Multivariate logistic regression in Python shows error

Question

Im trying to make prediction with logistic regression and to test accuracy with Python and sklearn library. Im using data that I downloaded from here:

http://archive.ics.uci.edu/ml/datasets/concrete+compressive+strength

its excel file. I wrote a code, but I always get the same error, and the error is:

ValueError: Unknown label type: 'continuous'

I have used the same logic when I made linear regression, and it works for linear regression.

This is the code:

import numpy as np
import pandas as pd
import xlrd
from sklearn import linear_model
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

#Reading data from excel

data = pd.read_excel("DataSet.xls").round(2)
data_size = data.shape[0]
#print("Number of data:",data_size,"\n",data.head())

my_data = data[(data["Superpl"] == 0) & (data["FlyAsh"] == 0) & (data["BlastFurSlag"] == 0)].drop(columns=["Superpl","FlyAsh","BlastFurSlag"])
my_data = my_data[my_data["Days"]<=28]
my_data_size = my_data.shape[0]
#print("Size of dataset for 28 days or less:", my_data_size, "\n", my_data.head())


def logistic_regression(data_input, cement, water,
                          coarse_aggr, fine_aggr, days):

    variable_list = []
    result_list = []

    for column in data_input:

        variable_list.append(column)
        result_list.append(column)

    variable_list = variable_list[:-1]
    result_list = result_list[-1]

    variables = data_input[variable_list]
    results = data_input[result_list]

    #accuracy of prediction (splittig dataframe in train and test)
    var_train, var_test, res_train, res_test = train_test_split(variables, results, test_size = 0.3, random_state = 42)

    #making logistic model and fitting the data into logistic model
    log_regression = linear_model.LogisticRegression()
    model = log_regression.fit(var_train, res_train)

    input_values = [cement, water, coarse_aggr, fine_aggr, days]

    #predicting the outcome based on the input_values
    predicted_strength = log_regression.predict([input_values]) #adding values for prediction
    predicted_strength = round(predicted_strength[0], 2)

    #calculating accuracy score
    score = log_regression.score(var_test, res_test)
    score = round(score*100, 2)

    prediction_info = "\nPrediction of future strenght: " + str(predicted_strength) + " MPa\n"
    accuracy_info = "Accuracy of prediction: " + str(score) + "%\n"
    full_info = prediction_info + accuracy_info

    return full_info

print(logistic_regression(my_data, 376.0, 214.6, 1003.5, 762.4, 3)) #true value affter 3 days: 16.28 MPa

Answer 1

Although you don't provide details of your data, judging from the error and the comment in the last line of your code:

#true value affter 3 days: 16.28 MPa

I conclude that you are in a regression (i.e numeric prediction) setting. A linear regression is an appropriate model for this task, but a logistic regression is not: logistic regression is for classification problems, and thus it expects binary (or categorical) data as target variables, not continuous values, hence the error.

In short, you are trying to apply a model that is inappropriate for your problem.

UPDATE (after link to the data): Indeed, reading closely the dataset description, you'll see (emphasis added):

The concrete compressive strength is the regression problem

while from scikit-learn User's Guide for logistic regression (again, emphasis added):

Logistic regression, despite its name, is a linear model for classification rather than regression.