| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748 |
- import copy
- import datetime
- import pandas as pd
- read_path = r'D:\data\长清\故障记录_20230420_20240419.csv'
- df = pd.read_csv(read_path, encoding='gb18030')
- df['风机名'] = df['风机名'].apply(lambda wind_name: 'A' + wind_name.replace('号风机', '').zfill(2))
- df = df[~df['状态码描述'].isin(['高偏航误差穿越', '手动偏航'])]
- df['激活时间'] = pd.to_datetime(df['激活时间'].apply(lambda x: x[0:x.rfind(":")]), errors='coerce')
- df['复位时间'] = pd.to_datetime(df['复位时间'].apply(lambda x: x[0:x.rfind(":")]), errors='coerce')
- df.dropna(subset=['激活时间', '复位时间'], inplace=True)
- def generate_next_10_min(dt):
- minute = dt.minute
- chazhi = 10 - int(minute % 10)
- now = dt + datetime.timedelta(minutes=chazhi)
- now = now.replace(second=0, microsecond=0)
- return now
- df['begin_time'] = df['激活时间'].apply(generate_next_10_min)
- df['end_time'] = df['复位时间'].apply(generate_next_10_min)
- df['chazhi_count'] = ((df['end_time'] - df['begin_time']).dt.seconds) // 600 + 1
- result_df = df[df['chazhi_count'] == 1]
- datas = [[]]
- for index, row in df[df['chazhi_count'] > 1].iterrows():
- for i in range(row['chazhi_count']):
- data = copy.deepcopy(row.values)
- data[6] = data[6] + datetime.timedelta(minutes=10 * i)
- datas.append(data)
- now_df = pd.DataFrame(datas, columns=df.columns)
- result_df = pd.concat([result_df, now_df])
- result_df.reset_index(inplace=True, drop=True)
- result_df.sort_values(by=['风机名', '激活时间', 'begin_time'], inplace=True)
- result_df.to_csv("故障记录.csv", encoding='utf8')
|
