https://archive.ics.uci.edu/ml/datasets/seeds
To construct the data, seven geometric parameters of wheat kernels were measured:
All of these parameters are real-valued continuous.
%matplotlib inline
import pandas as pd
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn import cross_validation, metrics
from sklearn import preprocessing
import matplotlib.pyplot as plt
cols = ['Area', 'Perimeter','Compactness','Kernel_Length','Kernel_Width','Assymetry_Coefficient','Kernel_Groove_Length', 'Class']
# read .csv from provided dataset
csv_filename="seeds_dataset.txt"
# df=pd.read_csv(csv_filename,index_col=0)
df=pd.read_csv(csv_filename,delim_whitespace=True,names=cols)
df.head()
features = df.columns[:-1]
features
X = df[features]
y = df['Class']
X.head()
# split dataset to 60% training and 40% testing
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.4, random_state=0)
print X_train.shape, y_train.shape
y.unique()
len(features)
# Apply PCA with the same number of dimensions as variables in the dataset
from sklearn.decomposition import PCA
pca = PCA(n_components=7)
pca.fit(X)
# Print the components and the amount of variance in the data contained in each dimension
print(pca.components_)
print(pca.explained_variance_ratio_)
%matplotlib inline
import matplotlib.pyplot as plt
plt.plot(list(pca.explained_variance_ratio_),'-o')
plt.title('Explained variance ratio as function of PCA components')
plt.ylabel('Explained variance ratio')
plt.xlabel('Component')
plt.show()
X = df[features].values
y= df['Class'].values
pca = PCA(n_components=2)
reduced_X = pca.fit_transform(X)
red_x, red_y = [], []
blue_x, blue_y = [], []
green_x, green_y = [], []
for i in range(len(reduced_X)):
if y[i] == 1:
red_x.append(reduced_X[i][0])
red_y.append(reduced_X[i][1])
elif y[i] == 2:
blue_x.append(reduced_X[i][0])
blue_y.append(reduced_X[i][1])
else:
green_x.append(reduced_X[i][0])
green_y.append(reduced_X[i][1])
plt.scatter(red_x, red_y, c='r', marker='x')
plt.scatter(blue_x, blue_y, c='b', marker='D')
plt.scatter(green_x, green_y, c='g', marker='.')
plt.show()
# Import clustering modules
from sklearn.cluster import KMeans
from sklearn.mixture import GMM
# First we reduce the data to two dimensions using PCA to capture variation
pca = PCA(n_components=2)
reduced_data = pca.fit_transform(X)
print(reduced_data[:10]) # print upto 10 elements
kmeans = KMeans(n_clusters=3)
clusters = kmeans.fit(reduced_data)
print(clusters)
# Plot the decision boundary by building a mesh grid to populate a graph.
x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
hx = (x_max-x_min)/1000.
hy = (y_max-y_min)/1000.
xx, yy = np.meshgrid(np.arange(x_min, x_max, hx), np.arange(y_min, y_max, hy))
# Obtain labels for each point in mesh. Use last trained model.
Z = clusters.predict(np.c_[xx.ravel(), yy.ravel()])
# Find the centroids for KMeans or the cluster means for GMM
centroids = kmeans.cluster_centers_
print('*** K MEANS CENTROIDS ***')
print(centroids)
# TRANSFORM DATA BACK TO ORIGINAL SPACE FOR ANSWERING 7
print('*** CENTROIDS TRANSFERED TO ORIGINAL SPACE ***')
print(pca.inverse_transform(centroids))
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure(1)
plt.clf()
plt.imshow(Z, interpolation='nearest',
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
cmap=plt.cm.Paired,
aspect='auto', origin='lower')
plt.plot(reduced_data[:, 0], reduced_data[:, 1], 'k.', markersize=2)
plt.scatter(centroids[:, 0], centroids[:, 1],
marker='x', s=169, linewidths=3,
color='w', zorder=10)
plt.title('Clustering on the seeds dataset (PCA-reduced data)\n'
'Centroids are marked with white cross')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())
plt.show()
distortions = []
for i in range(1, 11):
km = KMeans(n_clusters=i,
init='k-means++',
n_init=10,
max_iter=300,
random_state=0)
km.fit(X)
distortions .append(km.inertia_)
plt.plot(range(1,11), distortions , marker='o')
plt.xlabel('Number of clusters')
plt.ylabel('Distortion')
plt.tight_layout()
#plt.savefig('./figures/elbow.png', dpi=300)
plt.show()
import numpy as np
from matplotlib import cm
from sklearn.metrics import silhouette_samples
km = KMeans(n_clusters=3,
init='k-means++',
n_init=10,
max_iter=300,
tol=1e-04,
random_state=0)
y_km = km.fit_predict(X)
cluster_labels = np.unique(y_km)
n_clusters = cluster_labels.shape[0]
silhouette_vals = silhouette_samples(X, y_km, metric='euclidean')
y_ax_lower, y_ax_upper = 0, 0
yticks = []
for i, c in enumerate(cluster_labels):
c_silhouette_vals = silhouette_vals[y_km == c]
c_silhouette_vals.sort()
y_ax_upper += len(c_silhouette_vals)
color = cm.jet(i / n_clusters)
plt.barh(range(y_ax_lower, y_ax_upper), c_silhouette_vals, height=1.0,
edgecolor='none', color=color)
yticks.append((y_ax_lower + y_ax_upper) / 2)
y_ax_lower += len(c_silhouette_vals)
silhouette_avg = np.mean(silhouette_vals)
plt.axvline(silhouette_avg, color="red", linestyle="--")
plt.yticks(yticks, cluster_labels + 1)
plt.ylabel('Cluster')
plt.xlabel('Silhouette coefficient')
plt.tight_layout()
# plt.savefig('./figures/silhouette.png', dpi=300)
plt.show()
Our clustering with 3 centroids is good.
from sklearn.cluster import AgglomerativeClustering
ac = AgglomerativeClustering(n_clusters=3, affinity='euclidean', linkage='complete')
labels = ac.fit_predict(X)
print('Cluster labels: %s' % labels)
from sklearn.cross_validation import train_test_split
X = df[features]
y = df['Class']
X_train, X_test, y_train, y_test = train_test_split(X, y ,test_size=0.25, random_state=42)
from sklearn import cluster
clf = cluster.KMeans(init='k-means++', n_clusters=3, random_state=5)
clf.fit(X_train)
print clf.labels_.shape
print clf.labels_
# Predict clusters on testing data
y_pred = clf.predict(X_test)
from sklearn import metrics
print "Addjusted rand score:{:.2}".format(metrics.adjusted_rand_score(y_test, y_pred))
print "Homogeneity score:{:.2} ".format(metrics.homogeneity_score(y_test, y_pred))
print "Completeness score: {:.2} ".format(metrics.completeness_score(y_test, y_pred))
print "Confusion matrix"
print metrics.confusion_matrix(y_test, y_pred)
# Affinity propagation
aff = cluster.AffinityPropagation()
aff.fit(X_train)
print aff.cluster_centers_indices_.shape
y_pred = aff.predict(X_test)
from sklearn import metrics
print "Addjusted rand score:{:.2}".format(metrics.adjusted_rand_score(y_test, y_pred))
print "Homogeneity score:{:.2} ".format(metrics.homogeneity_score(y_test, y_pred))
print "Completeness score: {:.2} ".format(metrics.completeness_score(y_test, y_pred))
print "Confusion matrix"
print metrics.confusion_matrix(y_test, y_pred)
ms = cluster.MeanShift()
ms.fit(X_train)
print ms.cluster_centers_
y_pred = ms.predict(X_test)
from sklearn import metrics
print "Addjusted rand score:{:.2}".format(metrics.adjusted_rand_score(y_test, y_pred))
print "Homogeneity score:{:.2} ".format(metrics.homogeneity_score(y_test, y_pred))
print "Completeness score: {:.2} ".format(metrics.completeness_score(y_test, y_pred))
print "Confusion matrix"
print metrics.confusion_matrix(y_test, y_pred)
from sklearn import mixture
# Define a heldout dataset to estimate covariance type
X_train_heldout, X_test_heldout, y_train_heldout, y_test_heldout = train_test_split(
X_train, y_train,test_size=0.25, random_state=42)
for covariance_type in ['spherical','tied','diag','full']:
gm=mixture.GMM(n_components=3, covariance_type=covariance_type, random_state=42, n_init=5)
gm.fit(X_train_heldout)
y_pred=gm.predict(X_test_heldout)
print "Adjusted rand score for covariance={}:{:.2}".format(covariance_type,
metrics.adjusted_rand_score(y_test_heldout, y_pred))
gm = mixture.GMM(n_components=3, covariance_type='tied', random_state=42)
gm.fit(X_train)
# Print train clustering and confusion matrix
y_pred = gm.predict(X_test)
print "Addjusted rand score:{:.2}".format(metrics.adjusted_rand_score(y_test, y_pred))
print "Homogeneity score:{:.2} ".format(metrics.homogeneity_score(y_test, y_pred))
print "Completeness score: {:.2} ".format(metrics.completeness_score(y_test, y_pred))
print "Confusion matrix"
print metrics.confusion_matrix(y_test, y_pred)
pl=plt
from sklearn import decomposition
# In this case the seeding of the centers is deterministic,
# hence we run the kmeans algorithm only once with n_init=1
pca = decomposition.PCA(n_components=2).fit(X_train)
reduced_X_train = pca.transform(X_train)
# Step size of the mesh. Decrease to increase the quality of the VQ.
h = .01 # point in the mesh [x_min, m_max]x[y_min, y_max].
# Plot the decision boundary. For that, we will asign a color to each
x_min, x_max = reduced_X_train[:, 0].min() + 1, reduced_X_train[:, 0].max() - 1
y_min, y_max = reduced_X_train[:, 1].min() + 1, reduced_X_train[:, 1].max() - 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
gm.fit(reduced_X_train)
#print np.c_[xx.ravel(),yy.ravel()]
Z = gm.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
pl.figure(1)
pl.clf()
pl.imshow(Z, interpolation='nearest',
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
cmap=pl.cm.Paired,
aspect='auto', origin='lower')
#print reduced_X_train.shape
pl.plot(reduced_X_train[:, 0], reduced_X_train[:, 1], 'k.', markersize=2)
# Plot the centroids as a white X
centroids = gm.means_
pl.scatter(centroids[:, 0], centroids[:, 1],
marker='.', s=169, linewidths=3,
color='w', zorder=10)
pl.title('Mixture of gaussian models on the seeds dataset (PCA-reduced data)\n'
'Means are marked with white dots')
pl.xlim(x_min, x_max)
pl.ylim(y_min, y_max)
pl.xticks(())
pl.yticks(())
pl.show()