init docs

docs/大于4行时保留数据.py

@@ -0,0 +1,226 @@
+import sys
+print("Python 解释器路径:", sys.executable)
+print("已安装的包路径:", sys.path)
+import data
+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'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01 原始数据.xlsx')
+CLEANED_DATA_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01cleaned_scada_data.xlsx')
+#中间保存路径
+AFTER_LIMIT_POWER_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01after_limit_power_cleaning.xlsx')
+AFTER_TIP_SPEED_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01after_tip_speed_cleaning.xlsx')
+AFTER_SPEED_POWER_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01after_speed_power_cleaning.xlsx')
+RESULT_TABLE_PATH = Path(r'F:\风速区间功率均值表.xlsx')
+RESULT_PLOT_PATH = Path(r'F:\风速功率曲线.png')
+RATED_POWER = 4800  # 额定功率
+RATED_WIND_SPEED = 18# 额定风速
+POWER_STEP = 5
+WIND_SPEED_STEP = 0.25  # 风速区间步长
+WIND_SPEED_CHANGE_THRESHOLD = 1
+#TIME_THRESHOLD = pd.Timedelta(hours=2)
+IQR_MULTIPLIER1 = 1.8
+IQR_MULTIPLIER2 = 2
+MINIMUM_GENERATOR_SPEED = 1
+K = 0.9  # k值：删除小于k倍最小发电机转速的点
+
+
+# ----------------------
+# 工具函数：定义保存数据
+def save_intermediate_data(data,file_path,step_name):
+    """保存中间数据的专用函数，仅做保存"""
+    try:
+        if data.empty:
+            print(f"⚠️{step_name}为空，不保存")
+            return
+        #创建目录（如果不存在）
+        file_path.parent.mkdir(parents=True, exist_ok=True)
+        #保存数据
+        data.to_excel(file_path, index=False,engine='openpyxl')
+        print(f"✅ {step_name}已保存（{len(data)}条）至：{file_path}")
+    except Exception as e:
+        print(f"❌ 保存{step_name}失败：{str(e)}")
+
+# ----------------------
+# 数据清洗函数
+# ----------------------
+
+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()
+
+    # 1. 基础过滤：删除停机数据
+    initial_count = len(data)
+    data = data[data['平均有功功率'] > 0].copy()
+
+    #1.5 删除小于最小发电机转速的点
+    if not data.empty and '平均发电机转速' in data.columns:
+        # 计算阈值：k倍最小发电机转速
+        speed_threshold = K * MINIMUM_GENERATOR_SPEED
+        # 过滤数据
+        data = data[data['平均发电机转速'] >= speed_threshold].copy()
+        removed_count = initial_count - len(data)
+        print(f"发电机转速过滤后保留 {len(data)} 条数据（移除{removed_count}条低转速数据，阈值: {speed_threshold:.2f}）")
+        initial_count = len(data)
+
+    # 2. 时间列处理
+    if '时间' not in data.columns:
+        print("警告：数据中未找到'时间'列，无法进行限功率点识别")
+        return data
+
+    data['时间'] = pd.to_datetime(data['时间'], errors='coerce')
+    time_invalid_count = data['时间'].isna().sum()
+    data = data.dropna(subset=['时间'])
+    print(f"时间处理后保留 {len(data)} 条数据（移除{time_invalid_count}条无效时间数据）")
+
+    # 3. 识别并移除限功率点
+
+    if not data.empty:
+        min_power = data['平均有功功率'].min()
+        power_intervals = np.arange(min_power, RATED_POWER, POWER_STEP)
+        limit_power_points = []
+
+        for interval in power_intervals:
+            mask = (data['平均有功功率'] >= interval) & (data['平均有功功率'] < interval + POWER_STEP)
+            interval_data = data[mask]
+            if interval_data.empty:
+                continue
+
+            grouped = interval_data.groupby(interval_data['时间'].dt.date)
+            for date, group in grouped:
+                group_sorted = group.sort_values('时间')
+                wind_speed_range = group_sorted['平均风速'].max()-group_sorted['平均风速'].min()
+                if wind_speed_range > WIND_SPEED_CHANGE_THRESHOLD:
+                    limit_power_points.extend(group_sorted.index)
+
+        data = data.drop(limit_power_points,errors='ignore')
+        print(f"限功率识别后保留{len(data)}条数据(移除{len(limit_power_points)}条限功率数据)")
+        save_intermediate_data(data,AFTER_LIMIT_POWER_PATH,"限功率清洗后的数据")
+
+
+
+    # 4. 计算并清洗叶尖速比
+    if not data.empty and '平均风速' in data.columns :
+        data = data[data['平均风速'] > 0].copy()
+        print(f"移除风速为0的数据后保留 {len(data)} 条数据")
+
+        data['叶尖速比'] =data['平均发电机转速']*3.14*162*78*30/data['平均风速']
+        #data['叶尖速比']= data['叶轮转速']*100/data['平均风速']
+
+        if not data.empty:
+            wind_speed_min = data['平均风速'].min()
+            wind_speed_max = data['平均风速'].max()
+            wind_speed_intervals = np.arange(wind_speed_min, wind_speed_max, WIND_SPEED_STEP)
+            cleaned_data_list = []
+
+            for interval in wind_speed_intervals:
+                mask = (data['平均风速'] >= interval) & (data['平均风速'] < interval + WIND_SPEED_STEP)
+                interval_data = data[mask]
+
+                if len(interval_data) >= 4:
+                    q1 = interval_data['叶尖速比'].quantile(0.25)
+                    q3 = interval_data['叶尖速比'].quantile(0.75)
+                    iqr = q3 - q1
+                    lower = q1 - IQR_MULTIPLIER1 * iqr
+                    upper = q3 + IQR_MULTIPLIER2 * iqr
+                    interval_cleaned = interval_data[(interval_data['叶尖速比'] >= lower) &
+                                                     (interval_data['叶尖速比'] <= upper)]
+
+                else:
+                    interval_cleaned = interval_data
+
+                cleaned_data_list.append(interval_cleaned)
+
+        data = pd.concat(cleaned_data_list)
+        print(f"叶尖速比清洗后保留 {len(data)} 条数据")
+        save_intermediate_data(data,AFTER_TIP_SPEED_PATH,"叶尖速比清洗后的数据")
+
+    # 5. 风速-功率关系清洗
+    if not data.empty and '平均风速' in data.columns and '平均有功功率' in data.columns:
+        wind_speed_min = data['平均风速'].min()
+        wind_speed_max = data['平均风速'].max()
+        wind_speed_intervals = np.arange(wind_speed_min, wind_speed_max, WIND_SPEED_STEP)
+        final_cleaned_list = []
+
+        for interval in wind_speed_intervals:
+            mask = (data['平均风速'] >= interval) & (data['平均风速'] < interval + WIND_SPEED_STEP)
+            interval_data = data[mask]
+
+            if len(interval_data) >= 4:
+                q1 = interval_data['平均有功功率'].quantile(0.25)
+                q3 = interval_data['平均有功功率'].quantile(0.75)
+                iqr = q3 - q1
+                lower_limit = q1 - IQR_MULTIPLIER1 * iqr
+                upper_limit = q3 + IQR_MULTIPLIER2 * iqr
+
+                interval_cleaned = interval_data[(interval_data['平均有功功率'] >= lower_limit) &
+                                                 (interval_data['平均有功功率'] <= upper_limit)]
+            else:
+                interval_cleaned = interval_data
+            final_cleaned_list.append(interval_cleaned)
+
+        data = pd.concat(final_cleaned_list)
+        print(f"风速-功率清洗后保留 {len(data)} 条数据")
+        save_intermediate_data(data, AFTER_SPEED_POWER_PATH, "风速功率清洗后的数据")
+
+    # 6. 高风速区二次过滤
+    #if not data.empty and '平均风速' in data.columns:
+        #high_wind_mask = data['平均风速'] >= RATED_WIND_SPEED
+        #high_wind_data = data[high_wind_mask]
+
+        #if len(high_wind_data) > 0:
+            #robust_mean = high_wind_data['平均有功功率'].median()
+            #high_wind_filtered = high_wind_data[
+                #(high_wind_data['平均有功功率'] >= robust_mean * 0.98) &
+                #(high_wind_data['平均有功功率'] <= robust_mean * 1.02)
+                #]
+
+            #low_wind_data = data[~high_wind_mask]
+            #data = pd.concat([low_wind_data, high_wind_filtered])
+            #print(f"高风速区二次过滤后保留 {len(data)} 条数据")
+    return data
+
+
+# ----------------------
+# 主程序：执行数据清洗并保存结果
+# ----------------------
+if __name__ == "__main__":
+    # 加载原始数据
+    raw_data = load_data(RAW_DATA_PATH)
+
+    # 清洗数据
+    cleaned_data = clean_scada_data(raw_data)
+
+    # 保存清洗后的数据到指定路径
+    if cleaned_data is not None and not cleaned_data.empty:
+        try:
+            # 创建保存目录（如果不存在）
+            CLEANED_DATA_PATH.parent.mkdir(parents=True, exist_ok=True)
+
+            # 保存为Excel文件
+            cleaned_data.to_excel(CLEANED_DATA_PATH, index=False, engine='openpyxl')
+            print(f"清洗后的数据已成功保存到: {CLEANED_DATA_PATH}")
+        except Exception as e:
+            print(f"保存数据时出错: {str(e)}")
+    else:
+        print("没有可保存的清洗后数据")

docs/清洗完后直接生成功率曲线.py

@@ -0,0 +1,148 @@
+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)
+