I am trying to plot the hyperplane for the model I trained with LinearSVC and sklearn. Note that I am working with natural languages; before fitting the model I extracted features with CountVectorizer and TfidfTransformer.
Here the classifier:
from sklearn.svm import LinearSVC
from sklearn import svm
clf = LinearSVC(C=0.2).fit(X_train_tf, y_train)
Then I tried to plot as suggested on the Scikit-learn website:
# get the separating hyperplane
w = clf.coef_[0]
a = -w[0] / w[1]
xx = np.linspace(-5, 5)
yy = a * xx - (clf.intercept_[0]) / w[1]
# plot the parallels to the separating hyperplane that pass through the
# support vectors
b = clf.support_vectors_[0]
yy_down = a * xx + (b[1] - a * b[0])
b = clf.support_vectors_[-1]
yy_up = a * xx + (b[1] - a * b[0])
# plot the line, the points, and the nearest vectors to the plane
plt.plot(xx, yy, 'k-')
plt.plot(xx, yy_down, 'k--')
plt.plot(xx, yy_up, 'k--')
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
s=80, facecolors='none')
plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)
plt.axis('tight')
plt.show()
This example uses svm.SVC(kernel='linear'), while my classifier is LinearSVC. Therefore, I get this error:
AttributeError Traceback (most recent call last)
<ipython-input-39-6e231c530d87> in <module>()
7 # plot the parallels to the separating hyperplane that pass through the
8 # support vectors
----> 9 b = clf.support_vectors_[0]
1 yy_down = a * xx + (b[1] - a * b[0])
11 b = clf.support_vectors_[-1]
AttributeError: 'LinearSVC' object has no attribute 'support_vectors_'
How can I successfully plot the hyperplan of my LinearSVC classifier?
What about leaving the support_ out, which is not defined for a LinearSVC?
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
np.random.seed(0)
X = np.r_[np.random.randn(20, 2) - [2, 2], np.random.randn(20, 2) + [2, 2]]
Y = [0] * 20 + [1] * 20
fig, ax = plt.subplots()
clf2 = svm.LinearSVC(C=1).fit(X, Y)
# get the separating hyperplane
w = clf2.coef_[0]
a = -w[0] / w[1]
xx = np.linspace(-5, 5)
yy = a * xx - (clf2.intercept_[0]) / w[1]
# create a mesh to plot in
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx2, yy2 = np.meshgrid(np.arange(x_min, x_max, .2),
np.arange(y_min, y_max, .2))
Z = clf2.predict(np.c_[xx2.ravel(), yy2.ravel()])
Z = Z.reshape(xx2.shape)
ax.contourf(xx2, yy2, Z, cmap=plt.cm.coolwarm, alpha=0.3)
ax.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.coolwarm, s=25)
ax.plot(xx,yy)
ax.axis([x_min, x_max,y_min, y_max])
plt.show()
Related
I have an assignment in which I need to compare my own multi-class logistic regression and the built-in SKlearn one.
As part of it, I need to plot the decision boundaries of each, on the same figure (for 2,3, and 4 classes separately).
This is my model's decision boundaries for 3 classes:
Made with this code:
x1_min, x1_max = X[:,0].min()-.5, X[:,0].max()+.5
x2_min, x2_max = X[:,1].min()-.5, X[:,1].max()+.5
xx1, xx2 = np.meshgrid(np.linspace(x1_min, x1_max), np.linspace(x2_min, x2_max))
grid = np.c_[xx1.ravel(), xx2.ravel()]
for i in range(len(ws)):
probs = ol.predict_prob(grid, ws[i]).reshape(xx1.shape)
plt.contour(xx1, xx2, probs, [0.5], linewidths=1, colors='green')
where
ol - is my Own Linear regression
ws - the current weights
That's how I tried to plot the Sklearn boundaries:
for i in range(len(clf.coef_)):
w = clf.coef_[i]
a = -w[0] / w[1]
xx = np.linspace(x1_min, x1_max)
yy = a * xx - (clf.intercept_[0]) / w[1]
plt.plot(xx, yy, 'k-')
Resulting
I understand that it's due to the 1dim vs 2dim grids, but I can't understand how to solve it.
I also tried to use the built-in DecisionBoundaryDisplay but I couldn't figure out how to plot it with my boundaries + it doesn't plot only the lines but also the whole background is painted in the corresponding color.
A couple fixes:
Change clf.intercept_[1] to clf.intercept_[i]
If the xlimits and ylimits in the plot look strange, you can constrain them.
ax.set_xlim([x1_min, x1_max])
ax.set_ylim([x2_min, x2_max])
MRE:
import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import make_blobs
from sklearn.linear_model import LogisticRegression
X, y = make_blobs(n_features=2, centers=3, random_state=42)
fig, ax = plt.subplots(1, 2)
x1_min, x1_max = X[:,0].min()-.5, X[:,0].max()+.5
x2_min, x2_max = X[:,1].min()-.5, X[:,1].max()+.5
def draw_coef_lines(clf, X, y, ax, title):
for i in range(len(clf.coef_)):
w = clf.coef_[i]
a = -w[0] / w[1]
xx = np.linspace(x1_min, x1_max)
yy = a * xx - (clf.intercept_[i]) / w[1]
ax.plot(xx, yy, 'k-')
ax.scatter(X[:, 0], X[:, 1], c=y)
ax.set_xlim([x1_min, x1_max])
ax.set_ylim([x2_min, x2_max])
ax.set_title(title)
clf1 = LogisticRegression().fit(X, y)
clf2 = LogisticRegression(multi_class="ovr").fit(X, y)
draw_coef_lines(clf1, X, y, ax[0], "Multinomial")
draw_coef_lines(clf2, X, y, ax[1], "OneVsRest")
plt.show()
I am trying to make a visualization of different kernels effect of a support vector machine over a data-set but I have a problem reshaping an array size:
The dataset I am using is the following:
https://archive.ics.uci.edu/ml/datasets/human+activity+recognition+using+smartphones
df_train_X = pd.read_csv("X_train.txt", header=None, delim_whitespace=True)
df_train_y = pd.read_csv("y_train.txt", header=None, delim_whitespace=True)
X_train = df_train_X.values
y_train = df_train_y[0]
X = X_train
y = y_train
X = X[y != 0, :2]
y = y[y != 0]
n_sample = len(X)
np.random.seed(0)
order = np.random.permutation(n_sample)
X = X[order]
y = y[order].astype(np.float)
X_train = X[:int(.9 * n_sample)]
y_train = y[:int(.9 * n_sample)]
X_test = X[int(.9 * n_sample):]
y_test = y[int(.9 * n_sample):]
# fit the model
for kernel in ('linear', 'rbf', 'poly'):
clf = SVC(kernel=kernel, gamma=10)
clf.fit(X_train, y_train)
plt.figure()
plt.clf()
plt.scatter(X[:, 0], X[:, 1], c=y, zorder=10, cmap=plt.cm.Paired,
edgecolor='k', s=20)
# Circle out the test data
plt.scatter(X_test[:, 0], X_test[:, 1], s=80, facecolors='none',
zorder=10, edgecolor='k')
plt.axis('tight')
x_min = X[:, 0].min()
x_max = X[:, 0].max()
y_min = X[:, 1].min()
y_max = X[:, 1].max()
XX, YY = np.mgrid[x_min:x_max:200j, y_min:y_max:200j]
Z = clf.decision_function(np.c_[XX.ravel(), YY.ravel()])
# Put the result into a color plot
Z = Z.reshape(XX.shape)
plt.pcolormesh(XX, YY, Z > 0, cmap=plt.cm.Paired)
plt.contour(XX, YY, Z, colors=['k', 'k', 'k'],
linestyles=['--', '-', '--'], levels=[-.5, 0, .5])
plt.title(kernel)
plt.show()
The problem is related to Z = Z.reshape(XX.shape) since I get the following error that blocks the code execution: cannot reshape array of size 240000 into shape (200,200)
But I don't know how to solve it to perform the visualization.
I'm trying to plot the decision boundary of the SVM classifier using a precomputed Laplace kernel (code below) on the similar lines of this scikit-learn post. I'm taking test points as mesh grid values (xx, yy) just like as mentioned in the post and train points as X and y. I'm able to fit the pre-computed kernel using train points.
import numpy as np
#from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.svm import SVC
from sklearn.metrics.pairwise import laplacian_kernel
#Load the iris data
iris_data = load_iris()
#Split the data and target
X = iris_data.data[:, :2]
y = iris_data.target
#Step size in mesh plot
h = 0.02
#Convert X and y to a numpy array
X = np.array(X)
y = np.array(y)
#Using Laplacian kernel - https://scikit-learn.org/stable/modules/metrics.html#laplacian-kernel
K = np.array(laplacian_kernel(X, gamma=.5))
svm = SVC(kernel='precomputed').fit(K, np.ravel(y))
# create a mesh to plot in
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
#plt.subplot(2, 2, i + 1)
#plt.subplots_adjust(wspace=0.4, hspace=0.4)
# Calculate the gram matrix for test points. Here is where the error is coming. xx- test, X-train.
K_test = np.array(laplacian_kernel(xx, X, gamma=.5))
#Predict using the gram matrix for test
Z = svm.predict(np.c_[K_test])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap=plt.cm.coolwarm, alpha=0.8)
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.coolwarm)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.xticks(())
plt.yticks(())
plt.title('SVC with Laplace kernel')
plt.show()
However, when I try to plot the decision boundary on graph for grid points, I get the below error.
Traceback (most recent call last):
File "/home/user/Src/laplce.py", line 37, in <module>
K_test = np.array(laplacian_kernel(xx, X, gamma=.5))
File "/home/user/.local/lib/python3.9/site-packages/sklearn/metrics/pairwise.py", line 1136, in laplacian_kernel
X, Y = check_pairwise_arrays(X, Y)
File "/home/user/.local/lib/python3.9/site-packages/sklearn/utils/validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "/home/user/.local/lib/python3.9/site-packages/sklearn/metrics/pairwise.py", line 160, in check_pairwise_arrays
raise ValueError("Incompatible dimension for X and Y matrices: "
ValueError: Incompatible dimension for X and Y matrices: X.shape[1] == 280 while Y.shape[1] == 2
So, how do I resolve the error and plot the decision boundary for iris data ? Thanks in advance
The issue is getting your meshgrid into the same dimensions as the training matrix, before applying the laplacian. So if we run the code below to fit the svm :
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.svm import SVC
from sklearn.metrics.pairwise import laplacian_kernel
iris_data = load_iris()
X = iris_data.data[:, :2]
y = iris_data.target
h = 0.02
K = laplacian_kernel(X,gamma=.5)
svm = SVC(kernel='precomputed').fit(K, y)
Create the grid like you did:
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
x_test = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
xx,yy = np.meshgrid(np.arange(x_min, x_max, h),np.arange(y_min, y_max, h))
Your original input into the laplacian was (150,2) so you need to basically put your xx,yy into 2 columns:
x_test = np.vstack([xx.ravel(),yy.ravel()]).T
K_test = laplacian_kernel(x_test, X, gamma=.5)
Z = svm.predict(K_test)
Z = Z.reshape(xx.shape)
Then plot:
plt.contourf(xx, yy, Z, cmap=plt.cm.coolwarm, alpha=0.8)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.coolwarm)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
The points are more or less correct, you can see it does not resolve 1,2 very well:
pd.crosstab(y,svm.predict(K))
col_0 0 1 2
row_0
0 49 1 0
1 0 35 15
2 0 11 39
Why my decision line is not correctly represented in a graph, for the linear classification with svm
w = clf.coef_[0]
a = -w[0] / w[1]
XX = np.linspace(10, 30)
yy = a * XX - clf.intercept_[0] / w[1]
plt.plot(XX, yy, 'k-')
plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train)
plt.legend()
plt.show()
I was using "svm" classifier to classify it was a bike or car.
So, my features were 0,1,2 columns and dependents was 3rd column.I can able to clearly see the classification,but i don't know how to print all the points based on classification in diagram.
import numpy as np
import operator
from matplotlib import pyplot as plt
from sklearn import svm
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn.svm import SVC
dataframe=pd.read_csv(DATASET_PATH)
dataframe = dataframe.dropna(how='any',axis=0)
SVM_Trained_Model = preprocessing.LabelEncoder()
train_data=dataframe[0:len(dataframe)]
le=preprocessing.LabelEncoder()
col=dataframe.columns[START_TRAIN_COLUMN:].astype('U')
col_name=["no_of_wheels","dimensions","windows","vehicle_type"]
for i in range(0,len(col_name)):
self.train_data[col_name[i]]=le.fit_transform(self.train_data[col_name[i]])
train_column=np.array(train_data[col]).astype('U')
data=train_data.iloc[:,[0,1,2]].values
target=train_data.iloc[:,3].values
data_train, data_test, target_train, target_test = train_test_split(data,target, test_size = 0.30,
random_state = 0) `split test and test train`
svc_model=SVC(kernel='rbf', probability=True))'classifier model'
svc_model.fit(data_train, target_train)
all_labels =svc_model.predict(data_test)
X_set, y_set = data_train, target_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step =
0.01),np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
Xpred = np.array([X1.ravel(), X2.ravel()] + [np.repeat(0, X1.ravel().size) for _ in range(1)]).T
pred = svc_model.predict(Xpred).reshape(X1.shape)
plt.contourf(X1, X2, pred,alpha = 0.75, cmap = ListedColormap(('white','orange','pink')))
plt.xlim(X1.min(),X1.max())
plt.ylim(X2.min(), X2.max())
colors=['red','yellow','cyan','blue']
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],c = ListedColormap((colors[i]))(i), label
= j)
plt.title('Multiclass Classifier ')
plt.xlabel('Features')
plt.ylabel('Dependents')
plt.legend()
plt.show()
Image
So here is my diagram I need to print the points using python print() based on pink and white region in the diagram.Please help me to get this points.
You need to select and use only 2 features in order to make a 2D surface plot.
from sklearn.svm import SVC
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
iris = datasets.load_iris()
X = iris.data[:, :2] # we only take the first two features.
y = iris.target
def make_meshgrid(x, y, h=.02):
x_min, x_max = x.min() - 1, x.max() + 1
y_min, y_max = y.min() - 1, y.max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
return xx, yy
def plot_contours(ax, clf, xx, yy, **params):
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
out = ax.contourf(xx, yy, Z, **params)
return out
model = svm.SVC(kernel='linear')
clf = model.fit(X, y)
fig, ax = plt.subplots()
# title for the plots
title = ('Decision surface of linear SVC ')
# Set-up grid for plotting.
X0, X1 = X[:, 0], X[:, 1]
xx, yy = make_meshgrid(X0, X1)
plot_contours(ax, clf, xx, yy, cmap=plt.cm.coolwarm, alpha=0.8)
ax.scatter(X0, X1, c=y, cmap=plt.cm.coolwarm, s=20, edgecolors='k')
ax.set_ylabel('y label here')
ax.set_xlabel('x label here')
ax.set_xticks(())
ax.set_yticks(())
ax.set_title(title)
ax.legend()
plt.show()