python学习7

# -*- coding: utf-8 -*-
# @Time : 2024/3/9 16:30
# @Author : wangz
# @File : jason_read_and_make.py
from openpyxl import load_workbook

import csv
import numpy as np
import csv
import json
import pandas as pd

# -*- coding: gbk -*-
import sklearn.metrics


def csv_to_json(file_path, json_filepath):
    # 打开CSV文件

    data = []
    # with open(file_path, mode='r', newline='', encoding='utf-8') as csv_file:
    with open(file_path, mode='r', encoding='utf-8') as csv_file:
        # 创建CSV读取器
        csv_reader = csv.reader(csv_file)

        # 读取CSV文件的表头（如果有的话）
        headers = next(csv_reader)
        print(headers)
        for row in csv_reader:
            # 如果表头存在，则使用表头作为字典的键，否则使用列的索引
            if headers:
                # print(zip(headers, row))
                row_dict = {header: value for header, value in zip(headers, row)}
                # print(row_dict)


            else:
                # print(zip(headers, row))
                row_dict = {f'column_{i}': value for i, value in enumerate(row)}
                # 读取数据并存储到列表中
                # 将行数据添加到列表中
            data.append(row_dict)
            # 将列表转换为JSON格式并写入到新的JSON文件中
        # with open(json_filepath, mode='w', encoding='utf-8') as json_file:
        #     json.dump(data, json_file, ensure_ascii=False, indent=4)

    # return data


def pandas_read(file_path):
    CSVFILE = pd.read_csv(file_path, encoding='utf-8')
    print(CSVFILE)


def csv_to_txt(input_csv, output_txt):
    with open(input_csv, 'r', newline='', encoding='utf-8') as csvfile:
        reader = csv.reader(csvfile)

        # 打开TXT文件以写入
        with open(output_txt, 'w', encoding='utf-8') as txtfile:
            # 遍历CSV文件的每一行
            for row in reader:
                # 如果行不为空，则获取第一列的值并写入TXT文件
                if row:
                    print(row)
                    first_column_value = row[0]
                    txtfile.write(first_column_value + '\n')


def csv_to_csv(input_csv, output_csv):
    import csv

    # 定义输入和输出文件的路径

    # 打开输入CSV文件以读取
    with open(input_csv, 'r', newline='', encoding='utf-8') as infile:
        reader = csv.reader(infile)

        # 打开输出CSV文件以写入
        with open(output_csv, 'w', newline='', encoding='utf-8') as outfile:
            writer = csv.writer(outfile)

            # 遍历CSV文件的每一行，直到读取到前2000行或文件结束
            for i, row in enumerate(reader):
                # i = i + 200
                if i >= 3000:
                    break  # 如果已经读取了2000行，就跳出循环

                # print(row[1])

                # 获取第一列的值
                first_column_value = row[0]

                # 将第一列的值写入新的CSV文件
                writer.writerow(row)

    print("First 2000 values from the first column have been saved to", output_csv)


def is_row_empty(row):
    # 检查行中的每个元素，如果所有元素都是空字符串或None，则返回True
    return all(not x.strip() for x in row)


def is_cell_empty(cell):
    # 检查单元格是否为空字符串或None
    return cell is None or (isinstance(cell, str) and not cell.strip())


def check_empty_rows_in_csv(file_path):
    with open(file_path, 'r', newline='', encoding='utf-8') as csvfile:

        reader = csv.reader(csvfile)
        rows = list(reader)
        lengthrow = len(rows)
        lengthcolumn = len(rows[0])
        # print(lengthrow)
        # print(lengthcolumn)
        # print(str(63) + '  ' + rows[63][1])

        # lengthcolumn = len(rows[0])
        for i in range(lengthrow):
            # print(i)
            for j in range(lengthcolumn - 1):
                np.isnan(rows[i][j])
                print(i)
                print('yes')
        if rows == None:
            print(str(i) + 'no')

        # print(rows[1][0])


def ps_csv(file_path):
    aa = pd.read_csv(file_path)


# csv_filepath = r'C:\Users\wangz\Desktop\train.csv'  # 替换为你的CSV文件路径
csv_filepath = r'C:\Users\wangz\Desktop\train.csv'  # 替换为你的CSV文件路径
json_filepath = r'C:\Users\wangz\Desktop\train.json'  # 输出的JSON文件路径
# csv_to_json(csv_filepath, json_filepath)
# pandas_read(csv_filepath)


input_csv = r'C:\Users\wangz\Downloads\JDtest-100.csv'
output_txt = r'C:\Users\wangz\Downloads\JDtest.txt'
csv_to_txt(input_csv, output_txt)

# input_csv = r'C:\Users\wangz\Downloads\JDtrain.csv'
# output_csv = r'C:\Users\wangz\Downloads\JDtest-100.csv'
# csv_to_csv(input_csv, output_csv)

# 运行检查函数

# check_empty_rows_in_csv(output_csv)