yamaguchiyuto

import sys
import pickle
import numpy as np
import pandas as pd
from transe import TRANSE


modelfilepath = sys.argv[1]
h = sys.argv[2]
r = sys.argv[3]

yamaguchiyuto

import numpy as np
from scipy import linalg,sparse,random

class RESCAL:
    def __init__(self,r,lamb_A,lamb_R):
        self.r = r
        self.lamb_A = lamb_A
        self.lamb_R = lamb_R

    def fit(self,X,niter=30):

yamaguchiyuto

import re

def remove_usernames_and_urls(text):
    username_removed_text = re.sub('@\w+', '', text) # remove usernames
    return re.sub('(https?|ftp)(:\/\/[-_.!~*\'()a-zA-Z0-9;\/?:\@&=+\$,%#]+)', '', username_removed_text) # remove urls

yamaguchiyuto

import sys
import numpy as np
from sklearn import cross_validation
from oreore_ridge import RidgeRegression

def psi(xlist,M):
    """ make a design matrix """
    ret = []
    for x in xlist:
        ret.append([x**i for i in range(0,M+1)])

yamaguchiyuto

import sys
import numpy as np
import matplotlib.pyplot as plt
from sklearn import grid_search
from oreore_ridge import RidgeRegression

def psi(xlist,M):
    """ make a design matrix """
    ret = []
    for x in xlist:

yamaguchiyuto

import numpy as np
from sklearn.base import BaseEstimator, RegressorMixin

class RidgeRegression(BaseEstimator, RegressorMixin):
    def __init__(self,lamb=1.0):
        self.lamb = lamb

    def fit(self,X,y):
        A = np.dot(X.T,X) + self.lamb * np.identity(X.shape[1])
        b = np.dot(X.T,y)

yamaguchiyuto

import sys
import numpy as np
import random

from sklearn import datasets
from sklearn.semi_supervised import label_propagation
from sklearn import svm
from sklearn.grid_search import ParameterGrid

def score(estimator, X, y, parameters, validation_true_labels, test_true_labels, validation_set, test_set, X_validation_for_svm=None, X_test_for_svm=None):

yamaguchiyuto

import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
digits = load_digits()
plt.gray()
plt.matshow(digits.images[0])
plt.show()

yamaguchiyuto

import sys
import networkx as nx
from scipy.sparse import linalg
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

def plot(v,name,k,n=10000):
    for i in range(0,k-1):
        plt.plot(v[:n,i],v[:n,i+1],'r+')

yamaguchiyuto

import sys
import numpy as np
import networkx as nx
import matplotlib.pyplot as plt

def plot(data,filename,degreetype):
    """ Plot Distribution """
    plt.plot(range(len(data)),data,'bo')
    plt.yscale('log')
    plt.xscale('log')