diff --git a/codeback.py b/codeback.py index 2b88642..c6605ef 100644 --- a/codeback.py +++ b/codeback.py @@ -234,6 +234,15 @@ # 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]}')) diff --git a/config_jingbo.py b/config_jingbo.py index 2fb8d83..07e0f51 100644 --- a/config_jingbo.py +++ b/config_jingbo.py @@ -192,14 +192,14 @@ warning_data = { ### 开关 is_train = True # 是否训练 is_debug = False # 是否调试 -is_eta = True # 是否使用eta接口 +is_eta = False # 是否使用eta接口 is_timefurture = True # 是否使用时间特征 is_fivemodels = False # 是否使用之前保存的最佳的5个模型 is_edbcode = False # 特征使用edbcoding列表中的 is_edbnamelist = False # 自定义特征,对应上面的edbnamelist is_update_eta = False # 预测结果上传到eta is_update_report = False # 是否上传报告 -is_update_warning_data = True # 是否上传预警数据 +is_update_warning_data = False # 是否上传预警数据 # 数据截取日期 end_time = '' # 数据截取日期 diff --git a/lib/dataread.py b/lib/dataread.py index 6a7a08a..6599e00 100644 --- a/lib/dataread.py +++ b/lib/dataread.py @@ -1,5 +1,5 @@ -# from config_jingbo import * -from config_juxiting import * +from config_jingbo import * +# from config_juxiting import * # 导入模块 diff --git a/main_yuanyou.py b/main_yuanyou.py index 8f90557..82bf2b0 100644 --- a/main_yuanyou.py +++ b/main_yuanyou.py @@ -116,7 +116,7 @@ def predict_main(): logger.info('今天是周一,更新预测模型') # 计算最近20天预测残差最低的模型名称 - model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="20") + model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="60") # 删除空值率为40%以上的列,删除空行 model_results = model_results.dropna(thresh=len(model_results)*0.6,axis=1) model_results = model_results.dropna() @@ -135,7 +135,7 @@ def predict_main(): min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0]) # 取出现次数最多的模型名称 most_common_model = min_abs_error_rate_column_name.value_counts().idxmax() - logger.info(f"最近20天预测残差最低的模型名称:{most_common_model}") + logger.info(f"最近60天预测残差最低的模型名称:{most_common_model}") # 保存结果到数据库 @@ -151,31 +151,31 @@ def predict_main(): row, col = df.shape now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') - ex_Model(df, - horizon=horizon, - input_size=input_size, - train_steps=train_steps, - val_check_steps=val_check_steps, - early_stop_patience_steps=early_stop_patience_steps, - is_debug=is_debug, - dataset=dataset, - is_train=is_train, - is_fivemodels=is_fivemodels, - val_size=val_size, - test_size=test_size, - settings=settings, - now=now, - etadata=etadata, - modelsindex=modelsindex, - data=data, - is_eta=is_eta, - ) + # ex_Model(df, + # horizon=horizon, + # input_size=input_size, + # train_steps=train_steps, + # val_check_steps=val_check_steps, + # early_stop_patience_steps=early_stop_patience_steps, + # is_debug=is_debug, + # dataset=dataset, + # is_train=is_train, + # is_fivemodels=is_fivemodels, + # val_size=val_size, + # test_size=test_size, + # settings=settings, + # now=now, + # etadata=etadata, + # modelsindex=modelsindex, + # data=data, + # is_eta=is_eta, + # ) logger.info('模型训练完成') logger.info('训练数据绘图ing') - model_results3 = model_losss_juxiting(sqlitedb) + model_results3 = model_losss(sqlitedb) logger.info('训练数据绘图end') # 模型报告 @@ -207,7 +207,7 @@ def predict_main(): file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime), ssl=ssl, ) - m.send_mail() + # m.send_mail() if __name__ == '__main__': diff --git a/models/nerulforcastmodels.py b/models/nerulforcastmodels.py index d2beaa6..089a861 100644 --- a/models/nerulforcastmodels.py +++ b/models/nerulforcastmodels.py @@ -369,8 +369,8 @@ def model_losss(sqlitedb): # 最多频率的模型名称 - min_model_max_frequency_model = df_combined3['min_model'].value_counts().idxmax() - max_model_max_frequency_model = df_combined3['max_model'].value_counts().idxmax() + min_model_max_frequency_model = df_combined3['min_model'][-50:].value_counts().idxmax() + max_model_max_frequency_model = df_combined3['max_model'][-50:].value_counts().idxmax() df_predict['min_model'] = min_model_max_frequency_model df_predict['max_model'] = max_model_max_frequency_model df_predict['min_within_quantile'] = df_predict[min_model_max_frequency_model] @@ -756,7 +756,7 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu content = list() # 获取特征的近一月值 import pandas as pd - feature_data_df = pd.read_csv(os.path.join(dataset,'指标数据添加时间特征.csv'), parse_dates=['ds']).tail(20) + feature_data_df = pd.read_csv(os.path.join(dataset,'指标数据添加时间特征.csv'), parse_dates=['ds']).tail(60) def draw_feature_trend(feature_data_df, features): # 画特征近一周的趋势图 feature_df = feature_data_df[['ds','y']+features] @@ -976,222 +976,6 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu content.append(Graphs.draw_text('气泡图中,横轴为指标分类,纵轴为指标分类下的特征数量,气泡的面积越大表示该分类中特征的相关系数和越大。')) logger.info(f'绘制相关性总和的气泡图结束') - - - # # 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。')) content.append(Graphs.draw_little_title('模型选择:')) content.append(Graphs.draw_text(f'预测使用了{num_models}个模型进行训练拟合,通过评估指标MAE从小到大排列,前5个模型的简介如下:')) @@ -1230,15 +1014,6 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu # 添加图片 content.append(Graphs.draw_img(os.path.join(dataset,'预测值与真实值对比图.png'))) - # 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]}'))