diff --git a/src/explore.ipynb b/src/explore.ipynb
index b05c7c4039d7602ac2651a96d5fa077e8ea9e707..ce598d4328250fa7a0640ec59a69d7e046e62238 100644
--- a/src/explore.ipynb
+++ b/src/explore.ipynb
@@ -455,7 +455,7 @@
"print (df.query('af_group!=\"default\"'))\n",
"\n",
"# --> so available groups are \"default\" and \"feedback\"\n",
- "# TODO: question: what do they mean?\n",
+ "# question: what do they mean?\n",
"# From https://www.mediawiki.org/wiki/Extension:AbuseFilter/abuse_filter_table :\n",
"# \"The group this filter belongs to, as defined in $wgAbuseFilterValidGroups.\" still don't get it\n",
"'''\n",
@@ -8806,7 +8806,7 @@
},
{
"cell_type": "code",
- "execution_count": 34,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -8821,7 +8821,7 @@
"Name: afl_action, dtype: int64"
]
},
- "execution_count": 34,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -8833,6 +8833,87 @@
"df_feb2016['afl_action'].value_counts()"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "527 67669\n",
+ "61 26874\n",
+ "650 23054\n",
+ "633 19779\n",
+ "279 18099\n",
+ "636 17891\n",
+ "384 15776\n",
+ "135 11148\n",
+ "30 7936\n",
+ "172 7315\n",
+ "380 6982\n",
+ "364 6071\n",
+ "432 5500\n",
+ "550 5432\n",
+ "80 5424\n",
+ "271 5328\n",
+ "712 5260\n",
+ "3 5223\n",
+ "686 5181\n",
+ "752 5027\n",
+ "189 4706\n",
+ "220 4572\n",
+ "260 4259\n",
+ "614 4181\n",
+ "231 3741\n",
+ "680 3662\n",
+ "491 3572\n",
+ "225 3483\n",
+ "631 3479\n",
+ "46 3345\n",
+ " ... \n",
+ "699 23\n",
+ "709 23\n",
+ "674 21\n",
+ "698 20\n",
+ "624 19\n",
+ "167 17\n",
+ "16 16\n",
+ "742 15\n",
+ "744 13\n",
+ "139 13\n",
+ "751 12\n",
+ "639 11\n",
+ "745 10\n",
+ "459 10\n",
+ "642 10\n",
+ "242 9\n",
+ "750 8\n",
+ "731 8\n",
+ "738 8\n",
+ "554 7\n",
+ "718 7\n",
+ "294 6\n",
+ "597 4\n",
+ "710 3\n",
+ "706 2\n",
+ "651 2\n",
+ "694 1\n",
+ "666 1\n",
+ "2 1\n",
+ "1 1\n",
+ "Name: afl_filter, Length: 128, dtype: int64"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_feb2016['afl_filter'].value_counts()"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -9020,7 +9101,7 @@
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -9034,7 +9115,7 @@
"Name: afl_action, dtype: int64"
]
},
- "execution_count": 38,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -9053,6 +9134,87 @@
"Again, quite a high createaccount counts.."
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "527 51720\n",
+ "61 27554\n",
+ "650 24438\n",
+ "633 20600\n",
+ "279 19557\n",
+ "636 17656\n",
+ "384 14654\n",
+ "135 9725\n",
+ "271 9185\n",
+ "30 9008\n",
+ "172 7552\n",
+ "380 6795\n",
+ "80 6211\n",
+ "220 6064\n",
+ "550 6055\n",
+ "364 5967\n",
+ "752 5773\n",
+ "712 5669\n",
+ "686 5345\n",
+ "432 4782\n",
+ "189 4727\n",
+ "3 4465\n",
+ "260 4312\n",
+ "466 3698\n",
+ "225 3557\n",
+ "29 3536\n",
+ "631 3474\n",
+ "231 3371\n",
+ "614 3252\n",
+ "680 3216\n",
+ " ... \n",
+ "5 33\n",
+ "745 32\n",
+ "68 29\n",
+ "738 26\n",
+ "744 24\n",
+ "464 23\n",
+ "139 23\n",
+ "734 22\n",
+ "676 19\n",
+ "242 19\n",
+ "264 18\n",
+ "756 17\n",
+ "750 14\n",
+ "167 14\n",
+ "751 11\n",
+ "624 10\n",
+ "722 9\n",
+ "16 7\n",
+ "639 6\n",
+ "690 5\n",
+ "459 4\n",
+ "596 3\n",
+ "642 3\n",
+ "651 2\n",
+ "718 2\n",
+ "710 1\n",
+ "597 1\n",
+ "294 1\n",
+ "554 1\n",
+ "1 1\n",
+ "Name: afl_filter, Length: 127, dtype: int64"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_mar2016['afl_filter'].value_counts()"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 39,
@@ -11031,7 +11193,7 @@
}
],
"source": [
- "#TODO Multi line chart: a line per action;\n",
+ "# Multi line chart: a line per action;\n",
"# TODO why are there combis such as \"disallow,tag\", but no \"warn,tag\"?\n",
"\n",
"# style\n",
@@ -11322,7 +11484,7 @@
}
],
"source": [
- "#TODO Multi line chart: a line per action;\n",
+ "# Multi line chart: a line per action;\n",
"# TODO why are there combis such as \"disallow,tag\", but no \"warn,tag\"?\n",
"\n",
"# style\n",
@@ -12177,9 +12339,7 @@
}
],
"source": [
- "# TODO multi line chart\n",
- "#TODO Multi line chart: a line per action;\n",
- "# TODO why are there combis such as \"disallow,tag\", but no \"warn,tag\"?\n",
+ "# Multi line chart: a line per action;\n",
"\n",
"# style\n",
"plt.style.use('seaborn-darkgrid')\n",
@@ -14138,7 +14298,7 @@
}
],
"source": [
- "# TODO make the above pie chart for active filters only\n",
+ "# make the above pie chart for active filters only\n",
"enabled_tags_2nd = collections.Counter(flatten([x.split(\", \") for x in list(df_2nd.query('af_enabled==1')['manual_tags'])])).most_common()\n",
"\n",
"# compute num of filters per parent category\n",
@@ -14188,7 +14348,7 @@
"metadata": {},
"outputs": [],
"source": [
- "#TODO Plot (manual tags)*(hit count) for all filters\n",
+ "# Plot (manual tags)*(hit count) for all filters\n",
"\n",
"\"\"\"\n",
"Note\n",
@@ -15229,15 +15389,6 @@
"df_2009_tags_2nd"
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#TODO Plot a per year (manual tags)*(hit count) for all filters"
- ]
- },
{
"cell_type": "markdown",
"metadata": {},