{ "cells": [ { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import re\n", "import json\n", "import matplotlib.pyplot as plt\n", "\n", "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## USDA Food Database" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": false }, "outputs": [], "source": [ "db = json.load(open(\"dataset/foods.json.txt\"))" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "6636" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(db)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "dict_keys(['description', 'manufacturer', 'portions', 'id', 'tags', 'group', 'nutrients'])" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db[0].keys()" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'description': 'Protein',\n", " 'group': 'Composition',\n", " 'units': 'g',\n", " 'value': 25.18}" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db[0]['nutrients'][0]" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
descriptiongroupunitsvalue
0ProteinCompositiong25.18
1Total lipid (fat)Compositiong29.20
2Carbohydrate, by differenceCompositiong3.06
3AshOtherg3.28
4EnergyEnergykcal376.00
\n", "
" ], "text/plain": [ " description group units value\n", "0 Protein Composition g 25.18\n", "1 Total lipid (fat) Composition g 29.20\n", "2 Carbohydrate, by difference Composition g 3.06\n", "3 Ash Other g 3.28\n", "4 Energy Energy kcal 376.00" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "nutrients = pd.DataFrame(db[0]['nutrients'])\n", "nutrients.head()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
descriptiongroupidmanufacturer
0Cheese, carawayDairy and Egg Products1008
1Cheese, cheddarDairy and Egg Products1009
2Cheese, edamDairy and Egg Products1018
3Cheese, fetaDairy and Egg Products1019
4Cheese, mozzarella, part skim milkDairy and Egg Products1028
\n", "
" ], "text/plain": [ " description group id \\\n", "0 Cheese, caraway Dairy and Egg Products 1008 \n", "1 Cheese, cheddar Dairy and Egg Products 1009 \n", "2 Cheese, edam Dairy and Egg Products 1018 \n", "3 Cheese, feta Dairy and Egg Products 1019 \n", "4 Cheese, mozzarella, part skim milk Dairy and Egg Products 1028 \n", "\n", " manufacturer \n", "0 \n", "1 \n", "2 \n", "3 \n", "4 " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "info_keys = ['description', 'group', 'id', 'manufacturer']\n", "info = pd.DataFrame(db, columns=info_keys)\n", "\n", "info.head()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
id
count6636.000000
mean15733.055304
std8715.095274
min1008.000000
25%10170.750000
50%14445.000000
75%19188.250000
max93600.000000
\n", "
" ], "text/plain": [ " id\n", "count 6636.000000\n", "mean 15733.055304\n", "std 8715.095274\n", "min 1008.000000\n", "25% 10170.750000\n", "50% 14445.000000\n", "75% 19188.250000\n", "max 93600.000000" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "info.describe()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 6636 entries, 0 to 6635\n", "Data columns (total 4 columns):\n", "description 6636 non-null object\n", "group 6636 non-null object\n", "id 6636 non-null int64\n", "manufacturer 5195 non-null object\n", "dtypes: int64(1), object(3)\n", "memory usage: 207.5+ KB\n" ] } ], "source": [ "info.info()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "Vegetables and Vegetable Products 812\n", "Beef Products 618\n", "Baked Products 496\n", "Breakfast Cereals 403\n", "Fast Foods 365\n", "Legumes and Legume Products 365\n", "Lamb, Veal, and Game Products 345\n", "Sweets 341\n", "Fruits and Fruit Juices 328\n", "Pork Products 328\n", "Name: group, dtype: int64" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.value_counts(info.group)[:10]" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Now, to do some analysis on all of the nutrient data, it’s easiest to assemble the nutrients\n", "# for each food into a single large table. To do so, we need to take several steps. First, I’ll\n", "# convert each list of food nutrients to a DataFrame, add a column for the food id, and\n", "# append the DataFrame to a list. Then, these can be concatenated together with concat:\n", "\n", "nutrients = []\n", "for rec in db:\n", " fnuts = pd.DataFrame(rec['nutrients'])\n", " fnuts['id'] = rec['id']\n", " nutrients.append(fnuts)\n", "nutrients = pd.concat(nutrients, ignore_index=True)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 389355 entries, 0 to 389354\n", "Data columns (total 5 columns):\n", "description 389355 non-null object\n", "group 389355 non-null object\n", "units 389355 non-null object\n", "value 389355 non-null float64\n", "id 389355 non-null int64\n", "dtypes: float64(1), int64(1), object(3)\n", "memory usage: 14.9+ MB\n" ] } ], "source": [ "nutrients.info()" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "14179" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# check for duplicates, \n", "nutrients.duplicated().sum()" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# dropping the dups\n", "nutrients = nutrients.drop_duplicates()" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Since 'group' and 'description' is in both DataFrame objects, we can rename them to\n", "# make it clear what is what:\n", "\n", "col_mapping = {'description' : 'food',\n", " 'group' : 'fgroup'}\n", "info = info.rename(columns=col_mapping, copy=False)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 6636 entries, 0 to 6635\n", "Data columns (total 4 columns):\n", "food 6636 non-null object\n", "fgroup 6636 non-null object\n", "id 6636 non-null int64\n", "manufacturer 5195 non-null object\n", "dtypes: int64(1), object(3)\n", "memory usage: 207.5+ KB\n" ] } ], "source": [ "info.info()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Int64Index: 375176 entries, 0 to 389354\n", "Data columns (total 5 columns):\n", "nutrient 375176 non-null object\n", "nutgroup 375176 non-null object\n", "units 375176 non-null object\n", "value 375176 non-null float64\n", "id 375176 non-null int64\n", "dtypes: float64(1), int64(1), object(3)\n", "memory usage: 17.2+ MB\n" ] } ], "source": [ "col_mapping = {'description' : 'nutrient',\n", " 'group' : 'nutgroup'}\n", "nutrients = nutrients.rename(columns=col_mapping, copy=False)\n", "\n", "nutrients.info()" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Int64Index: 375176 entries, 0 to 375175\n", "Data columns (total 8 columns):\n", "nutrient 375176 non-null object\n", "nutgroup 375176 non-null object\n", "units 375176 non-null object\n", "value 375176 non-null float64\n", "id 375176 non-null int64\n", "food 375176 non-null object\n", "fgroup 375176 non-null object\n", "manufacturer 293054 non-null object\n", "dtypes: float64(1), int64(1), object(6)\n", "memory usage: 25.8+ MB\n" ] } ], "source": [ "# joining the data on column, using merge method\n", "ndata = pd.merge(nutrients, info, on='id', how='outer')\n", "\n", "ndata.info()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "nutrient Glycine\n", "nutgroup Amino Acids\n", "units g\n", "value 0.04\n", "id 6158\n", "food Soup, tomato bisque, canned, condensed\n", "fgroup Soups, Sauces, and Gravies\n", "manufacturer \n", "Name: 30000, dtype: object" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# checking 30000th row\n", "ndata.ix[30000]" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "nutrient Vitamin B-12\n", "nutgroup Vitamins\n", "units mcg\n", "value 0.04\n", "id 8185\n", "food Cereals, RALSTON, cooked with water, with salt\n", "fgroup Breakfast Cereals\n", "manufacturer \n", "Name: 50000, dtype: object" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ndata.loc[50000]" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": false }, "outputs": [], "source": [ "# aggregate the data on nutrient, fgroup columns\n", "# picking value column\n", "# \n", "result = ndata.groupby(['nutrient', 'fgroup'])['value'].quantile(0.5)" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\tools\\Anaconda3\\lib\\site-packages\\ipykernel\\__main__.py:1: FutureWarning: order is deprecated, use sort_values(...)\n", " if __name__ == '__main__':\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAvwAAAFeCAYAAAD5ZMv3AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "result['Zinc, Zn'].order().plot(kind='barh')" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\tools\\Anaconda3\\lib\\site-packages\\ipykernel\\__main__.py:1: FutureWarning: order is deprecated, use sort_values(...)\n", " if __name__ == '__main__':\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfMAAAFkCAYAAAA0bNKwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nANA5MQeAzv0vTS8eHVxQWecAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "result['Zinc, Zn'].order().plot(kind='box')" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "collapsed": true }, "outputs": [], "source": [ "by_nutrient = ndata.groupby(['nutgroup', 'nutrient'])\n", "get_maximum = lambda x: x.xs(x.value.idxmax())\n", "get_minimum = lambda x: x.xs(x.value.idxmin())\n", "max_foods = by_nutrient.apply(get_maximum)[['value', 'food']]\n", "\n", "# make the food a little smaller\n", "max_foods.food = max_foods.food.str[:50]" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "nutrient\n", "Alanine Gelatins, dry powder, unsweetened\n", "Arginine Seeds, sesame flour, low-fat\n", "Aspartic acid Soy protein isolate\n", "Cystine Seeds, cottonseed flour, low fat (glandless)\n", "Glutamic acid Soy protein isolate\n", "Glycine Gelatins, dry powder, unsweetened\n", "Histidine Whale, beluga, meat, dried (Alaska Native)\n", "Hydroxyproline KENTUCKY FRIED CHICKEN, Fried Chicken, ORIGINA...\n", "Isoleucine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Leucine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Lysine Seal, bearded (Oogruk), meat, dried (Alaska Na...\n", "Methionine Fish, cod, Atlantic, dried and salted\n", "Phenylalanine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Proline Gelatins, dry powder, unsweetened\n", "Serine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Threonine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Tryptophan Sea lion, Steller, meat with fat (Alaska Native)\n", "Tyrosine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Valine Soy protein isolate, PROTEIN TECHNOLOGIES INTE...\n", "Name: food, dtype: object" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "max_foods.ix['Amino Acids']['food']" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python [conda root]", "language": "python", "name": "conda-root-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 1 }