Machine learning for anomaly detection

# generate a random dataset with two functions

X_train, y_train = generate_data (n_train = 300 , train_only = True ,

n_features = 2 )

 
# Setting the percentage of emissions

outlier_fraction = 0.1

 
# Storing outliers and contributors in different arrays

X_outliers, X_inliers = get_outliers_inliers (X_train, y_train)

n_inliers = len (X_inliers)

n_outliers = len (X_outliers )

 
# Separate the two functions

f1 = X_train [:, [ 0 ]]. Reshape ( - 1 , 1 )

f2 = X_train [: , [ 1 ]]. reshape ( - 1 , 1 )

# Dataset rendering
# create grid

xx, yy = np.meshgrid (np.linspace ( - 10 , 10 , 200 ),

  np.linspace ( - 10 , 10 , 200 ))

 
# dot plot
plt.scatter (f1, f2)

plt.xlabel ( ’Feature 1’ )

plt.ylabel ( ’Feature 2’ )

# Train the classifier

clf = KNN (contamination = outlier_fraction)

clf.fit (X_train, y_train)

 
# You can print this to see all prediction scores

scores_pred = clf.decision_function (X_train) * - 1

< code class = "plain"> y_pred = clf.predict (X_train)

n_errors = (y_pred! = y_train). sum ()

# Counting the number of errors

print ( ’The number of prediciton errors are’ + str (n_errors))

# threshold for consideration
# datapoint inlier or outlier

threshold = stats.scoreatpercentile (scores_pred, 100 * outlier_fraction)

 
# solver calculates the raw
# anomaly score for each point

Z = clf.decision_function (np.c_ [xx.ravel (), yy.ravel () ]) * - 1

Z = Z.reshape (xx.shape)

 
# fill in the blue color map from the minimum anomaly
# score to the threshold

subplot = plt.subplot ( 1 , 2 , 1 )

subplot.contourf (xx, yy, Z, levels = np.linspace (Z. min (), 

threshold, 10 ), cmap = plt.cm.Blues_r)

 
# draw a red outline where the anomaly is
# grade equals threshold

a = subplot.contour (xx, yy, Z, levels = [threshold],

linewidths = 2 , colors = ’red’ )

 
# fill in orange contour lines where anomaly range
# score from threshold to maximum score for anomaly

subplot.contourf (xx, yy, Z, levels = [threshold, Z. max ()], colors = ’orange ’ )

  
# scatter plots of slots with white dots

b = subplot.scatter (X_train [: - n_outliers, 0 ], X_train [: - n_outliers, 1 ],

c = ’ white’ , s = 20 , edgecolor = ’k’ ) 

  
# dot graph to outliers with black dots

c = subplot.scatter (X_train [ - n_outliers :, 0 ], X_train [ - n_outliers :, 1 ], 

  c = ’black’ , s = 20 , edgecolor = ’k’ )

subplot.axis ( ’tight’ )

  
subplot.legend (

  [a.collections [ 0 ] , b, c],

[ ’learned decision function’ , ’ true inliers’ , ’true outliers’ ],

  prop = matplotlib.font_manager.FontProperties (size = 10 ),

loc = ’ lower right’ )

subplot.set_title ( ’ K-Nearest Neighbors’ )

subplot.set_xlim (( - 10 , 10 ))

subplot.set_ylim (( - 10 , 10 ))

plt.show ()