python - 将 python 数据框传递给对象并更改数据框

Question

我是 python 的新手，我正在尝试将参数(数据帧)传递给函数并通过读取 excel 文件更改参数(数据帧)的值。 (假设我已经导入了所有必要的文件)

我注意到 python 在这里没有通过引用传递参数，我最终没有初始化/更改数据框。

我读到 python 通过对象引用传递，而不是通过值或引用传递。但是，我不需要更改相同的数据框。

输出是:class 'pandas.core.frame.DataFrame'>

from pandas import DataFrame as df
class Data:
   x = df

   @staticmethod
   def import_File(df_name , file):
       df_name  = pd.io.excel.read_excel(file.replace('"',''), sheetname='Sheet1', header=0, skiprows=None, skip_footer=0, index_col=None, parse_cols=None, parse_dates=True, date_parser=True, na_values=None, thousands=None, convert_float=True, has_index_names=None, converters=None, engine=None )


def inputdata():
    Data.import_File(Data.x,r"C:\Users\Data\try.xlsx")
    print(Data.x)

Answer 1

你似乎在艰难地做着很多事情。我会尽量简化它，同时符合标准的使用模式。

# Whatever imports you need
import pandas as pd


# Static variables and methods should generally be avoided.
# Change class and variable names to whatever is more suitable.
# Names should be meaningful when possible.
class MyData:

    # Load data in constructor. Could easily do this in another method.
    def __init__(self, filename):
        self.data = pd.io.excel.read_excel(filename, sheetname='Sheet1')


def inputData():
    # In my experience, forward slashes work just fine on Windows.
    # Create new MyData object using constructor
    x = MyData('C:/Users/Data/try.xlsx')

    # Access member variable from object
    print(x.data)

这是它在方法而不是构造函数中加载的版本。

import pandas as pd


class MyData:

    # Constructor
    def __init__(self):
        # Whatever setup you need
        self.data = None
        self.loaded = False

    # Method with optional argument
    def loadFile(self, filename, sheetname='Sheet1')
        self.data = pd.io.excel.read_excel(filename, sheetname=sheetname)
        self.loaded = True


def inputData():
    x = MyData()
    x.loadFile('C:/Users/Data/try.xlsx')
    print(x.data)

    # load some other data, using sheetname 'Sheet2' instead of default
    y = MyData()
    y.loadFile('C:/Users/Data/tryagain.xlsx', 'Sheet2')
    # can also pass arguments by name in any order like this:
    # y.loadFile(sheetname='Sheet2', filename='C:/Users/Data/tryagain.xlsx')
    print(y.data)

    # x and y both still exist with different data.
    # calling x.loadFile() again with a different path will overwrite its data.

它不保存在您的原始代码中的原因是因为为参数名称赋值永远不会更改 Python 中的原始变量。你可以做的是这样的:

# Continuing from the last code block

def loadDefault(data):
    data.loadFile('C:/Users/Data/try.xlsx')

def testReference():
    x = MyData()
    loadDefault(x)
    # x.data now has been loaded
    print(x.data)


# Another example

def setIndex0(variable, value):
    variable[0] = value

def testSetIndex0():
    v = ['hello', 'world']
    setIndex0(v, 'Good morning')
    # v[0] now equals 'Good morning'
    print(v[0])

但是你不能这样做:

def setString(variable, value):
    # The only thing this changes is the value of variable inside this function.
    variable = value

def testSetString():
    v = 'Start'
    setString(v, 'Finish')
    # v is still 'Start'
    print(v)

如果您希望能够使用名称指定存储值的位置，您可以使用具有索引/键的数据结构。字典让您可以使用键访问和存储值。

import pandas as pd


class MyData:

    # Constructor
    def __init__(self):
        # make data a dictionary
        self.data = {}

    # Method with optional argument
    def loadFile(self, storename, filename, sheetname='Sheet1')
        self.data[storename] = pd.io.excel.read_excel(filename, sheetname=sheetname)

    # Access method
    def getData(self, name):
        return self.data[name]


def inputData():
    x = MyData()
    x.loadFile('name1', 'C:/Users/Data/try.xlsx')
    x.loadFile('name2', 'C:/Users/Data/tryagain.xlsx', 'Sheet2')

    # access Sheet1
    print(x.getData('name1'))

    # access Sheet2
    print(x.getData('name2'))

如果你真的希望函数是静态的，那么你根本不需要创建一个新的类。创建类的主要原因是将其用作可重用结构，以使用特定于该数据的方法来保存数据。

import pandas as pd

# wrap read_excel to make it easier to use
def loadFile(filename, sheetname='Sheet1'):
    return pd.io.excel.read_excel(filename, sheetname=sheetname)

def inputData():
    x = loadFile('C:/Users/Data/try.xlsx')
    print(x)

    # the above is exactly the same as
    x = pd.io.excel.read_excel('C:/Users/Data/try.xlsx', sheetname='Sheet1')
    print(x)