预测结果在通道外的,代表最接近真实值的预测结果不在置信波动范围内。')) # 波动率画图逻辑 # content.append(Graphs.draw_text('图示说明:')) # content.append(Graphs.draw_text('1. 确定波动率置信区间:统计近60个交易日的真实价格波动率,找出在 10% ,90% 的分位值作为波动率置信区间;')) # content.append(Graphs.draw_text('2. 确定通道上界:在所有模型的预测结果中 <= 前一天真实价格 乘以 90%的置信波动分位数')) # content.append(Graphs.draw_text('3. 确定通道下界:在所有模型的预测结果中 >= 前一天真实价格 乘以 10%的置信波动分位数')) # content.append(Graphs.draw_text('4. 预测结果没有真实值作为参考依据,通道上界取近20个交易日内预测在上界值的模型对应的预测值,通道下界同理;')) # content.append(Graphs.draw_text('5. 预测结果选用近20个交易日内,最多接近真实值的模型的预测值对应的预测结果;')) # content.append(Graphs.draw_text('6. 预测结果在通道外的,代表最接近真实值的预测结果不在置信波动范围内。')) # # 计算特征相关性 # data.rename(columns={y: 'y'}, inplace=True) # data['ds'] = pd.to_datetime(data['ds']) # data.drop(columns=['ds'], inplace=True) # # 创建一个空的 DataFrame 来保存相关系数 # correlation_df = pd.DataFrame(columns=['Feature', 'Correlation']) # # 计算各特征与目标列的皮尔逊相关系数,并保存到新的 Data 中 # for col in data.columns: # if col!= 'y': # pearson_correlation = np.corrcoef(data[col], data['y'])[0, 1] # spearman_correlation, _ = spearmanr(data[col], data['y']) # new_row = {'Feature': col, 'Pearson_Correlation': round(pearson_correlation,3), 'Spearman_Correlation': round(spearman_correlation,2)} # correlation_df = correlation_df._append(new_row, ignore_index=True) # correlation_df.drop('Correlation', axis=1, inplace=True) # correlation_df.dropna(inplace=True) # correlation_df.to_csv(os.path.join(dataset,'指标相关性分析.csv'), index=False) # data = correlation_df['Pearson_Correlation'].values.tolist() # # 生成 -1 到 1 的 20 个区间 # bins = np.linspace(-1, 1, 21) # # 计算每个区间的统计数(这里是区间内数据的数量) # hist_values = [np.sum((data >= bins[i]) & (data < bins[i + 1])) for i in range(len(bins) - 1)] # #设置画布大小 # plt.figure(figsize=(10, 6)) # # 绘制直方图 # plt.bar(bins[:-1], hist_values, width=(bins[1] - bins[0])) # # 添加标题和坐标轴标签 # plt.title('皮尔逊相关系数分布图') # plt.xlabel('区间') # plt.ylabel('统计数') # plt.savefig(os.path.join(dataset, '皮尔逊相关性系数.png')) # plt.close() # #设置画布大小 # plt.figure(figsize=(10, 6)) # data = correlation_df['Spearman_Correlation'].values.tolist() # # 计算每个区间的统计数(这里是区间内数据的数量) # hist_values = [np.sum((data >= bins[i]) & (data < bins[i + 1])) for i in range(len(bins) - 1)] # # 绘制直方图 # plt.bar(bins[:-1], hist_values, width=(bins[1] - bins[0])) # # 添加标题和坐标轴标签 # plt.title('斯皮尔曼相关系数分布图') # plt.xlabel('区间') # plt.ylabel('统计数') # plt.savefig(os.path.join(dataset, '斯皮尔曼相关性系数.png')) # plt.close() # content.append(Graphs.draw_text(f'指标相关性分析--皮尔逊相关系数:')) # # 皮尔逊正相关 不相关 负相关 的表格 # content.append(Graphs.draw_img(os.path.join(dataset,'皮尔逊相关性系数.png'))) # content.append(Graphs.draw_text('''皮尔逊相关系数说明:''')) # content.append(Graphs.draw_text('''衡量两个特征之间的线性相关性。''')) # content.append(Graphs.draw_text(''' # 相关系数为1:表示两个变量之间存在完全正向的线性关系,即当一个变量增加时,另一个变量也相应增加,且变化是完全一致的。''')) # content.append(Graphs.draw_text('''当前特征中正相关前十的有:''')) # top10_columns = correlation_df.sort_values(by='Pearson_Correlation',ascending=False).head(10)['Feature'].to_list() # top10 = ','.join(top10_columns) # content.append(Graphs.draw_text(f'''{top10}''')) # feature_df = feature_data_df[['ds','y']+top10_columns] # # 遍历X每一列,和yy画散点图 , # for i, col in enumerate(feature_df.columns): # print(f'正在绘制第{i+1}个特征{col}与价格散点图...') # if col not in ['ds', 'y']: # fig, ax1 = plt.subplots(figsize=(10, 6)) # # 在第一个坐标轴上绘制数据 # ax1.plot(feature_df['ds'], feature_df['y'], 'b-') # ax1.set_xlabel('日期') # ax1.set_ylabel('y', color='b') # ax1.tick_params('y', colors='b') # # 在 ax1 上添加文本显示值,添加一定的偏移避免值与曲线重叠 # for j in range(1,len(feature_df),2): # value = feature_df['y'].iloc[j] # date = feature_df['ds'].iloc[j] # offset = 1.001 # ax1.text(date, value * offset, str(round(value, 2)), ha='center', va='bottom', color='b', fontsize=10) # # 创建第二个坐标轴 # ax2 = ax1.twinx() # # 在第二个坐标轴上绘制数据 # line2 = ax2.plot(feature_df['ds'], feature_df[col], 'r-') # ax2.set_ylabel(col, color='r') # ax2.tick_params('y', colors='r') # # 在 ax2 上添加文本显示值,添加一定的偏移避免值与曲线重叠 # for j in range(0,len(feature_df),2): # value = feature_df[col].iloc[j] # date = feature_df['ds'].iloc[j] # offset = 1.001 # ax2.text(date, value * offset, str(round(value, 2)), ha='center', va='bottom', color='r', fontsize=10) # # 添加标题 # plt.title(col) # # 设置横坐标为日期格式并自动调整 # locator = mdates.AutoDateLocator() # formatter = mdates.AutoDateFormatter(locator) # ax1.xaxis.set_major_locator(locator) # ax1.xaxis.set_major_formatter(formatter) # # 文件名特殊字符处理 # col = col.replace('*', '-') # col = col.replace(':', '-') # plt.savefig(os.path.join(dataset, f'{col}与价格散点图.png')) # content.append(Graphs.draw_img(os.path.join(dataset, f'{col}与价格散点图.png'))) # plt.close() # content.append(Graphs.draw_text(f'指标相关性分析--斯皮尔曼相关系数:')) # # 皮尔逊正相关 不相关 负相关 的表格 # content.append(Graphs.draw_img(os.path.join(dataset,'斯皮尔曼相关性系数.png'))) # content.append(Graphs.draw_text('斯皮尔曼相关系数(Spearmans rank correlation coefficient)是一种用于衡量两个变量之间的单调关系(不一定是线性关系)的统计指标。')) # content.append(Graphs.draw_text('它的计算基于变量的秩次(即变量值的排序位置)而非变量的原始值。')) # content.append(Graphs.draw_text('斯皮尔曼相关系数的取值范围在 -1 到 1 之间。')) # content.append(Graphs.draw_text('当系数为 1 时,表示两个变量之间存在完全正的单调关系;')) # content.append(Graphs.draw_text('''当前特征中正单调关系前十的有:''')) # top10_columns = correlation_df.sort_values(by='Spearman_Correlation',ascending=False).head(10)['Feature'].to_list() # top10 = ','.join(top10_columns) # content.append(Graphs.draw_text(f'''{top10}''')) # feature_df = feature_data_df[['ds','y']+top10_columns] # # 遍历X每一列,和yy画散点图 , # for i, col in enumerate(feature_df.columns): # print(f'正在绘制第{i+1}个特征{col}与价格散点图...') # if col not in ['ds', 'y']: # fig, ax1 = plt.subplots(figsize=(10, 6)) # # 在第一个坐标轴上绘制数据 # ax1.plot(feature_df['ds'], feature_df['y'], 'b-') # ax1.set_xlabel('日期') # ax1.set_ylabel('y', color='b') # ax1.tick_params('y', colors='b') # # 在 ax1 上添加文本显示值,添加一定的偏移避免值与曲线重叠 # for j in range(1,len(feature_df),2): # value = feature_df['y'].iloc[j] # date = feature_df['ds'].iloc[j] # offset = 1.001 # ax1.text(date, value * offset, str(round(value, 2)), ha='center', va='bottom', color='b', fontsize=10) # # 创建第二个坐标轴 # ax2 = ax1.twinx() # # 在第二个坐标轴上绘制数据 # line2 = ax2.plot(feature_df['ds'], feature_df[col], 'r-') # ax2.set_ylabel(col, color='r') # ax2.tick_params('y', colors='r') # # 在 ax2 上添加文本显示值,添加一定的偏移避免值与曲线重叠 # for j in range(0,len(feature_df),2): # value = feature_df[col].iloc[j] # date = feature_df['ds'].iloc[j] # offset = 1.001 # ax2.text(date, value * offset, str(round(value, 2)), ha='center', va='bottom', color='r', fontsize=10) # # 添加标题 # plt.title(col) # # 设置横坐标为日期格式并自动调整 # locator = mdates.AutoDateLocator() # formatter = mdates.AutoDateFormatter(locator) # ax1.xaxis.set_major_locator(locator) # ax1.xaxis.set_major_formatter(formatter) # # 文件名特殊字符处理 # col = col.replace('*', '-') # col = col.replace(':', '-') # plt.savefig(os.path.join(dataset, f'{col}与价格散点图.png')) # content.append(Graphs.draw_img(os.path.join(dataset, f'{col}与价格散点图.png'))) # plt.close() # content.append(Graphs.draw_text('当系数为 -1 时,表示存在完全负的单调关系;')) # content.append(Graphs.draw_text('''当前特征中负单调关系前十的有:''')) # tail10_columns = correlation_df.sort_values(by='Spearman_Correlation',ascending=True).head(10)['Feature'].to_list() # top10 = ','.join(tail10_columns) # content.append(Graphs.draw_text(f'''{top10}''')) # # 获取特征的近一周值 # feature_df = feature_data_df[['ds','y']+tail10_columns] # # 遍历X每一列,和yy画散点图 , # for i, col in enumerate(feature_df.columns): # print(f'正在绘制第{i+1}个特征{col}与价格散点图...') # if col not in ['ds', 'y']: # fig, ax1 = plt.subplots(figsize=(10, 6)) # # 在第一个坐标轴上绘制数据 # ax1.plot(feature_df['ds'], feature_df['y'], 'b-') # ax1.set_xlabel('日期') # ax1.set_ylabel('y', color='b') # ax1.tick_params('y', colors='b') # # 在 ax1 上添加文本显示值,添加一定的偏移避免值与曲线重叠 # for j in range(len(feature_df)): # if j%2 == 1: # value = feature_df['y'].iloc[j] # date = feature_df['ds'].iloc[j] # offset = 1.001 # ax1.text(date, value * offset, str(round(value, 2)), ha='center', va='bottom', color='b', fontsize=10) # # 创建第二个坐标轴 # ax2 = ax1.twinx() # # 在第二个坐标轴上绘制数据 # line2 = ax2.plot(feature_df['ds'], feature_df[col], 'r-') # ax2.set_ylabel(col, color='r') # ax2.tick_params('y', colors='r') # # 在 ax2 上添加文本显示值,添加一定的偏移避免值与曲线重叠 # for j in range(1,len(feature_df),2): # value = feature_df[col].iloc[j] # date = feature_df['ds'].iloc[j] # offset = 1.001 # ax2.text(date, value * offset, str(round(value, 2)), ha='center', va='bottom', color='r', fontsize=10) # # 添加标题 # plt.title(col) # # 设置横坐标为日期格式并自动调整 # locator = mdates.AutoDateLocator() # formatter = mdates.AutoDateFormatter(locator) # ax1.xaxis.set_major_locator(locator) # ax1.xaxis.set_major_formatter(formatter) # # 文件名特殊字符处理 # col = col.replace('*', '-') # col = col.replace(':', '-') # plt.savefig(os.path.join(dataset, f'{col}与价格散点图.png')) # content.append(Graphs.draw_img(os.path.join(dataset, f'{col}与价格散点图.png'))) # plt.close() # content.append(Graphs.draw_text('当系数为 0 时,表示两个变量之间不存在单调关系。')) # content.append(Graphs.draw_text('与皮尔逊相关系数相比,斯皮尔曼相关系数对于数据中的异常值不敏感,更适用于处理非线性关系或存在极端值的数据。')) # 附1,特征列表 # content.append(Graphs.draw_little_title('附1、特征列表:')) # df_fuyi = pd.read_csv(os.path.join(dataset,'特征频度统计.csv'),encoding='utf-8') # for col in df_fuyi.columns: # fuyi = df_fuyi[col] # fuyi = fuyi.dropna() # content.append(Graphs.draw_text(f'{col}:')) # for i in range(len(fuyi)): # content.append(Graphs.draw_text(f'{i+1}、{fuyi[i]}')) ################################### 预测值与真实值绘图逻辑 ################################## # # 根据真实值y确定最大最小值,去掉最高最低的预测值 # import heapq # 使用堆来找到最大和最小的值 # def find_min_max_within_quantile(row): # true_value = row['y'] # row.drop(['ds','y'], inplace=True) # row = row.astype(float).round(2) # max_heap = [] # min_heap = [] # for col in row.index: # # 对比真实值进行分类 # if row[col] < true_value: # heapq.heappush(min_heap, row[col]) # elif row[col] > true_value: # heapq.heappush(max_heap, -row[col]) # 使用负号来实现最大堆 # if len(max_heap) == 1: # max_y = max_heap[0] # elif len(max_heap) == 0: # max_y = -min_heap[-1] # else: # max_y = heapq.nsmallest(2, max_heap)[1] # if len(min_heap) < 2 : # min_y = -max_heap[-1] # else: # min_y = heapq.nsmallest(2, min_heap)[-1] # # 获取最大和最小的值 # q10 = min_y # q90 = -max_y # # 获取最大和最小的模型名称 # min_model = row[row == q10].idxmin() # max_model = row[row == q90].idxmax() # # 设置上下界比例 # rote = 1 # q10 = q10 * rote # q90 = q90 * rote # logger.info(min_model,q10,max_model,q90) # return pd.Series([q10, q90, min_model, max_model], index=['min_within_quantile', 'max_within_quantile', 'min_model', 'max_model']) # # # 遍历行 # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1) # df_combined = df_combined.round(4) # print(df_combined3) #使用最佳五个模型进行绘图 # best_models = pd.read_csv(os.path.join(dataset,'best_modelnames.txt'),header=None).values.flatten().tolist() # def find_min_max_within_quantile(row): # row = row[best_models] # q10 = row.min() # q90 = row.max() # # 获取 row行最大最小值模型名称 # min_model = row[row == q10].idxmin() # max_model = row[row == q90].idxmin() # # # 判断flot值是否为空值 # # if pd.isna(q10) or pd.isna(q90): # return pd.Series([q10, q90,min_model,max_model], index=['min_within_quantile','max_within_quantile','min_model','max_model']) # # 遍历行 # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1) # df_combined = df_combined.round(4) # print(df_combined3) # # 通道使用模型评估前80%作为置信度 # def find_min_max_within_quantile(row): # row.drop(['ds','y'], inplace=True) # row = row.astype(float).round(2) # row_sorted = row # # 计算 10% 和 90% 位置的索引 # index_10 = 0 # index_90 = int(len(row_sorted) * 0.8) # q10 = row_sorted[index_10] # q90 = row_sorted[index_90] # # 获取模型名称 # min_model = row[row == q10].idxmin() # max_model = row[row == q90].idxmin() # # # 判断flot值是否为空值 # # if pd.isna(q10) or pd.isna(q90): # return pd.Series([q10, q90,min_model,max_model], index=['min_within_quantile','max_within_quantile','min_model','max_model']) # # 重新排列 # df_combined3 = df_combined3[['ds','y'] + allmodelnames] # # 遍历行 # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1) # df_combined = df_combined.round(4) # print(df_combined3) # # 通道使用预测模型的80%置信度 # def find_min_max_within_quantile(row): # row.drop(['ds','y'], inplace=True) # row = row.astype(float).round(2) # row_sorted = row.sort_values(ascending=True).reset_index(drop=True) # # 计算 10% 和 90% 位置的索引 # index_10 = int(len(row_sorted) * 0.1) # index_90 = int(len(row_sorted) * 0.9) # q10 = row_sorted[index_10] # q90 = row_sorted[index_90] # # 获取模型名称 # min_model = row[row == q10].idxmin() # max_model = row[row == q90].idxmin() # # # 判断flot值是否为空值 # # if pd.isna(q10) or pd.isna(q90): # return pd.Series([q10, q90,min_model,max_model], index=['min_within_quantile','max_within_quantile','min_model','max_model']) # # 遍历行 # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1) # df_combined = df_combined.round(4) # print(df_combined3) # # 计算波动率 # df_combined3['volatility'] = df_combined3['y'].pct_change().round(4) # # 计算近60日的波动率 10% 90%分位数 # df_combined3['quantile_10'] = df_combined3['volatility'].rolling(60).quantile(0.1) # df_combined3['quantile_90'] = df_combined3['volatility'].rolling(60).quantile(0.9) # df_combined3 = df_combined3.round(4) # # 计算分位数对应的价格 # df_combined3['quantile_10_price'] = df_combined3['y'] * (1 + df_combined3['quantile_10']) # df_combined3['quantile_90_price'] = df_combined3['y'] * (1 + df_combined3['quantile_90']) # # 遍历行 # def find_min_max_within_quantile(row): # # 获取分位数10%和90%的值 # q10 = row['quantile_10_price'] # q90 = row['quantile_90_price'] # # 判断flot值是否为空值 # if pd.isna(q10) or pd.isna(q90): # return pd.Series([None, None, None, None], index=['min_within_quantile','max_within_quantile','min_model','max_model']) # # 初始化最小和最大值为None # min_value = None # max_value = None # min_value_model = '' # max_value_model = '' # # 遍历指定列,找出在分位数范围内的最大最小值 # for model in modelnames: # value = row[model] # if value >= q10 and value <= q90: # if min_value is None or value < min_value: # min_value = value # min_value_model = model # if max_value is None or value > max_value: # max_value = value # max_value_model = model # 返回最大最小值 # return pd.Series([min_value, max_value,min_value_model,max_value_model], index=['min_within_quantile', 'max_within_quantile','min_model','max_model']) # # # 应用函数到每一行 # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1) # # 去除有空值的行 # df_combined3.dropna(inplace=True) # # # 保存到数据库 # df_combined3.to_sql('testandpredict_groupby', sqlitedb.connection, if_exists='replace', index=False) # df_combined3.to_csv(os.path.join(dataset,"testandpredict_groupby.csv"),index=False) # # 去掉方差最大的模型,其余模型预测最大最小值确定通道边界 # # 历史数据+预测数据 # # 拼接未来时间预测 # df_predict = loadcsv(os.path.join(dataset,'predict.csv')) # df_predict.drop('unique_id',inplace=True,axis=1) # df_predict.dropna(axis=1,inplace=True) # df_predict2 = df_predict.copy() # try: # df_predict['ds'] = pd.to_datetime(df_predict['ds'],format=r'%Y-%m-%d') # except ValueError : # df_predict['ds'] = pd.to_datetime(df_predict['ds'],format=r'%Y/%m/%d') # # 取第一行数据存储到数据库中 # first_row = df_predict.head(1) # first_row['ds'] = first_row['ds'].dt.strftime('%Y-%m-%d 00:00:00') # # # 将预测结果保存到数据库 # df_combined3 = pd.concat([df_combined3, df_predict]).reset_index(drop=True) # # # 判断 df 的数值列转为float # for col in df_combined3.columns: # try: # if col != 'ds': # df_combined3[col] = df_combined3[col].astype(float) # df_combined3[col] = df_combined3[col].round(2) # except ValueError: # pass # df_combined3.to_csv(os.path.join(dataset,"testandpredict_groupby.csv"),index=False) # df_combined3['ds'] = df_combined3['ds'].dt.strftime('%Y-%m-%d 00:00:00') # # # 判断表存在 # if not sqlitedb.check_table_exists('testandpredict_groupby'): # df_combined3.to_sql('testandpredict_groupby',sqlitedb.connection,index=False) # else: # for row in df_combined3.itertuples(index=False): # row_dict = row._asdict() # check_query = sqlitedb.select_data('testandpredict_groupby',where_condition = f"ds = '{row.ds}'") # if len(check_query) > 0: # set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()]) # sqlitedb.update_data('testandpredict_groupby',set_clause,where_condition = f"ds = '{row.ds}'") # continue # sqlitedb.insert_data('testandpredict_groupby',tuple(row_dict.values()),columns=row_dict.keys()) # ten_models = allmodelnames # # 计算每个模型的方差 # variances = df_combined3[ten_models].var() # # 找到方差最大的模型 # max_variance_model = variances.idxmax() # # 打印方差最大的模型 # print("方差最大的模型是:", max_variance_model) # # 去掉方差最大的模型 # df_combined3 = df_combined3.drop(columns=[max_variance_model]) # if max_variance_model in allmodelnames: # allmodelnames.remove(max_variance_model) # df_combined3['min'] = df_combined3[allmodelnames].min(axis=1) # df_combined3['max'] = df_combined3[allmodelnames].max(axis=1) # print(df_combined3[['min','max']]) # # 历史价格+预测价格 # df_combined3 = df_combined3[-50:] # 取50个数据点画图 # plt.figure(figsize=(20, 10)) # plt.plot(df_combined3['ds'], df_combined3['y'], label='真实值',marker='o') # plt.plot(df_combined3['ds'], df_combined3[most_model], label=most_model_name) # plt.fill_between(df_combined3['ds'], df_combined3['min'], df_combined3['max'], alpha=0.2) # plt.grid(True) # # # 显示历史值 # for i, j in zip(df_combined3['ds'][:-5], df_combined3['y'][:-5]): # plt.text(i, j, str(j), ha='center', va='bottom') # # 当前日期画竖虚线 # plt.axvline(x=df_combined3['ds'].iloc[-horizon], color='r', linestyle='--') # plt.legend() # plt.xlabel('日期') # plt.ylabel('价格') # plt.savefig(os.path.join(dataset,'历史价格-预测值.png'), bbox_inches='tight') # plt.close()