摘要：簡(jiǎn)介自年發(fā)布以來(lái)，已經(jīng)成為重要的機(jī)器學(xué)習(xí)庫(kù)了。簡(jiǎn)稱(chēng)，支持包括分類(lèi)回歸降維和聚類(lèi)四大機(jī)器學(xué)習(xí)算法。利用這幾大模塊的優(yōu)勢(shì)，可以大大提高機(jī)器學(xué)習(xí)的效率。已經(jīng)封裝了大量的機(jī)器學(xué)習(xí)算法，包括和。

自2007年發(fā)布以來(lái)，scikit-learn已經(jīng)成為Python重要的機(jī)器學(xué)習(xí)庫(kù)了。scikit-learn簡(jiǎn)稱(chēng)sklearn，支持包括分類(lèi)、回歸、降維和聚類(lèi)四大機(jī)器學(xué)習(xí)算法。還包含了特征提取、數(shù)據(jù)處理和模型評(píng)估三大模塊。

??sklearn是Scipy的擴(kuò)展，建立在NumPy和matplotlib庫(kù)的基礎(chǔ)上。利用這幾大模塊的優(yōu)勢(shì)，可以大大提高機(jī)器學(xué)習(xí)的效率。
??sklearn擁有著完善的文檔，上手容易，具有著豐富的API，在學(xué)術(shù)界頗受歡迎。sklearn已經(jīng)封裝了大量的機(jī)器學(xué)習(xí)算法，包括LIBSVM和LIBINEAR。同時(shí)sklearn內(nèi)置了大量數(shù)據(jù)集，節(jié)省了獲取和整理數(shù)據(jù)集的時(shí)間。

鏈路預(yù)測(cè)是通過(guò)歷史連接信息預(yù)測(cè)未來(lái)可能產(chǎn)生的連接，即通過(guò)當(dāng)前網(wǎng)絡(luò)中的連邊信息預(yù)測(cè)將來(lái)可能產(chǎn)生的連邊信息。

from sklearn.model_selection import train_test_split # 分割數(shù)據(jù)模塊
from sklearn.neighbors import KNeighborsClassifier # K最近鄰(kNN，k-NearestNeighbor)分類(lèi)算法
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn import preprocessing
import matplotlib.pyplot as plt
from sklearn.svm import SVC
from math import isnan

def Jaccavrd(MatrixAdjacency_Train):

Matrix_similarity = np.dot(MatrixAdjacency_Train,MatrixAdjacency_Train)

deg_row = sum(MatrixAdjacency_Train)
deg_row.shape = (deg_row.shape[0],1)
deg_row_T = deg_row.T
tempdeg = deg_row + deg_row_T
temp = tempdeg - Matrix_similarity

Matrix_similarity = Matrix_similarity / temp
return Matrix_similarity

def Salton_Cal(MatrixAdjacency_Train):

similarity = np.dot(MatrixAdjacency_Train,MatrixAdjacency_Train)

deg_row = sum(MatrixAdjacency_Train)
deg_row.shape = (deg_row.shape[0],1)
deg_row_T = deg_row.T
tempdeg = np.dot(deg_row,deg_row_T)
temp = np.sqrt(tempdeg)

np.seterr(divide="ignore", invalid="ignore")
Matrix_similarity = np.nan_to_num(similarity / temp)

return Matrix_similarity

def file2matrix(filepath):

f = open(filepath)
lines = f.readlines()
matrix = np.zeros((50, 50), dtype=float)
A_row = 0
for line in lines:
    list = line.strip("
").split(" ")
    matrix[A_row:] = list[0:50]
    A_row += 1
return matrix    

filepath = "3600/s0001.txt"
MatrixAdjacency = file2matrix(filepath)

similarity_matrix_Jaccavrd = Jaccavrd(MatrixAdjacency)
similarity_matrix_Salton = Salton_Cal(MatrixAdjacency)

filepath2 = "3600/s0002.txt"
MatrixAdjacency2 = file2matrix(filepath2)

similarity_matrix_Jaccavrd2 = Jaccavrd(MatrixAdjacency2)
similarity_matrix_Salton2 = Salton_Cal(MatrixAdjacency2)

filepath3 = "3600/s0003.txt"
MatrixAdjacency3 = file2matrix(filepath3)

similarity_matrix_Jaccavrd3 = Jaccavrd(MatrixAdjacency3)
similarity_matrix_Salton3 = Salton_Cal(MatrixAdjacency3)

Jaccard_Row = similarity_matrix_Jaccavrd.shape[0]
Jaccard_Column = similarity_matrix_Jaccavrd.shape[1]
Jaccard_List = []
for i in range(Jaccard_Row):

for j in range(Jaccard_Column):
    if i
獲取Salton相似性矩陣的行數(shù)和列數(shù)
Salton_Row = similarity_matrix_Salton.shape[0]
Salton_Column = similarity_matrix_Salton.shape[1]
Salton_List = []
for i in range(Salton_Row):
for j in range(Salton_Column):
    if i
獲取jaccard相似性矩陣的行數(shù)和列數(shù)
Jaccard_Row2 = similarity_matrix_Jaccavrd2.shape[0]
Jaccard_Column2 = similarity_matrix_Jaccavrd2.shape[1]
Jaccard_List2 = []
for i in range(Jaccard_Row2):
for j in range(Jaccard_Column2):
    if i
獲取Salton相似性矩陣的行數(shù)和列數(shù)
Salton_Row2 = similarity_matrix_Salton2.shape[0]
Salton_Column2 = similarity_matrix_Salton2.shape[1]
Salton_List2 = []
for i in range(Salton_Row2):
for j in range(Salton_Column2):
    if i
獲取jaccard相似性矩陣的行數(shù)和列數(shù)
Jaccard_Row3 = similarity_matrix_Jaccavrd3.shape[0]
Jaccard_Column3 = similarity_matrix_Jaccavrd3.shape[1]
Jaccard_List3 = []
for i in range(Jaccard_Row3):
for j in range(Jaccard_Column3):
    if i
獲取Salton相似性矩陣的行數(shù)和列數(shù)
Salton_Row3 = similarity_matrix_Salton3.shape[0]
Salton_Column3 = similarity_matrix_Salton3.shape[1]
Salton_List3 = []
for i in range(Salton_Row3):
for j in range(Salton_Column3):
    if i
獲取鄰接矩陣的行數(shù)和列數(shù)
Adjacency_Row = MatrixAdjacency.shape[0]
Adjacency_Column = MatrixAdjacency.shape[1]
Adjacency = []
for i in range(Adjacency_Row):
for j in range(Adjacency_Column):
    if i
獲取鄰接矩陣的行數(shù)和列數(shù)
Adjacency_Row2 = MatrixAdjacency2.shape[0]
Adjacency_Column2 = MatrixAdjacency2.shape[1]
Adjacency2 = []
for i in range(Adjacency_Row2):
for j in range(Adjacency_Column2):
    if i
獲取鄰接矩陣的行數(shù)和列數(shù)
Adjacency_Row3 = MatrixAdjacency3.shape[0]
Adjacency_Column3 = MatrixAdjacency3.shape[1]
Adjacency3 = []
for i in range(Adjacency_Row3):
for j in range(Adjacency_Column3):
    if i
data = np.zeros((1225,3))
data2 = np.zeros((1225,3))
data3 = np.zeros((1225,3))  
for i in range(1225):
data[i][0] =  Jaccard_List[i]
data[i][1] = Salton_List[i]
data[i][2] = Adjacency[i]

for j in range(1225):
data2[j][0] =  Jaccard_List2[j]
data2[j][1] = Salton_List2[j]
data2[j][2] = Adjacency2[j]

for k in range(1225):
data3[k][0] =  Jaccard_List3[k]
data3[k][1] = Salton_List3[k]
data3[k][2] = Adjacency3[k]

data_train_X = data[:,0:2]
data_train_y = data[:,2]
data_test_X = data2[:,0:2]
data_test_y = data2[:,2]
data_target_X = data3[:,0:2]
data_target_y = data3[:,2]
knn = KNeighborsClassifier()
knn.fit(data_train_X,data_train_y)
print(knn.predict(data_test_X))
print(data_test_y)
clf = SVC()
clf.fit(data_train_X,data_test_y)
print(clf.score(data_test_X,data_target_y))
項(xiàng)目詳細(xì)了解
如需詳細(xì)本項(xiàng)目信息，可發(fā)送郵件至18770918982@gmail.com