diff --git a/main_shiyoujiao_puhuo.py b/main_shiyoujiao_puhuo.py index 101ab33..1e592ad 100644 --- a/main_shiyoujiao_puhuo.py +++ b/main_shiyoujiao_puhuo.py @@ -1,9 +1,9 @@ # 读取配置 from lib.dataread import * -from config_shiyoujiao_lvyong import * +from config_shiyoujiao_puhuo import * from lib.tools import SendMail, exception_logger -from models.nerulforcastmodels import ex_Model, model_losss, shiyoujiao_lvyong_export_pdf +from models.nerulforcastmodels import ex_Model, model_losss, shiyoujiao_puhuo_export_pdf import datetime import torch torch.set_float32_matmul_precision("high") @@ -425,8 +425,8 @@ def predict_main(): reportname = '石油焦大模型普货渠道.pdf' # 报告文件名 # reportname = f'石油焦大模型普货日度预测--{end_time}.pdf' # 报告文件名 # reportname = reportname.replace(':', '-') # 替换冒号 - shiyoujiao_lvyong_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, - reportname=reportname, sqlitedb=sqlitedb), + shiyoujiao_puhuo_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, + reportname=reportname, sqlitedb=sqlitedb), logger.info('制作报告end') logger.info('模型训练完成') diff --git a/models/nerulforcastmodels.py b/models/nerulforcastmodels.py index 78c1524..601de6e 100644 --- a/models/nerulforcastmodels.py +++ b/models/nerulforcastmodels.py @@ -2807,6 +2807,325 @@ def shiyoujiao_lvyong_export_pdf(num_indicators=475, num_models=21, num_dayindic print(f"请求超时: {e}") +@exception_logger +def shiyoujiao_puhuo_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, inputsize=5, dataset='dataset', time='2024-07-30', reportname='report.pdf', sqlitedb='jbsh_yuanyou.db'): + global y + # 创建内容对应的空列表 + content = list() + # 获取特征的近一月值 + import pandas as pd + feature_data_df = pd.read_csv(os.path.join( + config.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60天的趋势图 + feature_df = feature_data_df[['ds', 'y']+features] + # 遍历X每一列,和yy画散点图 , + + for i, col in enumerate(features): + # try: + 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 + sns.lineplot(data=feature_df, x='ds', y='y', ax=ax1, color='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 + sns.lineplot(data=feature_df, x='ds', y=col, ax=ax2, color='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 = 1.0003 + 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(':', '-') + col = col.replace(r'/', '-') + col = col.replace(r'>', '-') + col = col.replace(r'<', '-') + plt.savefig(os.path.join(config.dataset, f'{col}与价格散点图.png')) + content.append(Graphs.draw_img( + os.path.join(config.dataset, f'{col}与价格散点图.png'))) + plt.close() + # except Exception as e: + # print(f'绘制第{i+1}个特征{col}与价格散点图时出错:{e}') + + # 添加标题 + content.append(Graphs.draw_title('石油焦铝用渠道')) + + # 预测结果 + content.append(Graphs.draw_little_title('一、预测结果:')) + # 添加历史走势及预测价格的走势图片 + content.append(Graphs.draw_img( + os.path.join(config.dataset, '历史价格-预测值.png'))) + # 波动率画图逻辑 + content.append(Graphs.draw_text('图示说明:')) + content.append(Graphs.draw_text( + ' 确定置信区间:设置残差置信阈值,以每周最佳模型为基准,选取在置信区间的预测值作为置信区间;')) + + # 取df中y列为空的行 + import pandas as pd + df = pd.read_csv(os.path.join( + config.dataset, 'predict.csv'), encoding='gbk') + df_true = pd.read_csv(os.path.join( + config.dataset, '指标数据添加时间特征.csv'), encoding='utf-8') # 获取预测日期对应的真实值 + df_true = df_true[['ds', 'y']] + eval_df = pd.read_csv(os.path.join( + config.dataset, 'model_evaluation.csv'), encoding='utf-8') + # 按评估指标排序,取前五 + fivemodels_list = eval_df['模型(Model)'].values # 列表形式,后面当作列名索引使用 + # 取 fivemodels_list 和 ds 列 + df = df[['ds'] + fivemodels_list.tolist()] + # 拼接预测日期对应的真实值 + df = pd.merge(df, df_true, on='ds', how='left') + # 删除全部为nan的列 + df = df.dropna(how='all', axis=1) + # 选择除 'ds' 列外的数值列,并进行类型转换和四舍五入 + num_cols = [col for col in df.columns if col != + 'ds' and pd.api.types.is_numeric_dtype(df[col])] + for col in num_cols: + df[col] = df[col].astype(float).round(2) + # 添加最大值、最小值、平均值三列 + df['平均值'] = df[num_cols].mean(axis=1).round(2) + df['最大值'] = df[num_cols].max(axis=1) + df['最小值'] = df[num_cols].min(axis=1) + # df转置 + df = df.T + # df重置索引 + df = df.reset_index() + # 添加预测值表格 + data = df.values.tolist() + col_width = 500/len(df.columns) + content.append(Graphs.draw_table(col_width, *data)) + content.append(Graphs.draw_little_title('二、上一预测周期偏差率分析:')) + df = pd.read_csv(os.path.join( + config.dataset, 'testandpredict_groupby.csv'), encoding='utf-8') + df4 = df.copy() # 计算偏差率使用 + # 去掉created_dt 列 + df4 = df4.drop(columns=['created_dt']) + # 计算模型偏差率 + # 计算各列对于y列的差值百分比 + df3 = pd.DataFrame() # 存储偏差率 + + # 删除有null的行 + df4 = df4.dropna() + df3['ds'] = df4['ds'] + for col in fivemodels_list: + df3[col] = round(abs(df4[col] - df4['y']) / df4['y'] * 100, 2) + # 找出决定系数前五的偏差率 + df3 = df3[['ds']+fivemodels_list.tolist()][-inputsize:] + # 找出上一预测区间的时间 + stime = df3['ds'].iloc[0] + etime = df3['ds'].iloc[-1] + # 添加偏差率表格 + fivemodels = '、'.join(eval_df['模型(Model)'].values[:5]) # 字符串形式,后面写入字符串使用 + content.append(Graphs.draw_text( + f'预测使用了{num_models}个模型进行训练,使用评估结果MAE前五的模型分别是 {fivemodels} ,模型上一预测区间 {stime} -- {etime}的偏差率(%)分别是:')) + # # 添加偏差率表格 + df3 = df3.T + df3 = df3.reset_index() + data = df3.values.tolist() + col_width = 500/len(df3.columns) + content.append(Graphs.draw_table(col_width, *data)) + + content.append(Graphs.draw_little_title('上一周预测准确率:')) + df4 = sqlitedb.select_data('accuracy_rote', order_by='结束日期 desc', limit=1) + df4 = df4.T + df4 = df4.reset_index() + df4 = df4.T + data = df4.values.tolist() + col_width = 500/len(df4.columns) + content.append(Graphs.draw_table(col_width, *data)) + + content.append(Graphs.draw_little_title('三、预测过程解析:')) + # 特征、模型、参数配置 + content.append(Graphs.draw_little_title('模型选择:')) + content.append(Graphs.draw_text( + f'本次预测使用了一个专门收集时间序列的NeuralForecast库中的{num_models}个模型:')) + content.append(Graphs.draw_text(f'使用40天的数据预测未来{inputsize}天的数据。')) + content.append(Graphs.draw_little_title('指标情况:')) + with open(os.path.join(config.dataset, '特征频度统计.txt'), encoding='utf-8') as f: + for line in f.readlines(): + content.append(Graphs.draw_text(line)) + + data = pd.read_csv(os.path.join(config.dataset, '指标数据添加时间特征.csv'), + encoding='utf-8') # 计算相关系数用 + df_zhibiaofenlei = loadcsv(os.path.join( + config.dataset, '特征处理后的指标名称及分类.csv')) # 气泡图用 + df_zhibiaoshuju = data.copy() # 气泡图用 + + # 绘制特征相关气泡图 + + grouped = df_zhibiaofenlei.groupby('指标分类') + grouped_corr = pd.DataFrame(columns=['指标分类', '指标数量', '相关性总和']) + + content.append(Graphs.draw_little_title('按指标分类分别与预测目标进行皮尔逊相关系数分析:')) + 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( + '''相关系数为-1:表示两个变量之间存在完全负向的线性关系,即当一个变量增加时,另一个变量会相应减少,且变化是完全相反的''')) + content.append(Graphs.draw_text( + '''相关系数接近0:表示两个变量之间不存在线性关系,即它们的变化不会随着对方的变化而变化。''')) + for name, group in grouped: + cols = group['指标名称'].tolist() + config.logger.info(f'开始绘制{name}类指标的相关性直方图') + cols_subset = cols + feature_names = ['y'] + cols_subset + correlation_matrix = df_zhibiaoshuju[feature_names].corr()['y'] + + # 绘制特征相关性直方分布图 + plt.figure(figsize=(10, 8)) + sns.histplot(correlation_matrix.values.flatten(), + bins=20, kde=True, color='skyblue') + plt.title(f'{name}类指标(共{len(cols_subset)}个)相关性直方分布图') + plt.xlabel('相关系数') + plt.ylabel('频数') + plt.savefig(os.path.join( + config.dataset, f'{name}类指标相关性直方分布图.png'), bbox_inches='tight') + plt.close() + content.append(Graphs.draw_img( + os.path.join(config.dataset, f'{name}类指标相关性直方分布图.png'))) + content.append(Graphs.draw_text( + f'{name}类指标(共{len(cols_subset)}个)的相关性直方分布图如上所示。')) + # 相关性大于0的特征 + positive_corr_features = correlation_matrix[correlation_matrix > 0].sort_values( + ascending=False).index.tolist()[1:] + + print(f'{name}下正相关的特征值有:', positive_corr_features) + if len(positive_corr_features) > 5: + positive_corr_features = positive_corr_features[0:5] + content.append(Graphs.draw_text( + f'{name}类指标中,与预测目标y正相关前五的特征有:{positive_corr_features}')) + draw_feature_trend(feature_data_df, positive_corr_features) + elif len(positive_corr_features) == 0: + pass + else: + positive_corr_features = positive_corr_features + content.append(Graphs.draw_text( + f'其中,与预测目标y正相关的特征有:{positive_corr_features}')) + draw_feature_trend(feature_data_df, positive_corr_features) + + # 相关性小于0的特征 + negative_corr_features = correlation_matrix[correlation_matrix < 0].sort_values( + ascending=True).index.tolist() + + print(f'{name}下负相关的特征值有:', negative_corr_features) + if len(negative_corr_features) > 5: + negative_corr_features = negative_corr_features[:5] + content.append(Graphs.draw_text( + f'与预测目标y负相关前五的特征有:{negative_corr_features}')) + draw_feature_trend(feature_data_df, negative_corr_features) + elif len(negative_corr_features) == 0: + pass + else: + content.append(Graphs.draw_text( + f'{name}类指标中,与预测目标y负相关的特征有:{negative_corr_features}')) + draw_feature_trend(feature_data_df, negative_corr_features) + # 计算correlation_sum 第一行的相关性的绝对值的总和 + correlation_sum = correlation_matrix.abs().sum() + config.logger.info(f'{name}类指标的相关性总和为:{correlation_sum}') + # 分组的相关性总和拼接到grouped_corr + goup_corr = pd.DataFrame( + {'指标分类': [name], '指标数量': [len(cols_subset)], '相关性总和': [correlation_sum]}) + grouped_corr = pd.concat( + [grouped_corr, goup_corr], axis=0, ignore_index=True) + + # 绘制相关性总和的气泡图 + config.logger.info(f'开始绘制相关性总和的气泡图') + plt.figure(figsize=(10, 10)) + sns.scatterplot(data=grouped_corr, x='相关性总和', y='指标数量', size='相关性总和', sizes=( + grouped_corr['相关性总和'].min()*5, grouped_corr['相关性总和'].max()*5), hue='指标分类', palette='viridis') + plt.title('指标分类相关性总和的气泡图') + plt.ylabel('数量') + plt.savefig(os.path.join(config.dataset, '指标分类相关性总和的气泡图.png'), + bbox_inches='tight') + plt.close() + content.append(Graphs.draw_img(os.path.join( + config.dataset, '指标分类相关性总和的气泡图.png'))) + 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。')) + config.logger.info(f'绘制相关性总和的气泡图结束') + 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:')) + # 读取模型简介 + with open(os.path.join(config.dataset, 'model_introduction.txt'), 'r', encoding='utf-8') as f: + for line in f: + line_split = line.strip().split('--') + if line_split[0] in fivemodels_list: + for introduction in line_split: + content.append(Graphs.draw_text(introduction)) + content.append(Graphs.draw_little_title('模型评估:')) + df = pd.read_csv(os.path.join( + config.dataset, 'model_evaluation.csv'), encoding='utf-8') + # 判断 df 的数值列转为float + for col in eval_df.columns: + if col not in ['模型(Model)']: + eval_df[col] = eval_df[col].astype(float) + eval_df[col] = eval_df[col].round(3) + # 筛选 fivemodels_list.tolist() 的行 + eval_df = eval_df[eval_df['模型(Model)'].isin(fivemodels_list)] + # df转置 + eval_df = eval_df.T + # df重置索引 + eval_df = eval_df.reset_index() + eval_df = eval_df.T + # # 添加表格 + data = eval_df.values.tolist() + col_width = 500/len(eval_df.columns) + content.append(Graphs.draw_table(col_width, *data)) + content.append(Graphs.draw_text('评估指标释义:')) + content.append(Graphs.draw_text( + '1. 均方根误差(RMSE):均方根误差是衡量预测值与实际值之间误差的一种方法,取值越小,误差越小,预测效果越好。')) + content.append(Graphs.draw_text( + '2. 平均绝对误差(MAE):平均绝对误差是衡量预测值与实际值之间误差的一种方法,取值越小,误差越小,预测效果越好。')) + content.append(Graphs.draw_text( + '3. 平均平方误差(MSE):平均平方误差是衡量预测值与实际值之间误差的一种方法,取值越小,误差越小,预测效果越好。')) + content.append(Graphs.draw_text('模型拟合:')) + # 添加图片 + content.append(Graphs.draw_img( + os.path.join(config.dataset, '预测值与真实值对比图.png'))) + # 生成pdf文件 + doc = SimpleDocTemplate(os.path.join( + config.dataset, reportname), pagesize=letter) + doc.build(content) + # pdf 上传到数字化信息平台 + try: + if config.is_update_report: + with open(os.path.join(config.dataset, reportname), 'rb') as f: + base64_data = base64.b64encode(f.read()).decode('utf-8') + upload_data["data"]["fileBase64"] = base64_data + upload_data["data"]["fileName"] = reportname + token = get_head_auth_report() + upload_report_data(token, upload_data) + except TimeoutError as e: + print(f"请求超时: {e}") + + @exception_logger def pp_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, inputsize=5, dataset='dataset', time='2024-07-30', reportname='report.pdf', sqlitedb='jbsh_yuanyou.db'): # 创建内容对应的空列表