def handler(msg_head):
decrypt = Security()
handle = MongoDAO()
rec_packet = pickle.loads(msg_head)
metadata = decrypt.app_decrypt(rec_packet[1])
if rec_packet[2] == 'key':
pub_key = handle.get_publicKey(metadata[1][0])
li = [pub_key, 'key']
send_to_client(pickle.dump(li))
elif rec_packet[2] == 'msg':
active = False
json = {"drop": msg_head, "status": "Not delivered"}
handle.insert(metadata[1][0], json)
if active:
send_to_client(msg_head)
elif rec_packet[2] == 'signup':
exist = False
exist = handle.if_user_exist(metadata[1][0])
if exist:
unique = ["User ID is Unique"]
send_to_client(pickle.dump(unique))
else:
Error = unique = ["User ID already exists - ERROR"]
send_to_client(pickle.dump(Error))
import MeCab
from mongo_dao import MongoDAO
import word_cloud
from wordcloud import WordCloud
target = "tenkou"
#MeCab準備
tagger = MeCab.Tagger("-Ochasen")
# mongoDBからデータを取得する
mongo = MongoDAO("db", target)
target_results = mongo.find()
# 解析結果の格納用
positive_words = []
negative_words = []
neutral_words = []
tweet_score = 0
# DBの接続先を辞書データに変更
mongo = MongoDAO("db", "noun")
for target_result in target_results:
text = target_result['text']
mecab_results = tagger.parse(text)
for result in mecab_results.split('\n'):
word = result.split('\t')[0]
import json
import networkx as nx
import matplotlib.pyplot as plt
from requests_oauthlib import OAuth1Session
from mongo_dao import MongoDAO
mongo = MongoDAO("db", "followers_info")
start_screen_name = 'yurinaNECOPLA' # このユーザーのフォロワーのうち相互フォローとなるユーザーに関するソーシャルグラフを出力，可視化する(これを変える)
# 新規グラフを作成
G = nx.Graph()
# ノードを追加
G.add_node(start_screen_name)
depth = 3
processed_list = []
def get_followers_list(screen_name):
result = mongo.find(filter={"screen_name": screen_name})
followers_list = []
try:
doc = result.next()
if doc != None:
for user in doc['followers_info']:
followers_list.append(user['screen_name'])
return followers_list
except StopIteration:
return followers_list
from mongo_dao import MongoDAO
import pandas as pd
db_url = 'mongodb://localhost:27017'
db_name = 'house_price_predict'
dao = MongoDAO(conn_url=db_url, dbname=db_name)
all_collections = dict()
for coll_name in dao.get_all_collection_names():
print(coll_name)
all_collections[coll_name] = pd.DataFrame(dao.get_all_documents(coll_name))
#print(all_collections[coll_name])
df = all_collections[coll_name]
print(df['price'].mean())
print(df['price'].std())
print(df['price'].count())
print(df['price'].min())
print(df['price'].max())
print(df[df['price'] < 8000000])
from mongo_dao import MongoDAO
import codecs
mongo = MongoDAO("db","noun")
dict_path = './dict/noun_dict.trim'
with codecs.open(dict_path, "r", "utf-8") as f:
for line in f:
d = line[:-1].split('\t')
print(d)
if d[1] == 'n':
d.append(-1)
elif d[1] == 'p':
d.append(1)
else:
d.append(0)
mongo.insert_one({"word": d[0], "np": d[1], "evaluation": d[2], "score": d[3]})
from ingatlan_com_crawler import IngatlanComCrawler
from mongo_dao import MongoDAO
db_url = 'mongodb://localhost:27017'
db_name = 'house_price_predict'
crawler = IngatlanComCrawler(
starter_url='https://ingatlan.com/szukites/elado+lakas+baja',
http_headers={
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36'
})
crawled_data = crawler.crawl()
dao = MongoDAO(conn_url=db_url, dbname=db_name)
dao.insert_documents(crawled_data)
collection_name = dao.collname
print('Visszaolvas db ' + collection_name)
print(len(dao.get_all_documents(collection_name)))
print(dao.get_all_collection_names())
words = []
for text in texts:
tokens = t.tokenize(text)
for token in tokens:
# 品詞から名詞だけ抽出
pos = token.part_of_speech.split(',')[0]
if pos in ['形容詞', '動詞']:
# 必要ない単語を省く(実際の結果を見てから不必要そうな単語を記載しました)
if token.base_form not in ["こと", "よう", "そう", "これ", "それ"]:
words_count[token.base_form] += 1
words.append(token.base_form)
return words_count, words
target = 'tenkou'
mongo = MongoDAO("db", target)
results = mongo.find(projection={"text": 1})
texts = []
for result in results:
s = result['text'].replace('\n', '')
text = s.split('http')
texts.append(text[0])
# with codecs.open('./output/tweet_data', 'r', 'utf-8') as f:
# reader = csv.reader(f, delimiter='\t')
# texts = []
# for row in reader:
# if(len(row) > 0):
# text = row[0].split('http')
# texts.append(text[0])