def Analysis(vector, K=2):
arr = (np.array(vector))
# mean normalization of the data . converting into normal distribution having mean=0 , -0.1<x<0.1
sc = StandardScaler()
x = sc.fit_transform(arr)
# Breaking into principle components
pca = PCA(n_components=2)
components = (pca.fit_transform(x))
# Applying kmeans algorithm for finding centroids
kmeans = KMeans(n_clusters=K, n_jobs=-1)
kmeans.fit_transform(components)
print("labels: ", kmeans.labels_)
centers = kmeans.cluster_centers_
# lables are assigned by the algorithm if 2 clusters then lables would be 0 or 1
lables = kmeans.labels_
colors = ["r.", "g.", "b.", "y.", "c."]
colors = colors[:K + 1]
for i in range(len(components)):
plt.plot(components[i][0],
components[i][1],
colors[lables[i]],
markersize=10)
plt.scatter(centers[:, 0],
centers[:, 1],
marker="x",
s=150,
linewidths=10,
zorder=15)
plt.xlabel("1st Principle Component")
plt.ylabel("2nd Principle Component")
title = "Styles Clusters"
plt.title(title)
plt.savefig("Results" + ".png")
#plt.show()
return kmeans.labels_
#statistical analysis
data.append(1)
print("the attribute array generated is \n",data)
#random forest algorithm
df = pd.read_csv("D:\\Codes\\Sem 7\\PMMS\\Dataset\\Training_Dataset.csv")
attributes = df.iloc[:,0:30].values
result = df.Result
attributes_train,attributes_test,result_train,result_test = train_test_split(attributes,result,test_size=0.5,random_state=0)
sc = StandardScaler()
attributes_train = sc.fit_transform(attributes_train)
attribites_test = sc.transform(attributes_test)
regressor = RandomForestRegressor(n_estimators=1000,random_state=42)
regressor.fit(attributes_train,result_train)
resul_pred = regressor.predict(attributes_test)
new_input = []
new_input.append(data)
array = np.array(new_input)
array.reshape(-1,1)
new_output = regressor.predict(array)
print(new_output)
if(new_output[0]<0):
print ("The website is a phishing website")
shuffle_split = StratifiedShuffleSplit(n_splits=1,
test_size=0.3,
train_size=0.7)
Wi = np.array([tt for tt in valori_ts])
Yi = np.array([c for c in classi])
for i in range(0, NUM_FEATURES_TOT):
Xi = np.array([f[0:i + 1] for f in valori_features])
for train_index, test_index in shuffle_split.split(Xi, Yi):
X_train, X_test = Xi[train_index], Xi[test_index]
Y_train, Y_test = Yi[train_index], Yi[test_index]
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
accuracyRF = accuracyRandomForest(X_train, X_test, Y_train, Y_test)
accuracyDT = accuracyDecisionTree(X_train, X_test, Y_train, Y_test)
accuracyKN = accuracyKNN(X_train, X_test, Y_train, Y_test)
accuracySVM = accuracySVC(X_train, X_test, Y_train, Y_test)
accuracyNB = accuracyNaiveBayes(X_train, X_test, Y_train, Y_test)
accuracyADA = accuracyAdaBoost(X_train, X_test, Y_train, Y_test)
acc_values = [
accuracyRF, accuracyDT, accuracyKN, accuracySVM, accuracyNB,
accuracyADA
]
accuracy_finali.append(acc_values)
##################################
for n in range(1, len(df.columns) + 1):
ica = FastICA(n_components=n)
X_new = ica.fit_transform(X) # Reconstruct signals
acc, clusters = run_clustering(X_new)
print "average EM score after X modified with ICA", n, "components, clusters =", clusters, "silhouette score =", acc
if dralg == 'rp':
#######################################################
######## KMeans after Sparse Random Projection ########
#######################################################
for n in range(1, len(df.columns) + 1):
# create the random projection
sp = SparseRandomProjection(n_components = n)
X_new = sp.fit_transform(X)
acc, clusters = run_clustering(X_new)
print "average EM score after X modified with Random Projectsion", n, "components, clusters =", clusters, "silhouette score =", acc
if dralg == 'lda':
##################################
######## KMeans after LDA ########
##################################
for n in range(1, len(df.columns) + 1):
for solver in ['svd', 'eigen']:
# create the random projection
lda = LDA(n_components = n, solver = solver)
X_new = lda.fit_transform(X, y)
acc, clusters = run_clustering(X_new)
print "average EM score after X modified with LDA", n, "components, clusters =", clusters, "silhouette score =", acc