我有一段python代码需要修改:import pandas as pd from scipy import stats from sklearn.preprocessing…
- User
我有一段python代码需要修改:import pandas as pd from scipy import stats from sklearn.preprocessing import MinMaxScaler, StandardScaler
读取微测站数据
micro_station_data = pd.read_excel(r'C:\Users\123\Desktop\micro_station_data.xlsx', skiprows=1)
读取国测站数据
national_station_data = pd.read_excel(r'C:\Users\123\Desktop\national_station_data.xls', skiprows=1)
数据预处理
def preprocess_data(data): # 将“时段”列转换为datetime格式 data['时段'] = pd.to_datetime(data['时段'], format ='%Y/%m/%d %H:%M:%S') # 对所有值为-99.0(E)和0.0(E)的数据进行空值处理 columns_to_replace = ['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压'] data.loc[:, columns_to_replace] = data.loc[:, columns_to_replace].replace([-99.0, 0.0], pd.NA) # 将非数字字符串替换为NaN值 data.loc[:, columns_to_replace] = data.loc[:, columns_to_replace].apply(pd.to_numeric, errors='coerce') # 使用各列的非空值均值替换空值 data = data.fillna(data.mean()) # 处理第一列数据 data['时段'] = data['时段'].dt.strftime('%Y-%m-%d %H:%M:%S') return data
对微测站数据进行预处理
preprocessed_micro_station_data = preprocess_data(micro_station_data)
对国测站数据进行预处理
preprocessed_national_station_data = preprocess_data(national_station_data)
Z-Score异常值检测
def detect_outliers(data): # 移除非数值型数据 numeric_data = data.select_dtypes(include=np.number) # 计算Z-Score z_scores = stats.zscore(numeric_data) # 设置阈值 threshold = 3 # 检测异常值 outliers = [] for i, row in enumerate(z_scores): for j, score in enumerate(row): if abs(score) > threshold: outliers.append((i, j))
return outliers对预处理后的微测站数据进行异常值检测
micro_station_outliers = detect_outliers(preprocessed_micro_station_data)
归一化
def normalize_data(data): scaler = MinMaxScaler() columns_to_normalize = ['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压'] normalized_data = scaler.fit_transform(data[columns_to_normalize]) # 将归一化后的数据与原数据进行合并 data[columns_to_normalize] = normalized_data return data
标准化
def standardize_data(data): scaler = StandardScaler() columns_to_standardize = ['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压'] standardized_data = scaler.fit_transform(data[columns_to_standardize]) # 将标准化后的数据与原数据进行合并 data[columns_to_standardize] = standardized_data return data
对预处理后的微测站数据进行归一化
normalized_micro_station_data = normalize_data(preprocessed_micro_station_data)
对预处理后的国测站数据进行标准化
standardized_national_station_data = standardize_data(preprocessed_national_station_data) import numpy as np from sklearn.metrics import mean_squared_error
定义校准模型
class CalibrationModel: def init(self, num_coefficients): self.num_coefficients = 13 self.coefficients = np.random.rand(num_coefficients) # 初始化校准系数
def calibrate_data(self, data): calibrated_data = data * self.coefficients # 校准微测站数据 return calibrated_data def evaluate(self, data1, data2): calibrated_data = self.calibrate_data(data1) mse = mean_squared_error(calibrated_data, data2) # 均方误差作为评估指标 return mse遗传算法
def genetic_algorithm(data1, data2, num_coefficients, population_size, num_generations): population = []
# 初始化种群 for _ in range(population_size): model = CalibrationModel(num_coefficients) population.append(model) # 迭代演化 for _ in range(num_generations): # 选择操作,选择适应度最高的个体 population.sort(key=lambda x: x.evaluate(data1, data2)) survivors = population[:population_size // 2] # 交叉操作,生成新个体 offspring = [] for i in range(population_size // 2): parent1 = np.random.choice(survivors) parent2 = np.random.choice(survivors) child = CalibrationModel(num_coefficients) child.coefficients = (parent1.coefficients + parent2.coefficients) / 2 offspring.append(child) # 变异操作,引入新的基因变体 for i in range(population_size // 2): model = np.random.choice(offspring) model.coefficients += np.random.normal(0, 0.1, num_coefficients) # 更新种群 population = survivors + offspring # 选择适应度最高的个体作为最终模型 population.sort(key=lambda x: x.evaluate(data1, data2)) best_model = population[0] return best_model粒子群算法
def particle_swarm_algorithm(data1, data2, num_coefficients, num_particles, num_iterations): particles = [] best_global_position = np.random.rand(num_coefficients) best_global_mse = float('inf')
# 初始化粒子群 for _ in range(num_particles): model = CalibrationModel(num_coefficients) particles.append(model) # 迭代更新 for _ in range(num_iterations): for particle in particles: mse = particle.evaluate(data1, data2) if mse < best_global_mse: best_global_mse = mse best_global_position = particle.coefficients # 更新粒子位置和速度 particle_velocity = np.random.rand(num_coefficients) particle_position = particle.coefficients + particle_velocity particle.coefficients = particle_position # 创建全局最优模型 best_model = CalibrationModel(num_coefficients) best_model.coefficients = best_global_position return best_model蚁群算法
def ant_colony_algorithm(data1, data2, num_coefficients, num_ants, num_iterations): pheromone = np.random.rand(num_coefficients) best_global_position = np.random.rand(num_coefficients) best_global_mse = float('inf')
# 迭代搜索 for _ in range(num_iterations): for _ in range(num_ants): model = CalibrationModel(num_coefficients) mse = model.evaluate(data1, data2) if mse < best_global_mse: best_global_mse = mse best_global_position = model.coefficients # 更新信息素 pheromone = pheromone + (1 / best_global_mse) # 创建全局最优模型 best_model = CalibrationModel(num_coefficients) best_model.coefficients = best_global_position return best_model选择进化学习算法
def select_calibration_algorithm(algorithm, data1, data2, num_coefficients, num_individuals, num_generations): if algorithm == 'genetic_algorithm': return genetic_algorithm(data1, data2, num_coefficients, num_individuals, num_generations) elif algorithm == 'particle_swarm_algorithm': return particle_swarm_algorithm(data1, data2, num_coefficients, num_individuals, num_generations) elif algorithm == 'ant_colony_algorithm': return ant_colony_algorithm(data1, data2, num_coefficients, num_individuals, num_generations) else: raise ValueError(f'Invalid calibratio algorithm: {algorithm}')
# 使用进化学习算法对微测站数据进行校准 calibration_algorithm = 'particle_swarm_algorithm'# 设置选择的进化学习算法 num_coefficients = 13 # 校准系数个数等于微测站数据的列数 calibration_model = select_calibration_algorithm(calibration_algorithm, preprocessed_micro_station_data.values, preprocessed_national_station_data.values, num_coefficients, 50, 100) # 使用校准模型对微测站数据进行校准 calibrated_micro_station_data = calibration_model.calibrate_data(preprocessed_micro_station_data.values) # 进一步校正数据(根据非常规气态污染物交叉干扰和天气因素) def further_calibration(data1, data2, num_coefficients): # 计算校正系数 calibration_factors = data2.mean() / data1.mean() # 应用校正系数 calibrated_data = data1 * calibration_factors return calibrated_data # 对微测站数据进行进一步校正 further_calibrated_micro_station_data = pd.DataFrame(further_calibrated_micro_station_data, columns=['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压']) # 输出进一步校正后的微测站数据 further_calibrated_micro_station_data = pd.DataFrame(further_calibrated_micro_station_data, columns=preprocessed_micro_station_data.columns) further_calibrated_micro_station_data.to_excel('C:/Users/123/Desktop/further_calibrated_micro_station_data.xlsx', index = False) # 输出校准后的微测站数据 calibrated_micro_station_data = pd.DataFrame(calibrated_micro_station_data, columns=['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压']) calibrated_micro_station_data.to_excel('C:/Users/123/Desktop/calibrated_micro_station_data.xlsx', index=False)统计校准后微测站数据的均值和标准差
mean_values = further_calibrated_micro_station_data[['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压']].mean() std_values = further_calibrated_micro_station_data[['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压']].std()
可视化均值和标准差
mean_values.plot(kind='bar', title='Mean Values of Further Calibrated Data') plt.xlabel('Variables') plt.ylabel('Mean') plt.show()
std_values.plot(kind='bar', title='Standard Deviation of Further Calibrated Data') plt.xlabel('Variables') plt.ylabel('Standard Deviation') plt.show()
- Assistant
import pandas as pd from scipy import stats from sklearn.preprocessing import MinMaxScaler, StandardScaler import numpy as np from sklearn.metrics import mean_squared_error import matplotlib.pyplot as plt
读取微测站数据
micro_station_data = pd.read_excel(r'C:\Users\123\Desktop\micro_station_data.xlsx', skiprows=1)
读取国测站数据
national_station_data = pd.read_excel(r'C:\Users\123\Desktop\national_station_data.xls', skiprows=1)
数据预处理
def preprocess_data(data): # 将“时段”列转换为datetime格式 data['时段'] = pd.to_datetime(data['时段'], format ='%Y/%m/%d %H:%M:%S') # 对所有值为-99.0(E)和0.0(E)的数据进行空值处理 columns_to_replace = ['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压'] data.loc[:, columns_to_replace] = data.loc[:, columns_to_replace].replace([-99.0, 0.0], pd.NA) # 将非数字字符串替换为NaN值 data.loc[:, columns_to_replace] = data.loc[:, columns_to_replace].apply(pd.to_numeric, errors='coerce') # 使用各列的非空值均值替换空值 data = data.fillna(data.mean()) # 处理第一列数据 data['时段'] = data['时段'].dt.strftime('%Y-%m-%d %H:%M:%S') return data
对微测站数据进行预处理
preprocessed_micro_station_data = preprocess_data(micro_station_data)
对国测站数据进行预处理
preprocessed_national_station_data = preprocess_data(national_station_data)
Z-Score异常值检测
def detect_outliers(data): # 移除非数值型数据 numeric_data = data.select_dtypes(include=np.number) # 计算Z-Score z_scores = stats.zscore(numeric_data) # 设置阈值 threshold = 3 # 检测异常值 outliers = [] for i, row in enumerate(z_scores): for j, score in enumerate(row): if abs(score) > threshold: outliers.append((i, j))
return outliers对预处理后的微测站数据进行异常值检测
micro_station_outliers = detect_outliers(preprocessed_micro_station_data)
归一化
def normalize_data(data): scaler = MinMaxScaler() columns_to_normalize = ['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压'] normalized_data = scaler.fit_transform(data[columns_to_normalize]) # 将归一化后的数据与原数据进行合并 data[columns_to_normalize] = normalized_data return data
标准化
def standardize_data(data): scaler = StandardScaler() columns_to_standardize = ['SO2', 'CO(mg/m3)', 'NO2', 'O3-1H', 'PM10', 'PM2.5', 'NO', 'NOX', '湿度', '温度', '风速', '风向', '大气压'] standardized_data = scaler.fit_transform(data[columns_to_standardize]) # 将标准化后的数据与原数据进行合并 data[columns_to_standardize] = standardized_data return data
对预处理后的微测站数据进行归一化
normalized_micro_station_data = normalize_data(preprocessed_micro_station_data)
对预处理后的国测站数据进行标准化
standardized_national_station_data = standardize_data(preprocessed_national_station_data)
定义校准模型
class CalibrationModel: def init(self, num_coefficients): self.num_coefficients = num_coefficients self.coefficients = np.random.rand(num_coefficients) # 初始化校准系数
def calibrate_data(self, data): calibrated_data = data * self.coefficients # 校准微测站数据 return calibrated_data def evaluate(self, data1, data2): calibrated_data = self.calibrate_data(data1) mse = mean_squared_error(calibrated_data, data2) # 均方误差作为评估指标 return mse遗传算法
def genetic_algorithm(data1, data2, num_coefficients, population_size, num_generations): population = []
# 初始化种群 for _ in range(population_size): model = CalibrationModel(num_coefficients) population.append(model) # 迭代演化 for _ in range(num_generations): # 选择操作,选择适应度最高的个体 population.sort(key=lambda x: x.evaluate(data1, data2)) survivors = population[:population_size // 2] # 交叉操作,生成新个体 offspring = [] for i in range(population_size // 2): parent1 = np.random.choice(survivors) parent2 = np.random.choice(survivors) child = CalibrationModel(num_coefficients) child.coefficients = (parent1.coefficients + parent2.coefficients)