交通量数据仿真获取与可视化

最新推荐文章于 2025-04-01 23:29:41 发布

Cherry_csc

最新推荐文章于 2025-04-01 23:29:41 发布

阅读量1.2k

点赞数 1

文章标签： python 交通物流

本文链接：https://blog.csdn.net/Cherry_csc/article/details/134187399

版权

数据来源

使用SUMO仿真获取数据，设置信号灯，利用SUMO中randomTrips工具进行随机车流的生成。选取路网其中一个车道，通过E1,E2 detector获取不同时刻"meanSpeed (m/s)", “flow (#/hour)”, “meanHaltingDuration(s)”, “nVehEntered(#)”, "meanOccupancy(%)"数据。其数据的含义如下表所示：

name	definition
meanVehicleNumber(#vehicles)	The mean number of vehicles that were on the detector (averaged over the interval duration).
flow (#vehicles/hour)	The number of contributing vehicles extrapolated to an hour
meanSpeed (m/s)	The mean velocity over all collected data samples.
meanOccupancy (%)	The percentage (0-100%) of the detector’s place that was occupied by vehicles, summed up for each time step and averaged by the interval duration.
meanHaltingDuration (s)	The mean halting duration of vehicles that entered the area and are still inside or have left the area within the reported interval.

通过这些数据，可以获取包含路段密度(meanOccupancy), 交通流量(flow), 速度(meanSpeed), 旅行时间(meanSpeed), 路段内车辆累积总量(meanVehicleNumber), 平均等待时间(meanHaltingDuration)等数据。

具体代码：

设置时间(时间步长为1s，每50s采集一次数据)

t_start = 200
t_end = 20000
sample_interval = 50

获取E1 detector output 数据

AverageFlow = defaultdict(list)
tree = ET.parse("E1.output.xml")
root = tree.getroot()
for interval_elem in root.iter("interval"):
    lane_id = interval_elem.get("id")
    interval_end = float(interval_elem.get("end"))
    averageflow = interval_elem.get("flow")
    if interval_end >= t_start and interval_end < t_end:
        AverageFlow[lane_id].append(averageflow)

获取E2 detector output数据

meanHaltingDuration = defaultdict(list)
meanOccupancy = defaultdict(list)
meanVehicleNumber = defaultdict(list)
tree = ET.parse("E2.output.xml")
root = tree.getroot()
for interval_elem in root.iter("interval"):
    lane_id = interval_elem.get("id")
    interval_end = float(interval_elem.get("end"))
    waitingtime = interval_elem.get("meanHaltingDuration")
    density = interval_elem.get("meanOccupancy")
    vehicle_num = interval_elem.get("meanVehicleNumber")
    if interval_end >= t_start and interval_end < t_end:
        meanHaltingDuration[lane_id].append(waitingtime)
        meanOccupancy[lane_id].append(density)
        meanVehicleNumber[lane_id].append(vehicle_num)

将数据写入csv文件

epsilon = 0.001
for lane in lane_net.keys():
    filename = lane + '.csv'
    with open(filename, mode='w', newline='') as file:
        writer = csv.writer(file)
        writer.writerow([
            "Time(s)", "AverageSpeed(m/s)",
            "AverageFlow(#/hour)", "meanHaltingDuration(s)",
            "meanVehicleNumber(#)", "meanOccupancy(%)", "MeanTravelTime(s)"
        ])
        for i in range(len(time)):
            writer.writerow([
                time[i], AverageSpeed[lane][i], AverageFlow[lane][i],
                meanHaltingDuration[lane][i], meanVehicleNumber[lane][i],
                meanOccupancy[lane][i], lane_net[lane]['laneLength'] /
                (AverageSpeed[lane][i] + epsilon)
            ])

数据特征

在这里插入图片描述

最大时间为19950，共396个时间点的数据。6个特征。

数据处理与分析

分析不同数据随时间的变化、各个交通量数据的概率统计特征以及不同交通量的相关性。

Line charts

绘制不同交通量随时间变化的图。代码如下：

import matplotlib.pyplot as plt

# Function to create a line chart
def plot_line_chart(df, x, y, y_label, title):
    plt.figure(figsize=(14, 7))
    plt.plot(df[x], df[y], marker='o')
    plt.title(title)
    plt.xlabel(x)
    plt.ylabel(y_label)
    plt.grid(True)
    plt.show()

# Create line charts for Average Speed, Average Flow, and Mean Travel Time, mean Halting Duration, mean Vehicle Number, and mean Occupancy
plot_line_chart(traffic_data, 'Time(s)', 'AverageSpeed(m/s)', 'Speed (m/s)', 'Average Speed Over Time')
plot_line_chart(traffic_data, 'Time(s)', 'AverageFlow(#/hour)', 'Flow (#/hour)', 'Average Flow Over Time')
plot_line_chart(traffic_data, 'Time(s)', 'MeanTravelTime(s)', 'Travel Time (s)', 'Mean Travel Time Over Time')
plot_line_chart(traffic_data, 'Time(s)', 'meanHaltingDuration(s)', 'Halting Duration (s)', 'Mean Halting Duration Over Time')
plot_line_chart(traffic_data, 'Time(s)', 'meanVehicleNumber(#)', 'Vehicle Number (#)', 'Mean Vehicle Number Over Time')
plot_line_chart(traffic_data, 'Time(s)', 'meanOccupancy(%)', 'Occupancy (%)', 'Mean Occupancy Over Time')

可视化结果如下：

Boxplot

研究不同交通量数据的统计特征。选择箱线图绘制，从而更好地了解每个特征的数据分布、中位数、四分位数以及可能的异常值。绘制代码如下：

# Set up the matplotlib figure and axes, with 2 rows and 3 columns
fig, axes = plt.subplots(2, 3, figsize=(15, 10))

# Flatten the axes array for easy iteration
axes = axes.flatten()

# Plot colored boxplots for each feature in its own subplot
for i, feature in enumerate(traffic_data.columns[1:]):
    traffic_data.boxplot(feature, ax=axes[i], patch_artist=True,
                         boxprops=dict(facecolor='#99FF99'))
    axes[i].set_title(f'Boxplot of {feature}', fontsize=10)
    axes[i].set_xlabel('')
    axes[i].set_ylabel('')

# Adjust layout to prevent overlapping
plt.tight_layout()
plt.show()

可视化结果如下：

Correlation Heatmap

绘制相关性热力图，研究不同交通量之间的相关系数。代码如下：

import seaborn as sns
import pandas as pd
from matplotlib import rcParams

# Set the global font to be Times New Roman
rcParams['font.family'] = 'serif'
rcParams['font.serif'] = 'Times New Roman'
df = pd.read_csv('0-4_0.csv')

# Calculate the correlation matrix
correlation_matrix = df.corr()

# Plot the heatmap
plt.figure(figsize=(12, 8))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=".2f")
plt.title('Heatmap of Correlation Between Different Traffic Features', fontsize=20)
# plt.xticks(rotation=0)
plt.show()