denzilc

from pprint import pprint
import numpy as np
from scipy import sparse
from scikits.learn.grid_search import GridSearchCV
from scikits.learn.cross_val import StratifiedKFold
from scikits.learn.metrics import f1_score, classification_report
from scikits.learn import svm
from scikits.learn.linear_model import LogisticRegression
from scikits.learn.linear_model.sparse import LogisticRegression as SparseLogisticRegression

denzilc

import numpy as np
import cPickle as pickle

from scipy import sparse
from scikits.learn.preprocessing.sparse import Normalizer
from scikits.learn import svm
from scikits.learn.grid_search import GridSearchCV
from scikits.learn.metrics.metrics import f1_score, classification_report,\
    confusion_matrix, precision_recall_fscore_support
from scikits.learn.cross_val import StratifiedKFold

denzilc

'''
Created on Jun 6, 2011

@author: denzilc
'''

import oauth2 as oauth
import urlparse
import time

denzilc

function [theta, J_history] = gradientDescent(X, y, theta, alpha, num_iters)
%GRADIENTDESCENT Performs gradient descent to learn theta
%   theta = GRADIENTDESENT(X, y, theta, alpha, num_iters) updates theta by 
%   taking num_iters gradient steps with learning rate alpha

% Initialize some useful values
m = length(y); % number of training examples
J_history = zeros(num_iters, 1);
theta_len = length(theta);

denzilc

function J = computeCost(X, y, theta)
%COMPUTECOST Compute cost for linear regression
%   J = COMPUTECOST(X, y, theta) computes the cost of using theta as the
%   parameter for linear regression to fit the data points in X and y

% Initialize some useful values
m = length(y); % number of training examples

% You need to return the following variables correctly 
J = 0;

denzilc

function [X_norm, mu, sigma] = featureNormalize(X)
%FEATURENORMALIZE Normalizes the features in X 
%   FEATURENORMALIZE(X) returns a normalized version of X where
%   the mean value of each feature is 0 and the standard deviation
%   is 1. This is often a good preprocessing step to do when
%   working with learning algorithms.

% You need to set these values correctly
X_norm = X;
mu = zeros(1, size(X, 2));

denzilc

function J = computeCostMulti(X, y, theta)
%COMPUTECOSTMULTI Compute cost for linear regression with multiple variables
%   J = COMPUTECOSTMULTI(X, y, theta) computes the cost of using theta as the
%   parameter for linear regression to fit the data points in X and y

% Initialize some useful values
m = length(y); % number of training examples

% You need to return the following variables correctly 
J = 0;

denzilc

function [J grad] = nnCostFunction(nn_params, ...
                                   input_layer_size, ...
                                   hidden_layer_size, ...
                                   num_labels, ...
                                   X, y, lambda)
%NNCOSTFUNCTION Implements the neural network cost function for a two layer
%neural network which performs classification
%   [J grad] = NNCOSTFUNCTON(nn_params, hidden_layer_size, num_labels, ...
%   X, y, lambda) computes the cost and gradient of the neural network. The
%   parameters for the neural network are "unrolled" into the vector

denzilc

import sys
import os
import re
import pprint

my_first_pat = "(?:[a-zA-Z]+[\w+\.\-]+[\-a-zA-Z]+)[ ]*(?:@|\bat\b|\(at\)|\bwhere\b|\b@\b)[ ]*(?:(?:(?:[\-a-zA-Z]+)[ ]*(?:\.|\ |\bdot\b|\bdom\b|\bdt\b)[ ]*(?:[\-a-zA-Z]+)[ ]*(?:\.|\ |\bdot\b|\bdom\b)[ ]*(?:[\-a-zA-Z\ ]+))|(?:(?:(?:[\-a-zA-Z]+)[ ]*(?:\.|\ |\bdot\b|\bdom\b|\bdt\b)[ ]*(?:[\-a-zA-Z\ ]+))))"

def striphtml(data):
    return re.sub(r'<[^>]*?>', ' ', data)

denzilc

import json, sys, collections
import base64
from Datum import Datum


class FeatureData :
    def __init__(self, words, prevLabel, position, 
                 wordsDict):
        self.w = words;
        self.pL = prevLabel