import numpy as np
import matplotlib.pyplot as mpl
from mpl_toolkits.mplot3d import Axes3D
from sklearn import linear_model
from sklearn.datasets import make_regression
# Generating synthetic data for training and testing
X, y = make_regression(n_samples=100, n_features=2, n_informative=1, random_state=0, noise=50)
# X and y are values for 3D space. We first need to train
# the machine, so we split X and y into X_train, X_test,
# y_train, and y_test. The *_train data will be given to the
# model to train it.
X_train, X_test = X[:80], X[-20:]
y_train, y_test = y[:80], y[-20:]
# Creating instance of model
regr = linear_model.LinearRegression()
# Training the model
regr.fit(X_train, y_train)
# Printing the coefficients
print(regr.coef_)
# [-10.25691752 90.5463984 ]
# Predicting y-value based on training
X1 = np.array([1.2, 4])
print(regr.predict([X1]))
# 350.860363861
# With the *_test data we can see how the result matches
# the data the model was trained with.
# It should be a good match as the *_train and *_test
# data come from the same sample. Output: 1 is perfect
# prediction and anything lower is worse.
print(regr.score(X_test, y_test))
# 0.949827492261
fig = mpl.figure(figsize=(8, 5))
ax = fig.add_subplot(111, projection='3d')
ax.view_init(elev=20, azim=0)
# ax = Axes3D(fig)
# Data
ax.scatter(X_train[:,0], X_train[:,1], y_train, facecolor='#00CC00')
ax.scatter(X_test[:,0], X_test[:,1], y_test, facecolor='#FF7800')
# Function with coefficient variables
coef = regr.coef_
line = lambda x1, x2: coef[0] * x1 + coef[1] * x2
grid_x1, grid_x2 = np.mgrid[-2:2:10j, -2:2:10j]
ax.plot_surface(grid_x1, grid_x2, line(grid_x1, grid_x2), alpha=0.1, color='k')
ax.xaxis.set_visible(False)
ax.yaxis.set_visible(False)
ax.zaxis.set_visible(False)
import numpy as np
import matplotlib.pyplot as mpl
from scipy.spatial import distance
from sklearn.cluster import DBSCAN
# Creating data
c1 = np.random.randn(100, 2) + 5
c2 = np.random.randn(50, 2)
# Creating a uniformly distributed background
u1 = np.random.uniform(low=-10, high=10, size=100)
u2 = np.random.uniform(low=-10, high=10, size=100)
c3 = np.column_stack([u1, u2])
# Pooling all the data into one 150 x 2 array
data = np.vstack([c1, c2, c3])
# Calculating the cluster with DBSCAN function.
# db.labels_ is an array with identifiers to the
# different clusters in the data.
#db = DBSCAN().fit(data, eps=0.95, min_samples=10)
db = DBSCAN().fit(data)
labels = db.labels_
# Retrieving coordinates for points in each
# identified core. There are two clusters
# denoted as 0 and 1 and the noise is denoted
# as -1. Here we split the data based on which
# component they belong to.
dbc1 = data[labels == 0]
dbc2 = data[labels == 1]
noise = data[labels == -1]
# Setting up plot details
x1, x2 = -12, 12
y1, y2 = -12, 12
fig = mpl.figure()
fig.subplots_adjust(hspace=0.1, wspace=0.1)
ax1 = fig.add_subplot(121, aspect='equal')
ax1.scatter(c1[:,0], c1[:,1], lw=0.5, color='#00CC00')
ax1.scatter(c2[:,0], c2[:,1], lw=0.5, color='#028E9B')
ax1.scatter(c3[:,0], c3[:,1], lw=0.5, color='#FF7800')
ax1.xaxis.set_visible(False)
ax1.yaxis.set_visible(False)
ax1.set_xlim(x1, x2)
ax1.set_ylim(y1, y2)
ax1.text(-11, 10, 'Original')
ax2 = fig.add_subplot(122, aspect='equal')
ax2.scatter(dbc1[:,0], dbc1[:,1], lw=0.5, color='#00CC00')
ax2.scatter(dbc2[:,0], dbc2[:,1], lw=0.5, color='#028E9B')
ax2.scatter(noise[:,0], noise[:,1], lw=0.5, color='#FF7800')
ax2.xaxis.set_visible(False)
ax2.yaxis.set_visible(False)
ax2.set_xlim(x1, x2)
ax2.set_ylim(y1, y2)
ax2.text(-11, 10, 'DBSCAN identified')
import numpy as np
from scipy.cluster import vq
# Creating data
c1 = np.random.randn(100, 2) + 5
c2 = np.random.randn(30, 2) - 5
c3 = np.random.randn(50, 2)
# Pooling all the data into one 180 x 2 array
data = np.vstack([c1, c2, c3])
# Calculating the cluster centroids and variance
# from kmeans
centroids, variance = vq.kmeans(data, 3)
# The identified variable contains the information
# we need to separate the points in clusters
# based on the vq function.
identified, distance = vq.vq(data, centroids)
# Retrieving coordinates for points in each vq
# identified core
vqc1 = data[identified == 0]
vqc2 = data[identified == 1]
vqc3 = data[identified == 2]
# Plotting the clustered data points and centroids
plt.figure(figsize=(8, 6))
plt.scatter(vqc1[:, 0], vqc1[:, 1], c='red', label='Cluster 1')
plt.scatter(vqc2[:, 0], vqc2[:, 1], c='blue', label='Cluster 2')
plt.scatter(vqc3[:, 0], vqc3[:, 1], c='green', label='Cluster 3')
plt.scatter(centroids[:, 0], centroids[:, 1], c='black', marker='x', s=100, label='Centroids')
plt.xlabel('X')
plt.ylabel('Y')
plt.title('Clustered Data with Centroids')
plt.legend()
plt.grid(True)
plt.show()
