thiagomarzagao

import numpy as np
import pandas as pd
from collections import Counter
from bs4 import BeautifulSoup
from scipy import stats
from matplotlib import pyplot as plt


path = '/path/to/export.xml'
with open(path) as f:

thiagomarzagao

import numpy as np
import pandas as pd
import forestci as fci
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import cross_val_predict

# set seed

thiagomarzagao

import os
import re
import time
import requests
import pandas as pd
from bs4 import BeautifulSoup

basepath = '/Volumes/UNTITLED/wimoveis/anuncios/'
hrefs = pd.read_csv('hrefs.csv') # get URLs
hrefs = set(hrefs['href']) # remove duplicate URLs

thiagomarzagao

import os
from bs4 import BeautifulSoup

hrefs = []
path = '/Volumes/UNTITLED/wimoveis/paginas/'
for fname in os.listdir(path):
    print(fname)
    if ('.html' in fname) and ('._' not in fname):
        with open(path + fname, mode = 'r') as f:
            html = f.read()

thiagomarzagao

import time
import requests

destination = '/Volumes/UNTITLED/wimoveis/paginas/'
base_url = 'https://www.wimoveis.com.br/'
num_pages = 1557 # number of results pages
for i in range(1, num_pages):
    print('page', i)
    query_url = base_url + 'apartamentos-venda-distrito-federal-goias-pagina-{}.html'.format(i)
    response = requests.get(query_url)

thiagomarzagao

import time
import random
import telepot
from telepot.loop import MessageLoop

bot = telepot.Bot('xxxxx')

family_group_id = 'xxxxx'

def handle(msg):

thiagomarzagao

* The main model
xtscc pressfree leftism presvrl leftismXpresvrl ief gdpcapita

* Effect of VRLpres at in-sample min, ave, and max, values of presidential leftism
lincom _b[presvrl] + _b[leftismXpresvrl]*1.5
lincom _b[presvrl] + _b[leftismXpresvrl]*7.194014
lincom _b[presvrl] + _b[leftismXpresvrl]*18

* Figure 1 data (the 'xtscc' add-on does not accept the # operator, so the 'margins'
* command could not be used to graph the interaction)

thiagomarzagao

Keybase proof

I hereby claim:

• I am thiagomarzagao on github.
• I am thiagomarzagao (https://keybase.io/thiagomarzagao) on keybase.
• I have a public key ASAVdCRfhIPn2ajeJwty8IPOGKV0NmlWGuSLIU5iSELYego

To claim this, I am signing this object:

thiagomarzagao

To produce the ADS I relied on supervised learning. I tried three different approaches, compared the results, 
and picked the approach that worked best. More specifically, I tried: a) a combination of Latent Semantic Analysis 
and tree-based regression methods; b) a combination of Latent Dirichlet Allocation and tree-based regression methods; 
and c) the Wordscores algorithm. The Wordscores algorithm outperformed the alternatives. 
I created a <a href="http://democracy-scores.org">web application</a> where anyone can tweak the training data and 
see how the results change (no coding required). <u>Data and code</u>. The two corpora (A and B) are available 
in <a href="http://math.nist.gov/MatrixMarket/formats.html#MMformat">MatrixMarket format</a>. 
Each corpus is accompanied by other files: an internal index; a Python pickle with a dictionary mapping word IDs 
to words; and a Python pickle with a dictionary mapping words to word IDs. Here are the links: 
<a href="https://s3.amazonaws.com/thiagomarzagao/corpor

thiagomarzagao

library(tm)

setwd('/Users/thiagomarzagao/Dropbox/dataScience/UnB-CIC/aulaText/')
comprasnet <- read.table('subset.csv', 
                         stringsAsFactors = FALSE, 
                         sep = ',', 
                         nrows = 1000)
corpus <- Corpus(VectorSource(comprasnet$V2))
corpus <- tm_map(corpus, PlainTextDocument)
tfidf <- DocumentTermMatrix(corpus, control = list(weighting = weightTfIdf))