根据配置选择报告函数名称
This commit is contained in:
parent
704e49b29f
commit
8ebbeed7b6
@ -211,7 +211,7 @@ upload_data = {
|
|||||||
### 开关
|
### 开关
|
||||||
is_train = True # 是否训练
|
is_train = True # 是否训练
|
||||||
is_debug = False # 是否调试
|
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_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_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_edbcode = False # 特征使用edbcoding列表中的
|
||||||
|
50
main.py
50
main.py
@ -106,11 +106,6 @@ def predict_main():
|
|||||||
sqlitedb.create_table('most_model',columns="ds datetime, most_common_model TEXT")
|
sqlitedb.create_table('most_model',columns="ds datetime, most_common_model TEXT")
|
||||||
sqlitedb.insert_data('most_model',(datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'),most_common_model,),columns=('ds','most_common_model',))
|
sqlitedb.insert_data('most_model',(datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'),most_common_model,),columns=('ds','most_common_model',))
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
if is_corr:
|
if is_corr:
|
||||||
df = corr_feature(df=df)
|
df = corr_feature(df=df)
|
||||||
|
|
||||||
@ -119,25 +114,25 @@ def predict_main():
|
|||||||
row,col = df.shape
|
row,col = df.shape
|
||||||
|
|
||||||
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
|
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
|
||||||
ex_Model(df,
|
# ex_Model(df,
|
||||||
horizon=horizon,
|
# horizon=horizon,
|
||||||
input_size=input_size,
|
# input_size=input_size,
|
||||||
train_steps=train_steps,
|
# train_steps=train_steps,
|
||||||
val_check_steps=val_check_steps,
|
# val_check_steps=val_check_steps,
|
||||||
early_stop_patience_steps=early_stop_patience_steps,
|
# early_stop_patience_steps=early_stop_patience_steps,
|
||||||
is_debug=is_debug,
|
# is_debug=is_debug,
|
||||||
dataset=dataset,
|
# dataset=dataset,
|
||||||
is_train=is_train,
|
# is_train=is_train,
|
||||||
is_fivemodels=is_fivemodels,
|
# is_fivemodels=is_fivemodels,
|
||||||
val_size=val_size,
|
# val_size=val_size,
|
||||||
test_size=test_size,
|
# test_size=test_size,
|
||||||
settings=settings,
|
# settings=settings,
|
||||||
now=now,
|
# now=now,
|
||||||
etadata = etadata,
|
# etadata = etadata,
|
||||||
modelsindex = modelsindex,
|
# modelsindex = modelsindex,
|
||||||
data = data,
|
# data = data,
|
||||||
is_eta=is_eta,
|
# is_eta=is_eta,
|
||||||
)
|
# )
|
||||||
|
|
||||||
|
|
||||||
logger.info('模型训练完成')
|
logger.info('模型训练完成')
|
||||||
@ -151,10 +146,13 @@ def predict_main():
|
|||||||
|
|
||||||
logger.info('制作报告ing')
|
logger.info('制作报告ing')
|
||||||
title = f'{settings}--{now}-预测报告' # 报告标题
|
title = f'{settings}--{now}-预测报告' # 报告标题
|
||||||
|
if 'Brent' in y:
|
||||||
brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
|
brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
|
||||||
reportname=reportname,sqlitedb=sqlitedb),
|
reportname=reportname,sqlitedb=sqlitedb),
|
||||||
# pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
|
else:
|
||||||
# reportname=reportname),
|
pp_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('制作报告end')
|
||||||
logger.info('模型训练完成')
|
logger.info('模型训练完成')
|
||||||
|
|
||||||
|
@ -950,6 +950,7 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu
|
|||||||
content.append(Graphs.draw_little_title('一、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
|
# 添加历史走势及预测价格的走势图片
|
||||||
content.append(Graphs.draw_img(os.path.join(dataset,'历史价格-预测值.png')))
|
content.append(Graphs.draw_img(os.path.join(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('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('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('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'))
|
||||||
@ -1393,8 +1394,526 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu
|
|||||||
print(f"请求超时: {e}")
|
print(f"请求超时: {e}")
|
||||||
|
|
||||||
|
|
||||||
|
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'):
|
||||||
|
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(f'dataset/指标数据添加时间特征.csv', parse_dates=['ds']).tail(20)
|
||||||
|
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]
|
||||||
|
# 遍历X每一列,和yy画散点图 ,
|
||||||
|
|
||||||
def pp_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inputsize=5,dataset='dataset',time = '2024-07-30',reportname='report.pdf'):
|
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'/', '-')
|
||||||
|
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()
|
||||||
|
# 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(f'{y}{time}预测报告'))
|
||||||
|
|
||||||
|
### 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(dataset,'历史价格-预测值.png')))
|
||||||
|
# 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。'))
|
||||||
|
|
||||||
|
|
||||||
|
# 取df中y列为空的行
|
||||||
|
import pandas as pd
|
||||||
|
df = pd.read_csv(os.path.join(dataset,'predict.csv'),encoding='gbk')
|
||||||
|
df_true = pd.read_csv(os.path.join(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(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(dataset,'testandpredict_groupby.csv'),encoding='utf-8')
|
||||||
|
df4 = df.copy() # 计算偏差率使用
|
||||||
|
# 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('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(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(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(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()
|
||||||
|
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(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(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()
|
||||||
|
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
|
||||||
|
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(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(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。'))
|
||||||
|
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:'))
|
||||||
|
|
||||||
|
### 读取模型简介
|
||||||
|
with open(os.path.join(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(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(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]}'))
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### 生成pdf文件
|
||||||
|
doc = SimpleDocTemplate(os.path.join(dataset,reportname), pagesize=letter)
|
||||||
|
# doc = SimpleDocTemplate(os.path.join(dataset,'reportname.pdf'), pagesize=letter)
|
||||||
|
doc.build(content)
|
||||||
|
# pdf 上传到数字化信息平台
|
||||||
|
# 读取pdf并转为base64
|
||||||
|
try:
|
||||||
|
if is_update_report:
|
||||||
|
with open(os.path.join(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}")
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
def pp_export_pdf_v1(num_indicators=475,num_models=21, num_dayindicator=202,inputsize=5,dataset='dataset',time = '2024-07-30',reportname='report.pdf'):
|
||||||
global y
|
global y
|
||||||
# 创建内容对应的空列表
|
# 创建内容对应的空列表
|
||||||
content = list()
|
content = list()
|
||||||
|
Loading…
Reference in New Issue
Block a user