Mercurial > hg > plosone_underreview

comparison notebooks/correlation_samples_outliers.ipynb @ 8:0f3eba42b425 branch-tests

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
added notebooks and utils
author Maria Panteli <m.x.panteli@gmail.com>
date Mon, 11 Sep 2017 18:23:14 +0100
parents
children 9847b954c217
comparison
equal deleted inserted replaced
7:46b2c713cc73 8:0f3eba42b425
1 {
2 "cells": [
3 {
4 "cell_type": "code",
5 "execution_count": 40,
6 "metadata": {
7 "collapsed": false
8 },
9 "outputs": [
10 {
11 "name": "stdout",
12 "output_type": "stream",
13 "text": [
14 "The autoreload extension is already loaded. To reload it, use:\n",
15 " %reload_ext autoreload\n"
16 ]
17 }
18 ],
19 "source": [
20 "import numpy as np\n",
21 "import pickle\n",
22 "from scipy.stats import pearsonr\n",
23 "import sys\n",
24 "\n",
25 "%matplotlib inline\n",
26 "import matplotlib.pyplot as plt\n",
27 "\n",
28 "%load_ext autoreload\n",
29 "%autoreload 2\n",
30 "\n",
31 "sys.path.append('../')\n",
32 "import scripts.results as results\n",
33 "import scripts.utils_spatial as utils_spatial"
34 ]
35 },
36 {
37 "cell_type": "code",
38 "execution_count": 18,
39 "metadata": {
40 "collapsed": false
41 },
42 "outputs": [
43 {
44 "name": "stdout",
45 "output_type": "stream",
46 "text": [
47 "WARNING: there are 21 disconnected observations\n",
48 "Island ids: [3, 6, 26, 35, 39, 45, 52, 61, 62, 66, 77, 85, 94, 97, 98, 102, 103, 107, 110, 120, 121]\n",
49 "Antigua and Barbuda\n",
50 "Australia\n",
51 "Cuba\n",
52 "Fiji\n",
53 "French Polynesia\n",
54 "Grenada\n",
55 "Iceland\n",
56 "Jamaica\n",
57 "Japan\n",
58 "Kiribati\n",
59 "Malta\n",
60 "New Zealand\n",
61 "Philippines\n",
62 "Puerto Rico\n",
63 "Republic of Serbia\n",
64 "Saint Lucia\n",
65 "Samoa\n",
66 "Solomon Islands\n",
67 "South Korea\n",
68 "The Bahamas\n",
69 "Trinidad and Tobago\n",
70 "most outliers \n",
71 " Country Outliers\n",
72 "60 Chad 0.636364\n",
73 "86 Gambia 0.540000\n",
74 "17 French Guiana 0.535714\n",
75 "43 Benin 0.500000\n",
76 "78 El Salvador 0.484848\n",
77 "136 Botswana 0.477778\n",
78 "6 Bolivia 0.457143\n",
79 "104 Bhutan 0.454545\n",
80 "14 Liberia 0.450000\n",
81 "63 Senegal 0.439024\n",
82 "least outliers \n",
83 " Country Outliers\n",
84 "1 Lithuania 0.000000\n",
85 "120 Kazakhstan 0.000000\n",
86 "119 Denmark 0.000000\n",
87 "107 Kiribati 0.000000\n",
88 "109 Democratic Republic of the Congo 0.042553\n",
89 "105 Sudan 0.044118\n",
90 "15 Netherlands 0.044776\n",
91 "84 Iraq 0.045977\n",
92 "74 Czech Republic 0.048780\n",
93 "85 Sierra Leone 0.050000\n"
94 ]
95 }
96 ],
97 "source": [
98 "X_list, Y, Yaudio = pickle.load(open('../data/lda_data_melodia_8.pickle','rb'))\n",
99 "ddf = results.load_metadata(Yaudio, metadata_file='../data/metadata.csv')\n",
100 "w, data_countries = utils_spatial.get_neighbors_for_countries_in_dataset(Y)\n",
101 "w_dict = utils_spatial.from_weights_to_dict(w, data_countries)\n",
102 "Xrhy, Xmel, Xmfc, Xchr = X_list\n",
103 "X = np.concatenate((Xrhy, Xmel, Xmfc, Xchr), axis=1)\n",
104 "\n",
105 "# global outliers\n",
106 "df_global, threshold, MD = results.get_outliers_df(X, Y, chi2thr=0.999)\n",
107 "results.print_most_least_outliers_topN(df_global, N=10)"
108 ]
109 },
110 {
111 "cell_type": "code",
112 "execution_count": 30,
113 "metadata": {
114 "collapsed": false
115 },
116 "outputs": [
117 {
118 "data": {
119 "text/html": [
120 "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
121 "<table border=\"1\" class=\"dataframe\">\n",
122 " <thead>\n",
123 " <tr style=\"text-align: right;\">\n",
124 " <th></th>\n",
125 " <th>Country</th>\n",
126 " <th>Outliers</th>\n",
127 " <th>N</th>\n",
128 " <th>OutliersN</th>\n",
129 " </tr>\n",
130 " </thead>\n",
131 " <tbody>\n",
132 " <tr>\n",
133 " <th>0</th>\n",
134 " <td> Canada</td>\n",
135 " <td> 0.060000</td>\n",
136 " <td> 100</td>\n",
137 " <td> 6</td>\n",
138 " </tr>\n",
139 " <tr>\n",
140 " <th>1</th>\n",
141 " <td> Lithuania</td>\n",
142 " <td> 0.000000</td>\n",
143 " <td> 47</td>\n",
144 " <td> 0</td>\n",
145 " </tr>\n",
146 " <tr>\n",
147 " <th>2</th>\n",
148 " <td> Cambodia</td>\n",
149 " <td> 0.263158</td>\n",
150 " <td> 19</td>\n",
151 " <td> 5</td>\n",
152 " </tr>\n",
153 " <tr>\n",
154 " <th>3</th>\n",
155 " <td> Ethiopia</td>\n",
156 " <td> 0.257143</td>\n",
157 " <td> 35</td>\n",
158 " <td> 9</td>\n",
159 " </tr>\n",
160 " <tr>\n",
161 " <th>4</th>\n",
162 " <td> Swaziland</td>\n",
163 " <td> 0.142857</td>\n",
164 " <td> 98</td>\n",
165 " <td> 14</td>\n",
166 " </tr>\n",
167 " </tbody>\n",
168 "</table>\n",
169 "</div>"
170 ],
171 "text/plain": [
172 " Country Outliers N OutliersN\n",
173 "0 Canada 0.060000 100 6\n",
174 "1 Lithuania 0.000000 47 0\n",
175 "2 Cambodia 0.263158 19 5\n",
176 "3 Ethiopia 0.257143 35 9\n",
177 "4 Swaziland 0.142857 98 14"
178 ]
179 },
180 "execution_count": 30,
181 "metadata": {},
182 "output_type": "execute_result"
183 }
184 ],
185 "source": [
186 "df_global['N'] = np.zeros(len(df_global))\n",
187 "df_global['OutliersN'] = np.zeros(len(df_global))\n",
188 "for i, country in enumerate(df_global['Country']):\n",
189 " n_counts = len(np.where(Y==country)[0])\n",
190 " df_global['N'].iloc[i] = n_counts\n",
191 " df_global['OutliersN'].iloc[i] = np.round(n_counts * df_global['Outliers'].iloc[i])\n",
192 "df_global.head()"
193 ]
194 },
195 {
196 "cell_type": "code",
197 "execution_count": 39,
198 "metadata": {
199 "collapsed": false
200 },
201 "outputs": [
202 {
203 "name": "stdout",
204 "output_type": "stream",
205 "text": [
206 "0.662469099039 1.18268680985e-18\n"
207 ]
208 },
209 {
210 "data": {
211 "text/plain": [
212 "<matplotlib.text.Text at 0x103c730d0>"
213 ]
214 },
215 "execution_count": 39,
216 "metadata": {},
217 "output_type": "execute_result"
218 },
219 {
220 "data": {
221 "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEPCAYAAACp/QjLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
222 "text/plain": [
223 "<matplotlib.figure.Figure at 0x111d213d0>"
224 ]
225 },
226 "metadata": {},
227 "output_type": "display_data"
228 }
229 ],
230 "source": [
231 "corr, pval = pearsonr(df_global['OutliersN'], df_global['N'])\n",
232 "print corr, pval\n",
233 "\n",
234 "plt.scatter(df_global['OutliersN'], df_global['N'])\n",
235 "plt.xlabel('outliers')\n",
236 "plt.ylabel('N')"
237 ]
238 },
239 {
240 "cell_type": "code",
241 "execution_count": 42,
242 "metadata": {
243 "collapsed": false
244 },
245 "outputs": [
246 {
247 "name": "stdout",
248 "output_type": "stream",
249 "text": [
250 "-0.122714085273 0.153126076772\n"
251 ]
252 },
253 {
254 "data": {
255 "text/plain": [
256 "<matplotlib.text.Text at 0x111dc7510>"
257 ]
258 },
259 "execution_count": 42,
260 "metadata": {},
261 "output_type": "execute_result"
262 },
263 {
264 "data": {
265 "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEPCAYAAABY9lNGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X2UHXWd5/H3t4mZbTQQbwIB5dEgYjwaOyCbEWfTjnY3\nzs4EkszxAZ3Twzgye1TYkWYITOIhSrcKQxhX57guPkCOo8yyi7BxBrrTsDRDdhlcJLARzAIZYEA3\nwRBgXA1r2Hz3j1u3c/t29e261fV47+d1Tp1zb3Xdut/6dXd9q35PZe6OiIhIo668AxARkWJSghAR\nkVBKECIiEkoJQkREQilBiIhIKCUIEREJlVqCMLNvm9leM9tZt+4vzOwnZvaImX3fzI6u+9mVZvaE\nme0ys/604hIRkWjSvIO4ETi3Yd024G3uvhx4HLgSwMyWAR8ClgWf+ZqZ6e5GRCRHqZ2E3f0+4MWG\ndePufih4+wBwQvD6POBmdz/o7k8DTwJnpxWbiIjMLs+r9D8C7ghevwF4ru5nzwFvzDwiERGZlEuC\nMLMNwK/d/XtNNtMcICIiOZqX9Rea2R8CvwO8r271T4ET696fEKxr/KyShohIDO5urX4m0zsIMzsX\n+DPgPHd/pe5HW4EPm9l8MzsVeDPww7B9uHvhl6uuuir3GBSn4lScirG2xJXaHYSZ3QysAhab2bPA\nVVR7Lc0Hxs0M4H53/6S7P2ZmtwCPAa8Cn/S5HJWIiMxZagnC3T8SsvrbTbb/AvCFtOIREZHWaKxB\nCnp7e/MOIRLFmSzFmawyxFmGGOfCylSTY2aqeRIRaZGZ4UVvpBYRkfJQghARkVBKECIiEkoJQkRE\nQilBiIhIKCUIEREJpQQhIiKhlCBERCSUEoSIiIRSghARkVBKECIiEkoJQkREQilBiIhIKCUIEREJ\npQQhIiKhlCBERCSUEoSIiIRSghARkVBKECIiEkoJQkREQilBiIhIKCUIEREJpQQhIiKhlCBERCSU\nEoSIiIRSghARkVCpJQgz+7aZ7TWznXXrKmY2bmaPm9k2M1tY97MrzewJM9tlZv1pxSUiItGkeQdx\nI3Buw7orgHF3Px24O3iPmS0DPgQsCz7zNTPT3Y2ISI5SOwm7+33Aiw2rVwNbgtdbgPOD1+cBN7v7\nQXd/GngSODut2MpkbGyM/v519PevY2xsbNr7OPtoNDIywqJFp7Fo0WmMjIxE2udsn4kSZ6vHksSx\nx9lHo8ZjT+M7WhWnvPOIU0rG3VNbgFOAnXXvX6x7bbX3wFeBj9b97JvAupD9eScZHR317u4lDjc5\n3OTz5x/j8+cvnHzf3b3ER0dHW9pH42eGh4cdjpr8ORzlw8PDTfc522dm+86o28xl+7DPzJ+/0OfP\nP6alfcx+7Ef6vHmL5vQ7mqs45Z1HnJKf4NzZ+jk8zoci77xJggje7/eZE8TakP0lXnBF1te3NvgH\n9mC5yWHllPd9fWunfW50dNT7+tZ6X99a7+lZNW0f9Z+pVJZO+3mlsrTpPhcsOLHpZ8Libowzyjbu\n1RNypbLU5807NnT7+rhqJ7jauuqxDTmMOqx1OCHSdzYzvbxWxvodJSlueWcdp+QnboKYl/INSqO9\nZnacu+8xs+OB54P1PwVOrNvuhGDdNJs2bZp83dvbS29vbzqRltTY2Bhr1gxy4MA1AHR1DSW+T7hn\nzvuMYmRkhI0brwW+Anx92s/37ds7Ja7t2wfZsOFiRka+GqxbDVwKfAv4MvCzTOIWydvExAQTExNz\n31GcrBJ1YfodxLXA+uD1FcCXgtfLgIeB+cCpwG7AQvaXRnItrDjVAtOvFIe8q+v10z5Tu8peunTZ\nrFVMYfts/Mzg4OAMcQ95V9ci7+lZNSXWKNUiU6/WRx0WT9k+7O5owYKTmlwpT9/HbNVajXcnaVcx\nhX3nbNuoiklmQ9GqmICbqV6y/Rp4FrgQqAB3AY8D24CFddv/OdXG6V3AwAz7TKn4iivsZNDsBBJW\nldDTc4739KzySmWp9/Sc48PDw1NOFvPmvdYXLDjJK5Wl09oSDlfVTN3n8ce/yaESVNusm5Z4enpW\n+dKly0KTU+P+e3pWeU/POdOOafr3Dvm8ecdOqVqangwqsySIM3zevGOnJaywcq8vo66u10+WTa3a\nq1Zerf6Oon5nK203cRNLnDilfAqXINJYOjFBtCrsBNKYELq6Fk07iTbWPzfeBdRfNVev3s8JTUSN\nJ9XqZ6N+z9STYpTG8PoEBEsc1k1Zd/hKeailu4ew5NPVtSjVE2mSbTci9eImiKzbICRlAwMD3Hbb\nFq688mqeeWYPJ598BrfeemdQJz8IwKFD0+vzG23efMOUzwBUKldz5pnLGRrawubNN0z7zDPP7Gn4\nHmhsO9i374Wm33PgQHXdwMAAGzZsAOD666/m4MGDHHvsCdx770OcddYYAwMDDAwMsHz5Mnbs+Drw\nBqo9p/ewfPkeFi/eCsDQ0HcAuOCCT7F//3Wh3xPVoUNvbvkzImWmBNGmdu16kgMHrmH/fujq+gyw\ns+6n59DV9ZngBA7d3esZGtoStps6b+fMM59i27ZbJ9ds3z7IgQOH93HyyWewf//UT5k9jntt35fx\n6KOvMjY2Fvkku2HDBs466yzWrBlk9+7Ps3t39Xtvu20LAwMDfPGLnw0aqv8NsIfu7vV88Ytbpu3/\nzDOXMz4e6SsBGBq6iLvv/shkGcF64GPAU9F30qKhoYumlWnj7yXKNiKJiXPbkdeCqpgimal6pLHa\nqVn9c9T68NkaS6uN4Cu92s10dFqVSFhdf0/POVO+a7Zqlfo4ZjquOOMohoeHg3Jb6TCU2ZiGVtsS\nRGaD2iCkJryhelXLJ5U4J6LGz0SpMx8dHfWenlXByXho2gk8ar37bEkgieMRKSMlCJkU52o571ia\nJYEk9iHSyeImCLVBtKFaQ3WtIXloaHqdfJliKdLxiHQSqyaXcjAzL1O8El3jaO3u7vWTDdFZ7kOk\nHZkZ7m4tf65MJ1wliPY2NjZWd5dwUawTexL7EGk3ShASW9FOqknFE3c/RSsPkbmKmyByb3huZUGN\n1IkrUoN2kvHE3U/RykMkCagXk8RRtJ4/rcTTrAtq3OMqWnmIJCFugtBjPaWUag3S4+OrGR9fzZo1\ng6V/Klq7P+Gt3Y+vLcXJKnkt6A4icUWrUklqzEPZqpiK9ntIWrsfX9GhKiaJK6/RwjN9b5R4oo7Q\njjvtdtbl0e5VW+1+fEUXN0FooJxMzoyapcYxC/UT8EWJJ8qkdXGPK4/yECmkOFklr4WC30Fo3p7o\nkriibKfybvcqmHY/vqJDdxD5anZFLOlopyv9dp9OpN2Pr11poFxC+vvXMT6+msMP2NlCX9/WKc9P\naFXWA7ay/D5NiyGSnbgD5XQHUVBZ35Fk/X26ohQpPt1BJCTpK+I07kiK9H0ikh3dQeRMV8Qi0nbi\ntGzntVDwXkxJyrrXR7PvK2NvoTLGLJIWNFCu/WR9kgv7vjJ2TyxjzCJpipsg1AYhTZWxbaKMMYuk\nKW4bhCbrExGRUGqklqaiTGlRNGWMWaSIVMUksyrjE9bKGLNIWvTIURERCaU2CBERSVQuCcLMrjSz\nR81sp5l9z8x+w8wqZjZuZo+b2TYzW5hHbCIiUpV5gjCzU4BPACvc/e3AEcCHgSuAcXc/Hbg7eC8i\nIjnJ4w7in4GDwJFmNg84EvgZsBqodTXZApyfQ2wiIhLIPEG4+35gM/BPVBPDS+4+Dixx973BZnuB\nJVnHJiIih2U+DsLMlgJ/CpwCvAz8JzP7WP027u5mFtpdadOmTZOve3t76e3tTStUEZFSmpiYYGJi\nYs77ybybq5l9COhz9z8O3v8BsBL4beC97r7HzI4H7nH3Mxo+q26uIiItKlM3113ASjPrNjMD3g88\nBvyAw5PnDAK35xCbiIgEchkoZ2aXU00Ch4CHgD8GFgC3ACcBTwMfdPeXGj6nOwgRkRZpJLU0pakn\nRDqXEoTMKOnHoYpIuShByIz0fASRzlamRmoRESkBPQ+iA+j5CCISh6qYOoQaqUU6l9ogREQklNog\nREQkUUoQIiISSglCRERCKUGIiEgoJQgREQmlBCGxjY2N0d+/jv7+dYyNjeUdTmmo3KQs1M1VYtH8\nTvGo3CQPGgchmdL8TvGo3CQPGgfRZlQNISJ501xMBdRYDbF9+2DhqiE0v1M8KjcpE1UxFVBZqiE0\nv1M8KjfJmtog2siKFb3s2HEh9Qmip+dGHnpoIseoRKSs4iYIVTEV0qvAZXXvLwPeklMsItKplCAK\naPHiJcBKYGuwZpDFi5/KMSIR6UTqxVRAQ0MX0d3918BqYDXd3X/N0NBFeYclIh1GbRAFpYZMEUmK\nGqlFSk4XBZIWJQiREtMUHJImJQiREivL2BcpJ021IR2tKFOTFCUOkUS4e2mWargiU42Ojnp39xKH\nmxxu8u7uJT46OlqqOIpyDNKegnNny+dcVTFJ6RWlemaucaiRWtJSqpHUZrYQ+CbwNsCBC4EngP8I\nnAw8DXzQ3V/KIz6RPAwMDCgpSKHk1Qbx74A73P2twDuAXcAVwLi7nw7cHbwXmVV1YOF6YAuwJZgh\nNfuBhUWJQyQpmVcxmdnRwA53f1PD+l3AKnffa2bHARPufkbDNqpiklBFqZ4pShwi9RLv5mpmV83w\nmVpr8edb/bJgv+8E/gPwGLAc+BHwp8Bz7v76YBsD9tfe131WCUISoRO5dJI02iB+SZAM6rwW+Diw\nGIiVIILvXAF82t3/h5l9mYbqJHd3MwvNBJs2bZp83dvbS29vb8wwpFOV4YFMInMxMTHBxMTEnPcT\nqYrJzI4CLqGaHG4BNrv787G+sFp9dL+7nxq8fw9wJfAm4L3uvsfMjgfuURWTpCGJXk+6A5EySWWg\nnJktMrNh4BHgNcAKd18fNzkAuPse4FkzOz1Y9X7gUeAHHP6PHQRuj/sdImmq3YGMj69mfHw1a9YM\nalCctKUZq5jM7DpgDXAD8A53/0WC33sx8F0zmw/sptrN9QjgFjP7OEE31wS/T2TSXJ8LvXnzDUH1\nVPV65sCB6jrdRUi7adYGcSnwa2AjsLHabjzJ3f2ouF/q7o8A7wr50fvj7lMkqoGBAW67bUtdFZHa\nH0TCaCS1SIs086qUjWZzFcmQGqmlTJQgREQklKb7FpFJmnZckqA7CJE2ozYSaaQ7CJGSSvpqf2o3\n3EEOHPgYF1zwKd1NSMuUIERylP6guzFgC/v3f1aD+qRlShAidbKuu59+tX/NZO+ouKZOO74JuC7R\n/UvnUIIQCbTLFBq1gYB9fVupVH6edzhSZnGeU5rXgp5JLRGNjo56X99a7+tbG/nZzn19a4NnQnuw\n3OR9fWtTjzPNZ1HrWdfiHv+Z1Lk8clQkTWWazjvtaT80rYjMhbq5StuJO513WPfQDRsu5t57HwLS\nHTGtkdnJUVlOl8YDg0Q6SuPV9qpVFzMy8tXU70TKdMdTdCrLhMWpl8prQW0QEkFS9e5ZtUnk0fbR\nrlSW4VAbhEiV6t1FkqEEIW1pYGBgzklhrg8WKtr3dAKVZbLUSJ2gpBrHOrWRrYjHnVVMRTz2slJZ\nThe3kTr3doVWFgrcBpFUvXen9lvv1OMWyQIx2yByP+m3FGyBE0RSjWN5DdZqdVBZ0tS4KJKeuAlC\nbRAdTt0CRWRGcbJKXgsFvoMoaxVTUa7cVcUkkh50B5GvpLpWdmoXzU49bpEiUy+mDqenj4m0v7i9\nmJQgRN0CRdqcEoS0vSInsiRjK/JxSjlpHIS0tSI3YicZW5GPU8oLjYOQrGU5fqIova3CJBlbkY9T\nyituglAvJolF4ydEOkCcrJLEAhwB7AB+ELyvAOPA48A2YGHIZxLPrEUX9So969HQWV/pFrnqpVOq\nmIow4l7ioWxVTMClwHeBrcH7a4HLg9frgS+FfCbpciu0qCeLPE4qc0kQcU80RT5BJRlbEY9zpr+x\nIsYq05UqQQAnAHcB7627g9gFLAleHwfsCvlc4gVXZFFPwnnN3xQnKRX5CllmFvY31tOzSr/Lkoib\nILrSq7xq6i+BPwMO1a1b4u57g9d7gSWZRyWR1UY+9/Vtpa9va+T2h82bbwjaLQaBahtGrUtnUY2N\njdHfv47+/nWMjY3lHU5hPPPMc6X7XUprMm+kNrPfBZ539x1m1hu2jbu7mYUOeNi0adPk697eXnp7\nQ3fRFqI+/CSvh6Qk8VCeolNjfFXY39jJJ5/G/v35xiXhJiYmmJiYmPuO4tx2zGUBvgA8CzwF/G/g\nl8B3qFYxHRdsczyqYnL34jZSx1W2KiZ1Oz2s8W+sbL/LTkbMKqZcR1Kb2SrgMnf/PTO7FnjB3a8x\nsyuo9mK6omF7zzNeSUaZRgr3969jfHw11WoUgGq12rZtt+YZVmGU6XfZyUo51UaQIIbcfbWZVYBb\ngJOAp4EPuvtLDdsrQaQgrX/ydjh5aDJDaQelTBCtUoJIXlonwHY6sbZDopPOpgQhsaRVhaKqGZHi\niJsg8urmKiIiBacE0eGGhi6iu3s9sAXYEnSRvaiw+02SxjckS+XZhuJ0fcproQO7uWYhrS6yRe56\nqy6ayVJ5Fhtl7ObaKrVBtE4NrOHURlKV1N+HyrPY1AYh09R6Eo2Pr2Z8fDVr1gzq1l8m5fn3oeqo\nkohz25HXgqqYWqJRwDNTlUiyfx+tlKfKPnvogUEi0dUmGzxcvVLOMRpF0Up5Tp2wEQ4cqK5T+ReP\nEkQby2sSv7LohMkGm0n676PTy7MdqQ2ijYVNyQ20XPer+uKp4pRHEcsw7pTtc1WGLtASiFMvldeC\n2iDmJE7dr+qLp1IZJqPIXaDbEWV6olzcRQlibuI0SqqheyqVoZRR3AShKiYREQmlRuoOEqdRUg3d\nU6kMpZNoJHWHiTNyVqOxp1IZStloum+RlOV1kldyiUblNLO4CSL3hudWFtRILTnJqyeSekBFo3Jq\nDk3WJ5KesMnoenq+weLFS4D0rlg1CV40KqfmNFmfSKZ28sgjj2kixBQUcVBhx4pz25HXgqqYJCeN\nVRhdXYsyGdvQaVUncY+308qpVaiKSSRd9Y2g+/a9wI4dF5JFlUYnNb7Opaqok8qpVXGrmDQOQiSi\n+snoas9SyGJsgybBi0bllDy1QUhTIyMjLFp0GosWncbIyEje4RRGXhPdtTtN5FcsqmKSGY2MjLBx\n47XAV4I1lzA8fDkbNmzIMyxpc6oqSp4GykniFi06jf37P0t9fXClcjUvvPBk7H3qn18ke2qDkMI7\nXG9/DQDbtw+qakakwNQGITO69NILgUuo1QfDJcG6eKY+arKaKGp3E3OlvvMiydMdhMyo1tZw/fVX\nA3DppcVsf9CdiUhK4gyemMsCnAjcAzwK/Bi4JFhfAcaBx4FtwMKQzyY0bKQz5f0Ur7QGM+mBPFV5\n/36luIg5UC6PO4iDwGfc/WEzex3wIzMbBy4Ext39WjNbD1wRLJKAIlxl17qGHm6k1lV+Uorw+5U2\nFCerJLkAtwPvB3YBS4J1xwG7QrZNNKt2kna+ym7HaRZavRto59+vzB1lfOSomZ0C9AAPUE0Oe4Mf\n7QWW5BRW4aTVALtv395SNezOVA5zHbRWtMGAtbsBTQQouYuTVZJYgNcBPwLOD96/2PDz/SGfSTSr\nlkFSV8eN+5k/f6HPn39Maa6607pLGB4edjhqcr9wlA8PDycQcXxx7gba8S5KkkOJ2iAws9cAtwLf\ncffbg9V7zew4d99jZscDz4d9dtOmTZOve3t76e3tTTnafE3tGgoHDlTXtVq33Fj/v2/f8imTzcXd\nb1aSKodG119/I9WR4oN1664uZG+tZtS+I/UmJiaYmJiY834yTxBmZsC3gMfc/ct1P9pK9b+0dha4\nPeTjUxKEtKZ+MrP+/nU5RyMzGRq6iO3bW58IUJPVSU3jxfPnPve5eDuKc9sxlwV4D3AIeBjYESzn\nUu3mehcl7uaaRjfDtKoO8qySiFNORatiSrtLqbqsSpKIWcWUWxtErGALnCDSPOGmdbLI4yQ0l3JK\nK97h4WGvVJZ6pbI0cnJQfb+USdwEocn6ElJ90MmpwFPBmlPp63uq9M/ETXpyvZkeCLNq1YqgPaA6\nxUeR2wD0/GMpG03Wl7N9+/YCfw9cF6y5jH373pJjRHOX1eCrf/zHJxgfv4vatOIbN14CUOgkIdIR\n4tx25LVQ4Cqmnp5V07om9vSsSvU7064iSmPwVVj1zIIFJ077nkplaWHr4ctaxVTU8pT0UaZuru1o\n8eJFkdYlpaxTK4R1x7zggk9N2+7Xv/5VYY+vjF1Ky/r3IjmLk1XyWijwHUTWV5VTr+5HHVZOXnUn\nJatjCutJtHTpOzV1RII0FUdnQ3cQ+crvqnKM2vCR/fthzZrkrgyzOqawacXvvfchdu9O/KtEpBVx\nskpeCwW+g8ja4av7lW15ZRj37kX17OHK2m4iyUDjIDrP6OioVypL2zJBuLd+so9yEixSAsk6liId\nu2RLCaJD6crwsNnq2YtUVkWKRdpf3AShZ1KXXJSprvW85qqoz8TOYvrvNJ/PnQf9jbWmNOUVJ6vk\ntaA7iJZ10pXqbMcapSdPVtN/t1Ovok76G0tCHuWFqpgkTNiJqKdnVdvWRTerZ4/yjxnWplOpLE0l\nznY5qbZTsstCHuUVN0Gom2sHeuSRH3Po0Gag/QZMNZvyukgD3IoUi8iM4mSVvBZ0B9GyxivVrq7X\nOwzpam8GRXzCXNG1091QFspUxaTZXDtA/Yys+/btZceOT6CZSGc2MjJSmplliyLpWX/bXdblFXc2\nVyWIDtM4J0939/q2qmISkemUICQyXe2JdBYlCBERCRU3QWignIiIhFKCEBGRUEoQIiISSglCRERC\nKUGIiEgoJQgREQmlBCEiIqGUIEREJJQShIiIhFKCEBGRUIVKEGZ2rpntMrMnzGx93vGIiHSywiQI\nMzsC+CvgXGAZ8BEze2u+UcUzMTGRdwiRKM5kKc5klSHOMsQ4F4VJEMDZwJPu/rS7HwT+Bjgv55hi\nKcsfjeJMluJMVhniLEOMc1GkBPFG4Nm6988F60REJAdFShCax1tEpEAK8zwIM1sJbHL3c4P3VwKH\n3P2aum2KEayISMmU+oFBZjYP+F/A+4CfAT8EPuLuP8k1MBGRDjUv7wBq3P1VM/s0MAYcAXxLyUFE\nJD+FuYMQEZFiKVIj9TRmVjGzcTN73My2mdnCGbb7tpntNbOdGcc368A+M/tK8PNHzKwny/jqYmga\np5mdYWb3m9krZjaUR4xBHLPF+dGgHP+nmf03M3tHQeM8L4hzh5n9yMx+u2gx1m33LjN71czWZhlf\n3ffPVpa9ZvZyUJY7zGxjEeMMtukNYvyxmU1kHGIthtnK87K6stwZ/O5Dz6sAuHthF+Ba4PLg9Xrg\nSzNs91tAD7Azw9iOAJ4ETgFeAzwMvLVhm98B7ghe/0vgH3IowyhxHgOcBQwDQzn9rqPE+ZvA0cHr\ncwtcnq+te/12quN7ChVj3Xb/FfhbYF1By7IX2JrH32SLcS4EHgVOCN4vLmKcDdv/LnBXs30W+g4C\nWA1sCV5vAc4P28jd7wNezCqoQJSBfZPxu/sDwEIzW5JtmLPH6e4/d/cHgYMZx1YvSpz3u/vLwdsH\ngBMyjhGixfnLurevA/ZlGB9EH3R6MfCfgZ9nGVydqHG23PsmYVHivAC41d2fA3D3rH/n0Ppg4wuA\nm5vtsOgJYom77w1e7wWyPrk2E2VgX9g2WZ/UyjIAsdU4Pw7ckWpE4SLFaWbnm9lPgDuBSzKKrWbW\nGM3sjVRPHv8+WJVHY2SUsnTg3UGV3R1mtiyz6A6LEuebgYqZ3WNmD5rZH2QW3WGR/4fM7EhgALi1\n2Q5z78VkZuPAcSE/2lD/xt29YOMgosbSePWT9TEUqcyaiRynmb0X+CPgnPTCmVGkON39duB2M/st\n4DvAW1KNquHrI2zzZeCK4P/KyOcqPUqcDwEnuvuvzOwDwO3A6emGNU2UOF8DrKDaTf9I4H4z+wd3\nfyLVyKZq5X/994Dt7v5Ss41yTxDu3jfTz4KG5+PcfY+ZHQ88n2Fos/kpcGLd+xOpZuxm25wQrMtS\nlDiLIFKcQcP0N4Bz3T3rakVosTzd/T4zm2dmi9z9hdSjq4oS45nA31RzA4uBD5jZQXffmk2IQIQ4\n3f0Xda/vNLOvmVnF3fdnFCNEK89ngX3ufgA4YGZ/DywHskwQrfxtfphZqpeAUjRSrw9eX8EMjdTB\nz08h20bqecDu4HvnM3sj9UryaVSdNc66bTeRXyN1lPI8iWoj3Mo8YmwhzqUc7kK+AthdtBgbtr8R\nWFvQslxSV5ZnA08XNM4zgLuoNhQfCewElhUtzmC7o4EXgO5Z95l1Ybd4wJWg0B8HtgELg/VvAP6u\nbrubqY6+/r9UM/mFGcX3Aaqjv58ErgzW/QnwJ3Xb/FXw80eAFTmVY9M4qVbxPQu8TLWx/5+A1xUw\nzm8Gf9g7guWHBS3Py4EfBzHeB7yraDE2bJtLgohYlp8KyvJh4L+T08VBxP/1y6j2ZNoJXFLgOAeB\n70XZnwbKiYhIqKL3YhIRkZwoQYiISCglCBERCaUEISIioZQgREQklBKEiIiEUoIQaZGZDQYj+2vv\nJ8xsRfD678zsqPyiE0mOEoRI6/6Q6mDNmsnBRO7+r939n6PuyMz0PyiFpT9OEcDMLg0eoLLTzP6t\nmZ1S/wCq4EErV5nZOqrPzviumT1kZv+iYT9Pm1kleP0xM3sgeDjL12vJwMz+j5ldZ2YPA79pZl8y\ns0eDGUv/IsPDFmlKCUI6npmdSfWu4Gyqc2Z9guoDYOo51UmFbwUeBC5w9xXu/krIdpjZW4EPAu92\n9x7gEPDRYJsjqc7L9U5gF3C+u7/N3ZcDVyd9fCJx5T6bq0gBvAf4vldn4sTMvg/8q5DtbIbXYdu9\nj+qMqQ8GM6Z2A3uCn/8/Ds/D/zLwipl9i+qT3f425jGIJE4JQqR61d948j+aqXfY3Uydbz/KJGZb\n3P3PQ9a/4sEkaO7+qpmdTTWh/D7w6eC1SO5UxSRSnXH1fDPrNrPXUn207Z3AsWZWMbPfoPr83ppf\nAM16Kjk9ylVTAAAAnUlEQVRwN/D7ZnYMQLCfkxo3DL5vobvfCVxK9RkCIoWgOwjpeO6+w8xuAn4Y\nrPqGuz9oZp8P1v0UeKzuIzcBXzezXwHvnmGfPzGzjcC2oHH6IPBJqlOp1999LAD+S9DYbcBnEjsw\nkTnSdN8iIhJKVUwiIhJKCUJEREIpQYiISCglCBERCaUEISIioZQgREQklBKEiIiEUoIQEZFQ/x8G\nX9vUTo3l8gAAAABJRU5ErkJggg==\n",
266 "text/plain": [
267 "<matplotlib.figure.Figure at 0x111dd7350>"
268 ]
269 },
270 "metadata": {},
271 "output_type": "display_data"
272 }
273 ],
274 "source": [
275 "corr, pval = pearsonr(df_global['Outliers'], df_global['N'])\n",
276 "print corr, pval\n",
277 "\n",
278 "plt.scatter(df_global['Outliers'], df_global['N'])\n",
279 "plt.xlabel('outliers')\n",
280 "plt.ylabel('N')"
281 ]
282 },
283 {
284 "cell_type": "code",
285 "execution_count": null,
286 "metadata": {
287 "collapsed": true
288 },
289 "outputs": [],
290 "source": []
291 }
292 ],
293 "metadata": {
294 "kernelspec": {
295 "display_name": "Python 2",
296 "language": "python",
297 "name": "python2"
298 },
299 "language_info": {
300 "codemirror_mode": {
301 "name": "ipython",
302 "version": 2
303 },
304 "file_extension": ".py",
305 "mimetype": "text/x-python",
306 "name": "python",
307 "nbconvert_exporter": "python",
308 "pygments_lexer": "ipython2",
309 "version": "2.7.12"
310 }
311 },
312 "nbformat": 4,
313 "nbformat_minor": 0
314 }