miguelmalvarez

(ns clojure-elasticsearch.core
  (:require [clojurewerkz.elastisch.rest :as esr]
            [clojurewerkz.elastisch.rest.index :as idx]
            [clojurewerkz.elastisch.rest.document :as doc]
            [clojurewerkz.elastisch.query :as q]))

(def index-name "test")
(def type "articles")
(def query "third")

miguelmalvarez

(ns ibmwatson.text
  (:require [clj-http.client :as client]))  	

(defn- text-call
  [text endpoint params]
  (let [root_url (str "http://access.alchemyapi.com/calls/text/" endpoint)]
	(client/get root_url {:query-params params})))

(defn entities
  [text api_key]

miguelmalvarez

from nltk import word_tokenize
from nltk.corpus import reuters 
from sklearn.feature_extraction.text import TfidfVectorizer
from nltk.stem.porter import PorterStemmer
import re
from nltk.corpus import stopwords

cachedStopWords = stopwords.words("english")

def tokenize(text):

miguelmalvarez

import pandas as pd
import numpy as np
import logging
import time
import datetime
from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
from sklearn.feature_selection import VarianceThreshold

miguelmalvarez

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn import cross_validation
import pandas as pd
import logging
import time
import datetime
import numpy as np
 
def log_info(message):

miguelmalvarez

def read_csv(file_path, has_header = True):
    with open(file_path) as f:
        if has_header: f.readline()
        data = []
        for line in f:
            line = line.strip().split(",")
            data.append([float(x) for x in line])
    return data
 
def write_csv(file_path, data):

miguelmalvarez

from sklearn.ensemble import RandomForestClassifier
import csv_io
 
def main():
    #Read in the training data and train the model
    train_data = csv_io.read_csv("data/train.csv")
    #the first column of the training set will be the judgements
    judgements = [str(int (x[0])) for x in train_data]
    train_instances = [x[1:] for x in train_data]