Upload folder using huggingface_hub

.env

@@ -0,0 +1,2 @@
+IDSC_ACC=sentient_test@idsc.com.sg
+IDSC_PASS=APItest1412

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.autopep8"
+    },
+    "python.formatting.provider": "none"
+}

README.md

@@ -1,12 +1,6 @@
 ---
-title: Inventory Optimization Demo
-emoji: 👀
-colorFrom: yellow
-colorTo: blue
+title: inventory-optimization-demo
+app_file: gr_app.py
 sdk: gradio
-sdk_version: 4.3.0
-app_file: app.py
-pinned: false
+sdk_version: 3.41.0
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

configs/idsc_config.yaml

@@ -0,0 +1,4 @@
+apikey: 61ef23ae00df4f91417ec0d45fe7b03319f1bdc7
+apikey_expire: 08/17/2023, 13:54:15
+email: sentient_test@idsc.com.sg
+password: APItest1412

data/mock/demand_table.csv

@@ -0,0 +1,4 @@
+product,demand
+White Bread,40
+Special Cake,40
+Wedding Cake,30

data/mock/product_table.csv

@@ -0,0 +1,4 @@
+product,price,cost,required_space_per_unit,inventory_consideration_range
+White Bread,100,70,3,0.1
+Special Cake,100,60,2,0.1
+Wedding Cake,100,50,3,0.1

gr_app.py

@@ -0,0 +1,235 @@
+import gradio as gr
+
+from src.gr.GradioApp import GradioApp
+from src.gr import gr_args
+
+# =============================== #
+# Inventory Optimization Demo App #
+# =============================== #
+
+app = GradioApp()
+
+demo = gr.Blocks(**gr_args.main_block)
+
+with demo:
+
+    gr.Markdown('# Inventory Optimization')
+
+    with gr.Tabs() as tabs:
+
+        # ============================ #
+        # Raw Material Optimization #
+        # ============================ #
+        with gr.TabItem('Raw Material Optimization', id=0):
+            with gr.Row():
+                with gr.Column():
+
+                    # Inventory Optimization #
+                    rm_md = gr.Markdown(**gr_args.rm_md)
+
+                    with gr.Row():
+
+                        # [ Load Demo Dataset ] #
+                        rm_demo_data_btn = gr.Button(
+                            **gr_args.rm_demo_data_btn)
+
+                rm_file = gr.File(**gr_args.rm_file)
+
+            # [Inventory Optimization Input] #
+            rm_input_df = gr.Dataframe(**gr_args.rm_input_df)
+
+            with gr.Row():
+
+                # [FG Storage Capacity] #
+                rm_storage_capacity = gr.Number(
+                    **gr_args.rm_storage_capacity)
+
+                # [FG Budget] #
+                rm_budget_constraint = gr.Number(
+                    **gr_args.rm_budget_constraint)
+
+            # [Optimize Raw Material Inventory] #
+            rm_btn = gr.Button(**gr_args.rm_btn)
+
+            gr.Markdown('# Raw Material Inventory Recommendations')
+            with gr.Row():
+                rm_total_capacity_usage_md = gr.Markdown()
+                rm_total_budget_usage_md = gr.Markdown()
+
+            rm_recom_df = gr.Dataframe()
+
+            rm_plot = gr.Plot()
+
+            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
+            # Raw Material Event Listeners #
+            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
+            rm_demo_data_btn.click(
+                app.rm_demo_data_btn__click,
+                [], [rm_input_df, rm_storage_capacity, rm_budget_constraint])
+
+            rm_file.upload(
+                app.rm_file__upload,
+                [rm_file], [rm_input_df])
+
+            rm_storage_capacity.change(
+                app.rm_storage_capacity__change,
+                [rm_storage_capacity], [])
+
+            rm_budget_constraint.change(
+                app.rm_budget_constraint__change,
+                [rm_budget_constraint], [])
+
+            rm_btn.click(
+                app.rm_btn__click,
+                [],
+                [rm_recom_df,
+                 rm_total_capacity_usage_md,
+                 rm_total_budget_usage_md,
+                 rm_plot])
+
+        # ================ #
+        # WIP Optimization #
+        # ================ #
+        with gr.TabItem('WIP Optimization', id=1):
+
+            with gr.Row():
+                with gr.Column():
+
+                    # Inventory Optimization #
+                    wip_md = gr.Markdown(**gr_args.wip_md)
+
+                    with gr.Row():
+
+                        # [ Load Demo Dataset ] #
+                        wip_demo_data_btn = gr.Button(
+                            **gr_args.wip_demo_data_btn)
+
+                wip_file = gr.File(**gr_args.wip_file)
+
+            # [Inventory Optimization Input] #
+            wip_input_df = gr.Dataframe(**gr_args.wip_input_df)
+
+            with gr.Row():
+
+                # [FG Storage Capacity] #
+                wip_storage_capacity = gr.Number(
+                    **gr_args.wip_storage_capacity)
+
+                # [FG Budget] #
+                wip_budget_constraint = gr.Number(
+                    **gr_args.wip_budget_constraint)
+
+            # [Optimize Raw Material Inventory] #
+            wip_btn = gr.Button(**gr_args.wip_btn)
+
+            gr.Markdown('# WIP Inventory Recommendations')
+            with gr.Row():
+                wip_total_capacity_usage_md = gr.Markdown()
+                wip_total_budget_usage_md = gr.Markdown()
+
+            wip_recom_df = gr.Dataframe()
+
+            wip_plot = gr.Plot()
+
+            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
+            # WIP Event Listeners #
+            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
+            wip_demo_data_btn.click(
+                app.wip_demo_data_btn__click,
+                [], [wip_input_df, wip_storage_capacity, wip_budget_constraint])
+
+            wip_file.upload(
+                app.wip_file__upload,
+                [wip_file], [wip_input_df])
+
+            wip_storage_capacity.change(
+                app.wip_storage_capacity__change,
+                [wip_storage_capacity], [])
+
+            wip_budget_constraint.change(
+                app.wip_budget_constraint__change,
+                [wip_budget_constraint], [])
+
+            wip_btn.click(
+                app.wip_btn__click,
+                [],
+                [wip_recom_df,
+                 wip_total_capacity_usage_md,
+                 wip_total_budget_usage_md,
+                 wip_plot])
+
+        # ============================ #
+        # Finishend Goods Optimization #
+        # ============================ #
+        with gr.TabItem('FG Optimization', id=2):
+            with gr.Row():
+                with gr.Column():
+
+                    # Inventory Optimization #
+                    inventory_md = gr.Markdown(**gr_args.inventory_md)
+
+                    with gr.Row():
+
+                        # [ Load Demo Dataset ] #
+                        demo_data_btn = gr.Button(**gr_args.demo_data_btn)
+
+                inventory_file = gr.File(**gr_args.inventory_file)
+
+            # [Inventory Optimization Input] #
+            inventory_input_df = gr.Dataframe(**gr_args.inventory_input_df)
+
+            with gr.Row():
+
+                # [FG Storage Capacity] #
+                inventory_storage_capacity = gr.Number(
+                    **gr_args.inventory_storage_capacity)
+
+                # [FG Budget] #
+                inventory_budget_constraint = gr.Number(
+                    **gr_args.inventory_budget_constraint)
+
+            # [Optimize Inventory] #
+            inventory_btn = gr.Button(**gr_args.inventory_btn)
+
+            gr.Markdown('# Inventory Recommendations')
+            with gr.Row():
+                inv_total_profit_md = gr.Markdown()
+                inv_total_capacity_usage_md = gr.Markdown()
+                inv_total_budget_usage_md = gr.Markdown()
+                inv_total_margin_md = gr.Markdown()
+
+            inv_recom_df = gr.Dataframe()
+
+            inv_plot = gr.Plot()
+
+            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
+            # FG Optimization Event Listeners #
+            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
+            demo_data_btn.click(
+                app.demo_data_btn__click,
+                [], [inventory_input_df, inventory_storage_capacity, inventory_budget_constraint])
+
+            inventory_file.upload(
+                app.inventory_file__upload,
+                [inventory_file], [inventory_input_df])
+
+            inventory_storage_capacity.change(
+                app.inventory_storage_capacity__change,
+                [inventory_storage_capacity], [])
+
+            inventory_budget_constraint.change(
+                app.inventory_budget_constraint__change,
+                [inventory_budget_constraint], [])
+
+            inventory_btn.click(
+                app.inventory_btn__click,
+                [],
+                [inv_recom_df,
+                 inv_total_profit_md,
+                 inv_total_capacity_usage_md,
+                 inv_total_budget_usage_md,
+                 inv_total_margin_md,
+                 inv_plot])
+
+
+demo.launch()

gradio/calculator.py

@@ -0,0 +1,33 @@
+import gradio as gr
+
+def calculator(num1, operation, num2):
+    if operation == "add":
+        return num1 + num2
+    elif operation == "subtract":
+        return num1 - num2
+    elif operation == "multiply":
+        return num1 * num2
+    elif operation == "divide":
+        if num2 == 0:
+            raise gr.Error("Cannot divide by zero!")
+        return num1 / num2
+
+demo = gr.Interface(
+    calculator,
+    [
+        "number", 
+        gr.Radio(["add", "subtract", "multiply", "divide"]),
+        "number"
+    ],
+    "number",
+    examples=[
+        [5, "add", 3],
+        [4, "divide", 2],
+        [-4, "multiply", 2.5],
+        [0, "subtract", 1.2],
+    ],
+    title="Toy Calculator",
+    description="Here's a sample toy calculator. Allows you to calculate things like $2+2=4$",
+)
+if __name__ == "__main__":
+    demo.launch()

gradio/hello.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import sys, os, io
+import pandas as pd
+sys.path.append(os.path.abspath('../src'))
+
+from idsc.idsc_apis import idsc_apis
+
+idsc = idsc_apis()
+
+
+def forecast(demand_table, product_table, storage_capacity):
+    demand_table_df = pd.read_csv(demand_table.name)
+    product_table_df = pd.read_csv(product_table.name)
+    
+    res = idsc.product_mix(
+        demand_table_df.to_json(), 
+        product_table_df.to_json(), 
+        storage_capacity)
+    return res 
+
+def upload_file(file):
+    return file.name
+
+def show():
+    return gr.update(visible=True)
+
+# demo = gr.Interface(
+#     fn=forecast, 
+#     inputs=[
+#         demand_table_upload_btn, 
+#         product_table_upload_btn,
+#         storage_capacity_input], 
+#     outputs="text")
+
+with gr.Blocks() as demo:
+    demand_table_file = gr.File(visible=False)
+    demand_table_upload_btn = gr.UploadButton(
+    'Demand Table',
+    file_types=['.csv'])
+    
+    product_table_file = gr.File()
+    product_table_upload_btn = gr.UploadButton(
+    'Product Table',
+    file_types=['.csv'])
+    
+    storage_capacity_input = gr.Number(
+    label='Storage Capacity',
+    minimum=0)
+    
+    optimize_inventory_btn = gr.Button('Optimize')
+    
+    demand_table_upload_btn.upload(
+        upload_file,
+        demand_table_upload_btn, 
+        demand_table_file)
+    
+    demand_table_file.change(fn=show)
+    
+demo.launch()

notebooks/inventory.ipynb

@@ -0,0 +1,1421 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "b60aa108",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests, yaml\n",
+    "import sys\n",
+    "import os\n",
+    "sys.path.append(os.path.abspath('../src'))\n",
+    "import pandas as pd\n",
+    "\n",
+    "from idsc.idsc_apis import idsc_apis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "5c549960",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "apikey still available, logged in\n"
+     ]
+    }
+   ],
+   "source": [
+    "idsc = idsc_apis()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "258034d8-ab4f-49cb-b4eb-e61bda31babc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "demand_table = pd.read_csv('../data/mock/demand_table.csv')\n",
+    "product_table = pd.read_csv('../data/mock/product_table.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "afb53f04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res = idsc.product_mix(demand_table.to_json(), product_table.to_json(), 100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "b33feb18",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'product_mix_result': {'White Bread': {'recommended_stock': 3},\n",
+       "  'Special Cake': {'recommended_stock': 26},\n",
+       "  'Wedding Cake': {'recommended_stock': 13}},\n",
+       " 'engine_code': 'optimax_product_mix',\n",
+       " 'probability_table': '{\"product\":{\"263\":\"Wedding Cake\",\"261\":\"Wedding Cake\",\"259\":\"Wedding Cake\",\"269\":\"Wedding Cake\",\"264\":\"Wedding Cake\",\"268\":\"Wedding Cake\",\"258\":\"Wedding Cake\",\"260\":\"Wedding Cake\",\"257\":\"Wedding Cake\",\"270\":\"Wedding Cake\",\"262\":\"Wedding Cake\",\"265\":\"Wedding Cake\",\"266\":\"Wedding Cake\",\"267\":\"Wedding Cake\",\"271\":\"Wedding Cake\",\"161\":\"Special Cake\",\"46\":\"White Bread\",\"256\":\"Wedding Cake\",\"255\":\"Wedding Cake\",\"275\":\"Wedding Cake\",\"272\":\"Wedding Cake\",\"34\":\"White Bread\",\"149\":\"Special Cake\",\"278\":\"Wedding Cake\",\"159\":\"Special Cake\",\"44\":\"White Bread\",\"35\":\"White Bread\",\"150\":\"Special Cake\",\"277\":\"Wedding Cake\",\"36\":\"White Bread\",\"151\":\"Special Cake\",\"253\":\"Wedding Cake\",\"43\":\"White Bread\",\"158\":\"Special Cake\",\"274\":\"Wedding Cake\",\"157\":\"Special Cake\",\"42\":\"White Bread\",\"162\":\"Special Cake\",\"47\":\"White Bread\",\"254\":\"Wedding Cake\",\"154\":\"Special Cake\",\"39\":\"White Bread\",\"276\":\"Wedding Cake\",\"163\":\"Special Cake\",\"48\":\"White Bread\",\"279\":\"Wedding Cake\",\"153\":\"Special Cake\",\"38\":\"White Bread\",\"152\":\"Special Cake\",\"37\":\"White Bread\",\"45\":\"White Bread\",\"160\":\"Special Cake\",\"164\":\"Special Cake\",\"49\":\"White Bread\",\"40\":\"White Bread\",\"155\":\"Special Cake\",\"41\":\"White Bread\",\"156\":\"Special Cake\",\"166\":\"Special Cake\",\"51\":\"White Bread\",\"273\":\"Wedding Cake\",\"82\":\"White Bread\",\"197\":\"Special Cake\",\"79\":\"White Bread\",\"194\":\"Special Cake\",\"81\":\"White Bread\",\"196\":\"Special Cake\",\"182\":\"Special Cake\",\"67\":\"White Bread\",\"52\":\"White Bread\",\"167\":\"Special Cake\",\"50\":\"White Bread\",\"165\":\"Special Cake\",\"280\":\"Wedding Cake\",\"80\":\"White Bread\",\"195\":\"Special Cake\",\"252\":\"Wedding Cake\",\"85\":\"White Bread\",\"200\":\"Special Cake\",\"199\":\"Special Cake\",\"84\":\"White Bread\",\"281\":\"Wedding Cake\",\"183\":\"Special Cake\",\"68\":\"White Bread\",\"251\":\"Wedding Cake\",\"181\":\"Special Cake\",\"66\":\"White Bread\",\"282\":\"Wedding Cake\",\"171\":\"Special Cake\",\"56\":\"White Bread\",\"33\":\"White Bread\",\"148\":\"Special Cake\",\"53\":\"White Bread\",\"168\":\"Special Cake\",\"173\":\"Special Cake\",\"58\":\"White Bread\",\"172\":\"Special Cake\",\"57\":\"White Bread\",\"60\":\"White Bread\",\"175\":\"Special Cake\",\"286\":\"Wedding Cake\",\"174\":\"Special Cake\",\"59\":\"White Bread\",\"198\":\"Special Cake\",\"83\":\"White Bread\",\"169\":\"Special Cake\",\"54\":\"White Bread\",\"86\":\"White Bread\",\"201\":\"Special Cake\",\"185\":\"Special Cake\",\"70\":\"White Bread\",\"184\":\"Special Cake\",\"69\":\"White Bread\",\"78\":\"White Bread\",\"193\":\"Special Cake\",\"250\":\"Wedding Cake\",\"71\":\"White Bread\",\"186\":\"Special Cake\",\"192\":\"Special Cake\",\"77\":\"White Bread\",\"191\":\"Special Cake\",\"76\":\"White Bread\",\"285\":\"Wedding Cake\",\"176\":\"Special Cake\",\"61\":\"White Bread\",\"249\":\"Wedding Cake\",\"74\":\"White Bread\",\"189\":\"Special Cake\",\"170\":\"Special Cake\",\"55\":\"White Bread\",\"190\":\"Special Cake\",\"75\":\"White Bread\",\"177\":\"Special Cake\",\"62\":\"White Bread\",\"283\":\"Wedding Cake\",\"188\":\"Special Cake\",\"73\":\"White Bread\",\"65\":\"White Bread\",\"180\":\"Special Cake\",\"187\":\"Special Cake\",\"72\":\"White Bread\",\"284\":\"Wedding Cake\",\"203\":\"Special Cake\",\"88\":\"White Bread\",\"63\":\"White Bread\",\"178\":\"Special Cake\",\"287\":\"Wedding Cake\",\"87\":\"White Bread\",\"202\":\"Special Cake\",\"32\":\"White Bread\",\"147\":\"Special Cake\",\"207\":\"Special Cake\",\"92\":\"White Bread\",\"290\":\"Wedding Cake\",\"90\":\"White Bread\",\"205\":\"Special Cake\",\"248\":\"Wedding Cake\",\"211\":\"Special Cake\",\"96\":\"White Bread\",\"89\":\"White Bread\",\"204\":\"Special Cake\",\"289\":\"Wedding Cake\",\"291\":\"Wedding Cake\",\"146\":\"Special Cake\",\"31\":\"White Bread\",\"64\":\"White Bread\",\"179\":\"Special Cake\",\"209\":\"Special Cake\",\"94\":\"White Bread\",\"288\":\"Wedding Cake\",\"224\":\"Special Cake\",\"109\":\"White Bread\",\"292\":\"Wedding Cake\",\"28\":\"White Bread\",\"143\":\"Special Cake\",\"30\":\"White Bread\",\"145\":\"Special Cake\",\"29\":\"White Bread\",\"144\":\"Special Cake\",\"208\":\"Special Cake\",\"93\":\"White Bread\",\"206\":\"Special Cake\",\"91\":\"White Bread\",\"223\":\"Special Cake\",\"108\":\"White Bread\",\"222\":\"Special Cake\",\"107\":\"White Bread\",\"220\":\"Special Cake\",\"105\":\"White Bread\",\"27\":\"White Bread\",\"142\":\"Special Cake\",\"245\":\"Wedding Cake\",\"95\":\"White Bread\",\"210\":\"Special Cake\",\"106\":\"White Bread\",\"221\":\"Special Cake\",\"26\":\"White Bread\",\"141\":\"Special Cake\",\"293\":\"Wedding Cake\",\"110\":\"White Bread\",\"225\":\"Special Cake\",\"112\":\"White Bread\",\"227\":\"Special Cake\",\"243\":\"Wedding Cake\",\"247\":\"Wedding Cake\",\"25\":\"White Bread\",\"140\":\"Special Cake\",\"244\":\"Wedding Cake\",\"294\":\"Wedding Cake\",\"212\":\"Special Cake\",\"97\":\"White Bread\",\"297\":\"Wedding Cake\",\"226\":\"Special Cake\",\"111\":\"White Bread\",\"298\":\"Wedding Cake\",\"246\":\"Wedding Cake\",\"104\":\"White Bread\",\"219\":\"Special Cake\",\"15\":\"White Bread\",\"130\":\"Special Cake\",\"295\":\"Wedding Cake\",\"296\":\"Wedding Cake\",\"237\":\"Wedding Cake\",\"113\":\"White Bread\",\"228\":\"Special Cake\",\"139\":\"Special Cake\",\"24\":\"White Bread\",\"218\":\"Special Cake\",\"103\":\"White Bread\",\"137\":\"Special Cake\",\"22\":\"White Bread\",\"299\":\"Wedding Cake\",\"131\":\"Special Cake\",\"16\":\"White Bread\",\"235\":\"Wedding Cake\",\"213\":\"Special Cake\",\"98\":\"White Bread\",\"120\":\"Special Cake\",\"5\":\"White Bread\",\"23\":\"White Bread\",\"138\":\"Special Cake\",\"7\":\"White Bread\",\"122\":\"Special Cake\",\"132\":\"Special Cake\",\"17\":\"White Bread\",\"129\":\"Special Cake\",\"14\":\"White Bread\",\"231\":\"Wedding Cake\",\"300\":\"Wedding Cake\",\"136\":\"Special Cake\",\"21\":\"White Bread\",\"242\":\"Wedding Cake\",\"8\":\"White Bread\",\"123\":\"Special Cake\",\"302\":\"Wedding Cake\",\"101\":\"White Bread\",\"216\":\"Special Cake\",\"9\":\"White Bread\",\"124\":\"Special Cake\",\"1\":\"White Bread\",\"116\":\"Special Cake\",\"233\":\"Wedding Cake\",\"234\":\"Wedding Cake\",\"303\":\"Wedding Cake\",\"13\":\"White Bread\",\"128\":\"Special Cake\",\"304\":\"Wedding Cake\",\"215\":\"Special Cake\",\"100\":\"White Bread\",\"20\":\"White Bread\",\"135\":\"Special Cake\",\"133\":\"Special Cake\",\"18\":\"White Bread\",\"3\":\"White Bread\",\"118\":\"Special Cake\",\"214\":\"Special Cake\",\"99\":\"White Bread\",\"232\":\"Wedding Cake\",\"217\":\"Special Cake\",\"102\":\"White Bread\",\"301\":\"Wedding Cake\",\"238\":\"Wedding Cake\",\"239\":\"Wedding Cake\",\"240\":\"Wedding Cake\",\"134\":\"Special Cake\",\"19\":\"White Bread\",\"4\":\"White Bread\",\"119\":\"Special Cake\",\"126\":\"Special Cake\",\"11\":\"White Bread\",\"117\":\"Special Cake\",\"2\":\"White Bread\",\"114\":\"White Bread\",\"229\":\"Special Cake\",\"236\":\"Wedding Cake\",\"241\":\"Wedding Cake\",\"121\":\"Special Cake\",\"6\":\"White Bread\",\"12\":\"White Bread\",\"127\":\"Special Cake\",\"125\":\"Special Cake\",\"10\":\"White Bread\"},\"demand\":{\"263\":33,\"261\":31,\"259\":29,\"269\":39,\"264\":34,\"268\":38,\"258\":28,\"260\":30,\"257\":27,\"270\":40,\"262\":32,\"265\":35,\"266\":36,\"267\":37,\"271\":41,\"161\":46,\"46\":46,\"256\":26,\"255\":25,\"275\":45,\"272\":42,\"34\":34,\"149\":34,\"278\":48,\"159\":44,\"44\":44,\"35\":35,\"150\":35,\"277\":47,\"36\":36,\"151\":36,\"253\":23,\"43\":43,\"158\":43,\"274\":44,\"157\":42,\"42\":42,\"162\":47,\"47\":47,\"254\":24,\"154\":39,\"39\":39,\"276\":46,\"163\":48,\"48\":48,\"279\":49,\"153\":38,\"38\":38,\"152\":37,\"37\":37,\"45\":45,\"160\":45,\"164\":49,\"49\":49,\"40\":40,\"155\":40,\"41\":41,\"156\":41,\"166\":51,\"51\":51,\"273\":43,\"82\":82,\"197\":82,\"79\":79,\"194\":79,\"81\":81,\"196\":81,\"182\":67,\"67\":67,\"52\":52,\"167\":52,\"50\":50,\"165\":50,\"280\":50,\"80\":80,\"195\":80,\"252\":22,\"85\":85,\"200\":85,\"199\":84,\"84\":84,\"281\":51,\"183\":68,\"68\":68,\"251\":21,\"181\":66,\"66\":66,\"282\":52,\"171\":56,\"56\":56,\"33\":33,\"148\":33,\"53\":53,\"168\":53,\"173\":58,\"58\":58,\"172\":57,\"57\":57,\"60\":60,\"175\":60,\"286\":56,\"174\":59,\"59\":59,\"198\":83,\"83\":83,\"169\":54,\"54\":54,\"86\":86,\"201\":86,\"185\":70,\"70\":70,\"184\":69,\"69\":69,\"78\":78,\"193\":78,\"250\":20,\"71\":71,\"186\":71,\"192\":77,\"77\":77,\"191\":76,\"76\":76,\"285\":55,\"176\":61,\"61\":61,\"249\":19,\"74\":74,\"189\":74,\"170\":55,\"55\":55,\"190\":75,\"75\":75,\"177\":62,\"62\":62,\"283\":53,\"188\":73,\"73\":73,\"65\":65,\"180\":65,\"187\":72,\"72\":72,\"284\":54,\"203\":88,\"88\":88,\"63\":63,\"178\":63,\"287\":57,\"87\":87,\"202\":87,\"32\":32,\"147\":32,\"207\":92,\"92\":92,\"290\":60,\"90\":90,\"205\":90,\"248\":18,\"211\":96,\"96\":96,\"89\":89,\"204\":89,\"289\":59,\"291\":61,\"146\":31,\"31\":31,\"64\":64,\"179\":64,\"209\":94,\"94\":94,\"288\":58,\"224\":109,\"109\":109,\"292\":62,\"28\":28,\"143\":28,\"30\":30,\"145\":30,\"29\":29,\"144\":29,\"208\":93,\"93\":93,\"206\":91,\"91\":91,\"223\":108,\"108\":108,\"222\":107,\"107\":107,\"220\":105,\"105\":105,\"27\":27,\"142\":27,\"245\":15,\"95\":95,\"210\":95,\"106\":106,\"221\":106,\"26\":26,\"141\":26,\"293\":63,\"110\":110,\"225\":110,\"112\":112,\"227\":112,\"243\":13,\"247\":17,\"25\":25,\"140\":25,\"244\":14,\"294\":64,\"212\":97,\"97\":97,\"297\":67,\"226\":111,\"111\":111,\"298\":68,\"246\":16,\"104\":104,\"219\":104,\"15\":15,\"130\":15,\"295\":65,\"296\":66,\"237\":7,\"113\":113,\"228\":113,\"139\":24,\"24\":24,\"218\":103,\"103\":103,\"137\":22,\"22\":22,\"299\":69,\"131\":16,\"16\":16,\"235\":5,\"213\":98,\"98\":98,\"120\":5,\"5\":5,\"23\":23,\"138\":23,\"7\":7,\"122\":7,\"132\":17,\"17\":17,\"129\":14,\"14\":14,\"231\":1,\"300\":70,\"136\":21,\"21\":21,\"242\":12,\"8\":8,\"123\":8,\"302\":72,\"101\":101,\"216\":101,\"9\":9,\"124\":9,\"1\":1,\"116\":1,\"233\":3,\"234\":4,\"303\":73,\"13\":13,\"128\":13,\"304\":74,\"215\":100,\"100\":100,\"20\":20,\"135\":20,\"133\":18,\"18\":18,\"3\":3,\"118\":3,\"214\":99,\"99\":99,\"232\":2,\"217\":102,\"102\":102,\"301\":71,\"238\":8,\"239\":9,\"240\":10,\"134\":19,\"19\":19,\"4\":4,\"119\":4,\"126\":11,\"11\":11,\"117\":2,\"2\":2,\"114\":114,\"229\":114,\"236\":6,\"241\":11,\"121\":6,\"6\":6,\"12\":12,\"127\":12,\"125\":10,\"10\":10},\"probability\":{\"263\":0.0368592173,\"261\":0.0359488332,\"259\":0.034826178,\"269\":0.0345176881,\"264\":0.0338754672,\"268\":0.0336984278,\"258\":0.0333003656,\"260\":0.032756232,\"257\":0.0325301611,\"270\":0.032197924,\"262\":0.0318970326,\"265\":0.0311347815,\"266\":0.030689652,\"267\":0.0290920836,\"271\":0.0283928783,\"161\":0.028135825,\"46\":0.028135825,\"256\":0.0280648941,\"255\":0.026794912,\"275\":0.0267789487,\"272\":0.0266978264,\"34\":0.02649434,\"149\":0.02649434,\"278\":0.0261790284,\"159\":0.0260993218,\"44\":0.0260993218,\"35\":0.0258797103,\"150\":0.0258797103,\"277\":0.0249885005,\"36\":0.0247542848,\"151\":0.0247542848,\"253\":0.0237528724,\"43\":0.0227409136,\"158\":0.0227409136,\"274\":0.0223511295,\"157\":0.0218458294,\"42\":0.0218458294,\"162\":0.0218256638,\"47\":0.0218256638,\"254\":0.0217967443,\"154\":0.0216395613,\"39\":0.0216395613,\"276\":0.0216095805,\"163\":0.0215321773,\"48\":0.0215321773,\"279\":0.0213346388,\"153\":0.0203048915,\"38\":0.0203048915,\"152\":0.020051612,\"37\":0.020051612,\"45\":0.0199892913,\"160\":0.0199892913,\"164\":0.0195399323,\"49\":0.0195399323,\"40\":0.019229393,\"155\":0.019229393,\"41\":0.0190548591,\"156\":0.0190548591,\"166\":0.018913738,\"51\":0.018913738,\"273\":0.0184784305,\"82\":0.0182737867,\"197\":0.0182737867,\"79\":0.0180723397,\"194\":0.0180723397,\"81\":0.0179847392,\"196\":0.0179847392,\"182\":0.0177538496,\"67\":0.0177538496,\"52\":0.017304322,\"167\":0.017304322,\"50\":0.0172683526,\"165\":0.0172683526,\"280\":0.017080318,\"80\":0.0165558467,\"195\":0.0165558467,\"252\":0.0164150156,\"85\":0.0163239057,\"200\":0.0163239057,\"199\":0.0155502511,\"84\":0.0155502511,\"281\":0.0155468033,\"183\":0.0153482999,\"68\":0.0153482999,\"251\":0.0150519811,\"181\":0.0149100957,\"66\":0.0149100957,\"282\":0.0145321593,\"171\":0.0145073305,\"56\":0.0145073305,\"33\":0.0143434204,\"148\":0.0143434204,\"53\":0.0139978926,\"168\":0.0139978926,\"173\":0.0137575929,\"58\":0.0137575929,\"172\":0.0133753577,\"57\":0.0133753577,\"60\":0.0132917234,\"175\":0.0132917234,\"286\":0.0128341354,\"174\":0.0125602164,\"59\":0.0125602164,\"198\":0.0122586994,\"83\":0.0122586994,\"169\":0.0121257892,\"54\":0.0121257892,\"86\":0.0121178443,\"201\":0.0121178443,\"185\":0.0117735274,\"70\":0.0117735274,\"184\":0.0117612458,\"69\":0.0117612458,\"78\":0.011635456,\"193\":0.011635456,\"250\":0.01154316,\"71\":0.0112493485,\"186\":0.0112493485,\"192\":0.0111785296,\"77\":0.0111785296,\"191\":0.0111410438,\"76\":0.0111410438,\"285\":0.0110507398,\"176\":0.0105914583,\"61\":0.0105914583,\"249\":0.0105420966,\"74\":0.0105078101,\"189\":0.0105078101,\"170\":0.0103408676,\"55\":0.0103408676,\"190\":0.0100856266,\"75\":0.0100856266,\"177\":0.0100635496,\"62\":0.0100635496,\"283\":0.0098274898,\"188\":0.009615686,\"73\":0.009615686,\"65\":0.0089209082,\"180\":0.0089209082,\"187\":0.0088669788,\"72\":0.0088669788,\"284\":0.008681397,\"203\":0.0085985317,\"88\":0.0085985317,\"63\":0.0083903575,\"178\":0.0083903575,\"287\":0.0079844742,\"87\":0.0075161459,\"202\":0.0075161459,\"32\":0.0065831021,\"147\":0.0065831021,\"207\":0.0063411487,\"92\":0.0063411487,\"290\":0.0061494519,\"90\":0.0060437383,\"205\":0.0060437383,\"248\":0.0057253414,\"211\":0.0057178973,\"96\":0.0057178973,\"89\":0.0056477112,\"204\":0.0056477112,\"289\":0.0055459619,\"291\":0.0054795932,\"146\":0.0054244868,\"31\":0.0054244868,\"64\":0.0053959746,\"179\":0.0053959746,\"209\":0.0051360659,\"94\":0.0051360659,\"288\":0.0050816214,\"224\":0.0048954825,\"109\":0.0048954825,\"292\":0.0047980717,\"28\":0.0045802571,\"143\":0.0045802571,\"30\":0.0044781409,\"145\":0.0044781409,\"29\":0.0043621607,\"144\":0.0043621607,\"208\":0.0043273171,\"93\":0.0043273171,\"206\":0.0041276299,\"91\":0.0041276299,\"223\":0.0040755787,\"108\":0.0040755787,\"222\":0.0039335012,\"107\":0.0039335012,\"220\":0.0038894774,\"105\":0.0038894774,\"27\":0.00385749,\"142\":0.00385749,\"245\":0.0036740912,\"95\":0.0036275468,\"210\":0.0036275468,\"106\":0.0035281844,\"221\":0.0035281844,\"26\":0.0033199252,\"141\":0.0033199252,\"293\":0.0032641712,\"110\":0.0031606894,\"225\":0.0031606894,\"112\":0.002931355,\"227\":0.002931355,\"243\":0.0029177054,\"247\":0.0027665343,\"25\":0.0026568393,\"140\":0.0026568393,\"244\":0.0026502146,\"294\":0.0025965544,\"212\":0.002554393,\"97\":0.002554393,\"297\":0.0022778517,\"226\":0.0022694948,\"111\":0.0022694948,\"298\":0.0022332029,\"246\":0.00198394,\"104\":0.0019647995,\"219\":0.0019647995,\"15\":0.0019036542,\"130\":0.0019036542,\"295\":0.0018337038,\"296\":0.0014691137,\"237\":0.0014035503,\"113\":0.0013588412,\"228\":0.0013588412,\"139\":0.0013444622,\"24\":0.0013444622,\"218\":0.001279575,\"103\":0.001279575,\"137\":0.0012722084,\"22\":0.0012722084,\"299\":0.0012112573,\"131\":0.0009974778,\"16\":0.0009974778,\"235\":0.0009420068,\"213\":0.000899227,\"98\":0.000899227,\"120\":0.0007732343,\"5\":0.0007732343,\"23\":0.0007673017,\"138\":0.0007673017,\"7\":0.000579398,\"122\":0.000579398,\"132\":0.0005463021,\"17\":0.0005463021,\"129\":0.0005379338,\"14\":0.0005379338,\"231\":0.0004810596,\"300\":0.0004541821,\"136\":0.0004143761,\"21\":0.0004143761,\"242\":0.0004077686,\"8\":0.000402153,\"123\":0.000402153,\"302\":0.0003903984,\"101\":0.0003871625,\"216\":0.0003871625,\"9\":0.0003653594,\"124\":0.0003653594,\"1\":0.0003608402,\"116\":0.0003608402,\"233\":0.0003515124,\"234\":0.0003474865,\"303\":0.0003399258,\"13\":0.0003227829,\"128\":0.0003227829,\"304\":0.0003183052,\"215\":0.0003102312,\"100\":0.0003102312,\"20\":0.0003036225,\"135\":0.0003036225,\"133\":0.0002644347,\"18\":0.0002644347,\"3\":0.0002636676,\"118\":0.0002636676,\"214\":0.0002458838,\"99\":0.0002458838,\"232\":0.0002280527,\"217\":0.0002082343,\"102\":0.0002082343,\"301\":0.0002049358,\"238\":0.0002048074,\"239\":0.0001971212,\"240\":0.0001920457,\"134\":0.0001910985,\"19\":0.0001910985,\"4\":0.0001887357,\"119\":0.0001887357,\"126\":0.0001747752,\"11\":0.0001747752,\"117\":0.0001710611,\"2\":0.0001710611,\"114\":0.0001586266,\"229\":0.0001586266,\"236\":0.0001076846,\"241\":0.0000884724,\"121\":0.0000860457,\"6\":0.0000860457,\"12\":0.0000617417,\"127\":0.0000617417,\"125\":0.0000430096,\"10\":0.0000430096}}',\n",
+       " 'plan_timestamp': '2023-08-15 16:24:11'}"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "res"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "87f7d882",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res_df = pd.DataFrame(res['product_mix_result'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "93b21c64",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>White Bread</th>\n",
+       "      <th>Special Cake</th>\n",
+       "      <th>Wedding Cake</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>recommended_stock</th>\n",
+       "      <td>3</td>\n",
+       "      <td>26</td>\n",
+       "      <td>13</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   White Bread  Special Cake  Wedding Cake\n",
+       "recommended_stock            3            26            13"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "res_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "c0e30697",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prob_table_df = pd.DataFrame(json.loads(res['probability_table']))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "0e465d87",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>product</th>\n",
+       "      <th>demand</th>\n",
+       "      <th>probability</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>263</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>33</td>\n",
+       "      <td>0.036859</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>261</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>31</td>\n",
+       "      <td>0.035949</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>259</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>29</td>\n",
+       "      <td>0.034826</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>269</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>39</td>\n",
+       "      <td>0.034518</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>264</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>34</td>\n",
+       "      <td>0.033875</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>White Bread</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0.000086</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>White Bread</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.000062</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>127</th>\n",
+       "      <td>Special Cake</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.000062</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>125</th>\n",
+       "      <td>Special Cake</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.000043</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>White Bread</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.000043</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>302 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          product  demand  probability\n",
+       "263  Wedding Cake      33     0.036859\n",
+       "261  Wedding Cake      31     0.035949\n",
+       "259  Wedding Cake      29     0.034826\n",
+       "269  Wedding Cake      39     0.034518\n",
+       "264  Wedding Cake      34     0.033875\n",
+       "..            ...     ...          ...\n",
+       "6     White Bread       6     0.000086\n",
+       "12    White Bread      12     0.000062\n",
+       "127  Special Cake      12     0.000062\n",
+       "125  Special Cake      10     0.000043\n",
+       "10    White Bread      10     0.000043\n",
+       "\n",
+       "[302 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prob_table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "b6f4c718",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w = prob_table_df[prob_table_df['product']==\"Wedding Cake\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "c1816949",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "2458d35e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>product</th>\n",
+       "      <th>demand</th>\n",
+       "      <th>probability</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>263</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>33</td>\n",
+       "      <td>0.036859</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>261</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>31</td>\n",
+       "      <td>0.035949</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>259</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>29</td>\n",
+       "      <td>0.034826</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>269</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>39</td>\n",
+       "      <td>0.034518</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>264</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>34</td>\n",
+       "      <td>0.033875</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>238</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.000205</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>239</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0.000197</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>240</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.000192</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>236</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0.000108</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>241</th>\n",
+       "      <td>Wedding Cake</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0.000088</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>74 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          product  demand  probability\n",
+       "263  Wedding Cake      33     0.036859\n",
+       "261  Wedding Cake      31     0.035949\n",
+       "259  Wedding Cake      29     0.034826\n",
+       "269  Wedding Cake      39     0.034518\n",
+       "264  Wedding Cake      34     0.033875\n",
+       "..            ...     ...          ...\n",
+       "238  Wedding Cake       8     0.000205\n",
+       "239  Wedding Cake       9     0.000197\n",
+       "240  Wedding Cake      10     0.000192\n",
+       "236  Wedding Cake       6     0.000108\n",
+       "241  Wedding Cake      11     0.000088\n",
+       "\n",
+       "[74 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "w"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "9b06145f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.collections.PathCollection at 0x12ba90350>"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.scatter(w['demand'], w['probability'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "d1bf1d32-58e6-4d03-89ca-129ee7371cff",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'product': {'263': 'Wedding Cake',\n",
+       "  '261': 'Wedding Cake',\n",
+       "  '259': 'Wedding Cake',\n",
+       "  '269': 'Wedding Cake',\n",
+       "  '264': 'Wedding Cake',\n",
+       "  '268': 'Wedding Cake',\n",
+       "  '258': 'Wedding Cake',\n",
+       "  '260': 'Wedding Cake',\n",
+       "  '257': 'Wedding Cake',\n",
+       "  '270': 'Wedding Cake',\n",
+       "  '262': 'Wedding Cake',\n",
+       "  '265': 'Wedding Cake',\n",
+       "  '266': 'Wedding Cake',\n",
+       "  '267': 'Wedding Cake',\n",
+       "  '271': 'Wedding Cake',\n",
+       "  '161': 'Special Cake',\n",
+       "  '46': 'White Bread',\n",
+       "  '256': 'Wedding Cake',\n",
+       "  '255': 'Wedding Cake',\n",
+       "  '275': 'Wedding Cake',\n",
+       "  '272': 'Wedding Cake',\n",
+       "  '34': 'White Bread',\n",
+       "  '149': 'Special Cake',\n",
+       "  '278': 'Wedding Cake',\n",
+       "  '159': 'Special Cake',\n",
+       "  '44': 'White Bread',\n",
+       "  '35': 'White Bread',\n",
+       "  '150': 'Special Cake',\n",
+       "  '277': 'Wedding Cake',\n",
+       "  '36': 'White Bread',\n",
+       "  '151': 'Special Cake',\n",
+       "  '253': 'Wedding Cake',\n",
+       "  '43': 'White Bread',\n",
+       "  '158': 'Special Cake',\n",
+       "  '274': 'Wedding Cake',\n",
+       "  '157': 'Special Cake',\n",
+       "  '42': 'White Bread',\n",
+       "  '162': 'Special Cake',\n",
+       "  '47': 'White Bread',\n",
+       "  '254': 'Wedding Cake',\n",
+       "  '154': 'Special Cake',\n",
+       "  '39': 'White Bread',\n",
+       "  '276': 'Wedding Cake',\n",
+       "  '163': 'Special Cake',\n",
+       "  '48': 'White Bread',\n",
+       "  '279': 'Wedding Cake',\n",
+       "  '153': 'Special Cake',\n",
+       "  '38': 'White Bread',\n",
+       "  '152': 'Special Cake',\n",
+       "  '37': 'White Bread',\n",
+       "  '45': 'White Bread',\n",
+       "  '160': 'Special Cake',\n",
+       "  '164': 'Special Cake',\n",
+       "  '49': 'White Bread',\n",
+       "  '40': 'White Bread',\n",
+       "  '155': 'Special Cake',\n",
+       "  '41': 'White Bread',\n",
+       "  '156': 'Special Cake',\n",
+       "  '166': 'Special Cake',\n",
+       "  '51': 'White Bread',\n",
+       "  '273': 'Wedding Cake',\n",
+       "  '82': 'White Bread',\n",
+       "  '197': 'Special Cake',\n",
+       "  '79': 'White Bread',\n",
+       "  '194': 'Special Cake',\n",
+       "  '81': 'White Bread',\n",
+       "  '196': 'Special Cake',\n",
+       "  '182': 'Special Cake',\n",
+       "  '67': 'White Bread',\n",
+       "  '52': 'White Bread',\n",
+       "  '167': 'Special Cake',\n",
+       "  '50': 'White Bread',\n",
+       "  '165': 'Special Cake',\n",
+       "  '280': 'Wedding Cake',\n",
+       "  '80': 'White Bread',\n",
+       "  '195': 'Special Cake',\n",
+       "  '252': 'Wedding Cake',\n",
+       "  '85': 'White Bread',\n",
+       "  '200': 'Special Cake',\n",
+       "  '199': 'Special Cake',\n",
+       "  '84': 'White Bread',\n",
+       "  '281': 'Wedding Cake',\n",
+       "  '183': 'Special Cake',\n",
+       "  '68': 'White Bread',\n",
+       "  '251': 'Wedding Cake',\n",
+       "  '181': 'Special Cake',\n",
+       "  '66': 'White Bread',\n",
+       "  '282': 'Wedding Cake',\n",
+       "  '171': 'Special Cake',\n",
+       "  '56': 'White Bread',\n",
+       "  '33': 'White Bread',\n",
+       "  '148': 'Special Cake',\n",
+       "  '53': 'White Bread',\n",
+       "  '168': 'Special Cake',\n",
+       "  '173': 'Special Cake',\n",
+       "  '58': 'White Bread',\n",
+       "  '172': 'Special Cake',\n",
+       "  '57': 'White Bread',\n",
+       "  '60': 'White Bread',\n",
+       "  '175': 'Special Cake',\n",
+       "  '286': 'Wedding Cake',\n",
+       "  '174': 'Special Cake',\n",
+       "  '59': 'White Bread',\n",
+       "  '198': 'Special Cake',\n",
+       "  '83': 'White Bread',\n",
+       "  '169': 'Special Cake',\n",
+       "  '54': 'White Bread',\n",
+       "  '86': 'White Bread',\n",
+       "  '201': 'Special Cake',\n",
+       "  '185': 'Special Cake',\n",
+       "  '70': 'White Bread',\n",
+       "  '184': 'Special Cake',\n",
+       "  '69': 'White Bread',\n",
+       "  '78': 'White Bread',\n",
+       "  '193': 'Special Cake',\n",
+       "  '250': 'Wedding Cake',\n",
+       "  '71': 'White Bread',\n",
+       "  '186': 'Special Cake',\n",
+       "  '192': 'Special Cake',\n",
+       "  '77': 'White Bread',\n",
+       "  '191': 'Special Cake',\n",
+       "  '76': 'White Bread',\n",
+       "  '285': 'Wedding Cake',\n",
+       "  '176': 'Special Cake',\n",
+       "  '61': 'White Bread',\n",
+       "  '249': 'Wedding Cake',\n",
+       "  '74': 'White Bread',\n",
+       "  '189': 'Special Cake',\n",
+       "  '170': 'Special Cake',\n",
+       "  '55': 'White Bread',\n",
+       "  '190': 'Special Cake',\n",
+       "  '75': 'White Bread',\n",
+       "  '177': 'Special Cake',\n",
+       "  '62': 'White Bread',\n",
+       "  '283': 'Wedding Cake',\n",
+       "  '188': 'Special Cake',\n",
+       "  '73': 'White Bread',\n",
+       "  '65': 'White Bread',\n",
+       "  '180': 'Special Cake',\n",
+       "  '187': 'Special Cake',\n",
+       "  '72': 'White Bread',\n",
+       "  '284': 'Wedding Cake',\n",
+       "  '203': 'Special Cake',\n",
+       "  '88': 'White Bread',\n",
+       "  '63': 'White Bread',\n",
+       "  '178': 'Special Cake',\n",
+       "  '287': 'Wedding Cake',\n",
+       "  '87': 'White Bread',\n",
+       "  '202': 'Special Cake',\n",
+       "  '32': 'White Bread',\n",
+       "  '147': 'Special Cake',\n",
+       "  '207': 'Special Cake',\n",
+       "  '92': 'White Bread',\n",
+       "  '290': 'Wedding Cake',\n",
+       "  '90': 'White Bread',\n",
+       "  '205': 'Special Cake',\n",
+       "  '248': 'Wedding Cake',\n",
+       "  '211': 'Special Cake',\n",
+       "  '96': 'White Bread',\n",
+       "  '89': 'White Bread',\n",
+       "  '204': 'Special Cake',\n",
+       "  '289': 'Wedding Cake',\n",
+       "  '291': 'Wedding Cake',\n",
+       "  '146': 'Special Cake',\n",
+       "  '31': 'White Bread',\n",
+       "  '64': 'White Bread',\n",
+       "  '179': 'Special Cake',\n",
+       "  '209': 'Special Cake',\n",
+       "  '94': 'White Bread',\n",
+       "  '288': 'Wedding Cake',\n",
+       "  '224': 'Special Cake',\n",
+       "  '109': 'White Bread',\n",
+       "  '292': 'Wedding Cake',\n",
+       "  '28': 'White Bread',\n",
+       "  '143': 'Special Cake',\n",
+       "  '30': 'White Bread',\n",
+       "  '145': 'Special Cake',\n",
+       "  '29': 'White Bread',\n",
+       "  '144': 'Special Cake',\n",
+       "  '208': 'Special Cake',\n",
+       "  '93': 'White Bread',\n",
+       "  '206': 'Special Cake',\n",
+       "  '91': 'White Bread',\n",
+       "  '223': 'Special Cake',\n",
+       "  '108': 'White Bread',\n",
+       "  '222': 'Special Cake',\n",
+       "  '107': 'White Bread',\n",
+       "  '220': 'Special Cake',\n",
+       "  '105': 'White Bread',\n",
+       "  '27': 'White Bread',\n",
+       "  '142': 'Special Cake',\n",
+       "  '245': 'Wedding Cake',\n",
+       "  '95': 'White Bread',\n",
+       "  '210': 'Special Cake',\n",
+       "  '106': 'White Bread',\n",
+       "  '221': 'Special Cake',\n",
+       "  '26': 'White Bread',\n",
+       "  '141': 'Special Cake',\n",
+       "  '293': 'Wedding Cake',\n",
+       "  '110': 'White Bread',\n",
+       "  '225': 'Special Cake',\n",
+       "  '112': 'White Bread',\n",
+       "  '227': 'Special Cake',\n",
+       "  '243': 'Wedding Cake',\n",
+       "  '247': 'Wedding Cake',\n",
+       "  '25': 'White Bread',\n",
+       "  '140': 'Special Cake',\n",
+       "  '244': 'Wedding Cake',\n",
+       "  '294': 'Wedding Cake',\n",
+       "  '212': 'Special Cake',\n",
+       "  '97': 'White Bread',\n",
+       "  '297': 'Wedding Cake',\n",
+       "  '226': 'Special Cake',\n",
+       "  '111': 'White Bread',\n",
+       "  '298': 'Wedding Cake',\n",
+       "  '246': 'Wedding Cake',\n",
+       "  '104': 'White Bread',\n",
+       "  '219': 'Special Cake',\n",
+       "  '15': 'White Bread',\n",
+       "  '130': 'Special Cake',\n",
+       "  '295': 'Wedding Cake',\n",
+       "  '296': 'Wedding Cake',\n",
+       "  '237': 'Wedding Cake',\n",
+       "  '113': 'White Bread',\n",
+       "  '228': 'Special Cake',\n",
+       "  '139': 'Special Cake',\n",
+       "  '24': 'White Bread',\n",
+       "  '218': 'Special Cake',\n",
+       "  '103': 'White Bread',\n",
+       "  '137': 'Special Cake',\n",
+       "  '22': 'White Bread',\n",
+       "  '299': 'Wedding Cake',\n",
+       "  '131': 'Special Cake',\n",
+       "  '16': 'White Bread',\n",
+       "  '235': 'Wedding Cake',\n",
+       "  '213': 'Special Cake',\n",
+       "  '98': 'White Bread',\n",
+       "  '120': 'Special Cake',\n",
+       "  '5': 'White Bread',\n",
+       "  '23': 'White Bread',\n",
+       "  '138': 'Special Cake',\n",
+       "  '7': 'White Bread',\n",
+       "  '122': 'Special Cake',\n",
+       "  '132': 'Special Cake',\n",
+       "  '17': 'White Bread',\n",
+       "  '129': 'Special Cake',\n",
+       "  '14': 'White Bread',\n",
+       "  '231': 'Wedding Cake',\n",
+       "  '300': 'Wedding Cake',\n",
+       "  '136': 'Special Cake',\n",
+       "  '21': 'White Bread',\n",
+       "  '242': 'Wedding Cake',\n",
+       "  '8': 'White Bread',\n",
+       "  '123': 'Special Cake',\n",
+       "  '302': 'Wedding Cake',\n",
+       "  '101': 'White Bread',\n",
+       "  '216': 'Special Cake',\n",
+       "  '9': 'White Bread',\n",
+       "  '124': 'Special Cake',\n",
+       "  '1': 'White Bread',\n",
+       "  '116': 'Special Cake',\n",
+       "  '233': 'Wedding Cake',\n",
+       "  '234': 'Wedding Cake',\n",
+       "  '303': 'Wedding Cake',\n",
+       "  '13': 'White Bread',\n",
+       "  '128': 'Special Cake',\n",
+       "  '304': 'Wedding Cake',\n",
+       "  '215': 'Special Cake',\n",
+       "  '100': 'White Bread',\n",
+       "  '20': 'White Bread',\n",
+       "  '135': 'Special Cake',\n",
+       "  '133': 'Special Cake',\n",
+       "  '18': 'White Bread',\n",
+       "  '3': 'White Bread',\n",
+       "  '118': 'Special Cake',\n",
+       "  '214': 'Special Cake',\n",
+       "  '99': 'White Bread',\n",
+       "  '232': 'Wedding Cake',\n",
+       "  '217': 'Special Cake',\n",
+       "  '102': 'White Bread',\n",
+       "  '301': 'Wedding Cake',\n",
+       "  '238': 'Wedding Cake',\n",
+       "  '239': 'Wedding Cake',\n",
+       "  '240': 'Wedding Cake',\n",
+       "  '134': 'Special Cake',\n",
+       "  '19': 'White Bread',\n",
+       "  '4': 'White Bread',\n",
+       "  '119': 'Special Cake',\n",
+       "  '126': 'Special Cake',\n",
+       "  '11': 'White Bread',\n",
+       "  '117': 'Special Cake',\n",
+       "  '2': 'White Bread',\n",
+       "  '114': 'White Bread',\n",
+       "  '229': 'Special Cake',\n",
+       "  '236': 'Wedding Cake',\n",
+       "  '241': 'Wedding Cake',\n",
+       "  '121': 'Special Cake',\n",
+       "  '6': 'White Bread',\n",
+       "  '12': 'White Bread',\n",
+       "  '127': 'Special Cake',\n",
+       "  '125': 'Special Cake',\n",
+       "  '10': 'White Bread'},\n",
+       " 'demand': {'263': 33,\n",
+       "  '261': 31,\n",
+       "  '259': 29,\n",
+       "  '269': 39,\n",
+       "  '264': 34,\n",
+       "  '268': 38,\n",
+       "  '258': 28,\n",
+       "  '260': 30,\n",
+       "  '257': 27,\n",
+       "  '270': 40,\n",
+       "  '262': 32,\n",
+       "  '265': 35,\n",
+       "  '266': 36,\n",
+       "  '267': 37,\n",
+       "  '271': 41,\n",
+       "  '161': 46,\n",
+       "  '46': 46,\n",
+       "  '256': 26,\n",
+       "  '255': 25,\n",
+       "  '275': 45,\n",
+       "  '272': 42,\n",
+       "  '34': 34,\n",
+       "  '149': 34,\n",
+       "  '278': 48,\n",
+       "  '159': 44,\n",
+       "  '44': 44,\n",
+       "  '35': 35,\n",
+       "  '150': 35,\n",
+       "  '277': 47,\n",
+       "  '36': 36,\n",
+       "  '151': 36,\n",
+       "  '253': 23,\n",
+       "  '43': 43,\n",
+       "  '158': 43,\n",
+       "  '274': 44,\n",
+       "  '157': 42,\n",
+       "  '42': 42,\n",
+       "  '162': 47,\n",
+       "  '47': 47,\n",
+       "  '254': 24,\n",
+       "  '154': 39,\n",
+       "  '39': 39,\n",
+       "  '276': 46,\n",
+       "  '163': 48,\n",
+       "  '48': 48,\n",
+       "  '279': 49,\n",
+       "  '153': 38,\n",
+       "  '38': 38,\n",
+       "  '152': 37,\n",
+       "  '37': 37,\n",
+       "  '45': 45,\n",
+       "  '160': 45,\n",
+       "  '164': 49,\n",
+       "  '49': 49,\n",
+       "  '40': 40,\n",
+       "  '155': 40,\n",
+       "  '41': 41,\n",
+       "  '156': 41,\n",
+       "  '166': 51,\n",
+       "  '51': 51,\n",
+       "  '273': 43,\n",
+       "  '82': 82,\n",
+       "  '197': 82,\n",
+       "  '79': 79,\n",
+       "  '194': 79,\n",
+       "  '81': 81,\n",
+       "  '196': 81,\n",
+       "  '182': 67,\n",
+       "  '67': 67,\n",
+       "  '52': 52,\n",
+       "  '167': 52,\n",
+       "  '50': 50,\n",
+       "  '165': 50,\n",
+       "  '280': 50,\n",
+       "  '80': 80,\n",
+       "  '195': 80,\n",
+       "  '252': 22,\n",
+       "  '85': 85,\n",
+       "  '200': 85,\n",
+       "  '199': 84,\n",
+       "  '84': 84,\n",
+       "  '281': 51,\n",
+       "  '183': 68,\n",
+       "  '68': 68,\n",
+       "  '251': 21,\n",
+       "  '181': 66,\n",
+       "  '66': 66,\n",
+       "  '282': 52,\n",
+       "  '171': 56,\n",
+       "  '56': 56,\n",
+       "  '33': 33,\n",
+       "  '148': 33,\n",
+       "  '53': 53,\n",
+       "  '168': 53,\n",
+       "  '173': 58,\n",
+       "  '58': 58,\n",
+       "  '172': 57,\n",
+       "  '57': 57,\n",
+       "  '60': 60,\n",
+       "  '175': 60,\n",
+       "  '286': 56,\n",
+       "  '174': 59,\n",
+       "  '59': 59,\n",
+       "  '198': 83,\n",
+       "  '83': 83,\n",
+       "  '169': 54,\n",
+       "  '54': 54,\n",
+       "  '86': 86,\n",
+       "  '201': 86,\n",
+       "  '185': 70,\n",
+       "  '70': 70,\n",
+       "  '184': 69,\n",
+       "  '69': 69,\n",
+       "  '78': 78,\n",
+       "  '193': 78,\n",
+       "  '250': 20,\n",
+       "  '71': 71,\n",
+       "  '186': 71,\n",
+       "  '192': 77,\n",
+       "  '77': 77,\n",
+       "  '191': 76,\n",
+       "  '76': 76,\n",
+       "  '285': 55,\n",
+       "  '176': 61,\n",
+       "  '61': 61,\n",
+       "  '249': 19,\n",
+       "  '74': 74,\n",
+       "  '189': 74,\n",
+       "  '170': 55,\n",
+       "  '55': 55,\n",
+       "  '190': 75,\n",
+       "  '75': 75,\n",
+       "  '177': 62,\n",
+       "  '62': 62,\n",
+       "  '283': 53,\n",
+       "  '188': 73,\n",
+       "  '73': 73,\n",
+       "  '65': 65,\n",
+       "  '180': 65,\n",
+       "  '187': 72,\n",
+       "  '72': 72,\n",
+       "  '284': 54,\n",
+       "  '203': 88,\n",
+       "  '88': 88,\n",
+       "  '63': 63,\n",
+       "  '178': 63,\n",
+       "  '287': 57,\n",
+       "  '87': 87,\n",
+       "  '202': 87,\n",
+       "  '32': 32,\n",
+       "  '147': 32,\n",
+       "  '207': 92,\n",
+       "  '92': 92,\n",
+       "  '290': 60,\n",
+       "  '90': 90,\n",
+       "  '205': 90,\n",
+       "  '248': 18,\n",
+       "  '211': 96,\n",
+       "  '96': 96,\n",
+       "  '89': 89,\n",
+       "  '204': 89,\n",
+       "  '289': 59,\n",
+       "  '291': 61,\n",
+       "  '146': 31,\n",
+       "  '31': 31,\n",
+       "  '64': 64,\n",
+       "  '179': 64,\n",
+       "  '209': 94,\n",
+       "  '94': 94,\n",
+       "  '288': 58,\n",
+       "  '224': 109,\n",
+       "  '109': 109,\n",
+       "  '292': 62,\n",
+       "  '28': 28,\n",
+       "  '143': 28,\n",
+       "  '30': 30,\n",
+       "  '145': 30,\n",
+       "  '29': 29,\n",
+       "  '144': 29,\n",
+       "  '208': 93,\n",
+       "  '93': 93,\n",
+       "  '206': 91,\n",
+       "  '91': 91,\n",
+       "  '223': 108,\n",
+       "  '108': 108,\n",
+       "  '222': 107,\n",
+       "  '107': 107,\n",
+       "  '220': 105,\n",
+       "  '105': 105,\n",
+       "  '27': 27,\n",
+       "  '142': 27,\n",
+       "  '245': 15,\n",
+       "  '95': 95,\n",
+       "  '210': 95,\n",
+       "  '106': 106,\n",
+       "  '221': 106,\n",
+       "  '26': 26,\n",
+       "  '141': 26,\n",
+       "  '293': 63,\n",
+       "  '110': 110,\n",
+       "  '225': 110,\n",
+       "  '112': 112,\n",
+       "  '227': 112,\n",
+       "  '243': 13,\n",
+       "  '247': 17,\n",
+       "  '25': 25,\n",
+       "  '140': 25,\n",
+       "  '244': 14,\n",
+       "  '294': 64,\n",
+       "  '212': 97,\n",
+       "  '97': 97,\n",
+       "  '297': 67,\n",
+       "  '226': 111,\n",
+       "  '111': 111,\n",
+       "  '298': 68,\n",
+       "  '246': 16,\n",
+       "  '104': 104,\n",
+       "  '219': 104,\n",
+       "  '15': 15,\n",
+       "  '130': 15,\n",
+       "  '295': 65,\n",
+       "  '296': 66,\n",
+       "  '237': 7,\n",
+       "  '113': 113,\n",
+       "  '228': 113,\n",
+       "  '139': 24,\n",
+       "  '24': 24,\n",
+       "  '218': 103,\n",
+       "  '103': 103,\n",
+       "  '137': 22,\n",
+       "  '22': 22,\n",
+       "  '299': 69,\n",
+       "  '131': 16,\n",
+       "  '16': 16,\n",
+       "  '235': 5,\n",
+       "  '213': 98,\n",
+       "  '98': 98,\n",
+       "  '120': 5,\n",
+       "  '5': 5,\n",
+       "  '23': 23,\n",
+       "  '138': 23,\n",
+       "  '7': 7,\n",
+       "  '122': 7,\n",
+       "  '132': 17,\n",
+       "  '17': 17,\n",
+       "  '129': 14,\n",
+       "  '14': 14,\n",
+       "  '231': 1,\n",
+       "  '300': 70,\n",
+       "  '136': 21,\n",
+       "  '21': 21,\n",
+       "  '242': 12,\n",
+       "  '8': 8,\n",
+       "  '123': 8,\n",
+       "  '302': 72,\n",
+       "  '101': 101,\n",
+       "  '216': 101,\n",
+       "  '9': 9,\n",
+       "  '124': 9,\n",
+       "  '1': 1,\n",
+       "  '116': 1,\n",
+       "  '233': 3,\n",
+       "  '234': 4,\n",
+       "  '303': 73,\n",
+       "  '13': 13,\n",
+       "  '128': 13,\n",
+       "  '304': 74,\n",
+       "  '215': 100,\n",
+       "  '100': 100,\n",
+       "  '20': 20,\n",
+       "  '135': 20,\n",
+       "  '133': 18,\n",
+       "  '18': 18,\n",
+       "  '3': 3,\n",
+       "  '118': 3,\n",
+       "  '214': 99,\n",
+       "  '99': 99,\n",
+       "  '232': 2,\n",
+       "  '217': 102,\n",
+       "  '102': 102,\n",
+       "  '301': 71,\n",
+       "  '238': 8,\n",
+       "  '239': 9,\n",
+       "  '240': 10,\n",
+       "  '134': 19,\n",
+       "  '19': 19,\n",
+       "  '4': 4,\n",
+       "  '119': 4,\n",
+       "  '126': 11,\n",
+       "  '11': 11,\n",
+       "  '117': 2,\n",
+       "  '2': 2,\n",
+       "  '114': 114,\n",
+       "  '229': 114,\n",
+       "  '236': 6,\n",
+       "  '241': 11,\n",
+       "  '121': 6,\n",
+       "  '6': 6,\n",
+       "  '12': 12,\n",
+       "  '127': 12,\n",
+       "  '125': 10,\n",
+       "  '10': 10},\n",
+       " 'probability': {'263': 0.0368592173,\n",
+       "  '261': 0.0359488332,\n",
+       "  '259': 0.034826178,\n",
+       "  '269': 0.0345176881,\n",
+       "  '264': 0.0338754672,\n",
+       "  '268': 0.0336984278,\n",
+       "  '258': 0.0333003656,\n",
+       "  '260': 0.032756232,\n",
+       "  '257': 0.0325301611,\n",
+       "  '270': 0.032197924,\n",
+       "  '262': 0.0318970326,\n",
+       "  '265': 0.0311347815,\n",
+       "  '266': 0.030689652,\n",
+       "  '267': 0.0290920836,\n",
+       "  '271': 0.0283928783,\n",
+       "  '161': 0.028135825,\n",
+       "  '46': 0.028135825,\n",
+       "  '256': 0.0280648941,\n",
+       "  '255': 0.026794912,\n",
+       "  '275': 0.0267789487,\n",
+       "  '272': 0.0266978264,\n",
+       "  '34': 0.02649434,\n",
+       "  '149': 0.02649434,\n",
+       "  '278': 0.0261790284,\n",
+       "  '159': 0.0260993218,\n",
+       "  '44': 0.0260993218,\n",
+       "  '35': 0.0258797103,\n",
+       "  '150': 0.0258797103,\n",
+       "  '277': 0.0249885005,\n",
+       "  '36': 0.0247542848,\n",
+       "  '151': 0.0247542848,\n",
+       "  '253': 0.0237528724,\n",
+       "  '43': 0.0227409136,\n",
+       "  '158': 0.0227409136,\n",
+       "  '274': 0.0223511295,\n",
+       "  '157': 0.0218458294,\n",
+       "  '42': 0.0218458294,\n",
+       "  '162': 0.0218256638,\n",
+       "  '47': 0.0218256638,\n",
+       "  '254': 0.0217967443,\n",
+       "  '154': 0.0216395613,\n",
+       "  '39': 0.0216395613,\n",
+       "  '276': 0.0216095805,\n",
+       "  '163': 0.0215321773,\n",
+       "  '48': 0.0215321773,\n",
+       "  '279': 0.0213346388,\n",
+       "  '153': 0.0203048915,\n",
+       "  '38': 0.0203048915,\n",
+       "  '152': 0.020051612,\n",
+       "  '37': 0.020051612,\n",
+       "  '45': 0.0199892913,\n",
+       "  '160': 0.0199892913,\n",
+       "  '164': 0.0195399323,\n",
+       "  '49': 0.0195399323,\n",
+       "  '40': 0.019229393,\n",
+       "  '155': 0.019229393,\n",
+       "  '41': 0.0190548591,\n",
+       "  '156': 0.0190548591,\n",
+       "  '166': 0.018913738,\n",
+       "  '51': 0.018913738,\n",
+       "  '273': 0.0184784305,\n",
+       "  '82': 0.0182737867,\n",
+       "  '197': 0.0182737867,\n",
+       "  '79': 0.0180723397,\n",
+       "  '194': 0.0180723397,\n",
+       "  '81': 0.0179847392,\n",
+       "  '196': 0.0179847392,\n",
+       "  '182': 0.0177538496,\n",
+       "  '67': 0.0177538496,\n",
+       "  '52': 0.017304322,\n",
+       "  '167': 0.017304322,\n",
+       "  '50': 0.0172683526,\n",
+       "  '165': 0.0172683526,\n",
+       "  '280': 0.017080318,\n",
+       "  '80': 0.0165558467,\n",
+       "  '195': 0.0165558467,\n",
+       "  '252': 0.0164150156,\n",
+       "  '85': 0.0163239057,\n",
+       "  '200': 0.0163239057,\n",
+       "  '199': 0.0155502511,\n",
+       "  '84': 0.0155502511,\n",
+       "  '281': 0.0155468033,\n",
+       "  '183': 0.0153482999,\n",
+       "  '68': 0.0153482999,\n",
+       "  '251': 0.0150519811,\n",
+       "  '181': 0.0149100957,\n",
+       "  '66': 0.0149100957,\n",
+       "  '282': 0.0145321593,\n",
+       "  '171': 0.0145073305,\n",
+       "  '56': 0.0145073305,\n",
+       "  '33': 0.0143434204,\n",
+       "  '148': 0.0143434204,\n",
+       "  '53': 0.0139978926,\n",
+       "  '168': 0.0139978926,\n",
+       "  '173': 0.0137575929,\n",
+       "  '58': 0.0137575929,\n",
+       "  '172': 0.0133753577,\n",
+       "  '57': 0.0133753577,\n",
+       "  '60': 0.0132917234,\n",
+       "  '175': 0.0132917234,\n",
+       "  '286': 0.0128341354,\n",
+       "  '174': 0.0125602164,\n",
+       "  '59': 0.0125602164,\n",
+       "  '198': 0.0122586994,\n",
+       "  '83': 0.0122586994,\n",
+       "  '169': 0.0121257892,\n",
+       "  '54': 0.0121257892,\n",
+       "  '86': 0.0121178443,\n",
+       "  '201': 0.0121178443,\n",
+       "  '185': 0.0117735274,\n",
+       "  '70': 0.0117735274,\n",
+       "  '184': 0.0117612458,\n",
+       "  '69': 0.0117612458,\n",
+       "  '78': 0.011635456,\n",
+       "  '193': 0.011635456,\n",
+       "  '250': 0.01154316,\n",
+       "  '71': 0.0112493485,\n",
+       "  '186': 0.0112493485,\n",
+       "  '192': 0.0111785296,\n",
+       "  '77': 0.0111785296,\n",
+       "  '191': 0.0111410438,\n",
+       "  '76': 0.0111410438,\n",
+       "  '285': 0.0110507398,\n",
+       "  '176': 0.0105914583,\n",
+       "  '61': 0.0105914583,\n",
+       "  '249': 0.0105420966,\n",
+       "  '74': 0.0105078101,\n",
+       "  '189': 0.0105078101,\n",
+       "  '170': 0.0103408676,\n",
+       "  '55': 0.0103408676,\n",
+       "  '190': 0.0100856266,\n",
+       "  '75': 0.0100856266,\n",
+       "  '177': 0.0100635496,\n",
+       "  '62': 0.0100635496,\n",
+       "  '283': 0.0098274898,\n",
+       "  '188': 0.009615686,\n",
+       "  '73': 0.009615686,\n",
+       "  '65': 0.0089209082,\n",
+       "  '180': 0.0089209082,\n",
+       "  '187': 0.0088669788,\n",
+       "  '72': 0.0088669788,\n",
+       "  '284': 0.008681397,\n",
+       "  '203': 0.0085985317,\n",
+       "  '88': 0.0085985317,\n",
+       "  '63': 0.0083903575,\n",
+       "  '178': 0.0083903575,\n",
+       "  '287': 0.0079844742,\n",
+       "  '87': 0.0075161459,\n",
+       "  '202': 0.0075161459,\n",
+       "  '32': 0.0065831021,\n",
+       "  '147': 0.0065831021,\n",
+       "  '207': 0.0063411487,\n",
+       "  '92': 0.0063411487,\n",
+       "  '290': 0.0061494519,\n",
+       "  '90': 0.0060437383,\n",
+       "  '205': 0.0060437383,\n",
+       "  '248': 0.0057253414,\n",
+       "  '211': 0.0057178973,\n",
+       "  '96': 0.0057178973,\n",
+       "  '89': 0.0056477112,\n",
+       "  '204': 0.0056477112,\n",
+       "  '289': 0.0055459619,\n",
+       "  '291': 0.0054795932,\n",
+       "  '146': 0.0054244868,\n",
+       "  '31': 0.0054244868,\n",
+       "  '64': 0.0053959746,\n",
+       "  '179': 0.0053959746,\n",
+       "  '209': 0.0051360659,\n",
+       "  '94': 0.0051360659,\n",
+       "  '288': 0.0050816214,\n",
+       "  '224': 0.0048954825,\n",
+       "  '109': 0.0048954825,\n",
+       "  '292': 0.0047980717,\n",
+       "  '28': 0.0045802571,\n",
+       "  '143': 0.0045802571,\n",
+       "  '30': 0.0044781409,\n",
+       "  '145': 0.0044781409,\n",
+       "  '29': 0.0043621607,\n",
+       "  '144': 0.0043621607,\n",
+       "  '208': 0.0043273171,\n",
+       "  '93': 0.0043273171,\n",
+       "  '206': 0.0041276299,\n",
+       "  '91': 0.0041276299,\n",
+       "  '223': 0.0040755787,\n",
+       "  '108': 0.0040755787,\n",
+       "  '222': 0.0039335012,\n",
+       "  '107': 0.0039335012,\n",
+       "  '220': 0.0038894774,\n",
+       "  '105': 0.0038894774,\n",
+       "  '27': 0.00385749,\n",
+       "  '142': 0.00385749,\n",
+       "  '245': 0.0036740912,\n",
+       "  '95': 0.0036275468,\n",
+       "  '210': 0.0036275468,\n",
+       "  '106': 0.0035281844,\n",
+       "  '221': 0.0035281844,\n",
+       "  '26': 0.0033199252,\n",
+       "  '141': 0.0033199252,\n",
+       "  '293': 0.0032641712,\n",
+       "  '110': 0.0031606894,\n",
+       "  '225': 0.0031606894,\n",
+       "  '112': 0.002931355,\n",
+       "  '227': 0.002931355,\n",
+       "  '243': 0.0029177054,\n",
+       "  '247': 0.0027665343,\n",
+       "  '25': 0.0026568393,\n",
+       "  '140': 0.0026568393,\n",
+       "  '244': 0.0026502146,\n",
+       "  '294': 0.0025965544,\n",
+       "  '212': 0.002554393,\n",
+       "  '97': 0.002554393,\n",
+       "  '297': 0.0022778517,\n",
+       "  '226': 0.0022694948,\n",
+       "  '111': 0.0022694948,\n",
+       "  '298': 0.0022332029,\n",
+       "  '246': 0.00198394,\n",
+       "  '104': 0.0019647995,\n",
+       "  '219': 0.0019647995,\n",
+       "  '15': 0.0019036542,\n",
+       "  '130': 0.0019036542,\n",
+       "  '295': 0.0018337038,\n",
+       "  '296': 0.0014691137,\n",
+       "  '237': 0.0014035503,\n",
+       "  '113': 0.0013588412,\n",
+       "  '228': 0.0013588412,\n",
+       "  '139': 0.0013444622,\n",
+       "  '24': 0.0013444622,\n",
+       "  '218': 0.001279575,\n",
+       "  '103': 0.001279575,\n",
+       "  '137': 0.0012722084,\n",
+       "  '22': 0.0012722084,\n",
+       "  '299': 0.0012112573,\n",
+       "  '131': 0.0009974778,\n",
+       "  '16': 0.0009974778,\n",
+       "  '235': 0.0009420068,\n",
+       "  '213': 0.000899227,\n",
+       "  '98': 0.000899227,\n",
+       "  '120': 0.0007732343,\n",
+       "  '5': 0.0007732343,\n",
+       "  '23': 0.0007673017,\n",
+       "  '138': 0.0007673017,\n",
+       "  '7': 0.000579398,\n",
+       "  '122': 0.000579398,\n",
+       "  '132': 0.0005463021,\n",
+       "  '17': 0.0005463021,\n",
+       "  '129': 0.0005379338,\n",
+       "  '14': 0.0005379338,\n",
+       "  '231': 0.0004810596,\n",
+       "  '300': 0.0004541821,\n",
+       "  '136': 0.0004143761,\n",
+       "  '21': 0.0004143761,\n",
+       "  '242': 0.0004077686,\n",
+       "  '8': 0.000402153,\n",
+       "  '123': 0.000402153,\n",
+       "  '302': 0.0003903984,\n",
+       "  '101': 0.0003871625,\n",
+       "  '216': 0.0003871625,\n",
+       "  '9': 0.0003653594,\n",
+       "  '124': 0.0003653594,\n",
+       "  '1': 0.0003608402,\n",
+       "  '116': 0.0003608402,\n",
+       "  '233': 0.0003515124,\n",
+       "  '234': 0.0003474865,\n",
+       "  '303': 0.0003399258,\n",
+       "  '13': 0.0003227829,\n",
+       "  '128': 0.0003227829,\n",
+       "  '304': 0.0003183052,\n",
+       "  '215': 0.0003102312,\n",
+       "  '100': 0.0003102312,\n",
+       "  '20': 0.0003036225,\n",
+       "  '135': 0.0003036225,\n",
+       "  '133': 0.0002644347,\n",
+       "  '18': 0.0002644347,\n",
+       "  '3': 0.0002636676,\n",
+       "  '118': 0.0002636676,\n",
+       "  '214': 0.0002458838,\n",
+       "  '99': 0.0002458838,\n",
+       "  '232': 0.0002280527,\n",
+       "  '217': 0.0002082343,\n",
+       "  '102': 0.0002082343,\n",
+       "  '301': 0.0002049358,\n",
+       "  '238': 0.0002048074,\n",
+       "  '239': 0.0001971212,\n",
+       "  '240': 0.0001920457,\n",
+       "  '134': 0.0001910985,\n",
+       "  '19': 0.0001910985,\n",
+       "  '4': 0.0001887357,\n",
+       "  '119': 0.0001887357,\n",
+       "  '126': 0.0001747752,\n",
+       "  '11': 0.0001747752,\n",
+       "  '117': 0.0001710611,\n",
+       "  '2': 0.0001710611,\n",
+       "  '114': 0.0001586266,\n",
+       "  '229': 0.0001586266,\n",
+       "  '236': 0.0001076846,\n",
+       "  '241': 8.84724e-05,\n",
+       "  '121': 8.60457e-05,\n",
+       "  '6': 8.60457e-05,\n",
+       "  '12': 6.17417e-05,\n",
+       "  '127': 6.17417e-05,\n",
+       "  '125': 4.30096e-05,\n",
+       "  '10': 4.30096e-05}}"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import json\n",
+    "json.loads(res['probability_table'])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "timeseries",
+   "language": "python",
+   "name": "timeseries"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1 @@
+python-dotenv

src/__init__.py

@@ -0,0 +1 @@
+# from apis.idsc_login import get_idsc_apikey

src/apis/idsc_login.py

@@ -0,0 +1,40 @@
+import requests, yaml, datetime
+
+def load_idsc_config():
+    with open('../configs/idsc_config', 'r') as file:
+        config = yaml.save_load(file)
+    return config
+
+def save_idsc_config(config):
+    with open('../configs/idsc_config', 'w') as file:
+        yaml.dump(config, file, default_flow_style=False)
+
+def get_idsc_apikey():
+    config = load_idsc_config()
+    expire = config.expire
+    expire_date = datetime.strptime(expire)
+    now = datetime.now()
+    
+    if expire_date < now:
+        return config.apikey
+    
+    new_expire = (now + datetime.timedelta(days=3)).strftime()
+    config.apikey = idsc_login()
+    config.expire = new_expire 
+    save_idsc_config(config)
+
+def idsc_login(email, password):
+    
+    json = {"email": email,
+            "pwd": password}
+
+    login_resp = requests.post(
+        'https://idsc.com.sg/user/login',
+        json=json    )
+
+    if login_resp.status_code == 200:
+        apikey = login_resp.json()["API_key"]
+        return apikey
+    else:
+        raise Exception(login_resp.json())
+

src/demo_data/example_inventory.csv

@@ -0,0 +1,6 @@
+SKU,demand,price,cost,space_per_unit,budgetary_cost,replenishment_rate
+Item_A,1262,50,11,1.5,10,0.1
+Item_B,68,120,19,3,20,0.1
+Item_C,179,60,9.5,5,10,0.1
+Item_D,516,10,8,2,8,0.1
+Item_E,563,30,13,1,15,0.1

src/demo_data/example_rm.csv

@@ -0,0 +1,3 @@
+SKU,demand,price,cost,space_per_unit,budgetary_cost,replenishment_rate
+Raw Material A,5000,2,1.1,0.5,1,0.1
+Raw Material B,3000,3,1.9,0.2,2,0.1

src/demo_data/example_wip.csv

@@ -0,0 +1,4 @@
+SKU,demand,price,cost,space_per_unit,replenishment_rate,budgetary_cost
+Item C,500,3,2,1,0.1,2
+Item B,2000,4,2,2,0.1,2
+Item A,1500,5,3,3,0.1,3

src/gr/GradioApp.py

@@ -0,0 +1,376 @@
+import gradio as gr
+import pandas as pd
+from ..idsc.idsc_apis import IDSC_API
+import matplotlib.pyplot as plt
+from .GradioFns import GradioFns
+
+fns = GradioFns()
+
+
+class GradioApp():
+    def __init__(self):
+        # [Constents] #
+        self.inventory_input_demo_path = 'src/demo_data/example_inventory.csv'
+        self.rm_input_demo_path = 'src/demo_data/example_rm.csv'
+        self.wip_input_demo_path = 'src/demo_data/example_wip.csv'
+
+        self.idsc = IDSC_API()
+
+        # [Inventory Values] #
+        self.inventory_input_df__value = pd.DataFrame()
+        self.inv_recom_df__value = pd.DataFrame()
+
+        self.inventory_storage_capacity__value = 0
+        self.inventory_budget_constraint__value = 0
+
+        self.inv_total_profit_md__val = 0
+        self.inv_total_capacity_usage_md__val = 0
+        self.inv_total_budget_usage_md__val = 0
+        self.inv_total_margin_md__val = 0
+
+        self.inv_plot__fig = plt.plot()
+
+        # [Raw Inventory Values] #
+        self.rm_input_df__value = pd.DataFrame()
+        self.rm_recom_df__value = pd.DataFrame()
+
+        self.rm_storage_capacity__value = 0
+        self.rm_budget_constraint__value = 0
+
+        self.rm_total_capacity_usage_md__val = 0
+        self.rm_total_budget_usage_md__val = 0
+
+        # [WIP Inventory Values] #
+        self.wip_input_df__value = pd.DataFrame()
+        self.wip_recom_df__value = pd.DataFrame()
+
+        self.wip_storage_capacity__value = 0
+        self.wip_budget_constraint__value = 0
+
+        self.wip_total_capacity_usage_md__val = 0
+        self.wip_total_budget_usage_md__val = 0
+
+    # =============== #
+    # Event Listeners #
+    # =============== #
+
+    def demo_data_btn__click(self):
+        print('Load inventory input demo.')
+        self.inventory_input_df__value = pd.read_csv(
+            self.inventory_input_demo_path)
+        self.inventory_storage_capacity__value = 5000
+        self.inventory_budget_constraint__value = 25000
+        return (
+            self.update__inventory_input_df(),
+            self.update__inventory_storage_capacity(),
+            self.update__inventory_budget_constraint())
+
+    def inventory_file__upload(self, file):
+        self.inventory_input_df__value = pd.read_csv(file.name)
+        return self.update__inventory_input_df()
+
+    def inventory_storage_capacity__change(self, value):
+        self.inventory_storage_capacity__value = value
+
+    def inventory_budget_constraint__change(self, value):
+        self.inventory_budget_constraint__value = value
+
+    def inventory_btn__click(self):
+        inventory_input_df = self.inventory_input_df__value
+
+        self.idsc.product_mix(
+            inventory_input_df.to_json(),
+            self.inventory_storage_capacity__value,
+            self.inventory_budget_constraint__value)
+
+        self.__update_inventory_res()
+
+        return (
+            self.update__inv_recom_df(),
+            self.update__inv_total_profit_md(),
+            self.update__inv_total_capacity_usage_md(),
+            self.update__inv_total_budget_usage_md(),
+            self.update__inv_total_margin_md(),
+            self.update__inv_plot())
+
+    def __update_inventory_res(self):
+        if self.idsc.product_mix__res:
+            # API call success
+            res = self.idsc.product_mix__res
+            print(res)
+            self.inv_recom_df__value = fns.format__inv_recom_df(
+                self.idsc.get_product_mix_recommendations_df(),
+                self.inventory_input_df__value)
+
+            self.inv_total_profit_md__val = res['total_profit']
+            self.inv_total_capacity_usage_md__val = res['total_capacity_usage']
+            self.inv_total_budget_usage_md__val = res['total_budget_usage']
+            self.inv_total_margin_md__val = \
+                round((res['total_profit'] - res['total_budget_usage']
+                       ) / res['total_profit'] * 100, 2)
+
+            self.inv_plot__fig = fns.plot__inv_res(
+                res,
+                self.inventory_storage_capacity__value,
+                self.inventory_budget_constraint__value,
+                self.inv_recom_df__value)
+
+        else:
+            self.inv_recom_df__value = pd.DataFrame()
+
+            self.inv_total_profit_md__val = '-'
+            self.inv_total_capacity_usage_md__val = '-'
+            self.inv_total_budget_usage_md__val = '-'
+            self.inv_total_margin_md__val = '-'
+
+            self.inv_plot__fig = plt.plot()
+
+    # ======== #
+    # Updaters #
+    # ======== #
+
+    def update__inventory_input_df(self):
+        return gr.Dataframe.update(
+            value=self.inventory_input_df__value)
+
+    def update__inv_recom_df(self):
+        return gr.Dataframe.update(
+            value=self.inv_recom_df__value)
+
+    def update__inventory_storage_capacity(self):
+        return gr.Number.update(
+            value=self.inventory_storage_capacity__value)
+
+    def update__inventory_budget_constraint(self):
+        return gr.Number.update(
+            value=self.inventory_budget_constraint__value)
+
+    def update__inv_total_profit_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Profit: \n # {self.inv_total_profit_md__val:,}')
+
+    def update__inv_total_capacity_usage_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Capacity Usage: \n # {self.inv_total_capacity_usage_md__val:,}')
+
+    def update__inv_total_budget_usage_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Budget Usage: \n # {self.inv_total_budget_usage_md__val:,}')
+
+    def update__inv_total_margin_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Margin: \n # {self.inv_total_margin_md__val}%')
+
+    def update__inv_plot(self):
+        return gr.Plot.update(value=self.inv_plot__fig)
+
+    # ============================ #
+    # Raw Material Event Listeners #
+    # ============================ #
+
+    def rm_demo_data_btn__click(self):
+        print('Load raw material input demo.')
+        self.rm_input_df__value = pd.read_csv(
+            self.rm_input_demo_path)
+        self.rm_storage_capacity__value = 4000
+        self.rm_budget_constraint__value = 10000
+        return (
+            self.update__rm_input_df(),
+            self.update__rm_storage_capacity(),
+            self.update__rm_budget_constraint())
+
+    def rm_file__upload(self, file):
+        self.rm_input_df__value = pd.read_csv(file.name)
+        return self.update__rm_input_df()
+
+    def rm_storage_capacity__change(self, value):
+        self.rm_storage_capacity__value = value
+
+    def rm_budget_constraint__change(self, value):
+        self.rm_budget_constraint__value = value
+
+    def rm_btn__click(self):
+        self.idsc.product_mix(
+            self.rm_input_df__value.to_json(),
+            self.rm_storage_capacity__value,
+            self.rm_budget_constraint__value)
+
+        self.__update_rm_res()
+
+        return (
+            self.update__rm_recom_df(),
+            self.update__rm_total_capacity_usage_md(),
+            self.update__rm_total_budget_usage_md(),
+            self.update__rm_plot())
+
+    def __update_rm_res(self):
+        if self.idsc.product_mix__res:
+            res = self.idsc.product_mix__res
+
+            self.rm_recom_df__value = fns.format__inv_recom_df(
+                self.idsc.get_product_mix_recommendations_df(),
+                self.rm_input_df__value
+            )
+            self.rm_total_capacity_usage_md__val = res['total_capacity_usage']
+            self.rm_total_budget_usage_md__val = res['total_budget_usage']
+
+            self.rm_plot__fig = fns.plot__rm_res(
+                res,
+                self.rm_storage_capacity__value,
+                self.rm_budget_constraint__value,
+                self.rm_recom_df__value)
+
+        else:
+            self.rm_recom_df__value = pd.DataFrame()
+            self.rm_total_capacity_usage_md__val = '-'
+            self.rm_total_budget_usage_md__val = '-'
+
+            self.rm_plot__fig = plt.plot()
+
+    # ===================== #
+    # Raw Material Updaters #
+    # ===================== #
+
+    def update__rm_input_df(self):
+
+        df = self.rm_input_df__value.rename(
+            columns={'price': 'transfer price'})
+        # df = df.drop(columns=['replenishment_rate'])
+
+        return gr.Dataframe.update(
+            value=df)
+
+    def update__rm_recom_df(self):
+        df = self.rm_recom_df__value.rename(
+            columns={'price': 'transfer price'})
+        df = df.drop(columns=['potential_lost_sales', 'expected_sales',
+                     'soldout_probability', 'revenue', 'margin (%)'])
+        return gr.Dataframe.update(
+            value=df)
+
+    def update__rm_storage_capacity(self):
+        return gr.Number.update(
+            value=self.rm_storage_capacity__value)
+
+    def update__rm_budget_constraint(self):
+        return gr.Number.update(
+            value=self.rm_budget_constraint__value)
+
+    def update__rm_total_capacity_usage_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Capacity Usage: \n # {self.rm_total_capacity_usage_md__val:,}')
+
+    def update__rm_total_budget_usage_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Budget Usage: \n # {self.rm_total_budget_usage_md__val:,}')
+
+    def update__rm_plot(self):
+        return gr.Plot.update(value=self.rm_plot__fig)
+
+    # =================== #
+    # WIP Event Listeners #
+    # =================== #
+
+    def wip_demo_data_btn__click(self):
+        print('Load raw material input demo.')
+        self.wip_input_df__value = pd.read_csv(
+            self.wip_input_demo_path)
+        self.wip_storage_capacity__value = 13000
+        self.wip_budget_constraint__value = 14000
+
+        return (
+            self.update__wip_input_df(),
+            self.update__wip_storage_capacity(),
+            self.update__wip_budget_constraint())
+
+    def wip_file__upload(self, file):
+        self.wip_input_df__value = pd.read_csv(file.name)
+        return self.update__wip_input_df()
+
+    def wip_storage_capacity__change(self, value):
+        self.wip_storage_capacity__value = value
+
+    def wip_budget_constraint__change(self, value):
+        self.wip_budget_constraint__value = value
+
+    def wip_btn__click(self):
+
+        self.idsc.product_mix(
+            self.wip_input_df__value.to_json(),
+            self.wip_storage_capacity__value,
+            self.wip_budget_constraint__value)
+
+        self.__update_wip_res()
+
+        return (
+            self.update__wip_recom_df(),
+            self.update__wip_total_capacity_usage_md(),
+            self.update__wip_total_budget_usage_md(),
+            self.update__wip_plot())
+
+    def __update_wip_res(self):
+        if self.idsc.product_mix__res:
+            res = self.idsc.product_mix__res
+
+            print('__update_wip_res')
+            print(res)
+
+            self.wip_recom_df__value = fns.format__inv_recom_df(
+                self.idsc.get_product_mix_recommendations_df(),
+                self.wip_input_df__value
+            )
+            self.wip_total_capacity_usage_md__val = res['total_capacity_usage']
+            self.wip_total_budget_usage_md__val = res['total_budget_usage']
+
+            self.wip_plot__fig = fns.plot__wip_res(
+                res,
+                self.wip_storage_capacity__value,
+                self.wip_budget_constraint__value,
+                self.wip_recom_df__value)
+
+        else:
+            self.wip_recom_df__value = pd.DataFrame()
+            self.wip_total_capacity_usage_md__val = '-'
+            self.wip_total_budget_usage_md__val = '-'
+
+            self.wip_plot__fig = plt.plot()
+
+    # ============ #
+    # WIP Updaters #
+    # ============ #
+
+    def update__wip_input_df(self):
+
+        df = self.wip_input_df__value.rename(
+            columns={'price': 'transfer price'})
+        # df = df.drop(columns=['replenishment_rate', 'budgetary_cost'])
+
+        return gr.Dataframe.update(
+            value=df)
+
+    def update__wip_recom_df(self):
+        df = self.wip_recom_df__value.rename(
+            columns={'price': 'transfer price', 'inventory_level': 'WIP'})
+        df = df.drop(columns=['potential_lost_sales', 'expected_sales',
+                     'soldout_probability', 'revenue', 'margin (%)'])
+        return gr.Dataframe.update(
+            value=df)
+
+    def update__wip_storage_capacity(self):
+        return gr.Number.update(
+            value=self.wip_storage_capacity__value)
+
+    def update__wip_budget_constraint(self):
+        return gr.Number.update(
+            value=self.wip_budget_constraint__value)
+
+    def update__wip_total_capacity_usage_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Capacity Usage: \n # {self.wip_total_capacity_usage_md__val:,}')
+
+    def update__wip_total_budget_usage_md(self):
+        return gr.Markdown.update(
+            value=f'### Total Budget Usage: \n # {self.wip_total_budget_usage_md__val:,}')
+
+    def update__wip_plot(self):
+        return gr.Plot.update(value=self.wip_plot__fig)

src/gr/GradioFns.py

@@ -0,0 +1,144 @@
+import matplotlib.pyplot as plt
+
+plt.rcParams['font.size'] = '18'
+
+
+class GradioFns():
+    def __init__(self) -> None:
+        pass
+
+    def format__inv_recom_df(self, inv_recom_df, inv_input_df):
+        inv_recom_df_cp = inv_recom_df.copy()
+
+        inv_recom_df_cp['revenue'] = 0
+        inv_recom_df_cp['cost'] = 0
+        # inv_recom_df_cp['margin'] = 0
+        inv_recom_df_cp['margin (%)'] = 0
+        inv_recom_df_cp['space_usage'] = 0
+
+        for i, row in inv_recom_df_cp.iterrows():
+            # print('row', row)
+            sku = row['SKU']
+
+            cost = float(inv_input_df[inv_input_df['SKU'] == sku]['cost'])
+            price = float(inv_input_df[inv_input_df['SKU'] == sku]['price'])
+            space = float(inv_input_df[inv_input_df['SKU']
+                                       == sku]['space_per_unit'])
+            margin = float(row['expected_sales'] * (price - cost))
+
+            revenue = row['expected_sales'] * price
+
+            inv_recom_df_cp.at[i, 'revenue'] = revenue
+            inv_recom_df_cp.at[i, 'cost'] = row['expected_sales'] * cost
+
+            # inv_recom_df_cp.at[i, 'margin'] = margin
+
+            if revenue > 0:
+                inv_recom_df_cp.at[i, 'margin (%)'] = round(
+                    (margin / revenue) * 100, 2)
+            inv_recom_df_cp.at[i,
+                               'space_usage'] = row['expected_sales'] * space
+
+        return inv_recom_df_cp
+
+    def plot__inv_res(self, inv_res, storage, budget, inv_recom_df):
+
+        fig, ax = plt.subplots(1, 3, figsize=(24, 7))
+
+        space_left = storage - inv_res['total_capacity_usage']
+
+        space_left = 0 if space_left < 0 else space_left
+
+        space_labels = [
+            f'{row["SKU"]}\n{row["space_usage"]}' for idx, row in inv_recom_df.iterrows()]
+
+        ax[0].pie([space_left] + inv_recom_df['space_usage'].tolist(),
+                  labels=[
+                      f'Storage Left\n{ int(space_left)}'] + space_labels,
+                  autopct='%.0f%%')
+
+        cost_left = budget - inv_res['total_budget_usage']
+        cost_left = 0 if cost_left < 0 else cost_left
+        cost_labels = [
+            f'{row["SKU"]}\n{row["cost"]}' for idx, row in inv_recom_df.iterrows()]
+
+        ax[1].pie([cost_left] + inv_recom_df['cost'].tolist(),
+                  labels=[f'Budget Left\n{int(cost_left)}'] + cost_labels,
+                  autopct='%.0f%%')
+        ax[2].bar(inv_recom_df['SKU'],
+                  inv_recom_df['inventory_level'], width=0.3)
+
+        ax[0].set_title('Forecasted Storage Space Usage')
+        ax[1].set_title('Costs')
+        ax[2].set_title('Forecasted Inventory Level')
+
+        fig.tight_layout()
+        return fig
+
+    def plot__rm_res(self, inv_res, storage, budget, inv_recom_df):
+
+        fig, ax = plt.subplots(1, 3, figsize=(24, 7))
+
+        space_left = storage - inv_res['total_capacity_usage']
+
+        space_left = 0 if space_left < 0 else space_left
+
+        space_labels = [
+            f'{row["SKU"]}\n{row["space_usage"]}' for idx, row in inv_recom_df.iterrows()]
+
+        ax[0].pie([space_left] + inv_recom_df['space_usage'].tolist(),
+                  labels=[
+                      f'Storage Left\n{ int(space_left)}'] + space_labels,
+                  autopct='%.0f%%')
+
+        cost_left = budget - inv_res['total_budget_usage']
+        cost_left = 0 if cost_left < 0 else cost_left
+        cost_labels = [
+            f'{row["SKU"]}\n{row["cost"]}' for idx, row in inv_recom_df.iterrows()]
+
+        ax[1].pie([cost_left] + inv_recom_df['cost'].tolist(),
+                  labels=[f'Budget Left\n{int(cost_left)}'] + cost_labels,
+                  autopct='%.0f%%')
+        ax[2].bar(inv_recom_df['SKU'],
+                  inv_recom_df['inventory_level'], width=0.3)
+
+        ax[0].set_title('Forecasted Storage Space Usage')
+        ax[1].set_title('Raw Material Costs')
+        ax[2].set_title('Forecasted Raw Material Inventory Level')
+
+        fig.tight_layout()
+        return fig
+
+    def plot__wip_res(self, inv_res, storage, budget, inv_recom_df):
+
+        fig, ax = plt.subplots(1, 3, figsize=(24, 7))
+
+        space_left = storage - inv_res['total_capacity_usage']
+
+        space_left = 0 if space_left < 0 else space_left
+
+        space_labels = [
+            f'{row["SKU"]}\n{row["space_usage"]}' for idx, row in inv_recom_df.iterrows()]
+
+        ax[0].pie([space_left] + inv_recom_df['space_usage'].tolist(),
+                  labels=[
+                      f'Capacity Left\n{ int(space_left)}'] + space_labels,
+                  autopct='%.0f%%')
+
+        cost_left = budget - inv_res['total_budget_usage']
+        cost_left = 0 if cost_left < 0 else cost_left
+        cost_labels = [
+            f'{row["SKU"]}\n{row["cost"]}' for idx, row in inv_recom_df.iterrows()]
+
+        ax[1].pie([cost_left] + inv_recom_df['cost'].tolist(),
+                  labels=[f'Budget Left\n{int(cost_left)}'] + cost_labels,
+                  autopct='%.0f%%')
+        ax[2].bar(inv_recom_df['SKU'],
+                  inv_recom_df['inventory_level'], width=0.3)
+
+        ax[0].set_title('Forecasted WIP Capacity Usage')
+        ax[1].set_title('WIP Costs')
+        ax[2].set_title('WIP Level')
+
+        fig.tight_layout()
+        return fig

src/gr/gr_args.py

@@ -0,0 +1,132 @@
+import pandas as pd
+
+main_block = {
+    'css': '''
+    footer {visibility: hidden}
+    
+    /* Modify the forecast button size */
+    .btn {width: 260px !important; margin: auto !important}
+    '''
+}
+
+inventory_md = {
+    'value': """
+    # Finishend Goods Optimization
+    - Data must contains column 'SKU', 'demand', 'price', 'cost', 'space_per_unit', 'budgetary_cost'
+    - Optional column : 'replenishment_rate' 
+    - Fill in "Finishend Goods Storage Capacity" and "Finished Goods Budget" before Optimize Inventory
+    """
+}
+
+rm_md = {
+    'value': """
+    # Raw Material Optimization
+    Optimize raw material purchasing based on the allocated storage space and purchase budget.
+    """
+}
+
+wip_md = {
+    'value': """
+    # WIP Optimization
+    Optimize working in progress items based on the production space and production budget.
+    """
+}
+
+
+demo_data_btn = {
+    'value': 'Load Demo Dataset',
+    'elem_classes': 'btn'
+}
+
+rm_demo_data_btn = {
+    'value': 'Load Demo Dataset',
+    'elem_classes': 'btn'
+}
+
+wip_demo_data_btn = {
+    'value': 'Load Demo Dataset',
+    'elem_classes': 'btn'
+}
+
+inventory_btn = {
+    'value': 'Optimize Inventory',
+    'elem_classes': 'btn',
+    'variant': 'primary',
+}
+
+rm_btn = {
+    'value': 'Optimize Raw Material Inventory',
+    'elem_classes': 'btn',
+    'variant': 'primary',
+}
+
+wip_btn = {
+    'value': 'Optimize WIP Inventory',
+    'elem_classes': 'btn',
+    'variant': 'primary',
+}
+
+#
+# File Inputs
+
+inventory_file = {
+    'file_types': ['.csv'],
+    'label': 'Finishend Goods Demand Data'
+}
+
+rm_file = {
+    'file_types': ['.csv'],
+    'label': 'Raw Material Demand Data'
+}
+
+wip_file = {
+    'file_types': ['.csv'],
+    'label': 'Working In Progress Data'
+}
+# ======= #
+# Numbers #
+# ======= #
+inventory_storage_capacity = {
+    'label': 'FG Storage Capacity',
+    'interactive': True}
+
+inventory_budget_constraint = {
+    'label': 'FG Budget',
+    'interactive': True}
+
+rm_storage_capacity = {
+    'label': 'Raw Material Storage Capacity',
+    'interactive': True}
+
+rm_budget_constraint = {
+    'label': 'Raw Material Budget',
+    'interactive': True}
+
+wip_storage_capacity = {
+    'label': 'WIP Capacity',
+    'interactive': True}
+
+wip_budget_constraint = {
+    'label': 'WIP Budget',
+    'interactive': True}
+
+# =========== #
+# Data Frames #
+# =========== #
+inventory_input_df = {
+    'value': pd.DataFrame(columns=['SKU', 'demand', 'price', 'cost', 'space_per_unit', 'budgetary_cost']),
+    'label': 'Inventory Optimization Input',
+    'height': 300,
+}
+
+rm_input_df = {
+    'value': pd.DataFrame(columns=['SKU', 'demand', 'price', 'cost']),
+    'label': 'Inventory Optimization Input',
+    'height': 300,
+}
+
+wip_input_df = {
+    'value': pd.DataFrame(columns=['SKU', 'demand', 'space_per_unit']),
+    'label': 'Inventory Optimization Input',
+    'height': 300,
+}

src/idsc/idsc_apis.py

@@ -0,0 +1,134 @@
+import yaml
+import requests
+import os
+import pandas as pd
+
+from datetime import datetime, timedelta
+from dotenv import load_dotenv
+load_dotenv()
+
+
+class IDSC_API():
+    '''
+    Wrapper class for all IDSC apis
+    '''
+
+    def __init__(self):
+        __location__ = os.path.realpath(
+            os.path.join(os.getcwd(), os.path.dirname(__file__)))
+
+        self.config_path = os.path.join(__location__, 'idsc_config.yaml')
+        self.logged_in = False
+        self.timeformat = '%m/%d/%Y, %H:%M:%S'
+        with open(self.config_path, 'r') as file:
+            self.config = yaml.safe_load(file)
+            
+        self.expire = self.config['apikey_expire']
+        self.apikey = self.config['apikey']
+        
+        self.login()
+
+        self.product_mix__res = None  # Save product_mix api response
+
+    def login(self):
+        
+        now = datetime.now()
+        expire_date = datetime.strptime(self.expire, self.timeformat)
+
+        if now >= expire_date:
+            print('apikey expired, requesting new one.')
+            self.apikey = self.fetch_apikey()
+            self.update_config()
+        else:
+            print('apikey still available, logged in')
+            
+        self.logged_in = True
+
+    def fetch_apikey(self):
+        # print(os.environ)
+        json = {
+            # "email": self.config['email'],
+            # "pwd": self.config['password']
+            'email': os.getenv('IDSC_ACC'),
+            'pwd': os.getenv('IDSC_PASS')
+        }
+
+        print('IDSC Logging in ...')
+        login_resp = requests.post(
+            'https://idsc.com.sg/user/login',
+            json=json)
+
+        if login_resp.status_code == 200:
+            apikey = login_resp.json()["API_key"]
+            return apikey
+        else:
+            raise Exception(login_resp.json())
+
+    def update_config(self):
+        now = datetime.now()
+        expire = (now + timedelta(days=3)).strftime(self.timeformat)
+        self.config['apikey'] = self.apikey
+        self.config['apikey_expire'] = expire
+        with open(self.config_path, 'w') as f:
+            yaml.dump(self.config, f, default_flow_style=False)
+
+    # =========== #
+    # Product mix #
+    # =========== #
+
+    def product_mix(
+            self,
+            product_data,
+            storage_capacity,
+            budget_constraint):
+
+        endpint = 'https://idsc.com.sg/optimax/product-mix/product-mix'
+        json = {'product_data': product_data,
+                'storage_capacity': storage_capacity,
+                'budget_constraint': budget_constraint
+                }
+
+        print('storage_capacity', storage_capacity)
+        print('budget_constraint', budget_constraint)
+        
+        self.login()
+
+        headers = {'api-key': self.apikey}
+
+        res = requests.post(endpint, json=json, headers=headers)
+
+        parsed_res = self._parse_response(res)
+
+        self.product_mix__res = parsed_res
+
+        return self.product_mix__res
+
+    def _parse_response(self, res):
+        if res.status_code != 200:
+            print(f'API call failed. {res.text}')
+            return False
+        return res.json()
+
+    def get_product_mix_recommendations_df(self):
+
+        try:
+            recommendations = self.product_mix__res['product_mix_recommendations']
+        except Exception:
+            return None
+
+        df_arr = []
+        for k, v in recommendations.items():
+            df = pd.DataFrame(v, index=[k])
+            df['SKU'] = k
+
+            # Make sure expected sales is always integer
+            df['expected_sales'] = int(df['expected_sales'])
+
+            # Rearrange the order, so 'SKU' columns is the first
+            cols = df.columns.tolist()
+            cols = cols[-1:] + cols[:-1]
+            df = df[cols]
+
+            df_arr.append(df)
+
+        return pd.concat(df_arr, ignore_index=True)

src/idsc/idsc_config.yaml

@@ -0,0 +1,2 @@
+apikey: f83c59b23ab2afbbabad60b305e00b16a46d0920
+apikey_expire: 11/17/2023, 15:27:25