nkt1546789

"""
Implementation of pairwise ranking using scikit-learn LinearSVC

Reference: "Large Margin Rank Boundaries for Ordinal Regression", R. Herbrich,
    T. Graepel, K. Obermayer.

Authors: Fabian Pedregosa <fabian@fseoane.net>
         Alexandre Gramfort <alexandre.gramfort@inria.fr>
"""

nkt1546789

from pylab import *

def string_kernel(s1,s2,n=inf):
    k1=[]
    k2=[]
    A=set()
    for k in xrange(1,min(n,len(s1)+1)):
        for i in xrange(0,len(s1)-(k-1)):
            A.add(s1[i:i+k])
    for k in xrange(1,min(n,len(s2)+1)):

nkt1546789

def intersected(a,b,c,d):
    x1=b[0]-a[0]
    x2=c[0]-d[0]
    x3=b[1]-a[1]
    x4=c[1]-d[1]
    d=float(x1*x4-x2*x3)
    if d==0: return False
    c1=c[0]-a[0]
    c2=c[1]-a[1]
    s=(c1*x4-c2*x2)/d

nkt1546789

def dijkstra(M,s,SELF=0,NOTCONNECTED=-1):
    """
    M: adjacency matrix
    s: starting point
    """
    n=len(M)
    table=[float("inf") for i in xrange(n)]
    done=set()
    heap=[]
    heappush(heap,[0,s])

nkt1546789

from multiprocessing import Pool
import requests

def urlopen(url):
    try: return requests.get(url).content
    except: return None

def urlsopen(urls):
    pool = Pool(processes=8)
    return pool.map(urlopen, urls)

nkt1546789

import numpy
from numpy import random
from numpy import linalg

def WMF(R,k=10,alpha=0.1,beta=10.,max_iteration=100000,stop_criterion=1e-6):
    """
    R: feedback matrix like R_ij represents the number that user_i clicks item_j
    k: dimensionality of latent factor vector
    alpha: regularization parameter
    beta: confidence parameter

nkt1546789

import numpy
from numpy import random
from matplotlib import pyplot
from sklearn import datasets
from sklearn import base
from sklearn import metrics
from sklearn import grid_search

class NonParametricKNN(base.BaseEstimator):
    def __init__(self,sigma=0.1):

nkt1546789

import numpy as np

def KernelITML(K,constraints,dm=None,dc=None,gamma=1.0,max_iter=1000,stop_threshold=1e-3):
    """
    K: initial kernel matrix.
    constraints: array or list whose element is in the form of (delta,i,j), where delta=1 if (i,j) is must-link and delta=-1 if (i,j) is cannot-link.
    dm: target distance for must-link. if not provided, dm is automatically selected.
    dc: target distance for cannot-link.
    gamma: trade-off parameter. gamma=1 gives stable solution. 
    max_iter: maximum number of iteration. 

nkt1546789

# coding: utf-8
from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import accuracy_score
from gensim.models import word2vec
import numpy as np
np.random.seed(0)

model=word2vec.Word2Vec.load("/path/to/your/model")

nkt1546789

import os,re
from os import path
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd

sns.set(style="white", context="talk")

HOMEPATH="/path/to/your/home_directory"
MAX_DEPTH=5