Python基础笔记（2）

import numpy as np
import csv


# 引入使用的文件


def get_alldata(filename):
    # 读取数据文件，获取列的标识，并将其与实验需要的标识进行比对，
    # 从而将数据文件中所需要使用的列的数据提取出来，为之后的处理做铺垫。
    with open(filename, 'r') as csv_file:
        col_name_all = csv_file.readline()[:-1]
        colname_str = "Clothing ID,Recommended IND,Positive Feedback Count,Class Name"
        col_name_all = col_name_all.split(",")
        colname_lst = colname_str.split(",")

        colindex_lst = []
        for i in col_name_all:
            if i in colname_lst:
                colindex_lst.append(col_name_all.index(i))

        dataset = []
        dataset1 = csv.reader(csv_file)
        for row in dataset1:
            adata = list(row[i] for i in colindex_lst)
            dataset.append(adata)
        print(dataset)
        return np.array(dataset)


def get_id_count_arr(dataset):
    # 通过将每行数据通过键值对存储