TestDome数据科学：未获得正确答案

Question

我尝试从TestDome回答此question，并得到250877.19298245612而不是建议的250000。请让我出了什么问题。谢谢

import numpy as np
from sklearn import linear_model

class MarketingCosts:

    # param marketing_expenditure list. Expenditure for each previous campaign.
    # param units_sold list. The number of units sold for each previous campaign.
    # param desired_units_sold int. Target number of units to sell in the new campaign.
    # returns float. Required amount of money to be invested.
    @staticmethod
    def desired_marketing_expenditure(marketing_expenditure, units_sold, desired_units_sold):
        X = [[i] for i in units_sold]
        reg = linear_model.LinearRegression()
        reg.fit(X, marketing_expenditure)
        return float(reg.predict(desired_units_sold))

#For example, with the parameters below the function should return 250000.0.
print(MarketingCosts.desired_marketing_expenditure(
    [300000, 200000, 400000, 300000, 100000],
    [60000, 50000, 90000, 80000, 30000],
    60000))

Answer 1

import numpy as np
from sklearn import linear_model

class MarketingCosts:

    # param marketing_expenditure list. Expenditure for each previous campaign.
    # param units_sold list. The number of units sold for each previous campaign.
    # param desired_units_sold int. Target number of units to sell in the new campaign.
    # returns float. Required amount of money to be invested.
    @staticmethod
    def desired_marketing_expenditure(marketing_expenditure, units_sold, desired_units_sold):
        marketing_expenditure = np.asarray(marketing_expenditure).reshape(-1, 1)
        units_sold = np.asarray(units_sold).reshape(-1, 1)
        reg = linear_model.LinearRegression()
        reg.fit(marketing_expenditure , units_sold)
        return np.float((desired_units_sold - reg.intercept_)/reg.coef_)

#For example, with the parameters below the function should return 250000.0.
print(MarketingCosts.desired_marketing_expenditure(
    [300000, 200000, 400000, 300000, 100000],
    [60000, 50000, 90000, 80000, 30000],
    60000))

Answer 2

我遇到了同样的问题，我在四舍五入地解决了第一个测试用例，从而使第二个无法通过...这是一个小样本，单变量回归，因此实际上看起来您不能使用普通回归，但是Theil -森回归。我检查了结果，得出的结果是250000.00003619，然后您将其取整。

来源： https://gist.github.com/mfakbar/f97949299171c75e868a37f3f578fa54

import numpy as np
from sklearn import linear_model

class MarketingCosts:

    # param marketing_expenditure list. Expenditure for each previous campaign.
    # param units_sold list. The number of units sold for each previous campaign.
    # param desired_units_sold int. Target number of units to sell in the new campaign.
    # returns float. Required amount of money to be invested.
    @staticmethod
    def desired_marketing_expenditure(marketing_expenditure, units_sold, desired_units_sold):
        y, x = np.array(marketing_expenditure), np.array(units_sold).reshape(-1, 1)
        regressor = linear_model.TheilSenRegressor(max_subpopulation=10)
        regressor.fit(x, y)
        desired_units_sold = np.array([desired_units_sold]).reshape(-1, 1)
        return float(round(regressor.predict(desired_units_sold).item()))

# For example, with the parameters below the function should return 250000.0.
print(MarketingCosts.desired_marketing_expenditure(
    [300000, 200000, 400000, 300000, 100000],
    [60000, 50000, 90000, 80000, 30000],
    60000))

Answer 3

我认为这是解决方案，因为我们试图从y预测X，并且此问题中的标签为units_sold。

import numpy as np
from sklearn import linear_model

class MarketingCosts:

    # param marketing_expenditure list. Expenditure for each previous campaign.
    # param units_sold list. The number of units sold for each previous campaign.
    # param desired_units_sold int. Target number of units to sell in the new campaign.
    # returns float. Required amount of money to be invested.
    @staticmethod
    def desired_marketing_expenditure(marketing_expenditure, units_sold, desired_units_sold):
        marketing_expenditure = marketing_expenditure.reshape(-1, 1)
        units_sold = units_sold.reshape(-1, 1)
        reg = linear_model.LinearRegression()
        reg.fit(marketing_expenditure , units_sold)
        return (desired_units_sold - reg.intercept_)/reg.coef_

#For example, with the parameters below the function should return 250000.0.
print(MarketingCosts.desired_marketing_expenditure(
    [300000, 200000, 400000, 300000, 100000],
    [60000, 50000, 90000, 80000, 30000],
    60000))

Answer 4

这是我通过所有测试的答案：

import numpy as np
from sklearn.linear_model import LinearRegression

def desired_marketing_expenditure(marketing_expenditure, units_sold, desired_units_sold):

    x = np.array(marketing_expenditure).reshape(-1, 1)
    y = np.array(units_sold).reshape(-1, 1)
    model = LinearRegression()
    model.fit(x , y)

    return (desired_units_sold - model.intercept_)/model.coef_    

Answer 5

这是我通过所有测试用例的答案

您可以找到执行线性回归here

的简单步骤

import numpy as np
from sklearn.linear_model import LinearRegression

def desired_marketing_expenditure(marketing_expenditure, units_sold, desired_units_sold):
    s_x = sum(marketing_expenditure)
    s_y = sum(units_sold)
    xy = [] 
    for i in range (len(marketing_expenditure)):
        z= marketing_expenditure[i]*units_sold[i]
        xy.append(z)
    s_xy = sum(xy)
    sq_x = [number ** 2 for number in marketing_expenditure]
    s_sq_x = sum(sq_x)
    sq_y = [number ** 2 for number in units_sold]
    s_sq_y = sum(sq_y)   
    
    # calculating coefficients a and b for liner regression
    a=((s_y*s_sq_x) - (s_x*s_xy))/(len(marketing_expenditure)*s_sq_x - (s_x**2))
    b=(len(marketing_expenditure)*s_xy - (s_x*s_y)) / 
       (len(marketing_expenditure)*s_sq_x - (s_x**2))
    return (desired_units_sold-a)/b


#For example, with the parameters below, the function should return 250000.0
print(desired_marketing_expenditure(
    [300000, 200000, 400000, 300000, 100000],
    [60000, 50000, 90000, 80000, 30000],
    60000))