运行方差分析并给出 F 统计值作为输出的函数 [英] Function to run ANOVA and give F stat values as the output

问题描述

我尝试编写的函数将获取提供的数据帧并计算 F 统计值并将其作为输出提供.

The function im trying to write would take the dataframe provided and calculate the F statistic values and provide those as the output.

数据格式最终

Color   Strength   Fabric  Sales
0         1         1         10
1         2         2         15

这里颜色、强度和面料是独立的，而销售额是相关的.

Here Color, strength and Fabric are independent while Sales is dependent.

def regression():
    X=Final.copy()
    y=Final[['Sales']].copy()
    X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=.2, random_state=0)
    sel=f_classif(X_train, y_train)
    p_values=pd.Series(sel[0], index=X_train.columns)
    p_values=p_values.reset_index()
    pd.options.display.float_format = "{:,.2f}".format
    return p_values


Final.apply(regression)

这是我想出的代码，但它抛出了一个错误

This is the code I came up with but its throwing an error

TypeError: regression() takes 0 positional arguments but 1 was given

这段代码可能有什么问题?

What could be going wrong with this code?

推荐答案

当您使用 .apply() 时，数据框或系列将作为参数传递给您调用的函数.文档 对此进行了更多解释.为了解决这个问题，而不是:

When you use .apply(), the dataframe or series is passed as an argument to the function you call. The documentation explains it more. In order to fix this, instead of:

Final.apply(regression)

你可以简单地调用 regression() 像这样:

You can simply call regression() like this:

m_p_values = regression()

现在变量 m_p_values 包含了 regression() 的返回值.

And now the variable m_p_values contains the return value of regression().

这篇关于运行方差分析并给出 F 统计值作为输出的函数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！