import matplotlib

from utils.file.trans_methods import create_file_path

matplotlib.use('Agg')
matplotlib.rcParams['font.family'] = 'SimHei'
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
matplotlib.rcParams['axes.unicode_minus'] = False
from matplotlib import pyplot as plt


def scatter(title, x_label, y_label, x_values, y_values, color=None, col_map=dict(), size=10,
            save_file_path=''):
    if save_file_path:
        create_file_path(save_file_path, True)
    else:
        save_file_path = title + '.png'

    plt.figure(figsize=(8, 6))
    plt.title(title, fontsize=16)
    plt.xlabel(x_label, fontsize=14)
    plt.ylabel(y_label, fontsize=14)
    if color is not None:
        plt.scatter(x_values, y_values, s=size, c=color)
        if col_map:
            patches = [plt.Rectangle((0, 0), 1, 1, fc=c) for c in col_map.values()]
            plt.legend(patches, list(col_map.keys()))
    else:
        plt.scatter(x_values, y_values, s=size)

    plt.savefig(save_file_path)
    plt.close()


if __name__ == '__main__':
    import pandas as pd
    import numpy as np
    from matplotlib import pyplot as plt

    df = pd.read_csv(r"/home/wzl/test_data/2024_10_17_14_54_46_200k_Root.csv")
    df.reset_index(inplace=True, drop=True)
    df.columns = ['data']

    # Calculate the moving average with a window of 3 (1 before, 1 after)
    window_size = 20
    moving_avg = df['data'].rolling(window=window_size).mean()
    df['moving_avg'] = moving_avg
    # Calculate the percentage difference
    percentage_diff = abs((df['data'] - moving_avg) / moving_avg) * 100
    df['percentage_diff'] = percentage_diff
    # Flag values that differ by more than threshold
    threshold = 3
    df['is_anomaly'] = percentage_diff < threshold

    avg = df['data'].mean()
    df['avg']=df['data'] > avg


    difference_ratio = df.iloc[window_size:]
    difference_ratio.reset_index(inplace=True)
    # 创建图形和轴对象
    plt.figure(figsize=(10, 6))
    colors = np.where((difference_ratio['is_anomaly'] == True) & (difference_ratio['avg'] == True), 'r', np.where((difference_ratio['is_anomaly'] == False) & (difference_ratio['avg'] == False), 'g', 'b'))

    datas = difference_ratio['data'].values
    # for i in range(len(datas)):
    #     plt.plot(i, datas[i], marker='o', color=colors[i])

    plt.figure(figsize=(10, 6))
    plt.scatter([i for i in range(len(datas))], datas,  c=colors)

    # 添加标题和标签
    plt.title('Difference Ratio of Each Data Point to Its Previous 10 Data Points Mean')
    plt.xlabel('Index')
    plt.ylabel('Difference Ratio')

    # 显示网格
    plt.grid(True)

    # 显示图形
    plt.show()