From 5205068e1d1f685aaec4b0008b65d32aafb9fa3e Mon Sep 17 00:00:00 2001
From: Lyudmila Vaseva <vaseva@mi.fu-berlin.de>
Date: Tue, 9 Jul 2019 17:58:34 +0200
Subject: [PATCH] Explore peak in hit nums beginning of 2016
---
quarries/quarry-37494 | 3 +
src/explore.ipynb | 297 ++++++++++++++++++++++++++++++++++++++++++
2 files changed, 300 insertions(+)
create mode 100644 quarries/quarry-37494
diff --git a/quarries/quarry-37494 b/quarries/quarry-37494
new file mode 100644
index 0000000..a8b14aa
--- /dev/null
+++ b/quarries/quarry-37494
@@ -0,0 +1,3 @@
+use enwiki_p;
+select * from abuse_filter_log
+where afl_timestamp < 20160201000000 and afl_timestamp >= 20160101000000;
diff --git a/src/explore.ipynb b/src/explore.ipynb
index ef63de2..cedbcab 100644
--- a/src/explore.ipynb
+++ b/src/explore.ipynb
@@ -734,6 +734,303 @@
"plt.show()"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Explore the peak in filter hits"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "10.68.16.39 1689\n",
+ "37.113.52.15 1249\n",
+ "95.152.44.52 1133\n",
+ "5.165.178.194 715\n",
+ "94.181.143.10 697\n",
+ "95.152.42.158 674\n",
+ "5.166.250.109 559\n",
+ "5.166.224.152 556\n",
+ "Acheter cialis 533\n",
+ "37.113.51.96 473\n",
+ "93.124.7.25 430\n",
+ "5.167.114.39 317\n",
+ "93.124.34.23 307\n",
+ "36.250.176.0 291\n",
+ "Wwekik2222kdjdj 279\n",
+ "37.113.37.111 274\n",
+ "94.181.170.143 247\n",
+ "Theadityapratap 239\n",
+ "94.181.156.128 229\n",
+ "93.124.46.78 222\n",
+ "Achat cialis 222\n",
+ "93.124.28.116 213\n",
+ "176.97.116.140 202\n",
+ "5.165.186.39 192\n",
+ "Acquistare cialis 190\n",
+ "93.124.74.221 187\n",
+ "AbhiJahazi 186\n",
+ "37.113.34.32 186\n",
+ "37.113.28.187 185\n",
+ "64.62.219.98 180\n",
+ " ... \n",
+ "Dharmendra780 1\n",
+ "Robertdenningraider13 1\n",
+ "SLCHT 1\n",
+ "2601:153:700:6870:B8D9:5791:192D:1DAE 1\n",
+ "59.96.9.214 1\n",
+ "207.32.26.5 1\n",
+ "208.61.1.124 1\n",
+ "149.126.106.19 1\n",
+ "121.216.118.139 1\n",
+ "HegerLoyneszhFG 1\n",
+ "2607:FB90:1903:33F9:4C08:6E2:70C7:20F6 1\n",
+ "Clutchmaster163955 1\n",
+ "86.160.200.85 1\n",
+ "38.78.194.51 1\n",
+ "69.174.87.60 1\n",
+ "PujolBoatmanJvfh 1\n",
+ "89.240.83.117 1\n",
+ "MarrowWylyLRFj 1\n",
+ "173.31.204.16 1\n",
+ "PettigrewSparacioETJg 1\n",
+ "Ednopsniwagn 1\n",
+ "Kevinfigs 1\n",
+ "162.228.50.214 1\n",
+ "LoeberArelUVURo 1\n",
+ "50.82.26.116 1\n",
+ "Kaileefiles 1\n",
+ "Bestraight 1\n",
+ "Dexon Software 1\n",
+ "203.59.81.156 1\n",
+ "119.154.88.171 1\n",
+ "Name: afl_user_text, Length: 139586, dtype: int64"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_jan2016 = pd.read_csv(\"quarry-37494-abuselog-entries-en-wiki-in-january-2016-run389216.csv\", sep=',')\n",
+ "\n",
+ "# Number of hits per editor\n",
+ "df_jan2016['afl_user_text'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "37.113.52.15 is a Russian IP (whois --> netname: ERTH-PENZA-PPPOE-16-NET)\n",
+ "95.152.44.52 too (whois--> netname: RU-PENZA-VT-DSL-200901)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "edit 300781\n",
+ "createaccount 71902\n",
+ "move 193\n",
+ "autocreateaccount 18\n",
+ "gatheredit 9\n",
+ "delete 4\n",
+ "Name: afl_action, dtype: int64"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Number of hits per editor's actions\n",
+ "df_jan2016['afl_action'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "527 71853\n",
+ "61 27072\n",
+ "650 24264\n",
+ "633 21099\n",
+ "279 18460\n",
+ "636 17279\n",
+ "384 15080\n",
+ "135 10028\n",
+ "30 7829\n",
+ "172 7471\n",
+ "271 7192\n",
+ "380 6554\n",
+ "80 6530\n",
+ "364 6238\n",
+ "686 6089\n",
+ "712 5597\n",
+ "466 5555\n",
+ "432 5398\n",
+ "220 5385\n",
+ "550 5215\n",
+ "189 4730\n",
+ "3 4656\n",
+ "148 4470\n",
+ "260 4148\n",
+ "614 4120\n",
+ "231 3398\n",
+ "631 3349\n",
+ "225 3245\n",
+ "46 3174\n",
+ "680 3134\n",
+ " ... \n",
+ "242 19\n",
+ "706 19\n",
+ "16 19\n",
+ "734 18\n",
+ "264 18\n",
+ "710 17\n",
+ "666 15\n",
+ "722 14\n",
+ "167 13\n",
+ "294 10\n",
+ "624 9\n",
+ "727 8\n",
+ "651 8\n",
+ "637 8\n",
+ "745 6\n",
+ "52 6\n",
+ "674 6\n",
+ "748 5\n",
+ "690 5\n",
+ "2 5\n",
+ "597 4\n",
+ "579 4\n",
+ "709 4\n",
+ "68 4\n",
+ "554 3\n",
+ "749 3\n",
+ "596 1\n",
+ "718 1\n",
+ "459 1\n",
+ "694 1\n",
+ "Name: afl_filter, Length: 138, dtype: int64"
+ ]
+ },
+ "execution_count": 44,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Number of hits per filter\n",
+ "df_jan2016['afl_filter'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "UserLogin 71920\n",
+ "Skateboard 660\n",
+ "Conchobar_Lads_Tomlinson 584\n",
+ "Billboard_(magazine) 536\n",
+ "Chris_Stark 467\n",
+ "Tyler_Joseph 431\n",
+ "Bulletin_board_system 339\n",
+ "Hailey_Baldwin 328\n",
+ "Flickr_-_Official_U.S._Navy_Imagery_-_Sailors_play_board_games_with_children_at_the_Cameron_Community_Ministries_during_Rochester_Navy_Week.jpg 322\n",
+ "Ryback 287\n",
+ "Aditya_Pratap 247\n",
+ "95.152.44.52 232\n",
+ "WikiProject_Film 232\n",
+ "British_Board_of_Film_Classification 224\n",
+ "10_Cloverfield_Lane 219\n",
+ "Keyboard_instrument 217\n",
+ "Board_game 203\n",
+ "176.97.116.140 202\n",
+ "93.124.46.78 198\n",
+ "AbhiJahazi 186\n",
+ "Board 184\n",
+ "Entertainment_Software_Rating_Board 178\n",
+ "Battle_of_the_Alamo 169\n",
+ "Computer_keyboard 161\n",
+ "Cultural_history_of_the_buttocks 155\n",
+ "Conchobar_Tomlinson 155\n",
+ "History_of_the_internal_combustion_engine 154\n",
+ "Skateboarder_(magazine) 146\n",
+ "WikiProject_Video_games 140\n",
+ "Cian_Mitchell 140\n",
+ " ... \n",
+ "Surfix 1\n",
+ "British_Colonial_Research_Committee 1\n",
+ "Nassau_County_Police_Department 1\n",
+ "Institute_of_Health_Sciences_Bhubaneswar 1\n",
+ "Underwater_Pompeii 1\n",
+ "El_Valle_de_Antón 1\n",
+ "Make_My_Journeys 1\n",
+ "Ten_Fold_Engineering 1\n",
+ "LNER_Class_A3_4472_Flying_Scotsman 1\n",
+ "North_Eastern_College 1\n",
+ "Zillow 1\n",
+ "Ww57614wW 1\n",
+ "Junkyard_Dog 1\n",
+ "John_Steptoe 1\n",
+ "Financial_doctor 1\n",
+ "Music_of_Portugal 1\n",
+ "Northwoods_Mall_(North_Charleston,_South_Carolina) 1\n",
+ "Niuman_Romero 1\n",
+ "Chaudhry_Faisal_Mushtaq 1\n",
+ "Big_Island_(Bay_of_Quinte) 1\n",
+ "Venus_of_Willendorf 1\n",
+ "Alexis_Argüello 1\n",
+ "Pdfpdf/Images_of_Adelaide 1\n",
+ "Chickasaw_State_Park_(Alabama) 1\n",
+ "Torin's_Passage 1\n",
+ "Gulshanthakurbohani 1\n",
+ "WPCH-TV 1\n",
+ "List_of_countries_with_IKEA_stores 1\n",
+ "Phelps,_New_York 1\n",
+ "Micheál_Quirke 1\n",
+ "Name: afl_title, Length: 91387, dtype: int64"
+ ]
+ },
+ "execution_count": 45,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Number of hits per intended edit page\n",
+ "df_jan2016['afl_title'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "To be fair, I don't see any particularly interesting or conspicious pattern, beside the 71920 attempts at account creations. But maybe it's exactly them that make the 71920 hits difference to all the \"standard\" numbers. I'm comparing this with September 2016 (238406 hits) for reference."
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
--
GitLab