智慧海洋建设-Task2 数据分析

查看缺失值：
print(f'There are {data_train.isnull().any().sum()} columns in train dataset with missing values.')

渔船轨迹可视化：

def visualize_three_traj():

    fig,axes = plt.subplots(nrows=3,ncols=3,figsize=(20,15))

    plt.subplots_adjust(wspace=0.2,hspace=0.2)

    # 对于每一个类别，随机选出刺网的三条轨迹进行可视化

    lables = ["ciwang","weiwang","tuowang"]

    for i,file_type in tqdm(enumerate(["ciwang_data","weiwang_data","tuowang_data"])):

        data1, data2, data3 = get_random_three_traj(type=file_type)

        for j, datax in enumerate([data1, data2, data3]):

            x_data = datax["x"].loc[-1:].values

            y_data = datax["y"].loc[-1:].values

            axes[i][j - 1].scatter(x_data[0], y_data[0], label="start", c="red", s=10, marker="8")

            axes[i][j - 1].plot(x_data, y_data, label=lables[i])

            axes[i][j - 1].scatter(x_data[len(x_data) - 1], y_data[len(y_data) - 1], label="end", c="green", s=10,

                                  marker="v")

            axes[i][j - 1].grid(alpha=2)

            axes[i][j - 1].legend(loc="best")

坐标序列可视化：

def visualize_one_traj_x_y():

    fig,axes = plt.subplots(nrows=2,ncols=1,figsize=(10,8))

    plt.subplots_adjust(wspace=0.5,hspace=0.5)

    data1 = get_random_one_traj(type="weiwang_data")

    x = data1["x"].loc[-1:]

    x = x / 10000

    y = data1["y"].loc[-1:]

    y = y / 10000

    arr1 = np.arange(len(x))

    arr2 = np.arange(len(y))

    axes[0].plot(arr1,x,label="x")

    axes[1].plot(arr2,y,label="y")

    axes[0].grid(alpha=3)

    axes[0].legend(loc="best")

    axes[1].grid(alpha=3)

    axes[1].legend(loc="best")

    plt.show()

渔船速度和方向可视化：

def visualize_three_traj_speed_direction():

    fig,axes = plt.subplots(nrows=3,ncols=2,figsize=(20,15))

    plt.subplots_adjust(wspace=0.3,hspace=0.3)

    # 随机选出刺网的三条轨迹进行可视化

    file_types = ["ciwang_data","weiwang_data","tuowang_data"]

    speed_types = ["ciwang_speed","weiwang_speed","tuowang_speed"]

    doirections = ["ciwang_direction","weiwang_direction","tuowang_direction"]

    colors = ['pink', 'lightblue', 'lightgreen']

    for i,file_name in tqdm(enumerate(file_types)):

        datax = get_random_one_traj(type=file_name)

        x_data = datax["速度"].loc[-1:].values

        y_data = datax["方向"].loc[-1:].values

        axes[i][0].plot(range(len(x_data)), x_data, label=speed_types[i], color=colors[i])

        axes[i][0].grid(alpha=2)

        axes[i][0].legend(loc="best")

        axes[i][1].plot(range(len(y_data)), y_data, label=doirections[i], color=colors[i])

        axes[i][1].grid(alpha=2)

        axes[i][1].legend(loc="best")

    plt.show()