from csv_operation import csv_reader
from sentiment import anlaysis
data2020 = csv_reader("2021-08southchinasea.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2020-08southchinasea.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2020':" + str(len(data2020)) + ", 'data2019':" + str(
len(data2019))
js_txt += compare_txt
# data2020full = csv_reader("2021_04_05southchinasea.csv", "data")
data2020full = data2020
print("\n2. sentiment anlaysis")
total_sentiment = 0
from csv_operation import csv_reader, csv_write
from itertools import groupby
import json
movies = csv_reader("paulg.csv", "twitter_data")
print('1sample', movies[0], "#" * 10, movies[1][12])
# i0_2 = 0
# i2_4 = 0
# i4_6 = 0
# i6_7 = 0
# i7_8 = 0
# year_revenue = []
for movie in movies:
time = movie[2]
i_str = movie[12]
# print(i_str, type(i_str))
if i_str not in ('[]', 'mentions') :
i_str = i_str.replace("\'", "\"")
t = json.loads(i_str)
print('name=paulg,name='+t[0]['screen_name']+",'"+time[:16]+"'")
# name=elonmusk,name=@WholeMarsBlog,'2015-12-07 22:38'
# for t in tlist:
# name = t['name']
# if movie['vote_average'] is not None:
# vote_count = float(movie['vote_average'])
# if vote_count < 2:
time.sleep(2)
try:
places_result['next_page_token']
print('-' * 20, places_result['next_page_token'])
except KeyError as e:
print('Complete')
else:
printHotels(searchString,
cityid,
cityname,
jobname,
next=places_result['next_page_token'])
if __name__ == "__main__":
citylist = csv_reader('rank_cities.csv')
print(citylist[0], citylist[0][0], citylist[0][1])
destination = citylist[0][1]
places = []
# printHotels(mymakets_A[0] + ' near ' + citylist[0][1], citylist[0][0], citylist[0][1], mymakets_A[0])
# print(len(places), places[0], '#'*20)
# print('\n')
# printHotels(mymakets_A[0] + ' near ' + citylist[1][1], citylist[1][0],citylist[1][1], mymakets_A[0])
# print(len(places), places[0], '#'*20)
for jobname in mymakets_A:
for cityrow in citylist:
cityid = cityrow[0]
cityname = cityrow[1]
if int(cityid) >= 100 and int(cityid) < 200:
print(
colored(jobname + cityid + cityname,
from csv_operation import csv_reader
from sentiment import anlaysis
data2020 = csv_reader("2021_q1_south_china_sea.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2020_q1_south_china_sea.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2020':" + str(len(data2020)) + ", 'data2019':" + str(
len(data2019))
js_txt += compare_txt
data2020full = csv_reader("2021_q1_south_china_sea.csv", "data")
print("\n2. sentiment anlaysis")
total_sentiment = 0
num_positive = 0
from csv_operation import csv_reader
from sentiment import anlaysis
data2020 = csv_reader("2021django.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2021flask.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2020':" + str(len(data2020)) + ", 'data2019':" + str(
len(data2019))
js_txt += compare_txt
data2020full = csv_reader("2021full.csv", "data")
print("\n2. sentiment anlaysis")
total_sentiment = 0
num_positive = 0
from csv_operation import csv_reader
from sentiment import anlaysis
data2020 = csv_reader("2020senkafu.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2019senkafu.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2020':" + str(len(data2020)) + ", 'data2019':" + str(
len(data2019))
js_txt += compare_txt
data2020full = csv_reader("2020senkafu_full.csv", "data")
print("\n2. sentiment anlaysis")
total_sentiment = 0
num_positive = 0
#找出电影演员和票房总收入的关联
from csv_operation import csv_reader, csv_write
from itertools import groupby
import json
movies = csv_reader("tmdb_5000_movies.csv", "data")
print('1sample', movies[0], "#" * 10)
print('len=', len(movies))
t = json.loads(movies[0]['keywords'])
print(len(t), t[0], t[1])
year_revenue = []
for movie in movies:
revenue = int(movie['revenue'])
tlist = json.loads(movie['keywords'])
for t in tlist:
name = t['name']
# print(year, revenue)
item = [name, revenue]
year_revenue.append(item)
print(year_revenue)
print('----#--------#--------#----')
my_list2 = []
keyword_revenue = []
keyword_revenue.append(['keyword', 'revenue'])
justwords = []
for i, g in groupby(sorted(year_revenue), key=lambda x: x[0]):
#找出电影演员和票房总收入的关联
from csv_operation import csv_reader, csv_write
from itertools import groupby
import json
movies = csv_reader("tmdb_5000_credits.csv", "data")
print('1sample', movies[0], "#" * 10)
print('len=', len(movies))
t = json.loads(movies[0]['cast'])
print(len(t), t[0], t[1])
year_revenue = []
for movie in movies:
tlist = json.loads(movie['cast'])
for t in tlist:
name = t['name']
# print(year, revenue)
item = [name, 1]
year_revenue.append(item)
print(year_revenue)
print('----#--------#--------#----')
my_list2 = []
for i, g in groupby(sorted(year_revenue), key=lambda x: x[0]):
count_v = sum(v[1] for v in g)
if count_v > 30:
my_list2.append({'word': i, 'size': count_v})
from csv_operation import csv_reader
from sentiment import anlaysis
data2020 = csv_reader("2020file.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2019file.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2020':" + str(len(data2020)) + ", 'data2019':" + str(len(data2019))
js_txt += compare_txt
data2020full = csv_reader("2020_total_file.csv", "data")
print("\n2. sentiment anlaysis")
from csv_operation import csv_reader
from sentiment import anlaysis
data2020 = csv_reader("2020tw.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2019tw.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2020':" + str(len(data2020)) + ", 'data2019':" + str(len(data2019))
js_txt += compare_txt
data2020full = csv_reader("2020tw_full.csv", "data")
print("\n2. sentiment anlaysis")
from csv_operation import csv_reader
from sentiment import anlaysis
# twint -s "Nezha" --since 2021-01-01 -o Nezha.csv --csv
# twint -s "senkaku islands" --since 2021-08-01 -o senkaku.csv --csv
# twint -s "south China sea" --since 2021-08-01 -o southchinasea.csv --csv
# proxychains4 twint -s "中国经济" --since 2021-11-10 -o china_economy.csv --csv
data2020 = csv_reader("2021-08senkaku.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-*-" * 10)
data2019 = csv_reader("2020-08senkaku.csv", "data")
print(data2019[0], "#" * 10, data2019[1], "#" * 10, " \n", data2019[2])
print("-" * 10, "tweets:")
print(data2020[1][10], "\n", "#" * 10, "\n", data2019[1][10])
js_txt = '''
var DATA = {
'''
print("\n1. Heat comparison")
print(len(data2020), " VS ", len(data2019))
compare_txt = "'data2021':" + str(len(data2020)) + ", 'data2020':" + str(
len(data2019))
js_txt += compare_txt
# data2020full = csv_reader("2021-06senkaku.csv", "data")
data2020full = data2020
import pandas as pd
from csv_operation import csv_reader
from sentiment import anlaysis
import time
# 检查数据集是否正常
data2020 = csv_reader("sum.csv", "data")
print(data2020[0], "#" * 10, data2020[1], "#" * 10, " \n", data2020[2])
print("-" * 10, "tweets:")
# print(data2020[1][3])
# print("data2020[1][10]=", data2020[1][10], "\n", "@" * 10)
print("start", "*-* *-* *-* *-* *-* " * 10)
# 处理基于天的热度
from collections import defaultdict
appearances = defaultdict(int)
for curr in data2020:
# curr = curr[0].split(',')
print('curr=>' * 3, curr)
if len(curr) >= 3 and "2020" in curr[3]:
appearances[curr[3]] += 1
print('appearances=> ' * 10, appearances)
# time.sleep(100)
# 持久化为其他程序做处理
import pickle
