简单的python格网算法算数据密集度demo

# 格网算法计算数据集区域数据密集度
import time
import random
import numpy as np
import pandas as pd

# 模拟数据集
def create_data():
    data_x = []
    data_y = []
    data = []
    for i in range(300000):
        x = random.randrange(0, 300000)
        y = random.randrange(-1500, 1500)
        data_x.append(x)
        data_y.append(y)
        data.append([x, y])
    return data_x, data_y, data

# 计算网格数据密集度
def calculate_density(gridSize, bounds):
    data_x, data_y, data = create_data()

    # 计算网格边界
    x = np.arange(bounds[0][0],
                  bounds[1][0] + gridSize,
                  gridSize)
    y = np.arange(bounds[0][1],
                  bounds[1][1] + gridSize,
                  gridSize)

    # 使用pandas构建网格
    grid = pd.DataFrame(0, index=x[:-1], columns=y[:-1])

    # 将数据分配到网格中
    for point in data:
        if point[0] < bounds[0][0] \
            or point[0] > bounds[1][0] \
            or point[1] < bounds[0][1] \
            or point[1] > bounds[1][1]:
            continue

        # 计算数据在那个网格内
        x_index = int((point[0] - bounds[0][0]) // gridSize)
        y_index = int((point[1] - bounds[0][1]) // gridSize)

        # 将网格计数 +1
        grid.iloc[x_index, y_index] += 1

    # 计算每个网格的密度
    densities = grid.to_numpy() / (gridSize * gridSize)

    # 将密度添加到数据中
    for point in data:
        if point[0] < bounds[0][0] \
            or point[0] > bounds[1][0] \
            or point[1] < bounds[0][1] \
            or point[1] > bounds[1][1]:
            continue

        # 计算数据在那个网格内
        x_index = int((point[0] - bounds[0][0]) // gridSize)
        y_index = int((point[1] - bounds[0][1]) // gridSize)

        point.append(densities[x_index, y_index])

    return densities, data

if __name__ == "__main__":
    start_time = time.time()
    densities, data = calculate_density(100,
                                  [[0, -1500], [300000, 1500]])
    end_time = time.time()
    print("消耗的时间:", end_time - start_time)
    print(densities)