def sendfile(self,sock,commandArgs,recoveryFunc):
try:
fileWorker = FileWorker(sock,commandArgs,recoveryFunc)
fileWorker.sendFileInfo()
fileWorker.sendPacketsTCP()
except FileWorkerError:
pass
def receivefile(self,sock,commandArgs,recoveryFunc):
try:
fileWorker = FileWorker(sock,commandArgs,recoveryFunc)
fileWorker.recvFileInfo()
fileWorker.recvPacketsTCP()
except FileWorkerError:
pass
class BreakerUpWords(object):
"""docstring for ProcessorEntities"""
def __init__(self):
super(BreakerUpWords, self).__init__()
self.worker = FileWorker()
self.load_words_codes()
def load_words_codes(self):
self.words_codes = {}
self.words_codes["words"] = []
self.words_codes["codes"] = []
data = self.worker.read("/home/rodrigo/Twitter Analysis Library/lib/db/hashtagsDataBase.csv")
for item in data:
attr = item.split(',')
word = attr[0]
code = attr[1]
self.words_codes["words"].append(word)
self.words_codes["codes"].append(code)
def save_words_codes(self):
num_codes = len(self.words_codes["words"])
lines = []
for i in range(num_codes):
word = self.words_codes["words"][i]
code = self.words_codes["codes"][i]
line = "%s,%s"%(word,code)
lines.append(line)
self.worker.write("hashtagsDataBase.csv",lines)
def break_up_words(self,tokens):
new_tokens = []
for token in tokens:
new_tokens = new_tokens + self.break_up(token)
return new_tokens
def break_up(self,token):
tokens = []
if token in self.words_codes["words"]:#if toke is words_codes so we will break up token
index = self.words_codes["words"].index(token)
code = self.words_codes["codes"][index]
token = self.segment(token,code)#break up the words with the specified code
for newToken in token:
tokens.append(newToken)
return tokens
else:
return [token]
def segment(self,text,segs):
words = []
last = 0
for i in range(len(segs)):
if segs[i] == '1':
words.append(text[last:i+1])
last = i+1
words.append(text[last:])
return words
def enter(file_name):
print('Enter info:\n')
disciplines = input('Enter disciplines \n ')
number = input('Enter number of semester \n')
hours = input('Enter hours in semester \n')
forms = input('Enter Exam or Offset \n')
name = input('Enter name \n')
surnames = input('Enter surnames \n')
data = [disciplines, number, hours, forms, name, surnames]
if validate(data):
FileWorker.write(file_name, data)
def load_stemming_words(self):
#load a set of knowing words
self.stemmingWords = {}
self.stemmingWords["words"] = []
self.stemmingWords["matches"] = []
fileWorker = FileWorker()
data = fileWorker.read("/home/rodrigo/Twitter Analysis Library/lib/db/stemmingDataBase.csv")
for word in data:
attr = word.split(',')
word = attr[0]
match = attr[1].rstrip()
self.stemmingWords["words"].append(word)
self.stemmingWords["matches"].append(match)
def downloadStateMachine(self,sock,fileInfoRoutine,packetsRoutine,recoverRoutine,clientMsg):
#transfer init
if self.status == QueryStatus.Actual:
self.fileWorker = FileWorker(sock,self.args,recoverRoutine)
try:
#get udp client addr
if sock.proto == IPPROTO_UDP:
self.getClientAddr()
fileInfoRoutine(self.fileWorker)
self.status = QueryStatus.InPorgress
except FileWorkerError as e:
self.clientIsAlive = False
self.completeState(e.args[0])
#packets
elif self.status == QueryStatus.InPorgress:
try:
if sock.proto == IPPROTO_UDP:
self.restoreClientAddrForUDP()
packetsRoutine(self.fileWorker)
if self.fileWorker.file.closed:
#download complete
self.completeState(clientMsg)
except FileWorkerError as e:
#download error
self.clientIsAlive = False
self.completeState(e.args[0])
def search(name):
semester = input('Searched by semester \n')
hours = 0
for lection_info in FileWorker.read_lines(name):
if semester == lection_info[1]:
hours += int(lection_info[2])
print("All hours", hours)
def count(name):
lectors = []
for lector_info in FileWorker.read_lines(name):
lector = lector_info[4] + ' ' + lector_info[5]
if lector not in lectors:
lectors.append(lector)
print('Unique Lektors', lectors)
def receivefile(self, sock, commandArgs, recoveryFunc):
try:
fileWorker = FileWorker(sock, commandArgs, recoveryFunc)
fileWorker.recvFileInfo()
fileWorker.recvPacketsTCP()
except FileWorkerError:
pass
def sendfile(self, sock, commandArgs, recoveryFunc):
try:
fileWorker = FileWorker(sock, commandArgs, recoveryFunc)
fileWorker.sendFileInfo()
fileWorker.sendPacketsTCP()
except FileWorkerError:
pass
def recvfileUDP(self, sock, commandArgs):
try:
fileWorker = FileWorker(sock, commandArgs, None)
fileWorker.recvFileInfo()
fileWorker.recvPacketsUDP()
except FileWorkerError:
pass
def download(sock,fileName):
fileWorker = FileWorker(sock,fileName,None,0)
try:
fileWorker.sendFileInfo()
fileWorker.sendPacketsTCP()
except FileWorkerError as e:
sock.sendMsg(e.args[0])
else:
sock.sendMsg('downloaded')
def __init__(self): super(BreakerUpWords, self).__init__() self.worker = FileWorker() self.load_words_codes()
import sys
sys.path.append('/home/rodrigo/Twitter Analysis Library/lib')
from FileWorker import *
import re
from pymongo import *
client = MongoClient('localhost', 27017)
db = client['db_terremoto']
collection = db['ecuador_terremoto']
tweets_iterator = collection.find()
data = {}
locations = []
for tweet in tweets_iterator:
if 'coordinates' in tweet.keys():
if tweet['coordinates'] != None:
coordinates = tweet['coordinates']
lng = coordinates['coordinates'][0]
lat = coordinates['coordinates'][1]
obj = {}
obj['coordinates'] = {}
obj['coordinates']['lat'] = lat
obj['coordinates']['lng'] = lng
locations.append(obj)
data["num_tweets"] = len(locations)
data["tweets"] = locations
FileWorker().writeJSON("locations.json", data)
def save_human(self):
FileWorker.write(self.file, [self.full_name, self.birth_date])
def get_humans(self):
return FileWorker.read(self.file)
def read(name):
print(FileWorker.read(name))
import sys
from pymongo import *
from TweetParser import *
from FileWorker import *
import json
fileName = "tw_ecuador_eeuu.csv"
client = MongoClient('localhost', 27017)
db = client['twitter_db']
collection = db['tw_ecuador_eeuu']
tweets_iterator = collection.find()
tweet_parser = TweetParser(fields = ['id','created_at','text'],mentionsFlag = False,
hashtagsFlag = False,urlsFlag=False,userFlag=True,coordinatesFlag=True,placeFlag=False)
lines = []
lines.append("userID,id,created_at,lat,lng")
for rawTweet in tweets_iterator:
tweet = tweet_parser.parse(rawTweet)
if tweet["coordinates"]:
#line = "%s,%s,%s,%.4f,%.4f,%s"%(tweet['user']['id'], tweet['id'],tweet['created_at'], tweet["coordinates"]['latitud'], tweet["coordinates"]['longitud'], tweet['text'])
line = "%s,%s,%s,%.4f,%.4f"%(tweet['user']['id'], tweet['id'],tweet['created_at'], tweet["coordinates"]['latitud'], tweet["coordinates"]['longitud'])
lines.append(line)
worker = FileWorker()
worker.write(fileName,lines)
#
#
import Globals as glb
import FileWorker as fw
import City as spacePoint
from GeneticAndEvoLib import GeneticAlgorithm as ga
import Visualizer as vis
if __name__ == "__main__":
#
#
fileWorker = fw.FileWorker(citiesFilepath=glb.CITIES_FILEPATH, optTourFilepath=glb.OPTIMAL_TOUR_FILEPATH)
citiesFileMetadata, optTourFileMetadata, \
citiesCoordsList, optTourPointIdList = fileWorker.run()
print()
print("Cities File Metadata: ")
print(citiesFileMetadata)
print()
print("Opt Tour File Metadata: ")
print(optTourFileMetadata)
print()
print("Cities Coords List: ")
print(citiesCoordsList)
print()
print("Opt Tour Point Id List: ")
print(optTourPointIdList)
#
