import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from pathlib import Path

# ----------------------
# 配置参数
# ----------------------
RAW_DATA_PATH = Path(r'H:\尽调项目\和展清云洛阳项目\6#\6 处理后.xlsx')


RESULT_TABLE_PATH = Path(r'H:\尽调项目\和展清云洛阳项目\6#\6风速区间功率均值表.xlsx')
RESULT_PLOT_PATH = Path(r'H:\尽调项目\和展清云洛阳项目\6#\6风速功率曲线.png')
RATED_POWER = 6700  # 额定功率
RATED_WIND_SPEED = 18 # 额定风速
POWER_STEP = 5
WIND_SPEED_STEP = 0.5  # 风速区间步长
WIND_SPEED_CHANGE_THRESHOLD = 1
#TIME_THRESHOLD = pd.Timedelta(hours=2)
IQR_MULTIPLIER = 1.5
MIN_DATA_COUNT = 3

def load_data(file_path):
    try:
        if not file_path.exists():
            raise FileNotFoundError(f"文件不存在: {file_path}")
        data = pd.read_excel(file_path, engine='openpyxl')
        print(f"成功读取数据，共{len(data)}条记录")
        return data
    except Exception as e:
        print(f"数据读取错误: {str(e)}")
        return None


def clean_scada_data(raw_data):
    if raw_data is None or raw_data.empty:
        print("无数据可清洗")
        return None

    data = raw_data.copy()

# ----------------------
# 区间功率均值计算与可视化（核心修改部分）
# ----------------------
def calculate_interval_power_mean(raw_data, wind_speed_step=0.5):
    """按风速区间计算功率平均值，区间采用左开右闭形式 (start, end]"""
    if raw_data is None or raw_data.empty:
        print("无清洗后的数据可计算均值")
        return None

    # 确定风速区间范围
    wind_min = 1 - wind_speed_step*0.5
    wind_max = 25 + wind_speed_step*0.5
    # 生成区间起点
    wind_intervals = np.arange(wind_min, wind_max, wind_speed_step)

    # 计算每个区间的平均功率（核心修改：使用左开右闭区间 (start, end]）
    result = []
    for interval_start in wind_intervals:
        interval_end = interval_start + wind_speed_step
        # 关键修改：左边界>，右边界≤
        mask = (raw_data['平均风速'] > interval_start) & (raw_data['平均风速'] <= interval_end)
        interval_data = raw_data[mask]





        if  not interval_data.empty:
            wind_mid = (interval_start + interval_end) / 2  # 区间中点
            power_mean = interval_data['平均有功功率'].mean()
            result.append({
                '风速区间起点': interval_start,
                '风速区间终点': interval_end,
                '风速': wind_mid,
                '实际功率': power_mean,
                '区间数据量': len(interval_data),
            })

    # 转换为DataFrame并按风速排序
    result_df = pd.DataFrame(result).sort_values('风速').reset_index(drop=True)
    print(f"已计算{len(result_df)}个风速区间的功率平均值（左开右闭区间）")
    return result_df


def plot_power_curve(result_df, rated_power, rated_wind_speed, save_path):
    """绘制风速-功率曲线并保存图片"""
    if result_df is None or result_df.empty:
        print("无数据可绘制曲线")
        return False

    plt.style.use('seaborn-v0_8-talk')
    fig, ax = plt.subplots(figsize=(12, 6))

    # 绘制功率曲线
    ax.plot(result_df['风速'], result_df['实际功率'],
            color='#2c7fb8', linewidth=2.5, marker='o', markersize=5,
            label='实际功率曲线')

    # 绘制额定功率参考线
    ax.axhline(y=rated_power, color='#e41a1c', linestyle='--', linewidth=1.5,
               label=f'额定功率 ({rated_power}kW)')

    # 绘制额定风速参考线
    ax.axvline(x=rated_wind_speed, color='#4daf4a', linestyle='-.', linewidth=1.5,
               label=f'额定风速 ({rated_wind_speed}m/s)')

    # 设置坐标轴标签和标题
    ax.set_xlabel('风速 (m/s)', fontsize=12)
    ax.set_ylabel('功率 (kW)', fontsize=12)
    ax.set_title('风速-功率曲线（左开右闭区间平均值）', fontsize=14, pad=20)

    # 添加网格和图例
    ax.grid(alpha=0.3)
    ax.legend(fontsize=10)

    # 调整布局并保存
    plt.tight_layout()
    plt.savefig(save_path, dpi=300, bbox_inches='tight')
    plt.close()
    print(f"功率曲线已保存至 {save_path}")
    return True


# ----------------------
# 主程序执行
# ----------------------
if __name__ == "__main__":
    # 1. 读取并清洗数据
    raw_data = load_data(RAW_DATA_PATH)


    # 2. 计算风速区间功率平均值（左开右闭区间）
    interval_power_df = calculate_interval_power_mean(raw_data, wind_speed_step=WIND_SPEED_STEP)

    # 3. 保存结果表格
    if interval_power_df is not None:
        try:
            RESULT_TABLE_PATH.parent.mkdir(parents=True, exist_ok=True)
            interval_power_df.to_excel(RESULT_TABLE_PATH, index=False)
            print(f"风速区间功率均值表已保存至 {RESULT_TABLE_PATH}")
        except Exception as e:
            print(f"保存表格失败：{str(e)}")

    # 4. 绘制并保存功率曲线图片
    if interval_power_df is not None:
        plot_power_curve(interval_power_df, RATED_POWER, RATED_WIND_SPEED, RESULT_PLOT_PATH)