Last active
April 19, 2017 23:17
-
-
Save kforeman/a549966a39242b717286bb48ada17afb to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": true | |
}, | |
"cell_type": "code", | |
"source": "import xarray as xr\nfrom fbd_core import db\nimport numpy as np\nimport pandas as pd", | |
"execution_count": 1, | |
"outputs": [] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Open example `DataArray`" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "da = xr.open_dataarray('/ihme/forecasting/data/fbd_scenarios_data/forecast/sev/20170406_weighted_quantiles/metab_sbp.nc')\nda = da.loc[{'year_id': 2015, 'scenario': 0, 'draw': 0}]\nda", | |
"execution_count": 2, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": "<xarray.DataArray (location_id: 188, age_group_id: 12, sex_id: 2)>\narray([[[ 0.083082, 0.039269],\n [ 0.132577, 0.060753],\n ..., \n [ 0.426379, 0.436346],\n [ 0.444403, 0.466056]],\n\n [[ 0.044293, 0.033703],\n [ 0.091831, 0.054983],\n ..., \n [ 0.39365 , 0.417222],\n [ 0.415969, 0.445148]],\n\n ..., \n [[ 0.070702, 0.044486],\n [ 0.129525, 0.073576],\n ..., \n [ 0.39822 , 0.463433],\n [ 0.399438, 0.500044]],\n\n [[ 0.076865, 0.067248],\n [ 0.143387, 0.101176],\n ..., \n [ 0.407869, 0.493196],\n [ 0.407822, 0.516327]]])\nCoordinates:\n * location_id (location_id) int32 6 7 8 10 11 12 13 14 15 16 17 18 19 20 ...\n year_id int32 2015\n * age_group_id (age_group_id) int32 10 11 12 13 14 15 16 17 18 19 20 21\n rei |S9 'metab_sbp'\n measure |S3 'sev'\n * sex_id (sex_id) int32 1 2\n quantile float64 0.025\n scenario int64 0\n draw int64 0" | |
}, | |
"metadata": {}, | |
"execution_count": 2 | |
} | |
] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Map `location_id` to `super_region_id`" | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Get list" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "sr_map = db.get_locations_by_level(3)[['location_id','super_region_id']]\nsr_map.head()", | |
"execution_count": 3, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>location_id</th>\n <th>super_region_id</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>6</td>\n <td>4</td>\n </tr>\n <tr>\n <th>1</th>\n <td>7</td>\n <td>4</td>\n </tr>\n <tr>\n <th>2</th>\n <td>8</td>\n <td>4</td>\n </tr>\n <tr>\n <th>3</th>\n <td>10</td>\n <td>4</td>\n </tr>\n <tr>\n <th>4</th>\n <td>11</td>\n <td>4</td>\n </tr>\n </tbody>\n</table>\n</div>", | |
"text/plain": " location_id super_region_id\n0 6 4\n1 7 4\n2 8 4\n3 10 4\n4 11 4" | |
}, | |
"metadata": {}, | |
"execution_count": 3 | |
} | |
] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Restrict to the 188 locations in the example `DataArray`" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "sr_map = sr_map.loc[sr_map['location_id'].isin(da.coords['location_id'].values)]", | |
"execution_count": 4, | |
"outputs": [] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Make an `xarray.DataArray` which maps `location_id` to `super_region_id` using 0/1" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "sr_map['match'] = int(1)\nx_map = sr_map.set_index(['location_id','super_region_id']).to_xarray()\nx_map = x_map.fillna(0)\nx_map", | |
"execution_count": 5, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": "<xarray.Dataset>\nDimensions: (location_id: 188, super_region_id: 7)\nCoordinates:\n * location_id (location_id) int64 6 7 8 10 11 12 13 14 15 16 17 18 19 ...\n * super_region_id (super_region_id) int64 4 31 64 103 137 158 166\nData variables:\n match (location_id, super_region_id) float64 1.0 0.0 0.0 0.0 ..." | |
}, | |
"metadata": {}, | |
"execution_count": 5 | |
} | |
] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Use array multiplication to do `groupby('super_region_id')`" | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Multiply to stratify locations by super regions" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "prod = da * x_map\nprod", | |
"execution_count": 6, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": "<xarray.Dataset>\nDimensions: (age_group_id: 12, location_id: 188, sex_id: 2, super_region_id: 7)\nCoordinates:\n * location_id (location_id) int64 6 7 8 10 11 12 13 14 15 16 17 18 19 ...\n * super_region_id (super_region_id) int64 4 31 64 103 137 158 166\n year_id int32 2015\n * age_group_id (age_group_id) int32 10 11 12 13 14 15 16 17 18 19 20 21\n rei |S9 'metab_sbp'\n measure |S3 'sev'\n * sex_id (sex_id) int32 1 2\n quantile float64 0.025\n scenario int64 0\n draw int64 0\nData variables:\n match (location_id, age_group_id, sex_id, super_region_id) float64 0.08308 ..." | |
}, | |
"metadata": {}, | |
"execution_count": 6 | |
} | |
] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Then sum across locations within a super region" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "by_sr = prod.sum(dim='location_id')", | |
"execution_count": 7, | |
"outputs": [] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Compare to `pandas.DataFrame` approach" | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Convert to dataframe" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false, | |
"scrolled": true | |
}, | |
"cell_type": "code", | |
"source": "df = da.to_dataframe(name='value').reset_index()\ndf.head()", | |
"execution_count": 8, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>location_id</th>\n <th>age_group_id</th>\n <th>sex_id</th>\n <th>year_id</th>\n <th>rei</th>\n <th>measure</th>\n <th>quantile</th>\n <th>scenario</th>\n <th>draw</th>\n <th>value</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>6</td>\n <td>10</td>\n <td>1</td>\n <td>2015</td>\n <td>metab_sbp</td>\n <td>sev</td>\n <td>0.025</td>\n <td>0</td>\n <td>0</td>\n <td>0.083082</td>\n </tr>\n <tr>\n <th>1</th>\n <td>6</td>\n <td>10</td>\n <td>2</td>\n <td>2015</td>\n <td>metab_sbp</td>\n <td>sev</td>\n <td>0.025</td>\n <td>0</td>\n <td>0</td>\n <td>0.039269</td>\n </tr>\n <tr>\n <th>2</th>\n <td>6</td>\n <td>11</td>\n <td>1</td>\n <td>2015</td>\n <td>metab_sbp</td>\n <td>sev</td>\n <td>0.025</td>\n <td>0</td>\n <td>0</td>\n <td>0.132577</td>\n </tr>\n <tr>\n <th>3</th>\n <td>6</td>\n <td>11</td>\n <td>2</td>\n <td>2015</td>\n <td>metab_sbp</td>\n <td>sev</td>\n <td>0.025</td>\n <td>0</td>\n <td>0</td>\n <td>0.060753</td>\n </tr>\n <tr>\n <th>4</th>\n <td>6</td>\n <td>12</td>\n <td>1</td>\n <td>2015</td>\n <td>metab_sbp</td>\n <td>sev</td>\n <td>0.025</td>\n <td>0</td>\n <td>0</td>\n <td>0.159037</td>\n </tr>\n </tbody>\n</table>\n</div>", | |
"text/plain": " location_id age_group_id sex_id year_id rei measure quantile \\\n0 6 10 1 2015 metab_sbp sev 0.025 \n1 6 10 2 2015 metab_sbp sev 0.025 \n2 6 11 1 2015 metab_sbp sev 0.025 \n3 6 11 2 2015 metab_sbp sev 0.025 \n4 6 12 1 2015 metab_sbp sev 0.025 \n\n scenario draw value \n0 0 0 0.083082 \n1 0 0 0.039269 \n2 0 0 0.132577 \n3 0 0 0.060753 \n4 0 0 0.159037 " | |
}, | |
"metadata": {}, | |
"execution_count": 8 | |
} | |
] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### Merge on super region" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "df = df.merge(sr_map[['location_id','super_region_id']])", | |
"execution_count": 9, | |
"outputs": [] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "### `groupby`" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "df_by_sr = df.groupby(['super_region_id','age_group_id','sex_id']).aggregate({'value': 'sum'})\ndf_by_sr.head()", | |
"execution_count": 10, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th></th>\n <th></th>\n <th>value</th>\n </tr>\n <tr>\n <th>super_region_id</th>\n <th>age_group_id</th>\n <th>sex_id</th>\n <th></th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th rowspan=\"5\" valign=\"top\">4</th>\n <th rowspan=\"2\" valign=\"top\">10</th>\n <th>1</th>\n <td>1.553835</td>\n </tr>\n <tr>\n <th>2</th>\n <td>0.720195</td>\n </tr>\n <tr>\n <th rowspan=\"2\" valign=\"top\">11</th>\n <th>1</th>\n <td>3.011857</td>\n </tr>\n <tr>\n <th>2</th>\n <td>1.277670</td>\n </tr>\n <tr>\n <th>12</th>\n <th>1</th>\n <td>3.415010</td>\n </tr>\n </tbody>\n</table>\n</div>", | |
"text/plain": " value\nsuper_region_id age_group_id sex_id \n4 10 1 1.553835\n 2 0.720195\n 11 1 3.011857\n 2 1.277670\n 12 1 3.415010" | |
}, | |
"metadata": {}, | |
"execution_count": 10 | |
} | |
] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Compare results" | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "def compare(sr, a, s):\n pandas_result = df_by_sr.loc[sr, a, s].value\n xarray_result = by_sr.loc[{'super_region_id': sr, 'age_group_id': a, 'sex_id': s}]['match'].values\n print(pandas_result, xarray_result)", | |
"execution_count": 11, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "compare(4, 11, 1)", | |
"execution_count": 12, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": "(3.0118570055526592, array(3.0118570055526592))\n", | |
"name": "stdout" | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "compare(166, 15, 2)", | |
"execution_count": 13, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": "(11.459929973513688, array(11.459929973513688))\n", | |
"name": "stdout" | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "combined = pd.merge(df_by_sr.reset_index(), by_sr.to_dataframe().reset_index())\ncombined.head()", | |
"execution_count": 14, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>super_region_id</th>\n <th>age_group_id</th>\n <th>sex_id</th>\n <th>value</th>\n <th>match</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>4</td>\n <td>10</td>\n <td>1</td>\n <td>1.553835</td>\n <td>1.553835</td>\n </tr>\n <tr>\n <th>1</th>\n <td>4</td>\n <td>10</td>\n <td>2</td>\n <td>0.720195</td>\n <td>0.720195</td>\n </tr>\n <tr>\n <th>2</th>\n <td>4</td>\n <td>11</td>\n <td>1</td>\n <td>3.011857</td>\n <td>3.011857</td>\n </tr>\n <tr>\n <th>3</th>\n <td>4</td>\n <td>11</td>\n <td>2</td>\n <td>1.277670</td>\n <td>1.277670</td>\n </tr>\n <tr>\n <th>4</th>\n <td>4</td>\n <td>12</td>\n <td>1</td>\n <td>3.415010</td>\n <td>3.415010</td>\n </tr>\n </tbody>\n</table>\n</div>", | |
"text/plain": " super_region_id age_group_id sex_id value match\n0 4 10 1 1.553835 1.553835\n1 4 10 2 0.720195 0.720195\n2 4 11 1 3.011857 3.011857\n3 4 11 2 1.277670 1.277670\n4 4 12 1 3.415010 3.415010" | |
}, | |
"metadata": {}, | |
"execution_count": 14 | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "np.all(combined['value'] == combined['match'])", | |
"execution_count": 15, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": "True" | |
}, | |
"metadata": {}, | |
"execution_count": 15 | |
} | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"name": "python2", | |
"display_name": "Python 2", | |
"language": "python" | |
}, | |
"language_info": { | |
"mimetype": "text/x-python", | |
"nbconvert_exporter": "python", | |
"name": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.12", | |
"file_extension": ".py", | |
"codemirror_mode": { | |
"version": 2, | |
"name": "ipython" | |
} | |
}, | |
"gist_id": "a549966a39242b717286bb48ada17afb" | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment