dylanjf

library(Matrix)
amazon_train = sparse.model.matrix(~. - 1, data = amazon_train)

dylanjf

amazon_test$ACTION1 = 1

#this is really just a placeholder variable so that the training examples wont be removed when I call match. 
#also, make sure you put this in the same column as it is in the training set...



amazon_test = sparse.model.matrix(~. - 1, data = amazon_test)

dylanjf

#read and separate data

amazon_train = read.csv("C:/Users/dylanjf/Desktop/amazon/train.csv")
amazon_train = amazon_train[,-10]
amazon_Ytrain = as.matrix(amazon_train[,1])
amazon_train = amazon_train[,-1]

amazon_test = read.csv("C:/Users/dylanjf/Desktop/amazon/test.csv")
amazon_test = amazon_test[,c(1:8)]

dylanjf

###"naive bayesian" approach... if matched in training to test, return the probability that the person
was accepted over all training examples###

#concatenate all base variables except for RESOURCE

train_person = paste(amazon_Xtrain[,2],amazon_Xtrain[,3],amazon_Xtrain[,4],
                     amazon_Xtrain[,5],amazon_Xtrain[,6],amazon_Xtrain[,7],amazon_Xtrain[,8], sep = "")

test_person = paste(amazon_Xtest[,2],amazon_Xtest[,3],amazon_Xtest[,4],
                    amazon_Xtest[,5],amazon_Xtest[,6],amazon_Xtest[,7],amazon_Xtest[,8], sep = "")

dylanjf

########3 rep 10 fold CV to determine feature sparsity percentage via RFE#########

#X = concatenated text features for training set (title, body, url) transformed via TfIdfVectorizer
#y = training set classification (0, 1)

import numpy as np
import pandas as pd
import sklearn.linear_model as lm
from sklearn.cross_validation import KFold
from sklearn import metrics

dylanjf

import numpy as np


class CorrMatrix():
    """
    creates and displays the correlation matrix for a data set in a
    memory efficient manner.

    additionally, allows the option to enable feature selection, cutting off
    highly correlated features at a given threshold.

dylanjf

from csv import DictReader
import numpy as np
import pandas as pd


class NestedDictCreator(dict):
    """
    Implementation of perl's autovivification feature.
    Used to generate nested dictionaries on the fly
    """

dylanjf

from abc import ABCMeta, abstractmethod
from typing import Dict

class Base(metaclass=ABCMeta):
    def __init__(self, a):
        self.a = a

    @abstractmethod
    def sub_thing(self, **data) -> Dict:
        pass

dylanjf

from abc import ABCMeta, abstractmethod
from typing import Dict

class Base(metaclass=ABCMeta):
    def __init__(self, a):
        self.a = a

    @abstractmethod
    def sub_thing(self, **data) -> Dict:
        pass