# xgboost修改版本
|
import os
|
import pickle
|
import pandas as pd
|
import numpy as np
|
from numpy.lib.stride_tricks import sliding_window_view
|
import tkinter as tk
|
import tkinter.font as tkfont
|
from tkinter import ttk
|
from datetime import timedelta
|
from time import time
|
import matplotlib.pyplot as plt
|
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg, NavigationToolbar2Tk
|
from xgboost import XGBRegressor
|
from lunardate import LunarDate
|
from sklearn.model_selection import train_test_split
|
from sklearn.metrics import mean_squared_error, mean_absolute_error
|
import matplotlib
|
|
# 配置 matplotlib 中文显示
|
matplotlib.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'SimSun', 'Arial Unicode MS']
|
matplotlib.rcParams['axes.unicode_minus'] = False
|
matplotlib.rcParams['font.family'] = 'sans-serif'
|
|
# 全局缓存变量及特征名称
|
cached_model = None
|
last_training_time = None
|
feature_columns = None
|
current_view = {'xlim': None, 'ylim': None} # 用于存储当前图表视图
|
|
# 数据加载与预处理函数
|
# -------------------------------
|
def load_data(upstream_file, downstream_file, river_level_file=None, flow_file=None):
|
"""
|
加载所有相关数据并进行数据质量处理
|
"""
|
try:
|
# 读取上游和下游数据
|
upstream_df = pd.read_csv(upstream_file)
|
downstream_df = pd.read_csv(downstream_file)
|
except FileNotFoundError:
|
print("文件未找到，请检查路径")
|
return None
|
|
# 确保列名一致
|
upstream_df.columns = ['DateTime', 'TagName', 'Value']
|
downstream_df.columns = ['DateTime', 'TagName', 'Value']
|
|
# 转换时间格式并设置为索引
|
upstream_df['DateTime'] = pd.to_datetime(upstream_df['DateTime'])
|
downstream_df['DateTime'] = pd.to_datetime(downstream_df['DateTime'])
|
|
# 设置DateTime为索引
|
upstream_df.set_index('DateTime', inplace=True)
|
downstream_df.set_index('DateTime', inplace=True)
|
|
# 数值处理 - 使用更稳健的转换方法
|
for df in [upstream_df, downstream_df]:
|
df['Value'] = pd.to_numeric(df['Value'], errors='coerce')
|
# 使用IQR方法检测异常值
|
Q1 = df['Value'].quantile(0.25)
|
Q3 = df['Value'].quantile(0.75)
|
IQR = Q3 - Q1
|
lower_bound = Q1 - 1.5 * IQR
|
upper_bound = Q3 + 1.5 * IQR
|
# 将异常值替换为边界值
|
df.loc[df['Value'] < lower_bound, 'Value'] = lower_bound
|
df.loc[df['Value'] > upper_bound, 'Value'] = upper_bound
|
|
# 过滤盐度小于5的数据
|
upstream_df = upstream_df[upstream_df['Value'] >= 5]
|
downstream_df = downstream_df[downstream_df['Value'] >= 5]
|
|
# 重命名Value列
|
upstream_df = upstream_df.rename(columns={'Value': 'upstream'})[['upstream']]
|
downstream_df = downstream_df.rename(columns={'Value': 'downstream'})[['downstream']]
|
|
# 合并数据
|
merged_df = pd.merge(upstream_df, downstream_df, left_index=True, right_index=True, how='inner')
|
|
# 加载长江水位数据（如果提供）
|
if river_level_file:
|
try:
|
river_level_df = pd.read_csv(river_level_file)
|
print(f"成功读取水位数据文件: {river_level_file}")
|
|
# 确保列名一致
|
if len(river_level_df.columns) >= 3:
|
river_level_df.columns = ['DateTime', 'TagName', 'Value']
|
elif len(river_level_df.columns) == 2:
|
river_level_df.columns = ['DateTime', 'Value']
|
river_level_df['TagName'] = 'water_level'
|
|
# 数据处理
|
river_level_df['DateTime'] = pd.to_datetime(river_level_df['DateTime'])
|
river_level_df.set_index('DateTime', inplace=True)
|
river_level_df['Value'] = pd.to_numeric(river_level_df['Value'], errors='coerce')
|
|
# 使用IQR方法处理异常值
|
Q1 = river_level_df['Value'].quantile(0.25)
|
Q3 = river_level_df['Value'].quantile(0.75)
|
IQR = Q3 - Q1
|
lower_bound = Q1 - 1.5 * IQR
|
upper_bound = Q3 + 1.5 * IQR
|
river_level_df.loc[river_level_df['Value'] < lower_bound, 'Value'] = lower_bound
|
river_level_df.loc[river_level_df['Value'] > upper_bound, 'Value'] = upper_bound
|
|
# 重命名并保留需要的列
|
river_level_df = river_level_df.rename(columns={'Value': 'water_level'})[['water_level']]
|
|
# 合并到主数据框
|
merged_df = pd.merge(merged_df, river_level_df, left_index=True, right_index=True, how='left')
|
|
# 对水位数据进行插值处理
|
merged_df['water_level'] = merged_df['water_level'].interpolate(method='time', limit=24)
|
merged_df['water_level'] = merged_df['water_level'].fillna(method='ffill').fillna(method='bfill')
|
|
# 创建平滑的水位数据
|
merged_df['water_level_smooth'] = merged_df['water_level'].rolling(window=24, min_periods=1, center=True).mean()
|
|
# 添加水位趋势特征
|
merged_df['water_level_trend_1h'] = merged_df['water_level_smooth'].diff(1)
|
merged_df['water_level_trend_24h'] = merged_df['water_level_smooth'].diff(24)
|
|
print(f"水位数据加载成功，范围: {merged_df['water_level'].min()} - {merged_df['water_level'].max()}")
|
except Exception as e:
|
print(f"水位数据加载失败: {str(e)}")
|
|
# 加载大通流量数据（如果提供）
|
if flow_file:
|
try:
|
flow_df = pd.read_csv(flow_file)
|
print(f"成功读取流量数据文件: {flow_file}")
|
|
# 确保列名一致
|
if len(flow_df.columns) >= 3:
|
flow_df.columns = ['DateTime', 'TagName', 'Value']
|
elif len(flow_df.columns) == 2:
|
flow_df.columns = ['DateTime', 'Value']
|
flow_df['TagName'] = 'flow'
|
|
# 数据处理
|
flow_df['DateTime'] = pd.to_datetime(flow_df['DateTime'])
|
flow_df.set_index('DateTime', inplace=True)
|
flow_df['Value'] = pd.to_numeric(flow_df['Value'], errors='coerce')
|
|
# 使用IQR方法处理异常值
|
Q1 = flow_df['Value'].quantile(0.25)
|
Q3 = flow_df['Value'].quantile(0.75)
|
IQR = Q3 - Q1
|
lower_bound = Q1 - 1.5 * IQR
|
upper_bound = Q3 + 1.5 * IQR
|
flow_df.loc[flow_df['Value'] < lower_bound, 'Value'] = lower_bound
|
flow_df.loc[flow_df['Value'] > upper_bound, 'Value'] = upper_bound
|
|
# 重命名并保留需要的列
|
flow_df = flow_df.rename(columns={'Value': 'flow'})[['flow']]
|
|
# 合并到主数据框
|
merged_df = pd.merge(merged_df, flow_df, left_index=True, right_index=True, how='left')
|
|
# 对流量数据进行插值处理
|
merged_df['flow'] = merged_df['flow'].interpolate(method='time', limit=24)
|
merged_df['flow'] = merged_df['flow'].fillna(method='ffill').fillna(method='bfill')
|
|
# 创建平滑的流量数据
|
merged_df['flow_smooth'] = merged_df['flow'].rolling(window=24, min_periods=1, center=True).mean()
|
|
# 添加流量趋势特征
|
merged_df['flow_trend_1h'] = merged_df['flow_smooth'].diff(1)
|
merged_df['flow_trend_24h'] = merged_df['flow_smooth'].diff(24)
|
|
# 添加流量统计特征
|
merged_df['mean_1d_flow'] = merged_df['flow_smooth'].rolling(window=24, min_periods=1).mean()
|
merged_df['mean_3d_flow'] = merged_df['flow_smooth'].rolling(window=72, min_periods=1).mean()
|
merged_df['std_1d_flow'] = merged_df['flow_smooth'].rolling(window=24, min_periods=1).std()
|
|
# 添加流量变化特征
|
merged_df['flow_change_1h'] = merged_df['flow_smooth'].diff(1)
|
merged_df['flow_change_24h'] = merged_df['flow_smooth'].diff(24)
|
|
# # 添加流量与盐度比率（确保下游平滑数据已创建）
|
# if 'downstream_smooth' in merged_df.columns:
|
# merged_df['flow_sal_ratio'] = merged_df['flow_smooth'] / merged_df['downstream_smooth']
|
# else:
|
# print("警告: 下游平滑数据未创建，跳过flow_sal_ratio计算")
|
|
print(f"流量数据加载成功，范围: {merged_df['flow'].min()} - {merged_df['flow'].max()} m³/s")
|
except Exception as e:
|
print(f"流量数据加载失败: {str(e)}")
|
|
# 对盐度数据进行插值和平滑处理
|
merged_df['upstream'] = merged_df['upstream'].interpolate(method='time', limit=24)
|
merged_df['downstream'] = merged_df['downstream'].interpolate(method='time', limit=24)
|
|
# 使用前向后向填充处理剩余的NaN值
|
merged_df['upstream'] = merged_df['upstream'].ffill().bfill()
|
merged_df['downstream'] = merged_df['downstream'].ffill().bfill()
|
|
# 创建平滑的盐度数据
|
merged_df['upstream_smooth'] = merged_df['upstream'].rolling(window=24, min_periods=1, center=True).mean()
|
merged_df['downstream_smooth'] = merged_df['downstream'].rolling(window=24, min_periods=1, center=True).mean()
|
|
# 添加趋势特征
|
merged_df['upstream_trend_1h'] = merged_df['upstream_smooth'].diff(1)
|
merged_df['upstream_trend_24h'] = merged_df['upstream_smooth'].diff(24)
|
merged_df['downstream_trend_1h'] = merged_df['downstream_smooth'].diff(1)
|
merged_df['downstream_trend_24h'] = merged_df['downstream_smooth'].diff(24)
|
|
# 填充NaN值
|
merged_df['upstream_trend_1h'] = merged_df['upstream_trend_1h'].fillna(0)
|
merged_df['upstream_trend_24h'] = merged_df['upstream_trend_24h'].fillna(0)
|
merged_df['downstream_trend_1h'] = merged_df['downstream_trend_1h'].fillna(0)
|
merged_df['downstream_trend_24h'] = merged_df['downstream_trend_24h'].fillna(0)
|
|
# 对低盐度部分使用更大的窗口进行平滑
|
low_sal_mask = merged_df['upstream'] < 50
|
if low_sal_mask.any():
|
merged_df.loc[low_sal_mask, 'upstream_smooth'] = merged_df.loc[low_sal_mask, 'upstream']\
|
.rolling(window=48, min_periods=1, center=True).mean()
|
|
# 数据验证和统计
|
print("\n数据质量统计:")
|
print(f"总数据量: {len(merged_df)}")
|
print(f"上游盐度范围: {merged_df['upstream'].min():.2f} - {merged_df['upstream'].max():.2f}")
|
print(f"下游盐度范围: {merged_df['downstream'].min():.2f} - {merged_df['downstream'].max():.2f}")
|
|
if 'water_level' in merged_df.columns:
|
print(f"水位范围: {merged_df['water_level'].min():.2f} - {merged_df['water_level'].max():.2f}")
|
print(f"水位缺失比例: {merged_df['water_level'].isna().mean()*100:.2f}%")
|
|
if 'flow' in merged_df.columns:
|
print(f"流量范围: {merged_df['flow'].min():.2f} - {merged_df['flow'].max():.2f} m³/s")
|
print(f"流量缺失比例: {merged_df['flow'].isna().mean()*100:.2f}%")
|
|
# 重置索引，将DateTime作为列
|
merged_df = merged_df.reset_index()
|
|
return merged_df
|
|
# df = load_data('青龙港1.csv', '一取水.csv')
|
|
# 测试
|
# df = load_data('青龙港1.csv', '一取水.csv')
|
# df.to_csv('merged_data.csv', index=False)
|
# print(f"Merged data saved to 'merged_data.csv' successfully")
|
|
# # 绘制盐度随时间变化图
|
# plt.figure(figsize=(12, 6))
|
# plt.plot(df['DateTime'], df['upstream_smooth'], label='上游盐度', color='blue')
|
# plt.plot(df['DateTime'], df['downstream_smooth'], label='下游盐度', color='red')
|
# plt.xlabel('时间')
|
# plt.ylabel('盐度')
|
# plt.title('盐度随时间变化图')
|
# plt.legend()
|
# plt.grid(True)
|
# plt.tight_layout()
|
# plt.savefig('salinity_time_series.png', dpi=300)
|
# plt.show()
|
|
|
# ----------------------特征工程部分
|
|
|
# -------------------------------
|
# 添加农历（潮汐）特征
|
# -------------------------------
|
def add_lunar_features(df):
|
lunar_day, lunar_phase_sin, lunar_phase_cos, is_high_tide = [], [], [], []
|
for dt in df['DateTime']:
|
ld = LunarDate.fromSolarDate(dt.year, dt.month, dt.day)
|
lunar_day.append(ld.day)
|
lunar_phase_sin.append(np.sin(2 * np.pi * ld.day / 15))
|
lunar_phase_cos.append(np.cos(2 * np.pi * ld.day / 15))
|
is_high_tide.append(1 if (ld.day <= 5 or (ld.day >= 16 and ld.day <= 20)) else 0)
|
df['lunar_day'] = lunar_day
|
df['lunar_phase_sin'] = lunar_phase_sin
|
df['lunar_phase_cos'] = lunar_phase_cos
|
df['is_high_tide'] = is_high_tide
|
return df
|
|
|
# -------------------------------
|
# 生成延迟特征（向量化，利用 shift）
|
# -------------------------------
|
def batch_create_delay_features(df, delay_hours):
|
"""
|
为数据框中的特定列创建延迟特征
|
"""
|
# 定义需要创建延迟特征的列
|
target_columns = ['upstream_smooth']
|
|
|
# target_columns = ['upstream_smooth', 'downstream_smooth']
|
# # 如果存在水位数据列，也为它创建延迟特征 暂时不使用
|
# if 'water_level_smooth' in df.columns:
|
# target_columns.append('water_level_smooth')
|
# elif 'water_level' in df.columns:
|
# print("注意: 水位平滑列不存在，使用原始水位列创建延迟特征")
|
# # 创建水位平滑列
|
# df['water_level_smooth'] = df['water_level'].rolling(window=24, min_periods=1, center=True).mean()
|
# df['water_level_smooth'] = df['water_level_smooth'].fillna(df['water_level'])
|
# target_columns.append('water_level_smooth')
|
|
# 创建延迟特征
|
for column in target_columns:
|
if column in df.columns:
|
for delay in delay_hours:
|
df[f'{column.split("_")[0]}_delay_{delay}h'] = df[column].shift(delay)
|
else:
|
print(f"警告: 列 {column} 不存在，跳过创建延迟特征")
|
|
return df
|
|
|
# 生成其他特征
|
def generate_features(df):
|
"""
|
生成其他特征，包括历史数据、时间特征、统计特征和外部特征，并将这些特征添加到原始DataFrame中
|
"""
|
try:
|
# 创建平滑的盐度数据
|
df['upstream_smooth'] = df['upstream'].rolling(window=24, min_periods=1, center=True).mean()
|
df['downstream_smooth'] = df['downstream'].rolling(window=24, min_periods=1, center=True).mean()
|
|
# 时间特征
|
df['hour'] = df['DateTime'].dt.hour
|
df['weekday'] = df['DateTime'].dt.dayofweek
|
df['month'] = df['DateTime'].dt.month
|
|
# 时间特征的sin和cos转换
|
df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
|
df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
|
df['weekday_sin'] = np.sin(2 * np.pi * df['weekday'] / 7)
|
df['weekday_cos'] = np.cos(2 * np.pi * df['weekday'] / 7)
|
df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
|
df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
|
|
# 统计特征
|
df['mean_1d_up'] = df['upstream_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_up'] = df['upstream_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_up'] = df['upstream_smooth'].rolling(window=24, min_periods=1).std()
|
|
df['mean_1d_down'] = df['downstream_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_down'] = df['downstream_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_down'] = df['downstream_smooth'].rolling(window=24, min_periods=1).std()
|
|
# 趋势特征
|
df['trend_1h_up'] = df['upstream_smooth'].diff(1)
|
df['trend_3h_up'] = df['upstream_smooth'].diff(3)
|
df['trend_6h_up'] = df['upstream_smooth'].diff(6)
|
df['trend_12h_up'] = df['upstream_smooth'].diff(12)
|
df['trend_24h_up'] = df['upstream_smooth'].diff(24)
|
|
df['trend_1h_down'] = df['downstream_smooth'].diff(1)
|
df['trend_3h_down'] = df['downstream_smooth'].diff(3)
|
df['trend_6h_down'] = df['downstream_smooth'].diff(6)
|
df['trend_12h_down'] = df['downstream_smooth'].diff(12)
|
df['trend_24h_down'] = df['downstream_smooth'].diff(24)
|
|
# 外部特征（水位和流量）
|
if 'water_level_smooth' in df.columns:
|
df['water_level_trend_1h'] = df['water_level_smooth'].diff(1)
|
df['water_level_trend_24h'] = df['water_level_smooth'].diff(24)
|
df['mean_1d_water_level'] = df['water_level_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_water_level'] = df['water_level_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_water_level'] = df['water_level_smooth'].rolling(window=24, min_periods=1).std()
|
|
if 'flow_smooth' in df.columns:
|
df['flow_trend_1h'] = df['flow_smooth'].diff(1)
|
df['flow_trend_24h'] = df['flow_smooth'].diff(24)
|
df['mean_1d_flow'] = df['flow_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_flow'] = df['flow_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_flow'] = df['flow_smooth'].rolling(window=24, min_periods=1).std()
|
|
return df
|
|
except Exception as e:
|
print(f"特征生成异常: {e}")
|
return df
|
|
|
# -------------------------------
|
# 向量化构造训练样本（优化特征工程）
|
# -------------------------------
|
def create_features_vectorized(df, look_back=168, forecast_horizon=1):
|
"""
|
向量化构造训练样本，使用过去7天的所有原始数据来预测未来1天的下游盐度均值
|
"""
|
try:
|
# 确保数据按时间排序
|
df = df.sort_values('DateTime')
|
|
# 获取所有数值列（排除DateTime列）
|
numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
|
if 'DateTime' in numeric_columns:
|
numeric_columns.remove('DateTime')
|
|
# 初始化特征和标签列表
|
features = [] # x输入
|
targets = [] # y输出
|
|
# 使用滑动窗口创建样本
|
for i in range(len(df) - look_back - forecast_horizon + 1):
|
# 获取7天的特征窗口
|
window = df.iloc[i:i+look_back]
|
|
# 提取特征 - 使用所有原始数据
|
window_features = []
|
for col in numeric_columns:
|
# 获取列数据并处理NaN值
|
col_values = window[col].fillna(method='ffill').fillna(method='bfill').values
|
window_features.extend(col_values)
|
|
# 添加时间特征
|
current_date = window['DateTime'].iloc[-1]
|
window_features.extend([
|
current_date.month,
|
current_date.day,
|
current_date.weekday()
|
])
|
|
# 获取目标值（未来1天的下游盐度均值）
|
next_day = df.iloc[i+look_back:i+look_back+24] # 获取未来24小时的数据
|
# 处理目标值中的NaN
|
target_values = next_day['downstream_smooth'].fillna(method='ffill').fillna(method='bfill').values
|
target = np.mean(target_values)
|
|
# 检查特征和目标值是否有效
|
if not np.any(np.isnan(window_features)) and not np.isnan(target) and not np.isinf(target):
|
features.append(window_features)
|
targets.append(target)
|
|
if not features:
|
print("警告: 未能生成任何有效特征")
|
return np.array([]), np.array([])
|
|
# 转换为numpy数组
|
X = np.array(features)
|
y = np.array(targets)
|
|
print(f"成功生成特征矩阵，形状: {X.shape}")
|
return X, y
|
|
except Exception as e:
|
print(f"特征创建异常: {e}")
|
return np.array([]), np.array([])
|
|
def generate_prediction_features(df, current_date, look_back=168):
|
"""
|
为预测生成特征，使用与create_features_vectorized相同的特征生成逻辑
|
"""
|
try:
|
# 确保数据按时间排序
|
df = df.sort_values('DateTime')
|
|
# 获取所有数值列（排除DateTime列）
|
numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
|
if 'DateTime' in numeric_columns:
|
numeric_columns.remove('DateTime')
|
|
# 找到当前日期在数据中的位置
|
current_idx = df[df['DateTime'] <= current_date].index[-1]
|
|
# 获取过去168小时（7天）的数据窗口
|
if current_idx < look_back:
|
print(f"数据不足，需要{look_back}小时的数据，但只有{current_idx+1}小时")
|
return None
|
|
window = df.iloc[current_idx-look_back+1:current_idx+1]
|
|
# 提取特征 - 使用所有原始数据
|
features = []
|
for col in numeric_columns:
|
# 直接使用原始数据作为特征
|
features.extend(window[col].values)
|
|
# 添加时间特征
|
features.extend([
|
current_date.month,
|
current_date.day,
|
current_date.weekday()
|
])
|
|
return np.array(features)
|
|
except Exception as e:
|
print(f"预测特征生成异常: {e}")
|
return None
|
|
|
# -------------------------------
|
# 获取模型准确度指标
|
# -------------------------------
|
def get_model_metrics():
|
"""获取保存在模型缓存中的准确度指标"""
|
model_cache_file = 'salinity_model.pkl'
|
if os.path.exists(model_cache_file):
|
try:
|
with open(model_cache_file, 'rb') as f:
|
model_data = pickle.load(f)
|
return {
|
'rmse': model_data.get('rmse', None),
|
'mae': model_data.get('mae', None)
|
}
|
except Exception as e:
|
print(f"获取模型指标失败: {e}")
|
return None
|
|
# -------------------------------
|
# 模型训练与预测，展示验证准确度（RMSE, MAE）
|
# -------------------------------
|
def train_and_predict(df, start_time, force_retrain=False):
|
global cached_model, last_training_time
|
model_cache_file = 'salinity_model.pkl'
|
model_needs_training = True
|
|
if os.path.exists(model_cache_file) and force_retrain:
|
try:
|
os.remove(model_cache_file)
|
print("已删除旧模型缓存（强制重新训练）")
|
except Exception as e:
|
print("删除缓存异常:", e)
|
|
train_df = df[df['DateTime'] < start_time].copy()
|
|
# 创建测试特征，检查当前特征维度
|
test_X, test_y = create_features_vectorized(train_df, look_back=7, forecast_horizon=1)
|
if test_X is None or test_y is None:
|
print("特征生成失败")
|
return None, None, None, None
|
|
current_feature_dim = test_X.shape[1] if len(test_X) > 0 else 0
|
print(f"当前特征维度: {current_feature_dim}")
|
|
cached_feature_dim = None
|
|
if not force_retrain and cached_model is not None and last_training_time is not None:
|
if last_training_time >= train_df['DateTime'].max():
|
try:
|
cached_feature_dim = cached_model.n_features_in_
|
print(f"缓存模型特征维度: {cached_feature_dim}")
|
|
if cached_feature_dim == current_feature_dim:
|
model_needs_training = False
|
print(f"使用缓存模型，训练时间: {last_training_time}")
|
else:
|
print(f"特征维度不匹配（缓存模型: {cached_feature_dim}，当前: {current_feature_dim}），需要重新训练")
|
except Exception as e:
|
print(f"检查模型特征维度失败: {e}")
|
elif not force_retrain and os.path.exists(model_cache_file):
|
try:
|
with open(model_cache_file, 'rb') as f:
|
model_data = pickle.load(f)
|
cached_model = model_data['model']
|
last_training_time = model_data['training_time']
|
|
try:
|
cached_feature_dim = cached_model.n_features_in_
|
print(f"文件缓存模型特征维度: {cached_feature_dim}")
|
if cached_feature_dim == current_feature_dim:
|
if last_training_time >= train_df['DateTime'].max():
|
model_needs_training = False
|
print(f"从文件加载模型，训练时间: {last_training_time}")
|
else:
|
print(f"特征维度不匹配（文件模型: {cached_feature_dim}，当前: {current_feature_dim}），需要重新训练")
|
except Exception as e:
|
print(f"检查模型特征维度失败: {e}")
|
except Exception as e:
|
print("加载模型失败:", e)
|
|
if model_needs_training:
|
print("开始训练新模型...")
|
if len(train_df) < 100:
|
print("训练数据不足")
|
return None, None, None, None
|
|
start_train = time()
|
X, y = create_features_vectorized(train_df, look_back=7, forecast_horizon=1)
|
if X is None or y is None:
|
print("特征生成失败")
|
return None, None, None, None
|
|
if len(X) == 0 or len(y) == 0:
|
print("样本生成不足，训练终止")
|
return None, None, None, None
|
|
print(f"训练样本数量: {X.shape[0]}, 特征维度: {X.shape[1]}")
|
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.1, random_state=42)
|
|
# 创建模型时设置 early_stopping_rounds
|
model = XGBRegressor(
|
n_estimators=200,
|
learning_rate=0.1,
|
max_depth=6,
|
min_child_weight=2,
|
subsample=0.8,
|
colsample_bytree=0.8,
|
gamma=0.1,
|
reg_alpha=0.1,
|
reg_lambda=1.0,
|
n_jobs=-1,
|
random_state=42,
|
early_stopping_rounds=10
|
)
|
|
try:
|
model.fit(X_train, y_train,
|
eval_set=[(X_val, y_val)],
|
eval_metric='rmse',
|
verbose=False)
|
|
# 在验证集上计算 RMSE 和 MAE
|
y_val_pred = model.predict(X_val)
|
rmse = np.sqrt(mean_squared_error(y_val, y_val_pred))
|
mae = mean_absolute_error(y_val, y_val_pred)
|
print(f"验证集 RMSE: {rmse:.4f}, MAE: {mae:.4f}")
|
|
# 特征重要性分析
|
feature_importance = model.feature_importances_
|
sorted_idx = np.argsort(feature_importance)[::-1]
|
|
# 生成特征名称
|
feature_names = []
|
# 获取所有数值列
|
numeric_columns = train_df.select_dtypes(include=[np.number]).columns.tolist()
|
if 'DateTime' in numeric_columns:
|
numeric_columns.remove('DateTime')
|
|
# 为每个数值列添加统计特征名称
|
for col in numeric_columns:
|
feature_names.extend([
|
f'{col}_7d_mean_mean',
|
f'{col}_7d_mean_std',
|
f'{col}_7d_std_mean',
|
f'{col}_7d_last_mean',
|
f'{col}_7d_mean_change'
|
])
|
|
# 添加时间特征名称
|
feature_names.extend(['month', 'day', 'weekday'])
|
|
# 确保特征名称数量与重要性数组长度匹配
|
if len(feature_names) != len(feature_importance):
|
print(f"警告: 特征名称数量({len(feature_names)})与重要性数组长度({len(feature_importance)})不匹配")
|
# 截取或填充特征名称以匹配重要性数组长度
|
feature_names = feature_names[:len(feature_importance)]
|
|
# 打印前10个重要特征
|
print("\nTop 10 重要特征:")
|
for i in range(min(10, len(sorted_idx))):
|
print(f"{i+1}. {feature_names[sorted_idx[i]]}: {feature_importance[sorted_idx[i]]:.6f}")
|
|
last_training_time = start_time
|
cached_model = model
|
|
with open(model_cache_file, 'wb') as f:
|
pickle.dump({
|
'model': model,
|
'training_time': last_training_time,
|
'feature_columns': feature_names,
|
'rmse': rmse,
|
'mae': mae,
|
'feature_dim': current_feature_dim
|
}, f)
|
print(f"模型训练完成，耗时: {time() - start_train:.2f}秒，特征维度: {current_feature_dim}")
|
except Exception as e:
|
print("模型训练异常:", e)
|
return None, None, None, None
|
else:
|
model = cached_model
|
|
# 预测部分
|
try:
|
# 初始化存储预测结果的列表
|
future_dates = [start_time + timedelta(days=i) for i in range(5)]
|
predictions = np.zeros(5)
|
|
# 创建预测所需的特征矩阵
|
X_pred = []
|
for i in range(5):
|
current_date = future_dates[i]
|
features = generate_prediction_features(df, current_date, look_back=7)
|
if features is None:
|
print(f"生成预测特征失败: {current_date}")
|
return None, None, None, None
|
X_pred.append(features)
|
|
# 批量预测
|
X_pred = np.array(X_pred)
|
predictions = model.predict(X_pred)
|
|
# 计算预测的置信区间
|
if model_needs_training:
|
# 使用训练时的验证集误差
|
y_train_pred = model.predict(X_train)
|
train_std = np.std(y_train - y_train_pred)
|
else:
|
# 使用模型缓存中的RMSE作为误差估计
|
try:
|
with open(model_cache_file, 'rb') as f:
|
model_data = pickle.load(f)
|
train_std = model_data.get('rmse', 1.0) # 如果没有RMSE，使用默认值1.0
|
except:
|
train_std = 1.0 # 如果无法获取RMSE，使用默认值1.0
|
|
prediction_intervals = np.array([
|
predictions - 1.96 * train_std,
|
predictions + 1.96 * train_std
|
])
|
|
return future_dates, predictions, model, prediction_intervals
|
except Exception as e:
|
print("预测过程异常:", e)
|
return None, None, None, None
|
|
# -------------------------------
|
# GUI界面部分
|
# -------------------------------
|
def run_gui():
|
def configure_gui_fonts():
|
font_names = ['微软雅黑', 'Microsoft YaHei', 'SimSun', 'SimHei']
|
for font_name in font_names:
|
try:
|
default_font = tkfont.nametofont("TkDefaultFont")
|
default_font.configure(family=font_name)
|
text_font = tkfont.nametofont("TkTextFont")
|
text_font.configure(family=font_name)
|
fixed_font = tkfont.nametofont("TkFixedFont")
|
fixed_font.configure(family=font_name)
|
return True
|
except Exception as e:
|
continue
|
return False
|
|
def on_predict():
|
try:
|
predict_start = time()
|
status_label.config(text="预测中...")
|
root.update()
|
start_time_dt = pd.to_datetime(entry.get())
|
force_retrain = retrain_var.get()
|
future_dates, predictions, model, prediction_intervals = train_and_predict(df, start_time_dt, force_retrain)
|
if future_dates is None or predictions is None:
|
status_label.config(text="预测失败")
|
return
|
|
# 获取并显示模型准确度指标
|
model_metrics = get_model_metrics()
|
if model_metrics:
|
metrics_text = f"模型准确度 - RMSE: {model_metrics['rmse']:.4f}, MAE: {model_metrics['mae']:.4f}"
|
metrics_label.config(text=metrics_text)
|
|
# 清除图形并重新绘制
|
ax.clear()
|
|
# 创建双y轴图表
|
ax2 = None
|
has_water_level = 'water_level' in df.columns and 'water_level_smooth' in df.columns
|
if has_water_level:
|
try:
|
ax2 = ax.twinx()
|
except Exception as e:
|
print(f"创建双y轴失败: {e}")
|
ax2 = None
|
|
# 绘制历史数据（最近 120 天）
|
history_end = min(start_time_dt, df['DateTime'].max())
|
history_start = history_end - timedelta(days=120)
|
hist_data = df[(df['DateTime'] >= history_start) & (df['DateTime'] <= history_end)]
|
|
# 确保数据不为空
|
if len(hist_data) == 0:
|
status_label.config(text="错误: 所选时间范围内没有历史数据")
|
return
|
|
# 绘制基本数据
|
ax.plot(hist_data['DateTime'], hist_data['downstream_smooth'],
|
label='一取水(下游)盐度', color='blue', linewidth=1.5)
|
ax.plot(hist_data['DateTime'], hist_data['upstream_smooth'],
|
label='青龙港(上游)盐度', color='purple', linewidth=1.5, alpha=0.7)
|
|
# 绘制水位数据（如果有）
|
if ax2 is not None and has_water_level:
|
try:
|
# 检查水位数据是否有足够的非NaN值
|
valid_water_level = hist_data['water_level_smooth'].dropna()
|
if len(valid_water_level) > 10: # 至少有10个有效值
|
ax2.plot(hist_data['DateTime'], hist_data['water_level_smooth'],
|
label='长江水位', color='green', linewidth=1.5, linestyle='--')
|
ax2.set_ylabel('水位 (m)', color='green')
|
ax2.tick_params(axis='y', labelcolor='green')
|
else:
|
print("水位数据有效值不足，跳过水位图")
|
except Exception as e:
|
print(f"绘制水位数据时出错: {e}")
|
|
|
# 绘制预测数据
|
if len(future_dates) > 0 and len(predictions) > 0:
|
ax.plot(future_dates, predictions, marker='o', linestyle='--',
|
label='递归预测盐度', color='red', linewidth=2)
|
|
# 添加预测的置信区间
|
if prediction_intervals is not None:
|
ax.fill_between(future_dates, prediction_intervals[0], prediction_intervals[1],
|
color='red', alpha=0.2, label='95% 置信区间')
|
|
# 绘制实际数据(如果有)
|
actual_data = df[(df['DateTime'] >= start_time_dt) & (df['DateTime'] <= future_dates[-1])]
|
actual_values = None
|
|
if not actual_data.empty:
|
actual_values = []
|
# 获取与预测日期最接近的实际数据
|
for pred_date in future_dates:
|
closest_idx = np.argmin(np.abs(actual_data['DateTime'] - pred_date))
|
actual_values.append(actual_data['downstream_smooth'].iloc[closest_idx])
|
|
# 绘制实际盐度曲线
|
ax.plot(future_dates, actual_values, marker='s', linestyle='-',
|
label='实际盐度', color='orange', linewidth=2)
|
|
# 设置图表标题和标签
|
ax.set_xlabel('日期')
|
ax.set_ylabel('盐度')
|
ax.set_title(f"从 {start_time_dt.strftime('%Y-%m-%d %H:%M:%S')} 开始的递归单步盐度预测")
|
|
# 设置图例并应用紧凑布局
|
if ax2 is not None:
|
try:
|
lines1, labels1 = ax.get_legend_handles_labels()
|
lines2, labels2 = ax2.get_legend_handles_labels()
|
if lines2: # 确保水位数据已绘制
|
ax.legend(lines1 + lines2, labels1 + labels2, loc='best')
|
else:
|
ax.legend(loc='best')
|
except Exception as e:
|
print(f"创建图例时出错: {e}")
|
ax.legend(loc='best')
|
else:
|
ax.legend(loc='best')
|
|
fig.tight_layout()
|
|
# 强制重绘
|
plt.close(fig)
|
fig.canvas.draw()
|
fig.canvas.flush_events()
|
plt.draw()
|
|
# 更新预测结果文本
|
predict_time = time() - predict_start
|
status_label.config(text=f"递归预测完成 (耗时: {predict_time:.2f}秒)")
|
|
# 显示预测结果
|
result_text = "递归单步预测结果:\n\n"
|
|
# 如果有实际值，计算差值和百分比误差
|
if actual_values is not None:
|
result_text += "日期 预测值 实际值 差值\n"
|
result_text += "--------------------------------------\n"
|
for i, (date, pred, actual) in enumerate(zip(future_dates, predictions, actual_values)):
|
diff = pred - actual
|
result_text += f"{date.strftime('%Y-%m-%d')} {pred:6.2f} {actual:6.2f} {diff:6.2f}\n"
|
else:
|
result_text += "日期 预测值\n"
|
result_text += "-------------------\n"
|
for i, (date, pred) in enumerate(zip(future_dates, predictions)):
|
result_text += f"{date.strftime('%Y-%m-%d')} {pred:6.2f}\n"
|
result_text += "\n无实际值进行对比"
|
|
update_result_text(result_text)
|
except Exception as e:
|
status_label.config(text=f"错误: {str(e)}")
|
import traceback
|
traceback.print_exc()
|
|
def on_scroll(event):
|
xlim = ax.get_xlim()
|
ylim = ax.get_ylim()
|
zoom_factor = 1.1
|
x_data = event.xdata if event.xdata is not None else (xlim[0]+xlim[1])/2
|
y_data = event.ydata if event.ydata is not None else (ylim[0]+ylim[1])/2
|
x_rel = (x_data - xlim[0]) / (xlim[1] - xlim[0])
|
y_rel = (y_data - ylim[0]) / (ylim[1] - ylim[0])
|
if event.step > 0:
|
new_width = (xlim[1]-xlim[0]) / zoom_factor
|
new_height = (ylim[1]-ylim[0]) / zoom_factor
|
x0 = x_data - x_rel * new_width
|
y0 = y_data - y_rel * new_height
|
ax.set_xlim([x0, x0+new_width])
|
ax.set_ylim([y0, y0+new_height])
|
else:
|
new_width = (xlim[1]-xlim[0]) * zoom_factor
|
new_height = (ylim[1]-ylim[0]) * zoom_factor
|
x0 = x_data - x_rel * new_width
|
y0 = y_data - y_rel * new_height
|
ax.set_xlim([x0, x0+new_width])
|
ax.set_ylim([y0, y0+new_height])
|
canvas.draw_idle()
|
|
def update_cursor(event):
|
if event.inaxes == ax:
|
canvas.get_tk_widget().config(cursor="fleur")
|
else:
|
canvas.get_tk_widget().config(cursor="")
|
|
def reset_view():
|
display_history()
|
status_label.config(text="图表视图已重置")
|
|
root = tk.Tk()
|
root.title("青龙港-陈行盐度预测系统")
|
try:
|
configure_gui_fonts()
|
except Exception as e:
|
print("字体配置异常:", e)
|
|
# 恢复输入框和控制按钮
|
input_frame = ttk.Frame(root, padding="10")
|
input_frame.pack(fill=tk.X)
|
|
ttk.Label(input_frame, text="输入开始时间 (YYYY-MM-DD HH:MM:SS)").pack(side=tk.LEFT)
|
entry = ttk.Entry(input_frame, width=25)
|
entry.pack(side=tk.LEFT, padx=5)
|
predict_button = ttk.Button(input_frame, text="预测", command=on_predict)
|
predict_button.pack(side=tk.LEFT)
|
status_label = ttk.Label(input_frame, text="提示: 第一次运行请勾选'强制重新训练模型'")
|
status_label.pack(side=tk.LEFT, padx=10)
|
|
control_frame = ttk.Frame(root, padding="5")
|
control_frame.pack(fill=tk.X)
|
retrain_var = tk.BooleanVar(value=False)
|
ttk.Checkbutton(control_frame, text="强制重新训练模型", variable=retrain_var).pack(side=tk.LEFT)
|
|
# 更新图例说明，加入水位数据信息
|
if 'water_level' in df.columns:
|
legend_label = ttk.Label(control_frame, text="图例: 紫色=青龙港上游数据, 蓝色=一取水下游数据, 红色=预测值, 绿色=长江水位")
|
else:
|
legend_label = ttk.Label(control_frame, text="图例: 紫色=青龙港上游数据, 蓝色=一取水下游数据, 红色=预测值, 橙色=实际值")
|
legend_label.pack(side=tk.LEFT, padx=10)
|
reset_button = ttk.Button(control_frame, text="重置视图", command=reset_view)
|
reset_button.pack(side=tk.LEFT, padx=5)
|
|
# 添加显示模型准确度的标签
|
metrics_frame = ttk.Frame(root, padding="5")
|
metrics_frame.pack(fill=tk.X)
|
model_metrics = get_model_metrics()
|
metrics_text = "模型准确度: 未知" if not model_metrics else f"模型准确度 - RMSE: {model_metrics['rmse']:.4f}, MAE: {model_metrics['mae']:.4f}"
|
metrics_label = ttk.Label(metrics_frame, text=metrics_text)
|
metrics_label.pack(side=tk.LEFT, padx=10)
|
|
# 结果显示区域
|
result_frame = ttk.Frame(root, padding="10")
|
result_frame.pack(fill=tk.BOTH, expand=True)
|
|
# 左侧放置图表
|
plot_frame = ttk.Frame(result_frame, width=800, height=600)
|
plot_frame.pack(side=tk.LEFT, fill=tk.BOTH, expand=True)
|
plot_frame.pack_propagate(False) # 不允许框架根据内容调整大小
|
|
# 右侧放置文本结果
|
text_frame = ttk.Frame(result_frame)
|
text_frame.pack(side=tk.RIGHT, fill=tk.Y)
|
|
# 使用等宽字体显示结果
|
result_font = tkfont.Font(family="Courier New", size=10, weight="normal")
|
|
# 添加文本框和滚动条
|
result_text = tk.Text(text_frame, width=50, height=25, font=result_font, wrap=tk.NONE)
|
result_text.pack(side=tk.LEFT, fill=tk.BOTH)
|
result_scroll = ttk.Scrollbar(text_frame, orient="vertical", command=result_text.yview)
|
result_scroll.pack(side=tk.RIGHT, fill=tk.Y)
|
result_text.configure(yscrollcommand=result_scroll.set)
|
result_text.configure(state=tk.DISABLED) # 初始设为只读
|
|
# 更新结果文本的函数
|
def update_result_text(text):
|
result_text.configure(state=tk.NORMAL)
|
result_text.delete(1.0, tk.END)
|
result_text.insert(tk.END, text)
|
result_text.configure(state=tk.DISABLED)
|
|
# 创建更高DPI的图形以获得更好的显示质量
|
fig, ax = plt.subplots(figsize=(10, 6), dpi=100)
|
fig.tight_layout(pad=3.0) # 增加内边距，防止标签被截断
|
|
# 创建画布并添加到固定大小的框架
|
canvas = FigureCanvasTkAgg(fig, master=plot_frame)
|
canvas.get_tk_widget().pack(side=tk.TOP, fill=tk.BOTH, expand=True)
|
|
# 添加工具栏，包含缩放、保存等功能
|
toolbar_frame = ttk.Frame(plot_frame)
|
toolbar_frame.pack(side=tk.BOTTOM, fill=tk.X)
|
toolbar = NavigationToolbar2Tk(canvas, toolbar_frame)
|
toolbar.update()
|
|
# 启用紧凑布局，并设置自动调整以使图表完全显示
|
def on_resize(event):
|
fig.tight_layout()
|
canvas.draw_idle()
|
|
# 添加图表交互功能
|
canvas.mpl_connect('resize_event', on_resize)
|
canvas.mpl_connect('scroll_event', on_scroll)
|
canvas.mpl_connect('motion_notify_event', update_cursor)
|
|
# 添加鼠标拖动功能
|
def on_press(event):
|
if event.inaxes != ax:
|
return
|
canvas.get_tk_widget().config(cursor="fleur")
|
ax._pan_start = (event.x, event.y, event.xdata, event.ydata)
|
|
def on_release(event):
|
ax._pan_start = None
|
canvas.get_tk_widget().config(cursor="")
|
canvas.draw_idle()
|
|
def on_motion(event):
|
if not hasattr(ax, '_pan_start') or ax._pan_start is None:
|
return
|
if event.inaxes != ax:
|
return
|
|
start_x, start_y, x_data, y_data = ax._pan_start
|
dx = event.x - start_x
|
dy = event.y - start_y
|
|
# 获取当前视图
|
xlim = ax.get_xlim()
|
ylim = ax.get_ylim()
|
|
# 计算图表坐标系中的移动
|
x_scale = (xlim[1] - xlim[0]) / canvas.get_tk_widget().winfo_width()
|
y_scale = (ylim[1] - ylim[0]) / canvas.get_tk_widget().winfo_height()
|
|
# 更新视图
|
ax.set_xlim(xlim[0] - dx * x_scale, xlim[1] - dx * x_scale)
|
ax.set_ylim(ylim[0] + dy * y_scale, ylim[1] + dy * y_scale)
|
|
# 更新拖动起点
|
ax._pan_start = (event.x, event.y, event.xdata, event.ydata)
|
|
canvas.draw_idle()
|
|
# 连接鼠标事件
|
canvas.mpl_connect('button_press_event', on_press)
|
canvas.mpl_connect('button_release_event', on_release)
|
canvas.mpl_connect('motion_notify_event', on_motion)
|
|
# 更新历史数据显示函数
|
def display_history():
|
try:
|
ax.clear()
|
end_date = df['DateTime'].max()
|
start_date = max(df['DateTime'].min(), end_date - timedelta(days=60))
|
hist_data = df[(df['DateTime'] >= start_date) & (df['DateTime'] <= end_date)]
|
|
if len(hist_data) == 0:
|
status_label.config(text="警告: 没有可用的历史数据")
|
return
|
|
# 创建双y轴图表
|
ax2 = None
|
has_water_level = 'water_level' in hist_data.columns and 'water_level_smooth' in hist_data.columns
|
if has_water_level:
|
ax2 = ax.twinx()
|
|
# 绘制数据
|
ax.plot(hist_data['DateTime'], hist_data['downstream_smooth'],
|
label='一取水(下游)盐度', color='blue', linewidth=1.5)
|
ax.plot(hist_data['DateTime'], hist_data['upstream_smooth'],
|
label='青龙港(上游)盐度', color='purple', linewidth=1.5, alpha=0.7)
|
|
# 设置边界，确保有一致的视图
|
y_min = min(hist_data['downstream_smooth'].min(), hist_data['upstream_smooth'].min()) * 0.9
|
y_max = max(hist_data['downstream_smooth'].max(), hist_data['upstream_smooth'].max()) * 1.1
|
ax.set_ylim(y_min, y_max)
|
|
# 如果有水位数据，在第二个y轴上绘制
|
if ax2 is not None and has_water_level:
|
try:
|
# 检查水位数据是否有足够的非NaN值
|
valid_water_level = hist_data['water_level_smooth'].dropna()
|
if len(valid_water_level) > 10: # 至少有10个有效值
|
ax2.plot(hist_data['DateTime'], hist_data['water_level_smooth'],
|
label='长江水位', color='green', linewidth=1.5, linestyle='--')
|
ax2.set_ylabel('水位 (m)', color='green')
|
ax2.tick_params(axis='y', labelcolor='green')
|
|
# 创建组合图例
|
lines1, labels1 = ax.get_legend_handles_labels()
|
lines2, labels2 = ax2.get_legend_handles_labels()
|
ax.legend(lines1 + lines2, labels1 + labels2, loc='best')
|
else:
|
print("水位数据有效值不足，跳过水位图")
|
ax.legend(loc='best')
|
except Exception as e:
|
print(f"绘制水位数据时出错: {e}")
|
ax.legend(loc='best')
|
else:
|
ax.legend(loc='best')
|
|
# 设置标签和标题
|
ax.set_xlabel('日期')
|
ax.set_ylabel('盐度')
|
ax.set_title('历史数据对比')
|
|
# 使用紧凑布局并绘制
|
fig.tight_layout()
|
|
# 使用多种方法确保图像显示
|
plt.close(fig) # 关闭旧的
|
fig.canvas.draw()
|
fig.canvas.flush_events()
|
plt.draw()
|
|
except Exception as e:
|
status_label.config(text=f"显示历史数据时出错: {str(e)}")
|
import traceback
|
traceback.print_exc()
|
|
display_history()
|
root.mainloop()
|
|
|
def resample_to_hourly(df):
|
"""
|
将分钟级数据重采样为小时级数据，计算每小时的平均值
|
"""
|
try:
|
# 确保DateTime是索引
|
if 'DateTime' in df.columns:
|
df = df.set_index('DateTime')
|
|
# 获取所有数值列
|
numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
|
|
# 按小时重采样，计算平均值
|
hourly_df = df[numeric_columns].resample('H').mean()
|
|
# 重置索引，将DateTime作为列
|
hourly_df = hourly_df.reset_index()
|
|
print(f"数据已从分钟级重采样为小时级，原始数据行数: {len(df)}，重采样后行数: {len(hourly_df)}")
|
return hourly_df
|
|
except Exception as e:
|
print(f"重采样数据异常: {e}")
|
return df
|
|
|
|
# -------------------------------
|
# 主程序入口：加载数据、添加特征、生成延迟特征后启动GUI
|
# -------------------------------
|
def save_processed_data(df, filename='processed_data.pkl'):
|
try:
|
df.to_pickle(filename)
|
print(f"已保存处理后的数据到 {filename}")
|
return True
|
except Exception as e:
|
print(f"保存数据失败: {e}")
|
return False
|
|
def load_processed_data(filename='processed_data.pkl'):
|
try:
|
if os.path.exists(filename):
|
df = pd.read_pickle(filename)
|
print(f"已从 {filename} 加载处理后的数据")
|
return df
|
else:
|
print(f"找不到处理后的数据文件 {filename}")
|
return None
|
except Exception as e:
|
print(f"加载数据失败: {e}")
|
return None
|
|
# 删除旧的处理数据（如果存在），以应用修复后的代码
|
if os.path.exists('processed_data.pkl'):
|
try:
|
os.remove('processed_data.pkl')
|
print("已删除旧的处理数据缓存，将使用修复后的代码重新处理数据")
|
except Exception as e:
|
print(f"删除缓存文件失败: {e}")
|
|
# 删除旧的模型文件（如果存在）
|
if os.path.exists('salinity_model.pkl'):
|
try:
|
os.remove('salinity_model.pkl')
|
print("已删除旧的模型文件，将重新训练模型")
|
except Exception as e:
|
print(f"删除模型文件失败: {e}")
|
|
# 尝试加载处理后的数据，如果不存在则重新处理
|
processed_data = load_processed_data()
|
if processed_data is not None:
|
df = processed_data
|
else:
|
# 添加长江液位数据作为参数
|
df = load_data('青龙港1.csv', '一取水.csv', '长江液位.csv', '大通流量.csv')
|
if df is not None:
|
# 添加时间特征
|
df['hour'] = df['DateTime'].dt.hour
|
df['weekday'] = df['DateTime'].dt.dayofweek
|
df['month'] = df['DateTime'].dt.month
|
|
# 添加农历特征
|
df = add_lunar_features(df)
|
|
# 添加延迟特征上游到下游3-5天，暂时每12小时为一个节点，根据效果后续再调整
|
# delay_hours = [1,2,3,4,6,12,24,36,48,60,72,84,96,108,120]
|
delay_hours = [72,84,96,108,120]
|
df = batch_create_delay_features(df, delay_hours)
|
|
# 添加统计特征
|
df['mean_1d_up'] = df['upstream_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_up'] = df['upstream_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_up'] = df['upstream_smooth'].rolling(window=24, min_periods=1).std()
|
df['max_1d_up'] = df['upstream_smooth'].rolling(window=24, min_periods=1).max()
|
df['min_1d_up'] = df['upstream_smooth'].rolling(window=24, min_periods=1).min()
|
|
df['mean_1d_down'] = df['downstream_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_down'] = df['downstream_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_down'] = df['downstream_smooth'].rolling(window=24, min_periods=1).std()
|
df['max_1d_down'] = df['downstream_smooth'].rolling(window=24, min_periods=1).max()
|
df['min_1d_down'] = df['downstream_smooth'].rolling(window=24, min_periods=1).min()
|
|
# 添加水位统计特征（如果水位数据存在）
|
if 'water_level' in df.columns:
|
# 首先创建水位平滑特征
|
if 'water_level_smooth' not in df.columns:
|
df['water_level_smooth'] = df['water_level'].rolling(window=24, min_periods=1, center=True).mean()
|
df['water_level_smooth'] = df['water_level_smooth'].fillna(df['water_level'])
|
|
# 添加水位统计特征
|
df['mean_1d_water_level'] = df['water_level_smooth'].rolling(window=24, min_periods=1).mean()
|
df['mean_3d_water_level'] = df['water_level_smooth'].rolling(window=72, min_periods=1).mean()
|
df['std_1d_water_level'] = df['water_level_smooth'].rolling(window=24, min_periods=1).std()
|
df['max_1d_water_level'] = df['water_level_smooth'].rolling(window=24, min_periods=1).max()
|
df['min_1d_water_level'] = df['water_level_smooth'].rolling(window=24, min_periods=1).min()
|
|
# 计算水位变化率
|
df['water_level_change_1h'] = df['water_level_smooth'].diff()
|
df['water_level_change_24h'] = df['water_level_smooth'].diff(24)
|
|
# 计算水位与盐度的相关特征
|
df['water_level_sal_ratio'] = df['water_level_smooth'] / df['downstream_smooth']
|
|
print("水位特征已添加")
|
|
# 添加其他特征
|
df = generate_features(df)
|
|
# 将数据重采样为小时级
|
df = resample_to_hourly(df)
|
|
# 保存处理后的数据
|
df.to_csv('merged_data_hour.csv', index=False)
|
print(f"Merged data saved to 'merged_data_hour.csv' successfully")
|
save_processed_data(df)
|
|
if df is not None:
|
run_gui()
|
else:
|
print("数据加载失败，无法运行预测。")
|
