python从txt文件读取数据

def loadData(filename,split,trainingSet=[],testSet=[]):
    with open(filename,'r') as file:
        lines = file.readlines()
        dataset = [[] for i in range(len(lines)-1)]
        for i in range(len(dataset)):
            dataset[i][:] = (item for item in lines[i].strip().split(','))   # 逐行读取数据
        print("dateset:",dataset)
        for x in range(len(dataset)):
            for y in range(len(dataset[0])-1):
                dataset[x][y] = float(dataset[x][y])          # 将除最后一列的数据转化为浮点型
            if random.random() < split:                # 将数据集进行划分
                trainingSet.append(dataset[x])
            else:
                testSet.append(dataset[x])
    print("trainingSet",len(trainingSet))
    print("testset",len(testSet))

loadData('irisdata.txt',0.8)

2、提取csv文件中的数据，把特征值转化为：特征名称：特征值 的字典格式，用于调用sklearn库。

转换结果如图：

with open("AllElectronics.csv", 'r') as file:
    data_lines = file.readlines()
    data = [[] for i in data_lines]
    for i in range(len(data_lines)):
        data[i][:] = (item for item in data_lines[i].strip().split(","))

headers = []
featureList = []
labelList = []
for i in data[0]:
    headers.append(i)  # 提取第一行类别名称
del(data[0])

for row in data:
    labelList.append(row[-1])
    rowDict = {}
    for i in range(1,len(row)-1):    # 把每一行转换成一个字典，便于直接利用sklearn直接提供的库函数
        rowDict[headers[i]] = row[i]
    featureList.append(rowDict)
print(labelList)
print(featureList)