python 去除excel中重复行 # y.drop_duplicates(keep=‘first‘, inplace=True)_python keep=

def removeDuplicateLineInfo():
    path = os.path.join(OutputPath, 'MacroInfo_cared_PLL0.xlsx')
    macro_info = pd.read_excel(path, sheet_name="frequency_plan", dtype=str, keep_default_na=False, header=0)

    # need to update keyName:'VCO freq (GHz)', if changed,
    # Delete invalid line with error message
    macro_info = macro_info[~ macro_info['VCO freq (GHz)'].isin(["Error"])]
    x = pd.DataFrame(macro_info.iloc[:, :])

    # Delete 重复行，并重新写入'MacroInfo_cared_PLL0_demo.xlsx'
    x.drop_duplicates(keep='first', inplace=True)
    path_simple = os.path.join(OutputPath, 'MacroInfo_cared_PLL0_simple.xlsx')
    x.to_excel(path_simple, header=1, index=False, encoding='utf-8', sheet_name='frequency_plan')

    # if PLL0 exist
    pll1Path = os.path.join(OutputPath, 'MacroInfo_cared_PLL1.xlsx')
    if (os.path.exists(pll1Path)):
        macro_info_PLL1 = pd.read_excel(pll1Path, sheet_name="frequency_plan", dtype=str, keep_default_na=False,
                                        header=0)
        macro_info_PLL1 = macro_info_PLL1[~macro_info_PLL1['VCO freq (GHz)'].isin(["Error"])]
        y = pd.DataFrame(macro_info_PLL1.iloc[:, :])
        if y.empty:
            print('PLL1 info is empty')
        else:
            print('PLL1 info is existed')

        # Delete 重复行，并重新写入'MacroInfo_cared_PLL0_demo.xlsx'
        y.drop_duplicates(keep='first', inplace=True)
        path_simple = os.path.join(OutputPath, 'MacroInfo_cared_PLL1_simple.xlsx')
        y.to_excel(path_simple, header=1, index=False, encoding='utf-8', sheet_name='frequency_plan')


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33