读取Kaggle下载的数据集(数据的读取 f’{path}\\CMaps\\train_FD001.txt’)
import pandas as pd
假设用户已经定义了列名,或者从文档中获取
例如,对于train_FD001.txt,有26列,列名如下(根据实际情况调整):
col_names = [‘unit_number’, ‘time_in_cycles’,
‘op_setting_1’, ‘op_setting_2’, ‘op_setting_3’] +
[f’sensor_measurement_{i}’ for i in range(1, 22)]
用户指定的路径
path = ‘D:/MyPytorch_study/nasa-engine-database/CMaps’ # 这里用用户指定的路径
假设要读取的文件是train_FD001.txt
file_path = f’{path}\CMaps\train_FD001.txt’
读取数据
train = pd.read_csv(file_path, sep=‘\s+’, header=None, names=col_names)
查看前5行
print(train.head())