Question

我必须使用pandas

比较Python中的两个CSV文件

有两个CSV文件包含不同形式的产品代码第一种方式： -

LYSB00LW3ZL3K-ELECTRNCS
LYSB00LW3ZL3K-ELECTRNCS- Standard Packaging- W20 - Dual Driver
LYSB01KH2MDPU-ELECTRNCS
LYSB01KH2MDPU-ELECTRNCS- Small Bangle
LYSB01KH2MDPU-ELECTRNCS- Large Bangle
LYSB06XXD7NYY-ELECTRNCS- Large
LYSB06XXD7NYY-ELECTRNCS- Small
LYSB01KM4T0PO-ELECTRNCS

第二种方式： - （如果您删除上述产品代码的LYS以及之后的所有内容 - 第二种形式存在）

B00LW3ZL3K
B01KH2MDPU

所以我必须比较两个文件，并将第一列作为产品代码制作新的csv文件，将第二列作为状态

结果应该以2种不同的情况提供输出

1）如果第二个文件中存在B00LW3ZL3K（产品代码），则应从第一个文件返回所有所属产品代码，并将其状态显示为“库存产品”

2）如果第二个文件中不存在B01KM4T0PO（产品代码），则应从第一个文件中返回所有所属产品代码，并将其状态显示为“产品缺货”

Output:
In-Stock
    LYSB00LW3ZL3K-ELECTRNCS
    LYSB00LW3ZL3K-ELECTRNCS- Standard Packaging- W20 - Dual Driver
    LYSB01KH2MDPU-ELECTRNCS
    LYSB01KH2MDPU-ELECTRNCS- Small Bangle
    LYSB01KH2MDPU-ELECTRNCS- Large Bangle

Out-of-Stock
   LYSB06XXD7NYY-ELECTRNCS- Large
   LYSB06XXD7NYY-ELECTRNCS- Small
   LYSB01KM4T0PO-ELECTRNCS

Answer 1

- 这是我解决这个问题的方法

import pandas as pd
import datetime
import os


class Update(object):
    def __init__(self, category):
        """Path to file"""
        masterfile = os.path.realpath('lys_masterfile.txt')
        update_file = os.path.realpath('Outputs/liveyoursport/Update_Spider/{}_Update.csv'.format(category))
        self.comparision(masterfile, update_file, category)

    def comparision(self, output_file, update_file, category):
        ''' Function to extract correct data by category '''
        sku_dict = {
            'Electronics': 'ELECTRNCS',
            'Sports Equipment': 'SPRTSEQIP',
            'Health and Beauty': 'HLTHBTY',
            "Women's Fashion Accessories": 'WMNFSHACCSS',
            'Toys and Games': 'TOYS',
            "Men's Fashion Shoes": 'MNFSHSHOE',
            "Other Sports Shoes": 'OTHSPRTSSHOE',
            "Women's Sports Shoes": 'WMNSPORTSHOE',
            "Men's Running Shoes": 'MNSRUNSHOE',
            "Amazon Global-Toys": 'GLBTOYS',
            "Women's Running Shoes": 'WMNRUNSHOE',
            "Women's Fashion Shoes": 'WMNFSHSHOE',
            "Computer & Accessories": 'CMPTRACCS',
            "Office Supplies": "OFFSUPPLIES",
            "Clothing Accessories": "CLTHACCSS",
            "TigerDirect": "TDRCT"
        }
        sku = sku_dict.get(category)

        def extraction(value):
            if isinstance(value, str) and sku in value:
                asin = value.split('-')[0].replace('LYS', '')
                return asin
            else:
                return 'None'

        """Extract only necessary field from file """
        masterfile_sku = pd.read_csv(output_file, usecols=['Product Code/SKU'], delimiter='\t', skip_blank_lines=True)

        """ Trying to extract SKU """
        masterfile_asin = masterfile_sku['Product Code/SKU'].apply(extraction)

        """ Making another dataFrame for comparision """
        products_df = pd.DataFrame(
            {'sku': masterfile_asin, 'Product Code/SKU': masterfile_sku['Product Code/SKU']}).query("sku != 'None'")

        """Fetching Update file and separating in_stock and out_stock """
        update_df = pd.read_csv(update_file, usecols=[2, 3], names=['sku', 'price'])
        update_in_stock_df = update_df.query("price != 'nan'")
        update_out_stock_df = update_df.query("price == 'nan'")

        """ Check for instock Product """
        in_stock = pd.merge(products_df, update_in_stock_df, on='sku', how='inner')
        # print in_stock

        """ Check for out-of-stock Product """
        out_of_stock = pd.merge(in_stock, products_df, on='sku', how='right', indicator=True).query(
            "_merge == 'right_only'")
        out_of_stock = pd.merge(out_of_stock, update_out_stock_df, on='sku', how='outer')
        out_of_stock = out_of_stock.drop_duplicates(subset='sku')

        """Writing all dataFrames"""
        in_stock.to_csv(os.path.realpath('Outputs/liveyoursport/in_stock/Lys_{}_in_stock.csv'.format(category)))
        out_of_stock.to_csv(
            os.path.realpath('Outputs/liveyoursport/out_of_stock/Lys_{}_out_of_stock.csv'.format(category)))


if __name__ == '__main__':
    a = datetime.datetime.now()
    Update("Women's Running Shoes")
    print 'Done'
    print 'Completed in {}'.format(datetime.datetime.now() - a)

熊猫比较CSV

1 个答案: