Spaces:
Sleeping
Sleeping
File size: 11,894 Bytes
246df79 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 |
import itertools
import os
import pickle
import re
from operator import itemgetter
import easy_db
from pprint import pprint
import json
import networkx as nx
from Pinpoint.RandomForest import *
import Pinpoint.FeatureExtraction
import csv
db_path = "../new-new-just-posts-and-clean-dates-parler-messages.db"
log_file = open("community_logs.txt", 'w')
log_file.write("")
log_file.close()
used_names = []
SHOULD_WRITE_CSVS = False
class grapher():
"""
A wrapper class used for generating a graph for interactions between users
"""
graph = None
def __init__(self):
"""
Constructor.
"""
self.graph = Graph()
def add_edge_wrapper(self, node_1_name, node_2_name, weight=1, relationship=None):
"""
A wrapper function used to add an edge connection or node.
:param node_1_name: from
:param node_2_name: to
:param weight:
:param relationship:
:return:
"""
# get node one ID
node_1 = None
for node in self.graph.vs:
if node["label"] == node_1_name.capitalize():
node_1 = node
if node_1 == None:
self.graph.add_vertices(1)
node_count = self.graph.vcount()
self.graph.vs[node_count-1]["id"] = node_count-1
self.graph.vs[node_count-1]["label"] = node_1_name.capitalize()
node_1 = self.graph.vs[node_count-1]
# get node two id
node_2 = None
for node in self.graph.vs:
if node["label"] == node_2_name.capitalize():
node_2 = node
if node_2 == None:
self.graph.add_vertices(1)
node_count = self.graph.vcount()
self.graph.vs[node_count - 1]["id"] = node_count - 1
self.graph.vs[node_count - 1]["label"] = node_2_name.capitalize()
node_2 = self.graph.vs[node_count - 1]
#print("User one {} - {}, user two {} - {}".format(node_1["label"], str(node_1["id"]),
# node_2["label"], str(node_2["id"])))
self.graph.add_edges([(node_1["id"], node_2["id"])])
#self.graph.add_edge(node_1_name, node_2_name, weight=weight, relation=relationship) # , attr={""}
def add_node(self, node_name):
"""
A wrapper function that adds a node with no edges to the graph
:param node_name:
"""
node_1 = None
for node in self.graph.vs:
if node["label"] == node_name.capitalize():
node_1 = node["id"]
if node_1 == None:
self.graph.add_vertices(1)
node_count = self.graph.vcount()
self.graph.vs[node_count-1]["id"] = node_count-1
self.graph.vs[node_count-1]["label"] = node_name.capitalize()
node_1 = self.graph.vs[node_count-1]
def get_database(where=None):
#print(where)
message_db = easy_db.DataBase(db_path)
if where is None:
return message_db.pull("parler_messages")
else:
return message_db.pull_where("parler_messages", where)
def get_mentioned_usernames_from_post(post):
# Process mentions
mentions = re.findall("\@([a-zA-Z\-\_]+)", post)
sanitised_list = []
for mention in mentions:
mention = mention.replace("@", "")
sanitised_list.append(mention)
return sanitised_list
def get_rows_from_csv_where_field_is(csv_name, username, month):
rows = []
with open(csv_name, 'rt', encoding="utf8") as f:
for row in csv.DictReader(f, fieldnames=["A","B","C","WC","Analytic","Clout","Authentic","Tone","WPS","Sixltr",
"Dic","function","pronoun","ppron","i","we","you","shehe","they","ipron",
"article","prep","auxverb","adverb","conj","negate","verb","adj","compare",
"interrog","number","quant","affect","posemo","negemo","anx","anger","sad",
"social","family","friend","female","male","cogproc","insight","cause","discrep",
"tentat","certain","differ","percept","see","hear","feel","bio","body","health",
"sexual","ingest","drives","affiliation","achieve","power","reward","risk",
"focuspast","focuspresent","focusfuture","relativ","motion","space","time","work",
"leisure","home","money","relig","death","informal","swear","netspeak","assent",
"nonflu","filler","AllPunc","Period","Comma","Colon","SemiC","QMark","Exclam",
"Dash","Quote","Apostro","Parenth","OtherP"]):
if username.strip().lower() in row["A"].strip().lower() \
and month.strip().lower() in row["B"].strip().lower():
rows.append(row)
return rows
month_graphs = {}
year_range = list(range(2017, 2022))
month_range = list(range(1, 13))
INITIAL_COMMUNITIES_FILE_NAME = "phase_one_communities_file.pickle"
SECOND_COMMUNITIES_FILE_NAME = "phase_two_communities_file.pickle"
print("Loading old {} file".format(INITIAL_COMMUNITIES_FILE_NAME))
pickle_file = open(INITIAL_COMMUNITIES_FILE_NAME, "rb")
month_graphs = pickle.load(pickle_file)
pickle_file.close()
print("loaded...")
# Get communities
month_graph_keys = list(month_graphs.keys())
month_graph_keys.sort()
list_of_community_objects = []
# get top 10 centrality users per month of parler
if not os.path.isfile(SECOND_COMMUNITIES_FILE_NAME):
dict_of_centrality_per_month = {}
dict_of_user_count_per_month = {}
dict_of_shrinkage = {}
total_unique_user_list = []
total_users = []
highest_centrality = 0
highest_centrality_user = None
date_of_highest_centrality = None
dict_of_messages = {}
number_of_users_dict = {}
highest_number_of_users = 0
highest_number_of_users_month = None
shrinkage_per_month = {}
last_month = None
all_months_centality = {}
all_centralities = {}
for month_key in month_graph_keys:
print("Reviewing graph for date '{}'".format(month_key))
graph = month_graphs[month_key].graph
user_nodes = graph.nodes.keys()
print("users {}".format(len(user_nodes)))
centrality_for_month = {}
iterator = 0
centrality_for_month = nx.degree_centrality(graph)
all_centralities[month_key] = centrality_for_month
# sort
if len(centrality_for_month) > 0:
sorted_list = sorted(centrality_for_month, key=centrality_for_month.get, reverse=True)[:10]
all_months_centality[month_key] = sorted_list
unique_users = {}
for month in all_months_centality:
for user in all_months_centality[month]:
if user not in unique_users.keys():
unique_users[user] = [{"month":month, "centrality":all_centralities[month][user]}]
else:
unique_users[user].append({"month":month, "centrality":all_centralities[month][user]})
pprint(unique_users)
# write to csv
if SHOULD_WRITE_CSVS:
seen_users = []
with open('all-messages.json.csv', 'w', encoding='utf8', newline='') as output_file:
writer = csv.DictWriter(output_file,fieldnames=["username","timestamp","message"])
for month in all_months_centality:
graph = month_graphs[month]
for user in all_months_centality[month]:
if user not in seen_users:
seen_users.append(user)
# get from database where username == user and month == month
# loop through messages.
# if above threshold is extremist.
if user != "-":
print("getting posts for user '{}'".format(user))
posts = get_database("username='{}' COLLATE NOCASE".format(user))
print("Posts found: {}".format(len(posts)))
if posts == None:
raise Exception("no posts, 'where' failed")
for post in posts:
#users_mentioned = get_mentioned_usernames_from_post(post["body"])
writer.writerow({"username": post["username"], "timestamp": post["Time"], "message": post["body"]})
model = random_forest()
model.train_model(features_file = None, force_new_dataset=False, model_location=r"far-right-baseline.model")
dict_of_users_all = {}
feature_extractor = Pinpoint.FeatureExtraction.feature_extraction(violent_words_dataset_location="swears",baseline_training_dataset_location="data/LIWC2015 Results (Storm_Front_Posts).csv")
# Get the is-extremist score for users for the month they were in the highest centrality
for month in all_months_centality:
for user in all_months_centality[month]:
print("Getting data for user {} and month {}".format(user, month))
# Get rows for this user and month
rows = get_rows_from_csv_where_field_is("data/LIWC2015 Results (all-messages.csv).csv", user, month)
# write these to a new (temp) csv
pprint(rows)
if len(rows) <= 1:
print("Not enough rows for {} {}".format(user, month))
continue
keys = rows[0].keys()
with open('temp.csv', 'w', newline='', encoding='utf8') as output_file:
dict_writer = csv.DictWriter(output_file, keys)
dict_writer.writeheader()
dict_writer.writerows(rows)
feature_extractor._reset_stored_feature_data()
feature_extractor._get_type_of_message_data(data_set_location="temp.csv")
with open("messages.json", 'w') as outfile:
json.dump(feature_extractor.completed_tweet_user_features, outfile, indent=4)
rows = model.get_features_as_df("messages.json", True)
print("Length of rows returned: {}".format(len(rows)))
number_of_connections = 0
number_of_connections_extremist = 0
is_extemist_count = 0
for row in rows:
post = row["C"]
is_extremist = model.model.predict(post)
print("Post '{}...' is extemist {}".format(post[:20], is_extremist))
if is_extremist:
is_extemist_count = is_extemist_count+1
# If we were to do mentione dusers we'd need to markup with LIWC again. Could I use the less reliable version without LIWC?
if is_extemist_count != 0:
percentage_extremist = len(rows) /is_extemist_count
else:
percentage_extremist = 0
if user not in dict_of_users_all:
dict_of_users_all[user] = {"months":{}}
if "months" in dict_of_users_all[user].keys():
dict_of_users_all[user]["months"][month] = percentage_extremist
with open('data.json', 'w') as fp:
json.dump(dict_of_users_all, fp)
# mark up csv with LIWC scores.
# number of unique users. manual 100 max (less users), otherwise doesn't really matter.
# classed as radicalised? Look at the accounts and posts, what are they up to over time.
# are any posts far right, mostly extremist material,
# when looking at connections - apply the same above. at time period on mention and overall.
# create the csv writer
# when have they been active, what monts are they extremist, how often, common words or phrases, etc
'''users_of_interest[user] = {
"centrality": month[user],
"is_extremist":,
"is_connections_extremist":,
}
'''
# radicalisation window?
# use high centrality users that are extremist
# look at the work.
|