基於Sklearn機器學習實戰---基於Sklearn模塊的鏈路預測

Sklearn簡介

自2007年發佈以來，scikit-learn已經成爲Python重要的機器學習庫了。scikit-learn簡稱sklearn，支持包括分類、迴歸、降維和聚類四大機器學習算法。還包含了特徵提取、數據處理和模型評估三大模塊。

  sklearn是Scipy的擴展，建立在NumPy和matplotlib庫的基礎上。利用這幾大模塊的優勢，可以大大提高機器學習的效率。
  sklearn擁有着完善的文檔，上手容易，具有着豐富的API，在學術界頗受歡迎。sklearn已經封裝了大量的機器學習算法，包括LIBSVM和LIBINEAR。同時sklearn內置了大量數據集，節省了獲取和整理數據集的時間。

項目簡介

鏈路預測是通過歷史連接信息預測未來可能產生的連接，即通過當前網絡中的連邊信息預測將來可能產生的連邊信息。

項目源碼

from sklearn.model_selection import train_test_split # 分割數據模塊
from sklearn.neighbors import KNeighborsClassifier # K最近鄰(kNN，k-NearestNeighbor)分類算法
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

定義計算共同鄰居指標的方法

define some functions to calculate some baseline index

計算Jaccard相似性指標

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

定義計算Salton指標的方法

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)

Matrix_similarity = np.nan_to_num(Matrix_similarity)

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('\n').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)

獲取jaccard相似性矩陣的行數和列數

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<j:
        index = similarity_matrix_Jaccavrd[i,j]
        if isnan(index) == True:
            index = 0
        Jaccard_List.append(index)

獲取Salton相似性矩陣的行數和列數

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<j:
        index = similarity_matrix_Salton[i,j]
        if isnan(index) == True:
            index = 0
        Salton_List.append(index)


        
        
        

獲取jaccard相似性矩陣的行數和列數

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<j:
        index2 = similarity_matrix_Jaccavrd2[i,j]
        if isnan(index2) == True:
            index2 = 0
        Jaccard_List2.append(index2)
        

獲取Salton相似性矩陣的行數和列數

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<j:
        index2 = similarity_matrix_Salton2[i,j]
        if isnan(index2) == True:
            index2 = 0
        Salton_List2.append(index2) 


        

獲取jaccard相似性矩陣的行數和列數

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<j:
        index3 = similarity_matrix_Jaccavrd3[i,j]
        if isnan(index3) == True:
            index3 = 0
        Jaccard_List3.append(index3)
        

獲取Salton相似性矩陣的行數和列數

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<j:
        index3 = similarity_matrix_Salton3[i,j]
        if isnan(index3) == True:
            index3 = 0
        Salton_List3.append(index3) 
        
        

獲取鄰接矩陣的行數和列數

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<j:
        index = MatrixAdjacency[i,j]
        Adjacency.append(index)
        

獲取鄰接矩陣的行數和列數

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<j:
        index2 = MatrixAdjacency2[i,j]
        Adjacency2.append(index2)
        
        

獲取鄰接矩陣的行數和列數

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<j:
        index3 = MatrixAdjacency3[i,j]
        Adjacency3.append(index3) 
        
               

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))

項目詳細瞭解

如需詳細本項目信息，可發送郵件至[email protected]