How to change output X in sklearn classification? - scikit-learn

I am generating a Dataset with the make_classification from sklearn.
I want my output in X to be either 1 or 0 (1 for positive, 0 for negative).
Is this possible?
plt.subplot(121)
plt.title("2 informative features, 1 cluster/class", fontsize="small")
X1, Y1 = make_classification(
n_samples=1000,
n_features=2,
n_redundant=0,
n_informative=2,
n_clusters_per_class=1,
weights=[0.92,0.098]
)
plt.scatter(X1[:, 0], X1[:, 1], marker="o", c=Y1, s=25, edgecolor="k")
plt.subplot(122)
plt.title("2 informative features, 2 clusters/class", fontsize="small")
X2, Y2 = make_classification(
n_samples=1000,
n_features=2,
n_redundant=0,
n_informative=2,
weights=[0.92,0.098]
)
plt.scatter(X2[:, 0], X2[:, 1], marker="o", c=Y2, s=25, edgecolor="k")

Related

How to improve cone - make the bases more like a circle?

I have a code for plotting a cone with some text and arrows like axes. How to change this code to get the bases of the cone looking like circles? Is the problem in the settings of margins? Or is it necessary to define circles in another way?
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits import mplot3d
from matplotlib.patches import FancyArrowPatch
from mpl_toolkits.mplot3d import proj3d
class Arrow3D(FancyArrowPatch):
def __init__(self, xs, ys, zs, *args, **kwargs):
FancyArrowPatch.__init__(self, (0, 0), (0, 0), *args, **kwargs)
self._verts3d = xs, ys, zs
def draw(self, renderer):
xs3d, ys3d, zs3d = self._verts3d
xs, ys, zs = proj3d.proj_transform(xs3d, ys3d, zs3d, renderer.M)
self.set_positions((xs[0], ys[0]), (xs[1], ys[1]))
FancyArrowPatch.draw(self, renderer)
nn = 400 # number of points along circle's perimeter
theta = np.linspace(0, 2*np.pi, nn)
rho = np.ones(nn)
# (x,y) represents points on circle's perimeter
x = np.ravel(rho*np.cos(theta))
y = np.ravel(rho*np.sin(theta))
fig, ax = plt.subplots()
plt.rcParams["figure.figsize"] = [5, 5]
figsize = (5, 5)
ax = plt.axes(projection='3d') # set the axes for 3D plot
ax.azim = -88 # y rotation (default=270)
ax.elev = 13 # x rotation (default=0)
# Low, high values of z for plotting 2 circles at different elevation
loz, hiz = -15, 15
# Plot two circles
ax.plot(x, y, hiz)
ax.plot(x, y, loz)
# Set some indices to get proper (x,y) for line plotting
lo1,hi1 = 15, 15+nn//2
lo2,hi2 = lo1+nn//2-27, hi1-nn//2-27
# Plot 3d lines using coordinates of selected points
ax.plot([x[lo1], x[hi1]], [y[lo1], y[hi1]], [loz, hiz])
ax.plot([x[lo2], x[hi2]], [y[lo2], y[hi2]], [loz, hiz])
eps = 0.005
ax.plot([0, 0], [0, 0], [0, 20]) # extend in z direction
ax.plot([0-eps, 0], [0-eps, -5], [0-eps, 0]) # extend in y direction
ax.plot([0, 1.3], [0, 0], [0, 0]) # extend in x direction
ax.plot([0+eps, 0.6], [0+eps, -4], [0+eps, 16]) # v vector
ax.plot([0.63, 0.63], [-4, -4], [16, -0.005]) # vertical projection
ax.plot([0+eps, 0.6], [0+eps, -4], [0+eps, -0.005]) # to the beginning
ax.scatter(0, 0, 20, marker=(3, 0, 0), s=100, clip_on=False)
ax.scatter(0, -5, 0, marker=(3, 0, 43), s=100, clip_on=False)
ax.scatter(1.3, 0, 0, marker=(3, 0, 30), s=100, clip_on=False)
ax.scatter(0.6, -4, 16, marker=(3, 0, 80), s=100, clip_on=False)
ax.scatter(0.6, -4, -0.005, marker=(3, 0, 0), s=100, clip_on=False)
a2 = Arrow3D([0.14, -0.515], [-5.581, 1.358], [14.73, 4.983], mutation_scale=20, arrowstyle="-|>", color="k", connectionstyle="arc3,rad=0.3")
ax.add_artist(a2)
ax.text3D(0.23, -5.23, 23.33, r'$A$')
ax.text3D(1.41, 1.29, -2.7, r'$B$')
ax.text3D(-0.31, 1.46, -12.6, r'$C$')
ax.text3D(0.4, -5.48, 17, r'$D$')
ax.text3D(0.64, 1.57, -9.95, r'$E$')
ax.text3D(-0.2, -5.5, 15.73, r'$F$')
# Hide axes
ax._axis3don = False
# Save the figure (.pdf)
margins = { # vvv margin in inches
"left" : 1 / figsize[0],
"bottom" : -2.45 / figsize[1],
"right" : 1 - 0.5 / figsize[0],
"top" : 1 + 1.8 / figsize[1]
}
fig.subplots_adjust(**margins)
plt.savefig('output.pdf')
plt.show()
From this code I got the following output:
The desired output is bases looking like a circle.
This is the view from above:
It is not a circle but an ellipse.
Desired shape of the cone:

PyPlot Change Scatter Label When Points Overlap

I am graphing my predicted and actual results of an ML project using pyplot. I have a scatter plot of each dataset as a subplot and the Y values are elements of [-1, 0, 1]. I would to change the color of the points if both points have the same X and Y value but am not sure how to implement this. Here is my code so far:
import matplotlib.pyplot as plt
Y = [1, 0, -1, 0, 1]
Z = [1, 1, 1, 1, 1]
plt.subplots()
plt.title('Title')
plt.xlabel('Timestep')
plt.ylabel('Score')
plt.scatter(x = [i for i in range(len(Y))], y = Y, label = 'Actual')
plt.scatter(x = [i for i in range(len(Y))], y = Z, label = 'Predicted')
plt.legend()
I would simply make use of NumPy indexing in this case. Specifically, first plot all the data points and then additionally highlight only those point which fulfill the condition X==Y and X==Z
import matplotlib.pyplot as plt
import numpy as np
fig = plt.figure()
Y = np.array([1, 0, -1, 0, 1])
Z = np.array([1, 1, 1, 1, 1])
X = np.arange(len(Y))
# Labels and titles here
plt.scatter(X, Y, label = 'Actual')
plt.scatter(X, Z, label = 'Predicted')
plt.scatter(X[X==Y], Y[X==Y], color='black', s=500)
plt.scatter(X[X==Z], Z[X==Z], color='red', s=500)
plt.xticks(X)
plt.legend()
plt.show()

Inconsistency in sklearn predict function for 'ovr' multi-class problems

I have found an inconsistency in the predict function of the SVM model for multiclass problems. I have trained a model with SKlearn SVM.SVC function for a multiclass prediction problem (see plot below).
But on some occasions, the predict functions gives me different results when I did the prediction instead with the argmax of the decision function. One can see that the inconsistency is close to the decision boundary.
This inconsistency vanishes when I use the OneVsRestClassifier directly. Does the predict function of the SVM.SVC classes some corrections or why does it differ from the argmax prediction?
Here is the code to reproduce the result:
import numpy as np
from sklearn import svm, datasets
from sklearn.multiclass import OneVsRestClassifier
from scipy.linalg import cho_solve, cho_factor
def create_data(n_samples, noise):
# 4 gaussian blobs with different means and variances
sample_per_cls = np.int(n_samples/4)
sample_per_cls_rest = sample_per_cls + n_samples - 4*sample_per_cls #puts the rest of the samples into the last class
x1 = np.random.multivariate_normal([20, 18], np.array([[2, 3], [3, 7]])*4*noise, sample_per_cls, 'warn')
x2 = np.random.multivariate_normal([13, 27], np.array([[10, 3], [3, 2]])*4*noise, sample_per_cls, 'warn')
x3 = np.random.multivariate_normal([9, 13], np.array([[6, 1], [1, 5]])*4*noise, sample_per_cls, 'warn')
x4 = np.random.multivariate_normal([14, 20], np.array([[4, 0.2], [0.2, 7]])*4*noise, sample_per_cls_rest, 'warn')
X = np.vstack([x1,x2,x3,x4])
#define the labels for each class
Y = np.empty([n_samples], dtype=np.int)
Y[0:sample_per_cls] = 0
Y[sample_per_cls:2*sample_per_cls] = 1
Y[2*sample_per_cls:3*sample_per_cls] = 2
Y[3*sample_per_cls:] = 3
#shuffle the data set
rand_int = np.arange(n_samples)
np.random.shuffle(rand_int)
X = X[rand_int]
Y = Y[rand_int]
return X, Y
X, Y = create_data(n_samples=800, noise=0.15)
clf = svm.SVC(C=0.5, kernel='rbf', gamma=0.1, decision_function_shape='ovr', cache_size=8000)
#the classifier below is consistent
#clf = OneVsRestClassifier(svm.SVC(C=0.5, kernel='rbf', gamma=0.1, decision_function_shape='ovr', cache_size=8000))
clf.fit(X,Y)
Xs = np.linspace(np.min(X[:,0] - 1), np.max(X[:,0] + 1), 150)
Ys = np.linspace(np.min(X[:,1] - 1), np.max(X[:,1] + 1), 150)
XX, YY = np.meshgrid(Xs, Ys)
test_set = np.stack([XX, YY], axis=2).reshape(-1,2)
#prediction via argmax of the decision function
pred = np.argmax(clf.decision_function(test_set), axis=1)
#prediction with sklearn function
pred_1 = clf.predict(test_set)
diff = np.equal(pred, pred_1)
error = np.where(diff == False)[0]
print(error)
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = [16, 10]
plt.contourf(XX, YY, pred_1.reshape(XX.shape), alpha=0.5, cmap='seismic')
plt.colorbar()
plt.scatter(X[:,0], X[:,1], c=Y, s=20, marker='o', edgecolors='k')
plt.scatter(test_set[error, 0], test_set[error, 1], c=pred_1[error], s=120, marker='^', edgecolors='k')
plt.show()
Triangles are marking the inconsistent points:

Why the network gives the same results for each Input in test?

My network transposes an image, with size 62*71, to a vector of 124 outputs. In the test, I got the same output for each input. I checked 4000 cases.
I cannot seem to signify the problem because the learning seems to be fine, there is an improvement of the error and get a relatively low error.
Someone maybe knows what is the problem?
#load data
data_in= np.transpose(np.loadtxt("images_in_10000.csv", delimiter=',',dtype=np.float32))
data_out= np.transpose(np.loadtxt("out_to_image_10000.csv", delimiter=',',dtype=np.float32))
x_train = data_in[0:6000, :]
x_test = data_in[6000:10001,:]
y_train = data_out[0:6000, :]
y_test = data_out[6000:10001, :]
#parametersa
batch=100
epochs=7
learning_rate=0.01
n = x_test.shape[1] #4392
m = x_train.shape[0] #6000
d = y_test.shape[1] #124
l = y_test.shape[0] #4000
trainX = tf.placeholder(tf.float32, [batch, n])
trainY = tf.placeholder(tf.float32, [batch, d])
testX = tf.placeholder(tf.float32, [l, n])
testY = tf.placeholder(tf.float32, [l, d])
W_c1= tf.Variable(tf.random_normal([5, 5, 1, 32]))
W_c2= tf.Variable(tf.random_normal([5, 5, 32, 64]))
W_fc= tf.Variable(tf.random_normal([18 * 16 * 64, 128]))
W_out= tf.Variable(tf.random_normal([128, d]))
b_c1= tf.Variable(tf.random_normal([32]))
b_c2=tf.Variable(tf.random_normal([64]))
b_fc=tf.Variable(tf.random_normal([128]))
b_out=tf.Variable(tf.random_normal([d]))
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def maxpool2d(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
def convolutional_neural_network(x):
x = tf.reshape(x, shape=[-1,61,72, 1])
conv1 = tf.nn.relu(conv2d(x, W_c1) + b_c1)
conv1 = maxpool2d(conv1)
conv2 = tf.nn.relu(conv2d(conv1, W_c2) + b_c2)
conv2 = maxpool2d(conv2)
fc = tf.reshape(conv2, [-1, 18 * 16 * 64])
fc = tf.nn.relu(tf.matmul(fc, W_fc) + b_fc)
output = tf.matmul(fc, W_out) + b_out
return output
prediction = convolutional_neural_network(trainX)
cost =tf.reduce_mean(tf.pow(prediction-trainY,2))
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)
prediction_t = convolutional_neural_network(testX)
losstest = tf.reduce_mean(tf.pow(prediction_t - testY, 2))
k=0
a = np.linspace(0, m - batch, m / batch, dtype=np.int32)
costshow = [0] * (len(a) * epochs)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(epochs):
epoch_loss = 0
for i in (np.linspace(0,m - batch, m / batch, dtype=np.int32)):
x = x_train[i:i + batch, :]
y = y_train[i:i + batch, :]
sess.run(optimizer, feed_dict={trainX: x, trainY: y})
cost_val = sess.run(cost, feed_dict={trainX: x, trainY: y})
costshow[k]=cost_val
print("Epoch=", '%04d' % (epoch + 1), "loss=", " {:.9f}".format(cost_val))
k = k + 1
print("finsh train-small ")
result = sess.run(prediction_t, feed_dict={testX: x_test})
test_loss = sess.run(losstest, feed_dict={testX: np.asarray(x_test), testY: np.asarray(y_test)})
print("Testing loss=", test_loss)
The metric behind a picture is clearly defined. The values of an image often ranges from 0-1 or 0-255. For CNN's you should normalize your input values (0-1).
Thus you have to be careful with your weight initialization. For example, if your have a bias of 0.6 and a value of 0.6, you get a 1.2 as image value and your plotting program thinks you are in the 0-255 range and everything is black.
So try to use the glorot-initializer for the weights and zero-initializer for the bias initializer:
Weights:
tf.get_variable("weight", shape=[5, 5, 1, 32], initializer=tf.glorot_uniform_initializer())
Bias:
tf.get_variable("bias", shape=[32], initializer=tf.zeros_initializer())
Furthermore, tf.Variabel is deprecated. It is better to use tf.get_variable.

LinearSVC() differs from SVC(kernel='linear')

When data is offset (not centered in zero), LinearSVC() and SVC(kernel='linear') are giving awfully different results. (EDIT: the problem might be it does not handle non-normalized data.)
import matplotlib.pyplot as plot
plot.ioff()
import numpy as np
from sklearn.datasets.samples_generator import make_blobs
from sklearn.svm import LinearSVC, SVC
def plot_hyperplane(m, X):
w = m.coef_[0]
a = -w[0] / w[1]
xx = np.linspace(np.min(X[:, 0]), np.max(X[:, 0]))
yy = a*xx - (m.intercept_[0]) / w[1]
plot.plot(xx, yy, 'k-')
X, y = make_blobs(n_samples=100, centers=2, n_features=2,
center_box=(0, 1))
X[y == 0] = X[y == 0] + 100
X[y == 1] = X[y == 1] + 110
for i, m in enumerate((LinearSVC(), SVC(kernel='linear'))):
m.fit(X, y)
plot.subplot(1, 2, i+1)
plot_hyperplane(m, X)
plot.plot(X[y == 0, 0], X[y == 0, 1], 'r.')
plot.plot(X[y == 1, 0], X[y == 1, 1], 'b.')
xv, yv = np.meshgrid(np.linspace(98, 114, 10), np.linspace(98, 114, 10))
_X = np.c_[xv.reshape((xv.size, 1)), yv.reshape((yv.size, 1))]
_y = m.predict(_X)
plot.plot(_X[_y == 0, 0], _X[_y == 0, 1], 'r.', alpha=0.4)
plot.plot(_X[_y == 1, 0], _X[_y == 1, 1], 'b.', alpha=0.4)
plot.show()
This is the result I get:
(left=LinearSVC(), right=SVC(kernel='linear'))
sklearn.__version__ = 0.17. But I also tested in Ubuntu 14.04, which comes with 0.15.
I thought about reporting the bug, but it seems too evident to be a bug. What am I missing?
Reading the documentation, they are using different underlying implementations. LinearSVC is using liblinear where SVC is using libsvm.
Looking closely at the coefficients and intercept, it seems LinearSVC applies regularization to the intercept where SVC does not.
By adding intercept_scaling, I was able to obtain the same results to both.
LinearSVC(loss='hinge', intercept_scaling=1000)

Resources