✨ Update Experimental Notebook

example/.gitignore

@@ -1,2 +1,4 @@
 datasets/
-tdce-basic/
+tdce-basic/
+results/
+result/

example/1-Basic-Model-Constructor.ipynb

@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "ae7385ba",
    "metadata": {},
    "outputs": [],
@@ -46,12 +46,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "4bb874d3",
    "metadata": {},
    "outputs": [],
    "source": [
     "run_from_online = False\n",
+    "ignore_download_dataset = True\n",
     "\n",
     "\n",
     "if run_from_online:\n",
@@ -75,18 +76,7 @@
     "    import viyacrab_augmentation as viya\n",
     "    import adjust_data as ajd\n",
     "    import result_display as rd\n",
-    "\n",
-    "    importlib.reload(tdce)\n",
-    "    importlib.reload(mfl)\n",
-    "    importlib.reload(efl)\n",
-    "    importlib.reload(cfl)\n",
-    "    importlib.reload(loss)\n",
-    "    importlib.reload(tdce)\n",
-    "    importlib.reload(cmc)\n",
-    "    importlib.reload(diva)\n",
-    "    importlib.reload(viya)\n",
-    "    importlib.reload(ajd)\n",
-    "    importlib.reload(rd)\n",
+    "    import mini_plot as mp\n",
     "    # fmt:on\n",
     "else :\n",
     "    # fmt:off\n",
@@ -105,19 +95,21 @@
     "    import viyacrab_augmentation as viya\n",
     "    import adjust_data as ajd\n",
     "    import result_display as rd\n",
-    "    \n",
-    "    importlib.reload(tdce)\n",
-    "    importlib.reload(mfl)\n",
-    "    importlib.reload(efl)\n",
-    "    importlib.reload(cfl)\n",
-    "    importlib.reload(loss)\n",
-    "    importlib.reload(tdce)\n",
-    "    importlib.reload(cmc)\n",
-    "    importlib.reload(diva)\n",
-    "    importlib.reload(viya)\n",
-    "    importlib.reload(ajd)\n",
-    "    importlib.reload(rd)\n",
-    "    # fmt:on\n"
+    "    import mini_plot as mp\n",
+    "    # fmt:on\n",
+    "\n",
+    "importlib.reload(tdce)\n",
+    "importlib.reload(mfl)\n",
+    "importlib.reload(efl)\n",
+    "importlib.reload(cfl)\n",
+    "importlib.reload(loss)\n",
+    "importlib.reload(tdce)\n",
+    "importlib.reload(cmc)\n",
+    "importlib.reload(diva)\n",
+    "importlib.reload(viya)\n",
+    "importlib.reload(ajd)\n",
+    "importlib.reload(rd)\n",
+    "importlib.reload(mp)"
    ]
   },
   {
@@ -137,6 +129,7 @@
    "outputs": [],
    "source": [
     "try:\n",
+    "    os.mkdir('result')\n",
     "    os.mkdir(f\"datasets\")\n",
     "    os.mkdir(f\"datasets/extended-random\")\n",
     "except FileExistsError:\n",
@@ -159,32 +152,36 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "capital_cost_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_capital_cost.csv\"\n",
-    "capital_path = 'datasets/extended-random/generated_capital_cost.csv'\n",
-    "employee_usage_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_employee_usage.csv\"\n",
-    "employee_path = 'datasets/extended-random/generated_employee_usage.csv'\n",
-    "material_usage_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_material_usage.csv\"\n",
-    "material_path = 'datasets/extended-random/generated_material_usage.csv'\n",
-    "process_data_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_process_data.csv\"\n",
-    "process_path = 'datasets/extended-random/generated_process_data.csv'\n",
-    "\n",
-    "\n",
-    "for link, path in [\n",
-    "    (capital_cost_link, capital_path),\n",
-    "    (employee_usage_link, employee_path),\n",
-    "    (material_usage_link, material_path),\n",
-    "    (process_data_link, process_path)\n",
-    "]:\n",
-    "    if not os.path.exists(path):\n",
-    "        response = requests.get(link)\n",
-    "        if response.status_code == 200:\n",
-    "            with open(path, 'wb') as file:\n",
-    "                file.write(response.content)\n",
-    "            print(f'File {path} downloaded successfully')\n",
-    "        else:\n",
-    "            print(f'Failed to download file {path}')\n",
-    "# Downloading the datasets\n",
-    "print(\"Downloading datasets...\")"
+    "def download_file():\n",
+    "    capital_cost_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_capital_cost.csv\"\n",
+    "    capital_path = 'datasets/extended-random/generated_capital_cost.csv'\n",
+    "    employee_usage_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_employee_usage.csv\"\n",
+    "    employee_path = 'datasets/extended-random/generated_employee_usage.csv'\n",
+    "    material_usage_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_material_usage.csv\"\n",
+    "    material_path = 'datasets/extended-random/generated_material_usage.csv'\n",
+    "    process_data_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_process_data.csv\"\n",
+    "    process_path = 'datasets/extended-random/generated_process_data.csv'\n",
+    "\n",
+    "\n",
+    "    for link, path in [\n",
+    "        (capital_cost_link, capital_path),\n",
+    "        (employee_usage_link, employee_path),\n",
+    "        (material_usage_link, material_path),\n",
+    "        (process_data_link, process_path)\n",
+    "    ]:\n",
+    "        if not os.path.exists(path):\n",
+    "            response = requests.get(link)\n",
+    "            if response.status_code == 200:\n",
+    "                with open(path, 'wb') as file:\n",
+    "                    file.write(response.content)\n",
+    "                print(f'File {path} downloaded successfully')\n",
+    "            else:\n",
+    "                print(f'Failed to download file {path}')\n",
+    "    # Downloading the datasets\n",
+    "    print(\"Downloading datasets...\")\n",
+    "\n",
+    "if (not ignore_download_dataset):\n",
+    "    download_file()"
    ]
   },
   {
@@ -229,6 +226,8 @@
     "    indent=False\n",
     ")\n",
     "\n",
+    "\n",
+    "\n",
     "outlier_index_widget = widgets.Dropdown(\n",
     "    options=['1', '1.5', '2'],\n",
     "    value='1.5',\n",
@@ -243,6 +242,22 @@
     "    indent=False\n",
     ")\n",
     "\n",
+    "use_early_stopping_widget = widgets.Checkbox(\n",
+    "    value=False,\n",
+    "    description='Enable Early Stopping',\n",
+    "    disabled=False,\n",
+    "    indent=False\n",
+    ")\n",
+    "\n",
+    "early_stopping_patience_widget = widgets.BoundedIntText(\n",
+    "    value=10,\n",
+    "    min=1,\n",
+    "    max=100,\n",
+    "    step=1,\n",
+    "    description='Early Stopping Patience Round:',\n",
+    "    disabled=False\n",
+    ")\n",
+    "\n",
     "element_level_lr_widget = widgets.Dropdown(\n",
     "    options=['0.001','0.05', '0.01','0.1','0.5'],\n",
     "    value='0.01',\n",
@@ -256,32 +271,37 @@
     "    description='Model Level Learning Rate:',\n",
     "    disabled=False,\n",
     ")\n",
+    "epoch_widget = widgets.BoundedIntText(\n",
+    "    value=100,\n",
+    "    min=10,\n",
+    "    max=1000,\n",
+    "    step=10,\n",
+    "    description='Number of Epochs:',\n",
+    "    disabled=False\n",
+    ")\n",
     "\n",
     "\n",
     "display(hour_day_employee_widget)\n",
     "display(hour_day_capital_cost_widget)\n",
     "display(use_outlier_removal_widget)\n",
     "display(outlier_index_widget)\n",
-    "display(use_augmentation_widget)"
+    "display(use_augmentation_widget)\n",
+    "display(use_early_stopping_widget)\n",
+    "display(early_stopping_patience_widget)\n",
+    "display(element_level_lr_widget)\n",
+    "display(model_level_lr_widget)\n",
+    "display(epoch_widget)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "ac4c4fc1",
-   "metadata": {},
-   "source": [
-    "Select Learning Rate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fce6161f",
+   "id": "204af1e1",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "display(element_level_lr_widget)\n",
-    "display(model_level_lr_widget)"
+    "If you config the value on the widget, please reexecute all of these bottom cells for create a model according to your data.\n",
+    "\n",
+    "\n",
+    "Getting Value from Widget"
    ]
   },
   {
@@ -295,7 +315,12 @@
     "hour_day_capital_cost = hour_day_capital_cost_widget.value\n",
     "use_outlier_removal= use_outlier_removal_widget.value\n",
     "outlier_index = float(outlier_index_widget.value)\n",
-    "use_augmentation = use_augmentation_widget.value"
+    "use_augmentation = use_augmentation_widget.value\n",
+    "element_level_lr = float(element_level_lr_widget.value)\n",
+    "model_level_lr = float(model_level_lr_widget.value)\n",
+    "use_early_stopping =use_early_stopping_widget.value\n",
+    "early_stopping_patience = early_stopping_patience_widget.value\n",
+    "epoch_number = epoch_widget.value"
    ]
   },
   {
@@ -314,12 +339,23 @@
    "outputs": [],
    "source": [
     "folder_path = 'datasets/extended-random'\n",
+    "output_folder_path = f'result/{model_level_lr}'\n",
     "\n",
     "cost_generator = cmc.CostMatrixGenerator()\n",
     "cost_generator.change_data_directory(folder_path)\n",
     "cost_generator.load_data()\n",
     "input_variation = diva.display_input_variation_by_directory(folder_path)\n",
-    "input_variation.to_csv(f\"{folder_path}/data_variation.csv\")"
+    "input_variation.to_csv(f\"{folder_path}/data_variation.csv\")\n",
+    "\n",
+    "(process_df,employee_usage,material_usage,capital_cost_usage) = cost_generator.get_data()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ea56434",
+   "metadata": {},
+   "source": [
+    "If you want to see the raw data, you can display using `process_df`, `process_df.head()`, `employee_df` and so on."
    ]
   },
   {
@@ -472,7 +508,241 @@
    "id": "d1bdcbbc",
    "metadata": {},
    "source": [
-    "## Initial Model"
+    "## Initial Model\n",
+    "\n",
+    "### Initial Layer\n",
+    "Create function to initial layer from cost matrix, it will automatically find what the input size is need for due to the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2fce43cf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def inital_layer(\n",
+    "    material_cost_matrix,\n",
+    "    employee_cost_matrix,\n",
+    "    capital_cost_matrix,\n",
+    "):\n",
+    "    total_col = 0\n",
+    "    # Material FC Layer\n",
+    "    row, high, col = material_cost_matrix.shape\n",
+    "    material_layer_1 = mfl.MaterialFCLayer(col, 1)\n",
+    "    # material_layer_1.annotate(material_cost_matrix, material_amount_matrix)\n",
+    "    total_col += col\n",
+    "\n",
+    "    # Monthy Employee FC Layer\n",
+    "    row, high, col = employee_cost_matrix.shape\n",
+    "    employee_layer_1 = efl.EmployeeFCLayer(col, 1, 8)\n",
+    "    total_col += col\n",
+    "    # monthy_employee_layer_1.annotate(monthy_employee_cost_matrix, duration_matrix)\n",
+    "\n",
+    "    # Capital Cost  FC Layer\n",
+    "    row, high, col = capital_cost_matrix.shape\n",
+    "    capital_cost_layer1 = cfl.CapitalCostFCLayer(col, 1, 21)\n",
+    "    total_col += col\n",
+    "    # capital_cost_layer1.annotate(\n",
+    "    #     capital_cost_matrix, life_time_matrix, machine_hour_matrix, duration_matrix)\n",
+    "\n",
+    "    return (\n",
+    "        material_layer_1,\n",
+    "        employee_layer_1,\n",
+    "        capital_cost_layer1,\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "662b0bd2",
+   "metadata": {},
+   "source": [
+    "### Model Initialization\n",
+    "Create the model object from its class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53684466",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initial Model\n",
+    "tdce_model = tdce.TDCEModel()\n",
+    "    \n",
+    "# Create the Layer\n",
+    "(\n",
+    "    material_layer_1,\n",
+    "    employee_layer_1,\n",
+    "    capital_cost_layer1,\n",
+    ") = inital_layer(\n",
+    "    capital_cost_matrix=capital_cost_matrix,\n",
+    "    employee_cost_matrix=employee_cost_matrix,\n",
+    "    material_cost_matrix=material_cost_matrix,\n",
+    ")\n",
+    "\n",
+    "# Add the Layer to the Model\n",
+    "tdce_model.inital_inside_element(\n",
+    "        material_layer=material_layer_1,\n",
+    "        capital_cost_layer=capital_cost_layer1,\n",
+    "        employee_layer=employee_layer_1,\n",
+    ")\n",
+    "\n",
+    "# Install the error calculator\n",
+    "tdce_model.use(loss=loss.mse, loss_prime=loss.mse_prime,\n",
+    "                   loss_percent=loss.rmspe)\n",
+    "\n",
+    "# Set Early Stopping\n",
+    "if use_early_stopping:\n",
+    "    tdce_model.activate_early_stopping()\n",
+    "    tdce_model.edit_patience_round(early_stopping_patience)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df6d4796",
+   "metadata": {},
+   "source": [
+    "Setting the learning rate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b75da97b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Use the same learning rate for all element level\n",
+    "tdce_model.set_learning_rate(\n",
+    "    element_level_lr,element_level_lr,element_level_lr\n",
+    ")\n",
+    "\n",
+    "# activate model weight\n",
+    "tdce_model.activete_model_weight()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "38df7ced",
+   "metadata": {},
+   "source": [
+    "## Training\n",
+    "\n",
+    "Fit a model with input and output data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2fe52d20",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "start_time = time.time()\n",
+    "\n",
+    "tdce_model.fit_with_validation(\n",
+    "        epoch=epoch_number,\n",
+    "        learning_rate=model_level_lr,\n",
+    "        material_amount_matrix=material_amount_matrix,\n",
+    "        material_cost_matrix=material_cost_matrix,\n",
+    "        employee_cost_matrix=employee_cost_matrix,\n",
+    "        employee_duration_matrix=employee_duration_matrix,\n",
+    "        employee_day_amount_matrix=employee_day_amount_matrix,\n",
+    "        result_matrix=result_matrix,\n",
+    "        capital_cost_matrix=capital_cost_matrix,\n",
+    "        day_amount_matrix=day_amount_matrix,\n",
+    "        validation_payload=validation_payload,\n",
+    "        capital_cost_duration_matrix=capital_cost_duration_matrix,\n",
+    "    )\n",
+    "\n",
+    "end_time = time.time()\n",
+    "time_usage = end_time - start_time\n",
+    "print(f\"Learning Rate: {model_level_lr} / {element_level_lr}\")\n",
+    "print(f\"Time Using {time_usage} Second\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39b9aa25",
+   "metadata": {},
+   "source": [
+    "Get the Error Listing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7fa00c92",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    os.mkdir(f\"{output_folder_path}\")\n",
+    "except FileExistsError:\n",
+    "    print(\"Folder is Exist\")\n",
+    "    pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8861bedb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "error_list = tdce_model.get_epoch_error()\n",
+    "sample_error_list = tdce_model.get_sample_error()\n",
+    "error_df = pd.DataFrame(error_list)\n",
+    "sample_error_df = pd.DataFrame(sample_error_list)\n",
+    "\n",
+    "\n",
+    "# Get Overall Output\n",
+    "minimum_error = error_df[\"error\"].min()\n",
+    "minimum_percent_error = error_df[\"error_percent\"].min()\n",
+    "minimum_validate_error = error_df[\"validate_error\"].min()\n",
+    "minimum_validate_percent_error = error_df[\"validate_error_percent\"].min()\n",
+    "\n",
+    "# Export the Output Result\n",
+    "error_df.to_csv(f\"{output_folder_path}/{epoch_number}-{element_level_lr}.csv\")\n",
+    "sample_error_df.to_csv(\n",
+    "    f\"{output_folder_path}/error-list-{epoch_number}-{element_level_lr}.csv\"\n",
+    ")\n",
+    "sample_payload = tdce_model.get_sample_payload()\n",
+    "sample_payload_df = pd.DataFrame(sample_payload)\n",
+    "\n",
+    "# Export all the sample / history of all training\n",
+    "sample_payload_df.to_csv(\n",
+    "    f\"{output_folder_path}/sample-payload-list-{epoch_number}-{element_level_lr}.csv\",\n",
+    "    index=False,\n",
+    ")\n",
+    "\n",
+    "print(f\"Minimum Error: {minimum_error}\"\n",
+    "      f\" / Minimum Percent Error (RMSPE): {minimum_percent_error}\"\n",
+    "      f\" / Minimum Validate Error: {minimum_validate_error}\"\n",
+    "      f\" / Minimum Validate Percent Error (RMSEP): {minimum_validate_percent_error}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "639b9b91",
+   "metadata": {},
+   "source": [
+    "## Visualization\n",
+    "Display the model training behavior"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dc3bdc9d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mp.plotting_learning_curve(epoch_error=error_df,element_learning_rate=element_level_lr,\n",
+    "                           model_learning_rate=model_level_lr)"
    ]
   }
  ],

functions/mini_plot.py

@@ -0,0 +1,51 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+sns.set_theme(style="whitegrid", font="Noto Sans",
+              font_scale=1)
+this_graph_palette = sns.color_palette("husl", 4)
+sns.set_palette(this_graph_palette)
+
+
+def plotting_learning_curve(epoch_error, element_learning_rate, model_learning_rate):
+    fig, ax = plt.subplots(1, 2, figsize=(8, 4))
+
+    ax[0].plot(
+        epoch_error["epoch"],
+        epoch_error["error"],
+        label="Training",
+        linewidth=2
+    )
+    ax[0].plot(
+        epoch_error["epoch"],
+        epoch_error["validate_error"],
+        label="Validation", linewidth=2
+    )
+    ax[0].set_title(
+        f"Learning Curve {model_learning_rate}/{element_learning_rate} in MSE",
+        fontdict={"fontsize": 12},
+    )
+    ax[1].plot(
+        epoch_error["epoch"],
+        epoch_error["error_percent"],
+        label="Training",
+        linewidth=2
+    )
+    ax[1].plot(
+        epoch_error["epoch"],
+        epoch_error["validate_error_percent"],
+        label="Validation", linewidth=2
+    )
+    ax[1].set_ylim(
+        0, 100)
+    ax[1].set_xlim(
+        0, 100)
+
+    ax[1].set_title(
+        f"Learning Curve {model_learning_rate}/{element_learning_rate} in RMSPE",
+        fontdict={"fontsize": 12},
+    )
+    ax[0].legend(loc="lower right")
+    ax[1].legend(loc="lower right")
+    fig.tight_layout(pad=3.0)