diff --git a/src/explore.ipynb b/src/explore.ipynb
index 47669f73dc17c7cd621faf3d8c51130cc4148f14..151b18aaf7263a91e061f388efab1ca8e8d94c50 100644
--- a/src/explore.ipynb
+++ b/src/explore.ipynb
@@ -26,7 +26,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -42,7 +42,7 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -317,418 +317,141 @@
"metadata": {},
"outputs": [
{
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>LogMonth</th>\n",
- " <th>Freq</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>2019-03-01</td>\n",
- " <td>34309</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>2019-02-01</td>\n",
- " <td>236606</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>2019-01-01</td>\n",
- " <td>252668</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>2018-12-01</td>\n",
- " <td>226287</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>2018-11-01</td>\n",
- " <td>253233</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>5</th>\n",
- " <td>2018-10-01</td>\n",
- " <td>256438</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>6</th>\n",
- " <td>2018-09-01</td>\n",
- " <td>230354</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>7</th>\n",
- " <td>2018-08-01</td>\n",
- " <td>216045</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>8</th>\n",
- " <td>2018-07-01</td>\n",
- " <td>205477</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>9</th>\n",
- " <td>2018-06-01</td>\n",
- " <td>209374</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>10</th>\n",
- " <td>2018-05-01</td>\n",
- " <td>238235</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>11</th>\n",
- " <td>2018-04-01</td>\n",
- " <td>242857</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>12</th>\n",
- " <td>2018-03-01</td>\n",
- " <td>255431</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>13</th>\n",
- " <td>2018-02-01</td>\n",
- " <td>213548</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>14</th>\n",
- " <td>2018-01-01</td>\n",
- " <td>235705</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>15</th>\n",
- " <td>2017-12-01</td>\n",
- " <td>213359</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>16</th>\n",
- " <td>2017-11-01</td>\n",
- " <td>254671</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>17</th>\n",
- " <td>2017-10-01</td>\n",
- " <td>224244</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>18</th>\n",
- " <td>2017-09-01</td>\n",
- " <td>212790</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>19</th>\n",
- " <td>2017-08-01</td>\n",
- " <td>195593</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>20</th>\n",
- " <td>2017-07-01</td>\n",
- " <td>176778</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>21</th>\n",
- " <td>2017-06-01</td>\n",
- " <td>184406</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>22</th>\n",
- " <td>2017-05-01</td>\n",
- " <td>231250</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>23</th>\n",
- " <td>2017-04-01</td>\n",
- " <td>225176</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>24</th>\n",
- " <td>2017-03-01</td>\n",
- " <td>257081</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>25</th>\n",
- " <td>2017-02-01</td>\n",
- " <td>246199</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>26</th>\n",
- " <td>2017-01-01</td>\n",
- " <td>256925</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>27</th>\n",
- " <td>2016-12-01</td>\n",
- " <td>226680</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>28</th>\n",
- " <td>2016-11-01</td>\n",
- " <td>258655</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>29</th>\n",
- " <td>2016-10-01</td>\n",
- " <td>254070</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>...</th>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>91</th>\n",
- " <td>2011-08-01</td>\n",
- " <td>133965</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>92</th>\n",
- " <td>2011-07-01</td>\n",
- " <td>133186</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>93</th>\n",
- " <td>2011-06-01</td>\n",
- " <td>143617</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>94</th>\n",
- " <td>2011-05-01</td>\n",
- " <td>173431</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>95</th>\n",
- " <td>2011-04-01</td>\n",
- " <td>160696</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>96</th>\n",
- " <td>2011-03-01</td>\n",
- " <td>177539</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>97</th>\n",
- " <td>2011-02-01</td>\n",
- " <td>173222</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>98</th>\n",
- " <td>2011-01-01</td>\n",
- " <td>181135</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>99</th>\n",
- " <td>2010-12-01</td>\n",
- " <td>157738</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>100</th>\n",
- " <td>2010-11-01</td>\n",
- " <td>195329</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>101</th>\n",
- " <td>2010-10-01</td>\n",
- " <td>206730</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>102</th>\n",
- " <td>2010-09-01</td>\n",
- " <td>174706</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>103</th>\n",
- " <td>2010-08-01</td>\n",
- " <td>138323</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>104</th>\n",
- " <td>2010-07-01</td>\n",
- " <td>127687</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>105</th>\n",
- " <td>2010-06-01</td>\n",
- " <td>146164</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>106</th>\n",
- " <td>2010-05-01</td>\n",
- " <td>206822</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>107</th>\n",
- " <td>2010-04-01</td>\n",
- " <td>197381</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>108</th>\n",
- " <td>2010-03-01</td>\n",
- " <td>217092</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>109</th>\n",
- " <td>2010-02-01</td>\n",
- " <td>206380</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>110</th>\n",
- " <td>2010-01-01</td>\n",
- " <td>193376</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>111</th>\n",
- " <td>2009-12-01</td>\n",
- " <td>166506</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>112</th>\n",
- " <td>2009-11-01</td>\n",
- " <td>210227</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>113</th>\n",
- " <td>2009-10-01</td>\n",
- " <td>226865</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>114</th>\n",
- " <td>2009-09-01</td>\n",
- " <td>213208</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>115</th>\n",
- " <td>2009-08-01</td>\n",
- " <td>162281</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>116</th>\n",
- " <td>2009-07-01</td>\n",
- " <td>160993</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>117</th>\n",
- " <td>2009-06-01</td>\n",
- " <td>179176</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>118</th>\n",
- " <td>2009-05-01</td>\n",
- " <td>211879</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>119</th>\n",
- " <td>2009-04-01</td>\n",
- " <td>179152</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>120</th>\n",
- " <td>2009-03-01</td>\n",
- " <td>99008</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "<p>121 rows × 2 columns</p>\n",
- "</div>"
- ],
- "text/plain": [
- " LogMonth Freq\n",
- "0 2019-03-01 34309\n",
- "1 2019-02-01 236606\n",
- "2 2019-01-01 252668\n",
- "3 2018-12-01 226287\n",
- "4 2018-11-01 253233\n",
- "5 2018-10-01 256438\n",
- "6 2018-09-01 230354\n",
- "7 2018-08-01 216045\n",
- "8 2018-07-01 205477\n",
- "9 2018-06-01 209374\n",
- "10 2018-05-01 238235\n",
- "11 2018-04-01 242857\n",
- "12 2018-03-01 255431\n",
- "13 2018-02-01 213548\n",
- "14 2018-01-01 235705\n",
- "15 2017-12-01 213359\n",
- "16 2017-11-01 254671\n",
- "17 2017-10-01 224244\n",
- "18 2017-09-01 212790\n",
- "19 2017-08-01 195593\n",
- "20 2017-07-01 176778\n",
- "21 2017-06-01 184406\n",
- "22 2017-05-01 231250\n",
- "23 2017-04-01 225176\n",
- "24 2017-03-01 257081\n",
- "25 2017-02-01 246199\n",
- "26 2017-01-01 256925\n",
- "27 2016-12-01 226680\n",
- "28 2016-11-01 258655\n",
- "29 2016-10-01 254070\n",
- ".. ... ...\n",
- "91 2011-08-01 133965\n",
- "92 2011-07-01 133186\n",
- "93 2011-06-01 143617\n",
- "94 2011-05-01 173431\n",
- "95 2011-04-01 160696\n",
- "96 2011-03-01 177539\n",
- "97 2011-02-01 173222\n",
- "98 2011-01-01 181135\n",
- "99 2010-12-01 157738\n",
- "100 2010-11-01 195329\n",
- "101 2010-10-01 206730\n",
- "102 2010-09-01 174706\n",
- "103 2010-08-01 138323\n",
- "104 2010-07-01 127687\n",
- "105 2010-06-01 146164\n",
- "106 2010-05-01 206822\n",
- "107 2010-04-01 197381\n",
- "108 2010-03-01 217092\n",
- "109 2010-02-01 206380\n",
- "110 2010-01-01 193376\n",
- "111 2009-12-01 166506\n",
- "112 2009-11-01 210227\n",
- "113 2009-10-01 226865\n",
- "114 2009-09-01 213208\n",
- "115 2009-08-01 162281\n",
- "116 2009-07-01 160993\n",
- "117 2009-06-01 179176\n",
- "118 2009-05-01 211879\n",
- "119 2009-04-01 179152\n",
- "120 2009-03-01 99008\n",
- "\n",
- "[121 rows x 2 columns]"
- ]
- },
- "execution_count": 5,
- "metadata": {},
- "output_type": "execute_result"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " LogMonth Freq\n",
+ "0 2019-03-01 34309\n",
+ "1 2019-02-01 236606\n",
+ "2 2019-01-01 252668\n",
+ "3 2018-12-01 226287\n",
+ "4 2018-11-01 253233\n",
+ "5 2018-10-01 256438\n",
+ "6 2018-09-01 230354\n",
+ "7 2018-08-01 216045\n",
+ "8 2018-07-01 205477\n",
+ "9 2018-06-01 209374\n",
+ "10 2018-05-01 238235\n",
+ "11 2018-04-01 242857\n",
+ "12 2018-03-01 255431\n",
+ "13 2018-02-01 213548\n",
+ "14 2018-01-01 235705\n",
+ "15 2017-12-01 213359\n",
+ "16 2017-11-01 254671\n",
+ "17 2017-10-01 224244\n",
+ "18 2017-09-01 212790\n",
+ "19 2017-08-01 195593\n",
+ "20 2017-07-01 176778\n",
+ "21 2017-06-01 184406\n",
+ "22 2017-05-01 231250\n",
+ "23 2017-04-01 225176\n",
+ "24 2017-03-01 257081\n",
+ "25 2017-02-01 246199\n",
+ "26 2017-01-01 256925\n",
+ "27 2016-12-01 226680\n",
+ "28 2016-11-01 258655\n",
+ "29 2016-10-01 254070\n",
+ "30 2016-09-01 238406\n",
+ "31 2016-08-01 192681\n",
+ "32 2016-07-01 171567\n",
+ "33 2016-06-01 201867\n",
+ "34 2016-05-01 294276\n",
+ "35 2016-04-01 319474\n",
+ "36 2016-03-01 360327\n",
+ "37 2016-02-01 366637\n",
+ "38 2016-01-01 372907\n",
+ "39 2015-12-01 307003\n",
+ "40 2015-11-01 338129\n",
+ "41 2015-10-01 264966\n",
+ "42 2015-09-01 272765\n",
+ "43 2015-08-01 215203\n",
+ "44 2015-07-01 207626\n",
+ "45 2015-06-01 236916\n",
+ "46 2015-05-01 250012\n",
+ "47 2015-04-01 201602\n",
+ "48 2015-03-01 188296\n",
+ "49 2015-02-01 163529\n",
+ "50 2015-01-01 163552\n",
+ "51 2014-12-01 137314\n",
+ "52 2014-11-01 154933\n",
+ "53 2014-10-01 165732\n",
+ "54 2014-09-01 132150\n",
+ "55 2014-08-01 93636\n",
+ "56 2014-07-01 80837\n",
+ "57 2014-06-01 94967\n",
+ "58 2014-05-01 132788\n",
+ "59 2014-04-01 129260\n",
+ "60 2014-03-01 157123\n",
+ "61 2014-02-01 146198\n",
+ "62 2014-01-01 151970\n",
+ "63 2013-12-01 131054\n",
+ "64 2013-11-01 156195\n",
+ "65 2013-10-01 163029\n",
+ "66 2013-09-01 122300\n",
+ "67 2013-08-01 117010\n",
+ "68 2013-07-01 113163\n",
+ "69 2013-06-01 109264\n",
+ "70 2013-05-01 163644\n",
+ "71 2013-04-01 146456\n",
+ "72 2013-03-01 156797\n",
+ "73 2013-02-01 196511\n",
+ "74 2013-01-01 169755\n",
+ "75 2012-12-01 147379\n",
+ "76 2012-11-01 186991\n",
+ "77 2012-10-01 204204\n",
+ "78 2012-09-01 160734\n",
+ "79 2012-08-01 122418\n",
+ "80 2012-07-01 110906\n",
+ "81 2012-06-01 123762\n",
+ "82 2012-05-01 178005\n",
+ "83 2012-04-01 173853\n",
+ "84 2012-03-01 184071\n",
+ "85 2012-02-01 197130\n",
+ "86 2012-01-01 192057\n",
+ "87 2011-12-01 175397\n",
+ "88 2011-11-01 211174\n",
+ "89 2011-10-01 224586\n",
+ "90 2011-09-01 171945\n",
+ "91 2011-08-01 133965\n",
+ "92 2011-07-01 133186\n",
+ "93 2011-06-01 143617\n",
+ "94 2011-05-01 173431\n",
+ "95 2011-04-01 160696\n",
+ "96 2011-03-01 177539\n",
+ "97 2011-02-01 173222\n",
+ "98 2011-01-01 181135\n",
+ "99 2010-12-01 157738\n",
+ "100 2010-11-01 195329\n",
+ "101 2010-10-01 206730\n",
+ "102 2010-09-01 174706\n",
+ "103 2010-08-01 138323\n",
+ "104 2010-07-01 127687\n",
+ "105 2010-06-01 146164\n",
+ "106 2010-05-01 206822\n",
+ "107 2010-04-01 197381\n",
+ "108 2010-03-01 217092\n",
+ "109 2010-02-01 206380\n",
+ "110 2010-01-01 193376\n",
+ "111 2009-12-01 166506\n",
+ "112 2009-11-01 210227\n",
+ "113 2009-10-01 226865\n",
+ "114 2009-09-01 213208\n",
+ "115 2009-08-01 162281\n",
+ "116 2009-07-01 160993\n",
+ "117 2009-06-01 179176\n",
+ "118 2009-05-01 211879\n",
+ "119 2009-04-01 179152\n",
+ "120 2009-03-01 99008\n"
+ ]
}
],
"source": [
"# filter hits per month (all filters) (data quarry from 05.03.2019, that's why hitcount Mar 2019 is so small)\n",
"df_hits = pd.read_csv(\"quarry-34014-how-many-abuse-filter-hits-have-been-there-per-month-en-wiki-run346197.csv\", sep=',')\n",
"df_hits['LogMonth'] = pd.to_datetime(df_hits['LogMonth'], format=\"%Y%m\")\n",
- "df_hits"
+ "\n",
+ "with pd.option_context('display.max_rows', None, 'display.max_columns', None):\n",
+ " print(df_hits)\n"
]
},
{