Skip to content

Instantly share code, notes, and snippets.

@ethanwhite

ethanwhite/scipy_version_comparison.ipynb

Last active February 29, 2016 16:52
Show Gist options
  • Save ethanwhite/30640ba9421ab4c18d41 to your computer and use it in GitHub Desktop.
Save ethanwhite/30640ba9421ab4c18d41 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
scipy_version_comparison.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"cbcdata16 = pd.read_csv(\"cbc_likelihoods.csv\")\n",
"cbcdata17 = pd.read_csv(\"cbc_likelihoods_scipy0pt17pt0.csv\")\n",
"fiadata16 = pd.read_csv(\"fia_likelihoods.csv\")\n",
"fiadata17 = pd.read_csv(\"fia_likelihoods_scipy0pt17pt0.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>site</th>\n",
" <th>S</th>\n",
" <th>N</th>\n",
" <th>likelihood_logseries</th>\n",
" <th>likelihood_pln</th>\n",
" <th>likelihood_negbin</th>\n",
" <th>likelihood_zipf</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>L105249</td>\n",
" <td>57</td>\n",
" <td>7400</td>\n",
" <td>-315.187361</td>\n",
" <td>-315.811735</td>\n",
" <td>-315.185351</td>\n",
" <td>-334.021427</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>L105252</td>\n",
" <td>57</td>\n",
" <td>3730</td>\n",
" <td>-262.599618</td>\n",
" <td>-264.710188</td>\n",
" <td>-262.482895</td>\n",
" <td>-274.556152</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>L105254</td>\n",
" <td>60</td>\n",
" <td>17359</td>\n",
" <td>-328.224545</td>\n",
" <td>-324.407750</td>\n",
" <td>-328.225260</td>\n",
" <td>-338.805827</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>L105355</td>\n",
" <td>64</td>\n",
" <td>12490</td>\n",
" <td>-367.702703</td>\n",
" <td>-364.746419</td>\n",
" <td>-367.701879</td>\n",
" <td>-387.606697</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>L105358</td>\n",
" <td>59</td>\n",
" <td>5622</td>\n",
" <td>-298.761115</td>\n",
" <td>-293.324891</td>\n",
" <td>-298.761042</td>\n",
" <td>-314.489174</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" site S N likelihood_logseries likelihood_pln \\\n",
"0 L105249 57 7400 -315.187361 -315.811735 \n",
"1 L105252 57 3730 -262.599618 -264.710188 \n",
"2 L105254 60 17359 -328.224545 -324.407750 \n",
"3 L105355 64 12490 -367.702703 -364.746419 \n",
"4 L105358 59 5622 -298.761115 -293.324891 \n",
"\n",
" likelihood_negbin likelihood_zipf \n",
"0 -315.185351 -334.021427 \n",
"1 -262.482895 -274.556152 \n",
"2 -328.225260 -338.805827 \n",
"3 -367.701879 -387.606697 \n",
"4 -298.761042 -314.489174 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cbcdata16.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>site</th>\n",
" <th>S</th>\n",
" <th>N</th>\n",
" <th>likelihood_logseries</th>\n",
" <th>likelihood_pln</th>\n",
" <th>likelihood_negbin</th>\n",
" <th>likelihood_zipf</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>L105249</td>\n",
" <td>57</td>\n",
" <td>7400</td>\n",
" <td>-315.187361</td>\n",
" <td>-315.811735</td>\n",
" <td>-315.185293</td>\n",
" <td>-334.021427</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>L105252</td>\n",
" <td>57</td>\n",
" <td>3730</td>\n",
" <td>-262.599618</td>\n",
" <td>-264.710188</td>\n",
" <td>-262.482895</td>\n",
" <td>-274.556152</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>L105254</td>\n",
" <td>60</td>\n",
" <td>17359</td>\n",
" <td>-328.224545</td>\n",
" <td>-324.407750</td>\n",
" <td>-328.225260</td>\n",
" <td>-338.805827</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>L105355</td>\n",
" <td>64</td>\n",
" <td>12490</td>\n",
" <td>-367.702703</td>\n",
" <td>-364.746419</td>\n",
" <td>-367.701881</td>\n",
" <td>-387.606697</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>L105358</td>\n",
" <td>59</td>\n",
" <td>5622</td>\n",
" <td>-298.761115</td>\n",
" <td>-293.324891</td>\n",
" <td>-298.761041</td>\n",
" <td>-314.489174</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" site S N likelihood_logseries likelihood_pln \\\n",
"0 L105249 57 7400 -315.187361 -315.811735 \n",
"1 L105252 57 3730 -262.599618 -264.710188 \n",
"2 L105254 60 17359 -328.224545 -324.407750 \n",
"3 L105355 64 12490 -367.702703 -364.746419 \n",
"4 L105358 59 5622 -298.761115 -293.324891 \n",
"\n",
" likelihood_negbin likelihood_zipf \n",
"0 -315.185293 -334.021427 \n",
"1 -262.482895 -274.556152 \n",
"2 -328.225260 -338.805827 \n",
"3 -367.701881 -387.606697 \n",
"4 -298.761041 -314.489174 "
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cbcdata17.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>site</th>\n",
" <th>S</th>\n",
" <th>N</th>\n",
" <th>likelihood_logseries</th>\n",
" <th>likelihood_pln</th>\n",
" <th>likelihood_negbin</th>\n",
" <th>likelihood_zipf</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>101001000202</td>\n",
" <td>10</td>\n",
" <td>46</td>\n",
" <td>-22.655330</td>\n",
" <td>-22.827227</td>\n",
" <td>-22.655354</td>\n",
" <td>-23.442329</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>101001000381</td>\n",
" <td>11</td>\n",
" <td>34</td>\n",
" <td>-20.711992</td>\n",
" <td>-20.884389</td>\n",
" <td>-20.712055</td>\n",
" <td>-21.611147</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>101001000385</td>\n",
" <td>10</td>\n",
" <td>48</td>\n",
" <td>-24.310473</td>\n",
" <td>-24.185236</td>\n",
" <td>-24.163248</td>\n",
" <td>-25.935552</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>101001000450</td>\n",
" <td>10</td>\n",
" <td>35</td>\n",
" <td>-19.836834</td>\n",
" <td>-19.790231</td>\n",
" <td>-19.836975</td>\n",
" <td>-20.450116</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>101005000025</td>\n",
" <td>11</td>\n",
" <td>72</td>\n",
" <td>-28.107216</td>\n",
" <td>-28.279725</td>\n",
" <td>-28.107247</td>\n",
" <td>-28.841166</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" site S N likelihood_logseries likelihood_pln \\\n",
"0 101001000202 10 46 -22.655330 -22.827227 \n",
"1 101001000381 11 34 -20.711992 -20.884389 \n",
"2 101001000385 10 48 -24.310473 -24.185236 \n",
"3 101001000450 10 35 -19.836834 -19.790231 \n",
"4 101005000025 11 72 -28.107216 -28.279725 \n",
"\n",
" likelihood_negbin likelihood_zipf \n",
"0 -22.655354 -23.442329 \n",
"1 -20.712055 -21.611147 \n",
"2 -24.163248 -25.935552 \n",
"3 -19.836975 -20.450116 \n",
"4 -28.107247 -28.841166 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fiadata16.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>site</th>\n",
" <th>S</th>\n",
" <th>N</th>\n",
" <th>likelihood_logseries</th>\n",
" <th>likelihood_pln</th>\n",
" <th>likelihood_negbin</th>\n",
" <th>likelihood_zipf</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>101001000202</td>\n",
" <td>10</td>\n",
" <td>46</td>\n",
" <td>-22.655330</td>\n",
" <td>-22.827227</td>\n",
" <td>-22.655576</td>\n",
" <td>-23.442329</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>101001000381</td>\n",
" <td>11</td>\n",
" <td>34</td>\n",
" <td>-20.711992</td>\n",
" <td>-20.884389</td>\n",
" <td>-20.712009</td>\n",
" <td>-21.611147</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>101001000385</td>\n",
" <td>10</td>\n",
" <td>48</td>\n",
" <td>-24.310473</td>\n",
" <td>-24.185236</td>\n",
" <td>-24.163248</td>\n",
" <td>-25.935552</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>101001000450</td>\n",
" <td>10</td>\n",
" <td>35</td>\n",
" <td>-19.836834</td>\n",
" <td>-19.790231</td>\n",
" <td>-19.837057</td>\n",
" <td>-20.450116</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>101005000025</td>\n",
" <td>11</td>\n",
" <td>72</td>\n",
" <td>-28.107216</td>\n",
" <td>-28.279725</td>\n",
" <td>-28.107251</td>\n",
" <td>-28.841166</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" site S N likelihood_logseries likelihood_pln \\\n",
"0 101001000202 10 46 -22.655330 -22.827227 \n",
"1 101001000381 11 34 -20.711992 -20.884389 \n",
"2 101001000385 10 48 -24.310473 -24.185236 \n",
"3 101001000450 10 35 -19.836834 -19.790231 \n",
"4 101005000025 11 72 -28.107216 -28.279725 \n",
"\n",
" likelihood_negbin likelihood_zipf \n",
"0 -22.655576 -23.442329 \n",
"1 -20.712009 -21.611147 \n",
"2 -24.163248 -25.935552 \n",
"3 -19.837057 -20.450116 \n",
"4 -28.107251 -28.841166 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fiadata17.head()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'CBC Likelihood Difference. Min: -52.6179478695, Max: 104.347081203'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEACAYAAACznAEdAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDARJEgD/D7NI2/CbKW5IAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fa61ab14750>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cbcdiff = cbcdata17[\"likelihood_negbin\"] - cbcdata16[\"likelihood_negbin\"]\n",
"cbcdiff = cbcdiff.replace(np.inf, np.nan)\n",
"cbcdiff = cbcdiff.dropna()\n",
"histogram = plt.hist(cbcdiff)\n",
"\"CBC Likelihood Difference. Min: {}, Max: {}\".format(min(cbcdiff), max(cbcdiff))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'Fia Likelihood Difference. Min: -12.3659447913, Max: 13.660184152'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEACAYAAABYq7oeAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\no7qmAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fa61a9b2810>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fiadiff = fiadata17[\"likelihood_negbin\"] - fiadata16[\"likelihood_negbin\"]\n",
"fiadiff = fiadiff.replace(np.inf, np.nan)\n",
"fiadiff = fiadiff.dropna()\n",
"histogram = plt.hist(fiadiff)\n",
"\"Fia Likelihood Difference. Min: {}, Max: {}\".format(min(fiadiff), max(fiadiff))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"logseries likelihood diff. Min: 0.0, Max: 0.0\n",
"pln likelihood diff. Min: -4.66229721496e-10, Max: 0.0115344462863\n",
"negbin likelihood diff. Min: -104.347081203, Max: 52.6179478695\n",
"zipf likelihood diff. Min: 0.0, Max: 0.0\n"
]
}
],
"source": [
"for model in ['logseries', 'pln', 'negbin', 'zipf']:\n",
" diff = cbcdata16[\"likelihood_\" + model] - cbcdata17[\"likelihood_\" + model]\n",
" print(model + \" likelihood diff. \" + \"Min: {}, Max: {}\".format(min(diff), max(diff)))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.11"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
@davharris
Copy link

Thanks @ethanwhite

To clarify, this is the same code from Xiao's PR #39 of macroecotools both times, but with Scipy 0.16 versus 0.17?

And are the only differences are in the negative binomial?

@ethanwhite
Copy link
Author

To clarify, this is the same code from Xiao's PR #39 of macroecotools both times, but with Scipy 0.16 versus 0.17?

Yes

And are the only differences are in the negative binomial?

Basically, see new results at bottom.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment