逻辑回归：ValueError：未知标签类型：“连续”

Question

I want to use logistic regression to predict and plot a curve<\/a> from an Excel dataset and get its slope coefficients. However, when I run the code (see below) the error " ValueError: Unknown label type: 'continuous'. " occurs.

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import PolynomialFeatures
import seaborn as sns
from sklearn.linear_model import LogisticRegression


df = pd.read_excel('Fatigue2.xlsx',sheet_name='Sheet4')

X = df[['Strain1', 'Temperature1']]
y = df['Cycles1']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=101)

#poly = PolynomialFeatures(degree=2)
#X_ = poly.fit_transform(X_train)

LR = LogisticRegression()
LR.fit(X_train,y_train)

g = sns.lmplot(x='Cycles1', y='Strain1', hue = 'Temperature1', data=df, fit_reg= False)
g.set(xscale='log', yscale ='log')
g.set_axis_labels("Cycles (log N)", "Strain")

print ('Coefficients : ', LR.coef_, 'Intercept :', LR.intercept_)

Answer 1

LogisticRegression from sklearn is a classifier, ie it expects that the response variable is categorical.

Your task is of regression. Moreover, the plot does not seem to have the asymptotic behavior of a logit on the right. You may have better results using a polynomial regression as described here .

Answer 2

Based on docs type_of_target(y) :

Determine the type of data indicated by the target.

Note that this type is the most specific type that can be inferred. For example:

• binary is more specific but compatible with multiclass .
• multiclass of integers is more specific but compatible with continuous .
• multilabel-indicator is more specific but compatible with multiclass-multioutput .

Parameters

y : array-like

Returns

target_type : string

One of:

• 'continuous': y is an array-like of floats that are not all integers, and is 1d or a column vector.
• ...

change y as y.astype(int)