Я пытаюсь построить границу решения для нелинейной логистической регрессии, как показано на следующем рисунке
import scikitplot.plotters as skplt
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification
from sklearn import metrics
from ggplot import *
import time
def mapFeature(X1, X2, df=True):
"""
X1, X2: dtype = pd.DataFrame, float, int
either a single value or a vector of values
df : dtype = boolean
whether it's a single scalar value or a vector of values
----------
Return: dtype = m row vector or m x n vector of feature values
Calculates each feature and returns its value
"""
# add a column of ones for intercept parameter
out = pd.DataFrame({'1':np.ones(X1.size)})
# max 6th degree polynomial
for i in range(1,7):
for j in range(i+1):
# all the combinations of polynomials up to 7th degree
value = (X1**(i-j))*(X2**j)
col_name = 'X1**{} * X2**{}'.format(i-j, j)
# When we give a vector with only one dimension, we need to specify
# whether to add it as a column or a row. 0 denotes adding a row,
# and 1 would be a column.
if df:
out = out.join(pd.DataFrame({col_name: value}))
else:
out = out.join(pd.DataFrame({col_name: value}, index=[0]))
return out
if __name__ == '__main__':
data = pd.read_csv('ex2data2.txt', header=None,
names=['Test1', 'Test2', 'Pass'])
X = data.iloc[:, :2]
y = data.iloc[:,2]
X = mapFeature(X.iloc[:,0], X.iloc[:,1])
clf = LogisticRegression().fit(X, y)
theta = clf.coef_
u = np.linspace(start, end, 30)
v = np.linspace(start, end, 30)
uu, vv = np.meshgrid(u, v)
z = np.zeros((30, 30))
for i in range(30):
for j in range(30):
z[i,j] = mapFeature(u[i], v[i], df=False).values.dot(theta.T)
plt.contour(uu, vv, z, [0])
plt.show()