jonas/master-thesis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Better Initialization

Browse Source
This commit is contained in:
Jonas Weinz 2019-12-01 14:04:07 +01:00
parent 020685c86a
commit 9c406c3e48
14 changed files with 15621 additions and 1647 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8738
EvolutionaryAlgorithm/EvolutionaryAlgorithm.ipynb
View File

File diff suppressed because one or more lines are too long

1117
EvolutionaryAlgorithm/EvolutionaryAlgorithm.py Normal file
View File

File diff suppressed because it is too large Load Diff

5386
EvolutionaryAlgorithm/InitializationPlots.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

371
EvolutionaryAlgorithm/InteractiveVersion.ipynb Normal file
View File

@ -0,0 +1,371 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# User Interface for the Evolutionary Algorithm"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <script type=\"text/javascript\">\n",
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
" if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
" if (typeof require !== 'undefined') {\n",
" require.undef(\"plotly\");\n",
" requirejs.config({\n",
" paths: {\n",
" 'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n",
" }\n",
" });\n",
" require(['plotly'], function(Plotly) {\n",
" window._Plotly = Plotly;\n",
" });\n",
" }\n",
" </script>\n",
" "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" <script type=\"text/javascript\">\n",
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
" if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
" if (typeof require !== 'undefined') {\n",
" require.undef(\"plotly\");\n",
" requirejs.config({\n",
" paths: {\n",
" 'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n",
" }\n",
" });\n",
" require(['plotly'], function(Plotly) {\n",
" window._Plotly = Plotly;\n",
" });\n",
" }\n",
" </script>\n",
" "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/jonas/Dokumente/gitRepos/master_thesis/EvolutionaryAlgorithm/EvolutionaryAlgorithm.py:58: TqdmExperimentalWarning:\n",
"\n",
"Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n",
"\n"
]
}
],
"source": [
"import EvolutionaryAlgorithm"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import ipywidgets as widgets\n",
"from IPython.display import display, HTML, Markdown"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# user widgets\n",
"w_result_out = widgets.Output()\n",
"w_ing_list_out = widgets.Output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**setup input ingredients:**"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"**number of input ingredients:**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5796ec52773740c59e747c0e5f77410e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"ToggleButtons(index=3, options=('1', '2', '3', '4', '5', '6', '7', '8', '9', '10'), style=ToggleButtonsStyle(b…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"**maximum number of additional ingredients:**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "92fd11191481475a9c40ae76201b4772",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"ToggleButtons(index=3, options=('0', '1', '2', '3', '4', '5', '6', '7', '8', '9'), style=ToggleButtonsStyle(bu…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "618b5a44910843bbaed8b36c3ad2bc46",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Output()"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"**number of evolutionary cycles:**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "301ebb9ed6024493ad85c2b79402345e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"ToggleButtons(index=1, options=('0', '5', '10', '15', '20', '25', '30', '35', '40', '45'), style=ToggleButtons…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"**population size:**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c90d303cd2cb43d1aae401ac6226e3a1",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"ToggleButtons(index=1, options=('5', '10', '15', '20', '25', '30', '35', '40', '45', '50'), style=ToggleButton…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "cea1f9de60344298ac8417d755ad74df",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Button(description='run EA', style=ButtonStyle())"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3ac8e962dfeb445fa3417dbdbfd5c44c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Output()"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"w_number_input_ings = widgets.ToggleButtons(\n",
" options = [str(i+1) for i in range(10)],\n",
" value='4')\n",
"w_number_input_ings.style.button_width=\"10px\"\n",
"w_number_additional_ings = widgets.ToggleButtons(options=[str(i) for i in range(10)], value='3')\n",
"w_number_additional_ings.style.button_width=\"10px\"\n",
"\n",
"'''\n",
"containers = [\n",
" widgets.Combobox(\n",
" # value='John',\n",
" placeholder='Choose Ingredient',\n",
" options=EvolutionaryAlgorithm.m_base_mix.get_labels(),\n",
" description=f'Ingredient {i}',\n",
" ensure_option=True,\n",
" disabled=False\n",
" )\n",
"\n",
" for i in range(10)]\n",
"'''\n",
"\n",
"containers = [\n",
" widgets.Text(\n",
" # value='John',\n",
" placeholder='Choose Ingredient',\n",
" description=f'Ingredient {i}',\n",
" disabled=False\n",
" )\n",
"\n",
" for i in range(10)]\n",
"\n",
"ingredients = []\n",
"w_ing_container = widgets.VBox(ingredients)\n",
"\n",
"display(Markdown(\"**number of input ingredients:**\"))\n",
"display(w_number_input_ings)\n",
"display(Markdown(\"**maximum number of additional ingredients:**\"))\n",
"display(w_number_additional_ings)\n",
"\n",
"def update_ings(e=None):\n",
" if len(w_ing_container.children) == int(w_number_input_ings.value):\n",
" return\n",
" \n",
" w_ing_list_out.clear_output()\n",
" with w_ing_list_out:\n",
" display(widgets.VBox([containers[i] for i in range(int(w_number_input_ings.value))]))\n",
"\n",
"update_ings()\n",
"display(w_ing_list_out)\n",
"\n",
"# control evo cycle:\n",
"w_number_cycles = widgets.ToggleButtons(options=[str(i*5) for i in range(10)], value='5')\n",
"w_number_cycles.style.button_width=\"10px\"\n",
"\n",
"w_population_size = widgets.ToggleButtons(options=[str((i+1)*5) for i in range(10)], value='10')\n",
"w_population_size.style.button_width=\"10px\"\n",
"\n",
"display(Markdown(\"**number of evolutionary cycles:**\"))\n",
"display(w_number_cycles)\n",
"display(Markdown(\"**population size:**\"))\n",
"display(w_population_size)\n",
"\n",
"\n",
"w_run_button = widgets.Button(description=\"run EA\")\n",
"\n",
"def run(e=None):\n",
" w_result_out.clear_output()\n",
" with w_result_out:\n",
" p = EvolutionaryAlgorithm.Population(\n",
" [containers[i].value for i in range(int(w_number_input_ings.value))],\n",
" max_additional_ings=int(w_number_additional_ings.value)\n",
" )\n",
" p.run(int(w_number_cycles.value))\n",
" display(Markdown(\"**Population after running EA:**\"))\n",
" p.plot_population(collect_scores=int(w_population_size.value)>0)\n",
" \n",
"display(w_run_button)\n",
"display(w_result_out)\n",
"w_run_button.on_click(run)\n",
"\n",
"w_number_input_ings.observe(update_ings)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

132
EvolutionaryAlgorithm/ea_tools.ipynb
View File

@ -1,28 +1,8 @@
{ {
"nbformat": 4,
"nbformat_minor": 2,
"metadata": {
"language_info": {
"name": "python",
"codemirror_mode": {
"name": "ipython",
"version": 3
}
},
"orig_nbformat": 2,
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"npconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": 3
},
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [],
"source": [ "source": [
"# Statistical Tools" "# Statistical Tools"
] ]
@ -33,14 +13,13 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import numpy as np" "import numpy as np\n",
"import scipy.stats"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [],
"source": [ "source": [
"* Helper function to calculate the wheel of fortune" "* Helper function to calculate the wheel of fortune"
] ]
@ -61,14 +40,109 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def wheel_of_fortune_selection(items: list, item_scores:list):\n", "def wheel_of_fortune_weights(items:list, item_scores:list):\n",
" ordering = np.argsort(item_scores)\n", " rank = scipy.stats.rankdata(item_scores)\n",
" ordering = ordering + 1\n",
"\n", "\n",
" wheel_weights = wheel_of_fortune(ordering, len(ordering))\n", " n = len(items)\n",
"\n", "\n",
" return np.random.choice(items, p=wheel_weights)\n" " return wheel_of_fortune(rank, n)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def wheel_of_fortune_selection(items: list, item_scores:list, num_choices=1):\n",
" \n",
" wheel_weights = wheel_of_fortune_weights(items, item_scores)\n",
" \n",
" n = min(len(items), num_choices)\n",
" \n",
" choice = np.random.choice(items, size=n, replace=False, p=wheel_weights)\n",
" \n",
" if num_choices == 1:\n",
" return choice[0]\n",
"\n",
" return choice\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def combined_wheel_of_fortune_selection(items_list:list, item_scores_list:list, num_choices=1):\n",
" \n",
" scores = {}\n",
" \n",
" for i in range(len(items_list)):\n",
" items = items_list[i]\n",
" item_scores = item_scores_list[i]\n",
" \n",
" w = wheel_of_fortune_weights(items, item_scores)\n",
" #print(items, item_scores)\n",
" #print(w)\n",
" \n",
" for j, item in enumerate(items):\n",
" if item in scores:\n",
" scores[item] += w[j]\n",
" else:\n",
" scores[item] = w[j]\n",
" \n",
" combined_items = []\n",
" combined_scores = []\n",
" \n",
" for i,s in scores.items():\n",
" combined_items.append(i)\n",
" combined_scores.append(s)\n",
" \n",
" combined_scores = np.array(combined_scores)\n",
" \n",
" #print(combined_scores)\n",
" #print(np.sum(combined_scores))\n",
" \n",
" combined_scores /= len(items_list)\n",
" \n",
" #print(combined_scores)\n",
" \n",
" #print(np.sum(combined_scores))\n",
" \n",
" n = min(len(combined_items), num_choices)\n",
" \n",
" return np.random.choice(combined_items, size=n, replace=False, p=combined_scores)\n",
" \n",
" "
] ]
} }
] ],
"metadata": {
"file_extension": ".py",
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5rc1"
},
"mimetype": "text/x-python",
"name": "python",
"npconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": 3
},
"nbformat": 4,
"nbformat_minor": 4
} }

67
EvolutionaryAlgorithm/ea_tools.py
View File

@ -4,6 +4,7 @@
# # Statistical Tools # # Statistical Tools
import numpy as np import numpy as np
import scipy.stats
# * Helper function to calculate the wheel of fortune # * Helper function to calculate the wheel of fortune
@ -12,11 +13,67 @@ def wheel_of_fortune(rank_i,n):
return rank_i / (0.5 * n * (n + 1)) return rank_i / (0.5 * n * (n + 1))
def wheel_of_fortune_selection(items: list, item_scores:list): def wheel_of_fortune_weights(items:list, item_scores:list):
ordering = np.argsort(item_scores) rank = scipy.stats.rankdata(item_scores)
ordering = ordering + 1
n = len(items)
return wheel_of_fortune(rank, n)
def wheel_of_fortune_selection(items: list, item_scores:list, num_choices=1):
wheel_weights = wheel_of_fortune_weights(items, item_scores)
n = min(len(items), num_choices)
choice = np.random.choice(items, size=n, replace=False, p=wheel_weights)
if num_choices == 1:
return choice[0]
return choice
def combined_wheel_of_fortune_selection(items_list:list, item_scores_list:list, num_choices=1):
scores = {}
for i in range(len(items_list)):
items = items_list[i]
item_scores = item_scores_list[i]
w = wheel_of_fortune_weights(items, item_scores)
#print(items, item_scores)
#print(w)
for j, item in enumerate(items):
if item in scores:
scores[item] += w[j]
else:
scores[item] = w[j]
combined_items = []
combined_scores = []
for i,s in scores.items():
combined_items.append(i)
combined_scores.append(s)
combined_scores = np.array(combined_scores)
#print(combined_scores)
#print(np.sum(combined_scores))
combined_scores /= len(items_list)
#print(combined_scores)
#print(np.sum(combined_scores))
n = min(len(combined_items), num_choices)
return np.random.choice(combined_items, size=n, replace=False, p=combined_scores)
wheel_weights = wheel_of_fortune(ordering, len(ordering))
return np.random.choice(items, p=wheel_weights)

1
RecipeAnalysis/AdjMatrixTests.ipynb Normal file
View File

@ -0,0 +1 @@
{"cells":[{"cell_type":"code","execution_count":1,"metadata":{},"outputs":[{"data":{"text/html":" <script type=\"text/javascript\">\n window.PlotlyConfig = {MathJaxConfig: 'local'};\n if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n if (typeof require !== 'undefined') {\n require.undef(\"plotly\");\n requirejs.config({\n paths: {\n 'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n }\n });\n require(['plotly'], function(Plotly) {\n window._Plotly = Plotly;\n });\n }\n </script>\n "},"metadata":{},"output_type":"display_data"},{"data":{"text/html":" <script type=\"text/javascript\">\n window.PlotlyConfig = {MathJaxConfig: 'local'};\n if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n if (typeof require !== 'undefined') {\n require.undef(\"plotly\");\n requirejs.config({\n paths: {\n 'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n }\n });\n require(['plotly'], function(Plotly) {\n window._Plotly = Plotly;\n });\n }\n </script>\n "},"metadata":{},"output_type":"display_data"}],"source":"import sys\nsys.path.append(\"../\")\n\nimport settings\n\nimport pycrfsuite\n\nimport json\n\nimport db.db_settings as db_settings\nfrom db.database_connection import DatabaseConnection\n\nfrom Tagging.conllu_generator import ConlluGenerator\nfrom Tagging.crf_data_generator import *\n\nfrom RecipeAnalysis.Recipe import Ingredient\n\nfrom difflib import SequenceMatcher\n\nimport numpy as np\n\nimport plotly.graph_objs as go\nfrom plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot\nfrom plotly.subplots import make_subplots\ninit_notebook_mode(connected=True)\n\nfrom graphviz import Digraph\n\nimport itertools\n\nimport random\n\nimport plotly.io as pio\npio.renderers.default = \"jupyterlab\"\n\nfrom IPython.display import Markdown, HTML, display\n\nfrom copy import deepcopy"},{"cell_type":"code","execution_count":2,"metadata":{},"outputs":[],"source":"import dill\nm_act = dill.load(open(\"m_act.dill\", \"rb\"))\nm_mix = dill.load(open(\"m_mix.dill\", \"rb\"))\nm_base_act = dill.load(open(\"m_base_act.dill\", \"rb\"))\nm_base_mix = dill.load(open(\"m_base_mix.dill\", \"rb\"))\n\n#m_act.apply_threshold(3)\n#m_mix.apply_threshold(3)\n#m_base_act.apply_threshold(5)\n#m_base_mix.apply_threshold(5)\n\n\n#c_act = m_act.get_csr()\n#c_mix = m_mix.get_csr()\n#c_base_act = m_base_act.get_csr()\n#c_base_mix = m_base_mix.get_csr()\n\nc_act = m_act._csr\nc_mix = m_mix._csr\nc_base_act = m_base_act._csr\nc_base_mix = m_base_mix._csr"},{"cell_type":"code","execution_count":3,"metadata":{},"outputs":[],"source":"base_ingredients = m_base_mix.get_labels()\nactions = m_act.get_labels()[0]"},{"cell_type":"markdown","execution_count":null,"metadata":{},"outputs":[],"source":"## get most used ingredients"},{"cell_type":"code","execution_count":18,"metadata":{},"outputs":[],"source":"ings = []\ning_sum = []\n\nfor ing in base_ingredients:\n ings.append(ing)\n ing_sum.append(m_base_mix.get_sum(ing))"},{"cell_type":"code","execution_count":20,"metadata":{},"outputs":[],"source":"ing_sort = np.argsort(-np.array(ing_sum))"},{"cell_type":"code","execution_count":23,"metadata":{},"outputs":[],"source":"w = np.array(ing_sum)[ing_sort[:20]]\ntop_ings = np.array(ings)[ing_sort[:20]]"},{"cell_type":"code","execution_count":24,"metadata":{},"outputs":[{"data":{"text/plain":"array(['salt', 'sugar', 'water', 'butter', 'onion', 'egg', 'flour',\n 'olive oil', 'milk', 'sprinkle', 'pepper', 'cream', 'garlic clove',\n 'cheese', 'tomato', 'dough', 'sauce', 'black pepper', 'roll',\n 'vanilla extract'], dtype='<U148')"},"execution_count":24,"metadata":{},"output_type":"execute_result"}],"source":"top_ings"},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":""}],"nbformat":4,"nbformat_minor":2,"metadata":{"language_info":{"name":"python","codemirror_mode":{"name":"ipython","version":3}},"orig_nbformat":2,"file_extension":".py","mimetype":"text/x-python","name":"python","npconvert_exporter":"python","pygments_lexer":"ipython3","version":3}}

368
RecipeAnalysis/AdjacencyMatrix.ipynb
View File

File diff suppressed because one or more lines are too long

355
RecipeAnalysis/AdjacencyMatrixRefinement.ipynb Normal file
View File

@ -0,0 +1,355 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Further Refinement of raw Adjacency Matrices"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"sys.path.append(\"../\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/jonas/.local/lib/python3.7/site-packages/ipykernel_launcher.py:5: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n",
" \"\"\"\n"
]
},
{
"data": {
"text/html": [
" <script type=\"text/javascript\">\n",
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
" if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
" if (typeof require !== 'undefined') {\n",
" require.undef(\"plotly\");\n",
" requirejs.config({\n",
" paths: {\n",
" 'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n",
" }\n",
" });\n",
" require(['plotly'], function(Plotly) {\n",
" window._Plotly = Plotly;\n",
" });\n",
" }\n",
" </script>\n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import dill\n",
"import numpy as np\n",
"import settings\n",
"import AdjacencyMatrix\n",
"from tqdm.autonotebook import tqdm\n",
"from Recipe import Ingredient"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"m_act = dill.load(open(\"m_act_raw.dill\", \"rb\"))\n",
"m_mix = dill.load(open(\"m_mix_raw.dill\", \"rb\"))\n",
"m_base_act = dill.load(open(\"m_base_act_raw.dill\", \"rb\"))\n",
"m_base_mix = dill.load(open(\"m_base_mix_raw.dill\", \"rb\"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Grouping Actions"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"groups = {\n",
" 'place':None,\n",
" 'heat':'heat',\n",
" 'cook':'heat',\n",
" 'bake':'heat',\n",
" 'grill':'heat',\n",
" 'melt':'heat',\n",
" 'blend':None,\n",
" 'beat':'prepare',\n",
" 'spread':None,\n",
" 'cool':'cool',\n",
" 'brown':'heat',\n",
" 'cut':'prepare',\n",
" 'chill':'cool',\n",
" 'drain':None,\n",
" 'boil':'heat',\n",
" 'simmer':'heat',\n",
" 'pour':None,\n",
" 'freeze':'cool',\n",
" 'saute':'heat',\n",
" 'rinse':'prepare',\n",
" 'warm':'heat',\n",
" 'wash':'prepare',\n",
" 'knead':'prepare',\n",
" 'peel':'prepare',\n",
" 'parboil':'heat',\n",
" 'break':'prepare',\n",
" 'broil':'heat',\n",
" 'scorch':'heat',\n",
" 'skim':None,\n",
" 'fry':'heat',\n",
" 'refrigerate':'cool',\n",
" 'burn':'heat',\n",
" 'thicken':None,\n",
" 'grate':'prepare',\n",
" 'brush':'prepare',\n",
" 'open':'prepare',\n",
" 'crack':'prepare',\n",
" 'poach':'heat',\n",
" 'slice':'prepare',\n",
" 'whisk':None,\n",
" 'dice':'prepare',\n",
" 'marinate':None,\n",
" 'whip':None,\n",
" 'sour':None,\n",
" 'soak':None,\n",
" 'steam':'heat',\n",
" 'chop':'prepare',\n",
" 'mince':None,\n",
" 'mash':'prepare',\n",
" 'squeeze':'prepare',\n",
" 'wipe':'prepare',\n",
" 'thaw':'prepare',\n",
" 'curdle':'heat',\n",
" 'sweeten':None,\n",
" 'baste':None,\n",
" 'carve':None,\n",
" 'grind':'prepare',\n",
" 'debone':'prepare',\n",
" 'steep':None,\n",
" 'clarify':None,\n",
" 'macerate':'prepare',\n",
" 'crumple':'prepare',\n",
" 'braise':'heat',\n",
" 'gut':None,\n",
" 'bury':None\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* now refactor the matrices to new versions that only contain those groups"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# create new matrices:\n",
"m_grouped_act = AdjacencyMatrix.adj_matrix()\n",
"m_grouped_mix = AdjacencyMatrix.adj_matrix(True)\n",
"m_grouped_base_act = AdjacencyMatrix.adj_matrix()\n",
"#m_grouped_base_mix = AdjacencyMatrix.adj_matrix(True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2db5dd15c87740729f16f5c258707db2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=741659), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"c = m_act.get_csr()\n",
"\n",
"label_acts, labels_ings = m_act.get_labels()\n",
"acts, ings = c.nonzero()\n",
"for i_act,j_ing in tqdm(zip(acts,ings), total=len(acts)):\n",
" ing = Ingredient.from_json(labels_ings[j_ing])\n",
" act = label_acts[i_act]\n",
" \n",
" grouped_ing = Ingredient(ing._base_ingredient)\n",
" for a in ing._action_set:\n",
" grouped_ing.apply_action(groups[a])\n",
" \n",
" grouped_act = groups[act]\n",
" \n",
" m_grouped_act.add_entry(grouped_act, grouped_ing.to_json(),1)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1d3f802944654954a6abbf8cb70f116e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=4472620), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"c = m_mix.get_csr()\n",
"\n",
"labels_ings = m_mix.get_labels()\n",
"ings_a, ings_b = c.nonzero()\n",
"for i_ing,j_ing in tqdm(zip(ings_a,ings_b), total=len(ings_a)):\n",
" ing_a = Ingredient.from_json(labels_ings[i_ing])\n",
" ing_b = Ingredient.from_json(labels_ings[j_ing])\n",
" \n",
" grouped_ing_a = Ingredient(ing_a._base_ingredient)\n",
" for a in ing_a._action_set:\n",
" grouped_ing_a.apply_action(groups[a])\n",
" \n",
" grouped_ing_b = Ingredient(ing_b._base_ingredient)\n",
" for a in ing_b._action_set:\n",
" grouped_ing_b.apply_action(groups[a])\n",
" \n",
" m_grouped_mix.add_entry(grouped_ing_a.to_json(), grouped_ing_b.to_json(),1)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "92548999e3a6427bb33af20d3e53d9ef",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=114804), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"c = m_base_act.get_csr()\n",
"\n",
"label_acts, labels_ings = m_base_act.get_labels()\n",
"acts, ings = c.nonzero()\n",
"for i_act,j_ing in tqdm(zip(acts,ings), total=len(acts)):\n",
" base_ing = labels_ings[j_ing]\n",
" act = label_acts[i_act]\n",
" \n",
" grouped_act = groups[act]\n",
" \n",
" m_grouped_base_act.add_entry(grouped_act, base_ing,1)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"dill.dump(m_grouped_act, file=open(\"m_grouped_act_raw.dill\", 'wb'))\n",
"dill.dump(m_grouped_mix, file=open(\"m_grouped_mix_raw.dill\", 'wb'))\n",
"dill.dump(m_grouped_base_act, file=open(\"m_grouped_base_act_raw.dill\", 'wb'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

2
RecipeAnalysis/AdjacencyMatrixTests.ipynb
View File

@ -64,7 +64,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.3" "version": "3.7.5rc1"
} }
}, },
"nbformat": 4, "nbformat": 4,

537
RecipeAnalysis/MatrixGeneration.ipynb
View File

File diff suppressed because one or more lines are too long

184
RecipeAnalysis/Recipe Analysis.ipynb
View File

File diff suppressed because one or more lines are too long

4
RecipeAnalysis/Recipe.ipynb
View File

@ -264,6 +264,8 @@
" \n", " \n",
" if touch:\n", " if touch:\n",
" self._last_touched_instruction = instruction_number\n", " self._last_touched_instruction = instruction_number\n",
" \n",
" return self\n",
" \n", " \n",
" def similarity(self, ingredient, use_actions=False, action_factor = 0.5):\n", " def similarity(self, ingredient, use_actions=False, action_factor = 0.5):\n",
" sim,_,_ = string_similarity(self._base_ingredient, ingredient._base_ingredient)\n", " sim,_,_ = string_similarity(self._base_ingredient, ingredient._base_ingredient)\n",
@ -1434,7 +1436,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.3" "version": "3.7.5"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
RecipeAnalysis/Recipe.py
View File

@ -161,6 +161,8 @@ class Ingredient(object):
if touch: if touch:
self._last_touched_instruction = instruction_number self._last_touched_instruction = instruction_number
return self
def similarity(self, ingredient, use_actions=False, action_factor = 0.5): def similarity(self, ingredient, use_actions=False, action_factor = 0.5):
sim,_,_ = string_similarity(self._base_ingredient, ingredient._base_ingredient) sim,_,_ = string_similarity(self._base_ingredient, ingredient._base_ingredient)
if not use_actions: if not use_actions: