refactor(documentclass): update title handling by using input files for maketitle

Closes #91

.gitignore

@@ -2,3 +2,4 @@
 data/**/*.csv
 .venv/
 *.pyc
+*.egg-info/

.gitmessage

@@ -21,6 +21,7 @@
 # 
 # Scope:
 #   latex    (changes to thesis LaTeX)
+#   documentclass (LaTeX in-house document class changes)
 #   src      (changes to Python source code)
 #   nb       (changes to notebooks)
 #   ml       (ML model specific changes)

.vscode/settings.json

@@ -1,3 +1,4 @@
 {
-  "python.analysis.extraPaths": ["./code/src/features"]
+  "python.analysis.extraPaths": ["./code/src/features"],
+  "jupyter.notebookFileRoot": "${workspaceFolder}/code"
 }

README.md

@@ -16,3 +16,8 @@ The repository is private and access is restricted only to those who have been g
 All contents of this repository, including the thesis idea, code, and associated data, are copyrighted © 2024 by Rifqi Panuluh. Unauthorized use or duplication is prohibited.
 
 [LICENSE](https://github.com/nuluh/thesis?tab=License-1-ov-file#readme)
+
+## How to Run `stft.ipynb`
+
+1. run `pip install -e .` in root project first
+2. run the notebook

code/notebooks/stft.ipynb

@@ -155,7 +155,7 @@
     "import pandas as pd\n",
     "import numpy as np\n",
     "from scipy.signal import stft, hann\n",
-    "from multiprocessing import Pool\n",
+    "# from multiprocessing import Pool\n",
     "\n",
     "# Function to compute and append STFT data\n",
     "def process_stft(args):\n",
@@ -321,9 +321,9 @@
    "source": [
     "import pandas as pd\n",
     "import matplotlib.pyplot as plt\n",
-    "ready_data1 = []\n",
+    "ready_data1a = []\n",
     "for file in os.listdir('D:/thesis/data/converted/raw/sensor1'):\n",
-    "    ready_data1.append(pd.read_csv(os.path.join('D:/thesis/data/converted/raw/sensor1', file)))\n",
+    "    ready_data1a.append(pd.read_csv(os.path.join('D:/thesis/data/converted/raw/sensor1', file)))\n",
     "# colormesh give title x is frequency and y is time and rotate/transpose the data\n",
     "# Plotting the STFT Data"
    ]
@@ -334,8 +334,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ready_data1[0]\n",
+    "# len(ready_data1a)\n",
-    "plt.pcolormesh(ready_data1[0])"
+    "# plt.pcolormesh(ready_data1[0])\n",
+    "ready_data1a[0].max().max()"
    ]
   },
   {
@@ -345,7 +346,8 @@
    "outputs": [],
    "source": [
     "for i in range(6):\n",
-    "    plt.pcolormesh(ready_data1[i])\n",
+    "    plt.pcolormesh(ready_data1a[i], cmap=\"jet\", vmax=0.03, vmin=0.0)\n",
+    "    plt.colorbar() \n",
     "    plt.title(f'STFT Magnitude for case {i} sensor 1')\n",
     "    plt.xlabel(f'Frequency [Hz]')\n",
     "    plt.ylabel(f'Time [sec]')\n",
@@ -358,9 +360,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ready_data2 = []\n",
+    "ready_data2a = []\n",
     "for file in os.listdir('D:/thesis/data/converted/raw/sensor2'):\n",
-    "    ready_data2.append(pd.read_csv(os.path.join('D:/thesis/data/converted/raw/sensor2', file)))"
+    "    ready_data2a.append(pd.read_csv(os.path.join('D:/thesis/data/converted/raw/sensor2', file)))"
    ]
   },
   {
@@ -369,8 +371,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(len(ready_data1))\n",
+    "print(len(ready_data1a))\n",
-    "print(len(ready_data2))"
+    "print(len(ready_data2a))"
    ]
   },
   {
@@ -379,10 +381,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x1 = 0\n",
+    "x1a = 0\n",
-    "print(type(ready_data1[0]))\n",
+    "print(type(ready_data1a[0]))\n",
-    "ready_data1[0].iloc[:,0]\n",
+    "ready_data1a[0].iloc[:,0]"
-    "# x1 = x1 + ready_data1[0].shape[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Checking length of the total array"
    ]
   },
   {
@@ -391,16 +399,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x1 = 0\n",
+    "x1a = 0\n",
-    "print(type(x1))\n",
+    "print(type(x1a))\n",
-    "for i in range(len(ready_data1)):\n",
+    "for i in range(len(ready_data1a)):\n",
-    "    # print(ready_data1[i].shape)\n",
+    "    print(type(ready_data1a[i].shape[0]))\n",
-    "    # print(ready_data1[i].)\n",
+    "    x1a = x1a + ready_data1a[i].shape[0]\n",
-    "    print(type(ready_data1[i].shape[0]))\n",
+    "    print(type(x1a))\n",
-    "    x1 = x1 + ready_data1[i].shape[0]\n",
-    "    print(type(x1))\n",
     "\n",
-    "print(x1)"
+    "print(x1a)"
    ]
   },
   {
@@ -409,13 +415,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x2 = 0\n",
+    "x2a = 0\n",
     "\n",
-    "for i in range(len(ready_data2)):\n",
+    "for i in range(len(ready_data2a)):\n",
-    "    print(ready_data2[i].shape)\n",
+    "    print(ready_data2a[i].shape)\n",
-    "    x2 = x2 + ready_data2[i].shape[0]\n",
+    "    x2a = x2a + ready_data2a[i].shape[0]\n",
     "\n",
-    "print(x2)"
+    "print(x2a)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Flatten 6 array into one array"
    ]
   },
   {
@@ -424,28 +437,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x1 = ready_data1[0]\n",
+    "# Combine all dataframes in ready_data1a into a single dataframe\n",
-    "# print(x1)\n",
+    "if ready_data1a:  # Check if the list is not empty\n",
-    "print(type(x1))\n",
+    "    # Use pandas concat function instead of iterative concatenation\n",
-    "for i in range(len(ready_data1) - 1):\n",
+    "    combined_data = pd.concat(ready_data1a, axis=0, ignore_index=True)\n",
-    "    #print(i)\n",
-    "    x1 = np.concatenate((x1, ready_data1[i + 1]), axis=0)\n",
-    "# print(x1)\n",
-    "pd.DataFrame(x1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "x2 = ready_data2[0]\n",
     "    \n",
-    "for i in range(len(ready_data2) - 1):\n",
+    "    print(f\"Type of combined data: {type(combined_data)}\")\n",
-    "    #print(i)\n",
+    "    print(f\"Shape of combined data: {combined_data.shape}\")\n",
-    "    x2 = np.concatenate((x2, ready_data2[i + 1]), axis=0)\n",
+    "    \n",
-    "pd.DataFrame(x2)"
+    "    # Display the combined dataframe\n",
+    "    combined_data\n",
+    "else:\n",
+    "    print(\"No data available in ready_data1a list\")\n",
+    "    combined_data = pd.DataFrame()\n",
+    "\n",
+    "# Store the result in x1a for compatibility with subsequent code\n",
+    "x1a = combined_data"
    ]
   },
   {
@@ -454,20 +461,29 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(x1.shape)\n",
+    "# Combine all dataframes in ready_data1a into a single dataframe\n",
-    "print(x2.shape)"
+    "if ready_data2a:  # Check if the list is not empty\n",
+    "    # Use pandas concat function instead of iterative concatenation\n",
+    "    combined_data = pd.concat(ready_data2a, axis=0, ignore_index=True)\n",
+    "    \n",
+    "    print(f\"Type of combined data: {type(combined_data)}\")\n",
+    "    print(f\"Shape of combined data: {combined_data.shape}\")\n",
+    "    \n",
+    "    # Display the combined dataframe\n",
+    "    combined_data\n",
+    "else:\n",
+    "    print(\"No data available in ready_data1a list\")\n",
+    "    combined_data = pd.DataFrame()\n",
+    "\n",
+    "# Store the result in x1a for compatibility with subsequent code\n",
+    "x2a = combined_data"
    ]
   },
   {
-   "cell_type": "code",
+   "cell_type": "markdown",
-   "execution_count": null,
    "metadata": {},
-   "outputs": [],
    "source": [
-    "y_1 = [1,1,1,1]\n",
+    "### Creating the label"
-    "y_2 = [0,1,1,1]\n",
-    "y_3 = [1,0,1,1]\n",
-    "y_4 = [1,1,0,0]"
    ]
   },
   {
@@ -490,39 +506,41 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "y_data = [y_1, y_2, y_3, y_4, y_5, y_6]"
+    "y_data = [y_1, y_2, y_3, y_4, y_5, y_6]\n",
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in range(len(y_data)):\n",
-    "    print(ready_data1[i].shape[0])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in range(len(y_data)):\n",
-    "    y_data[i] = [y_data[i]]*ready_data1[i].shape[0]\n",
-    "    y_data[i] = np.array(y_data[i])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "y_data"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(len(y_data)):\n",
+    "    print(ready_data1a[i].shape[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "for i in range(len(y_data)):\n",
+    "    y_data[i] = [y_data[i]]*ready_data1a[i].shape[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(y_data[0])\n",
+    "# y_data"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -552,10 +570,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.model_selection import train_test_split\n",
+    "from src.ml.model_selection import create_ready_data\n",
     "\n",
-    "x_train1, x_test1, y_train, y_test = train_test_split(x1, y, test_size=0.2, random_state=2)\n",
+    "X1a, y = create_ready_data('D:/thesis/data/converted/raw/sensor1')\n",
-    "x_train2, x_test2, y_train, y_test = train_test_split(x2, y, test_size=0.2, random_state=2)"
+    "X2a, y = create_ready_data('D:/thesis/data/converted/raw/sensor2')"
    ]
   },
   {
@@ -565,6 +583,17 @@
    "outputs": [],
    "source": [
     "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "x_train1, x_test1, y_train, y_test = train_test_split(X1a, y, test_size=0.2, random_state=2)\n",
+    "x_train2, x_test2, y_train, y_test = train_test_split(X2a, y, test_size=0.2, random_state=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "from sklearn.metrics import accuracy_score\n",
     "from sklearn.ensemble import RandomForestClassifier, BaggingClassifier\n",
     "from sklearn.tree import DecisionTreeClassifier\n",
@@ -592,130 +621,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "accuracies1 = []\n",
+    "def train_and_evaluate_model(model, model_name, sensor_label, x_train, y_train, x_test, y_test):\n",
-    "accuracies2 = []\n",
+    "    model.fit(x_train, y_train)\n",
-    "\n",
+    "    y_pred = model.predict(x_test)\n",
-    "\n",
+    "    accuracy = accuracy_score(y_test, y_pred) * 100\n",
-    "# 1. Random Forest\n",
+    "    return {\n",
-    "rf_model = RandomForestClassifier()\n",
+    "        \"model\": model_name,\n",
-    "rf_model.fit(x_train1, y_train)\n",
+    "        \"sensor\": sensor_label,\n",
-    "rf_pred1 = rf_model.predict(x_test1)\n",
+    "        \"accuracy\": accuracy\n",
-    "acc1 = accuracy_score(y_test, rf_pred1) * 100\n",
+    "    }"
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"Random Forest Accuracy for sensor 1:\", acc1)\n",
-    "rf_model.fit(x_train2, y_train)\n",
-    "rf_pred2 = rf_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, rf_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"Random Forest Accuracy for sensor 2:\", acc2)\n",
-    "# print(rf_pred)\n",
-    "# print(y_test)\n",
-    "\n",
-    "# 2. Bagged Trees\n",
-    "bagged_model = BaggingClassifier(estimator=DecisionTreeClassifier(), n_estimators=10)\n",
-    "bagged_model.fit(x_train1, y_train)\n",
-    "bagged_pred1 = bagged_model.predict(x_test1)\n",
-    "acc1 = accuracy_score(y_test, bagged_pred1) * 100\n",
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"Bagged Trees Accuracy for sensor 1:\", acc1)\n",
-    "bagged_model.fit(x_train2, y_train)\n",
-    "bagged_pred2 = bagged_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, bagged_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"Bagged Trees Accuracy for sensor 2:\", acc2)\n",
-    "\n",
-    "# 3. Decision Tree\n",
-    "dt_model = DecisionTreeClassifier()\n",
-    "dt_model.fit(x_train1, y_train)\n",
-    "dt_pred1 = dt_model.predict(x_test1)\n",
-    "acc1 = accuracy_score(y_test, dt_pred1) * 100\n",
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"Decision Tree Accuracy for sensor 1:\", acc1)\n",
-    "dt_model.fit(x_train2, y_train)\n",
-    "dt_pred2 = dt_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, dt_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"Decision Tree Accuracy for sensor 2:\", acc2)\n",
-    "\n",
-    "# 4. KNeighbors\n",
-    "knn_model = KNeighborsClassifier()\n",
-    "knn_model.fit(x_train1, y_train)\n",
-    "knn_pred1 = knn_model.predict(x_test1)\n",
-    "acc1 = accuracy_score(y_test, knn_pred1) * 100\n",
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"KNeighbors Accuracy for sensor 1:\", acc1)\n",
-    "knn_model.fit(x_train2, y_train)\n",
-    "knn_pred2 = knn_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, knn_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"KNeighbors Accuracy for sensor 2:\", acc2)\n",
-    "\n",
-    "# 5. Linear Discriminant Analysis\n",
-    "lda_model = LinearDiscriminantAnalysis()\n",
-    "lda_model.fit(x_train1, y_train)\n",
-    "lda_pred1 = lda_model.predict(x_test1)\n",
-    "acc1 = accuracy_score(y_test, lda_pred1) * 100\n",
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"Linear Discriminant Analysis Accuracy for sensor 1:\", acc1)\n",
-    "lda_model.fit(x_train2, y_train)\n",
-    "lda_pred2 = lda_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, lda_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"Linear Discriminant Analysis Accuracy for sensor 2:\", acc2)\n",
-    "\n",
-    "# 6. Support Vector Machine\n",
-    "svm_model = SVC()\n",
-    "svm_model.fit(x_train1, y_train)\n",
-    "svm_pred1 = svm_model.predict(x_test1)\n",
-    "acc1 = accuracy_score(y_test, svm_pred1) * 100\n",
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"Support Vector Machine Accuracy for sensor 1:\", acc1)\n",
-    "svm_model.fit(x_train2, y_train)\n",
-    "svm_pred2 = svm_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, svm_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"Support Vector Machine Accuracy for sensor 2:\", acc2)\n",
-    "\n",
-    "# 7. XGBoost\n",
-    "xgboost_model = XGBClassifier()\n",
-    "xgboost_model.fit(x_train1, y_train)\n",
-    "xgboost_pred1 = xgboost_model.predict(x_test1)\n",
-    "acc1 = accuracy_score(y_test, xgboost_pred1) * 100\n",
-    "accuracies1.append(acc1)\n",
-    "# format with color coded if acc1 > 90\n",
-    "acc1 = f\"\\033[92m{acc1:.2f}\\033[00m\" if acc1 > 90 else f\"{acc1:.2f}\"\n",
-    "print(\"XGBoost Accuracy:\", acc1)\n",
-    "xgboost_model.fit(x_train2, y_train)\n",
-    "xgboost_pred2 = xgboost_model.predict(x_test2)\n",
-    "acc2 = accuracy_score(y_test, xgboost_pred2) * 100\n",
-    "accuracies2.append(acc2)\n",
-    "# format with color coded if acc2 > 90\n",
-    "acc2 = f\"\\033[92m{acc2:.2f}\\033[00m\" if acc2 > 90 else f\"{acc2:.2f}\"\n",
-    "print(\"XGBoost Accuracy:\", acc2)"
    ]
   },
   {
@@ -724,8 +638,59 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(accuracies1)\n",
+    "# Define models for sensor1\n",
-    "print(accuracies2)"
+    "models_sensor1 = {\n",
+    "    # \"Random Forest\": RandomForestClassifier(),\n",
+    "    # \"Bagged Trees\": BaggingClassifier(estimator=DecisionTreeClassifier(), n_estimators=10),\n",
+    "    # \"Decision Tree\": DecisionTreeClassifier(),\n",
+    "    # \"KNN\": KNeighborsClassifier(),\n",
+    "    # \"LDA\": LinearDiscriminantAnalysis(),\n",
+    "    \"SVM\": SVC(),\n",
+    "    \"XGBoost\": XGBClassifier()\n",
+    "}\n",
+    "\n",
+    "results_sensor1 = []\n",
+    "for name, model in models_sensor1.items():\n",
+    "    res = train_and_evaluate_model(model, name, \"sensor1\", x_train1, y_train, x_test1, y_test)\n",
+    "    results_sensor1.append(res)\n",
+    "    print(f\"{name} on sensor1: Accuracy = {res['accuracy']:.2f}%\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "models_sensor2 = {\n",
+    "    # \"Random Forest\": RandomForestClassifier(),\n",
+    "    # \"Bagged Trees\": BaggingClassifier(estimator=DecisionTreeClassifier(), n_estimators=10),\n",
+    "    # \"Decision Tree\": DecisionTreeClassifier(),\n",
+    "    # \"KNN\": KNeighborsClassifier(),\n",
+    "    # \"LDA\": LinearDiscriminantAnalysis(),\n",
+    "    \"SVM\": SVC(),\n",
+    "    \"XGBoost\": XGBClassifier()\n",
+    "}\n",
+    "\n",
+    "results_sensor2 = []\n",
+    "for name, model in models_sensor2.items():\n",
+    "    res = train_and_evaluate_model(model, name, \"sensor2\", x_train2, y_train, x_test2, y_test)\n",
+    "    results_sensor2.append(res)\n",
+    "    print(f\"{name} on sensor2: Accuracy = {res['accuracy']:.2f}%\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_results = {\n",
+    "    \"sensor1\": results_sensor1,\n",
+    "    \"sensor2\": results_sensor2\n",
+    "}\n",
+    "\n",
+    "print(all_results)"
    ]
   },
   {
@@ -737,36 +702,48 @@
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "models = [rf_model, bagged_model, dt_model, knn_model, lda_model, svm_model, xgboost_model]\n",
+    "def prepare_plot_data(results_dict):\n",
-    "model_names = [\"Random Forest\", \"Bagged Trees\", \"Decision Tree\", \"KNN\", \"LDA\", \"SVM\", \"XGBoost\"]\n",
+    "    # Gather unique model names\n",
+    "    models_set = {entry['model'] for sensor in results_dict.values() for entry in sensor}\n",
+    "    models = sorted(list(models_set))\n",
     "    \n",
-    "bar_width = 0.35  # Width of each bar\n",
+    "    # Create dictionaries mapping sensor -> accuracy list ordered by model name\n",
-    "index = np.arange(len(model_names))  # Index for the bars\n",
+    "    sensor_accuracies = {}\n",
+    "    for sensor, entries in results_dict.items():\n",
+    "        # Build a mapping: model -> accuracy for the given sensor\n",
+    "        mapping = {entry['model']: entry['accuracy'] for entry in entries}\n",
+    "        # Order the accuracies consistent with the sorted model names\n",
+    "        sensor_accuracies[sensor] = [mapping.get(model, 0) for model in models]\n",
     "    \n",
-    "# Plotting the bar graph\n",
+    "    return models, sensor_accuracies\n",
-    "plt.figure(figsize=(14, 8))\n",
     "\n",
-    "# Bar plot for Sensor 1\n",
+    "def plot_accuracies(models, sensor_accuracies):\n",
-    "plt.bar(index, accuracies1, width=bar_width, color='blue', label='Sensor 1')\n",
+    "    bar_width = 0.35\n",
+    "    x = np.arange(len(models))\n",
+    "    sensors = list(sensor_accuracies.keys())\n",
     "    \n",
-    "# Bar plot for Sensor 2\n",
+    "    plt.figure(figsize=(10, 6))\n",
-    "plt.bar(index + bar_width, accuracies2, width=bar_width, color='orange', label='Sensor 2')\n",
+    "    # Assume two sensors for plotting grouped bars\n",
+    "    plt.bar(x - bar_width/2, sensor_accuracies[sensors[0]], width=bar_width, color='blue', label=sensors[0])\n",
+    "    plt.bar(x + bar_width/2, sensor_accuracies[sensors[1]], width=bar_width, color='orange', label=sensors[1])\n",
     "    \n",
-    "# Add values on top of each bar\n",
+    "    # Add text labels on top of bars\n",
-    "for i, acc1, acc2 in zip(index, accuracies1, accuracies2):\n",
+    "    for i, (a1, a2) in enumerate(zip(sensor_accuracies[sensors[0]], sensor_accuracies[sensors[1]])):\n",
-    "    plt.text(i, acc1 + .1, f'{acc1:.2f}%', ha='center', va='bottom', color='black')\n",
+    "        plt.text(x[i] - bar_width/2, a1 + 0.1, f\"{a1:.2f}%\", ha='center', va='bottom', color='black')\n",
-    "    plt.text(i + bar_width, acc2 + 1, f'{acc2:.2f}%', ha='center', va='bottom', color='black')\n",
+    "        plt.text(x[i] + bar_width/2, a2 + 0.1, f\"{a2:.2f}%\", ha='center', va='bottom', color='black')\n",
     "    \n",
-    "# Customize the plot\n",
+    "    plt.xlabel('Model Name')\n",
-    "plt.xlabel('Model Name →')\n",
+    "    plt.ylabel('Accuracy (%)')\n",
-    "plt.ylabel('Accuracy →')\n",
+    "    plt.title('Accuracy of Classifiers for Each Sensor')\n",
-    "plt.title('Accuracy of classifiers for Sensors 1 and 2 with 513 features')\n",
+    "    plt.xticks(x, models)\n",
-    "plt.xticks(index + bar_width / 2, model_names)  # Set x-tick positions\n",
     "    plt.legend()\n",
-    "plt.ylim(0, 100)\n",
+    "    plt.ylim(0, 105)\n",
+    "    plt.tight_layout()\n",
+    "    plt.show()\n",
     "\n",
-    "# Show the plot\n",
+    "# Use the functions\n",
-    "plt.show()\n"
+    "models, sensor_accuracies = prepare_plot_data(all_results)\n",
+    "plot_accuracies(models, sensor_accuracies)\n"
    ]
   },
   {
@@ -787,51 +764,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def spectograph(data_dir: str):\n",
+    "from src.ml.model_selection import create_ready_data\n",
-    "    # print(os.listdir(data_dir))\n",
-    "    for damage in os.listdir(data_dir):\n",
-    "        # print(damage)\n",
-    "        d = os.path.join(data_dir, damage)\n",
-    "        # print(d)\n",
-    "        for file in os.listdir(d):\n",
-    "            # print(file)\n",
-    "            f = os.path.join(d, file)\n",
-    "            print(f)\n",
-    "            # sensor1 = pd.read_csv(f, skiprows=1, sep=';')\n",
-    "            # sensor2 = pd.read_csv(f, skiprows=1, sep=';')\n",
     "\n",
-    "            # df1 = pd.DataFrame()\n",
+    "X1b, y = create_ready_data('D:/thesis/data/converted/raw_B/sensor1')\n",
-    "\n",
+    "X2b, y = create_ready_data('D:/thesis/data/converted/raw_B/sensor2')"
-    "            # df1['s1'] = sensor1[sensor1.columns[-1]]\n",
-    "            # df1['s2'] = sensor2[sensor2.columns[-1]]\n",
-    "ed\n",
-    "            # # Combined Plot for sensor 1 and sensor 2 from data1 file in which motor is operated at 800 rpm\n",
-    "\n",
-    "            # plt.plot(df1['s2'], label='sensor 2')\n",
-    "            # plt.plot(df1['s1'], label='sensor 1')\n",
-    "            # plt.xlabel(\"Number of samples\")\n",
-    "            # plt.ylabel(\"Amplitude\")\n",
-    "            # plt.title(\"Raw vibration signal\")\n",
-    "            # plt.legend()\n",
-    "            # plt.show()\n",
-    "\n",
-    "            # from scipy import signal\n",
-    "            # from scipy.signal.windows import hann\n",
-    "\n",
-    "            # vibration_data = df1['s1']\n",
-    "\n",
-    "            # # Applying STFT\n",
-    "            # window_size = 1024\n",
-    "            # hop_size = 512\n",
-    "            # window = hann(window_size)  # Creating a Hanning window\n",
-    "            # frequencies, times, Zxx = signal.stft(vibration_data, window=window, nperseg=window_size, noverlap=window_size - hop_size)\n",
-    "\n",
-    "            # # Plotting the STFT Data\n",
-    "            # plt.pcolormesh(times, frequencies, np.abs(Zxx), shading='gouraud')\n",
-    "            # plt.title(f'STFT Magnitude for case 1 signal sensor 1 ')\n",
-    "            # plt.ylabel('Frequency [Hz]')\n",
-    "            # plt.xlabel('Time [sec]')\n",
-    "            # plt.show()"
    ]
   },
   {
@@ -840,7 +776,115 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "spectograph('D:/thesis/data/converted/raw')"
+    "y.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import accuracy_score, classification_report\n",
+    "# 4. Validate on Dataset B\n",
+    "y_pred_svm = svm_model.predict(X1b)\n",
+    "\n",
+    "# 5. Evaluate\n",
+    "print(\"Accuracy on Dataset B:\", accuracy_score(y, y_pred_svm))\n",
+    "print(classification_report(y, y_pred_svm))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import accuracy_score, classification_report\n",
+    "# 4. Validate on Dataset B\n",
+    "y_pred = rf_model2.predict(X2b)\n",
+    "\n",
+    "# 5. Evaluate\n",
+    "print(\"Accuracy on Dataset B:\", accuracy_score(y, y_pred))\n",
+    "print(classification_report(y, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_predict = svm_model2.predict(X2b.iloc[[5312],:])\n",
+    "print(y_predict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y[5312]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Confusion Matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
+    "\n",
+    "\n",
+    "cm = confusion_matrix(y, y_pred_svm) # -> ndarray\n",
+    "\n",
+    "# get the class labels\n",
+    "labels = svm_model.classes_\n",
+    "\n",
+    "# Plot\n",
+    "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=labels)\n",
+    "disp.plot(cmap=plt.cm.Blues)  # You can change colormap\n",
+    "plt.title(\"SVM Sensor1 CM Train w/ Dataset A Val w/ Dataset B\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Self-test CM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1. Predict sensor 1 on Dataset A\n",
+    "y_train_pred = svm_model.predict(x_train1)\n",
+    "\n",
+    "# 2. Import confusion matrix tools\n",
+    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# 3. Create and plot confusion matrix\n",
+    "cm_train = confusion_matrix(y_train, y_train_pred)\n",
+    "labels = svm_model.classes_\n",
+    "\n",
+    "disp = ConfusionMatrixDisplay(confusion_matrix=cm_train, display_labels=labels)\n",
+    "disp.plot(cmap=plt.cm.Blues)\n",
+    "plt.title(\"Confusion Matrix: Train & Test on Dataset A\")\n",
+    "plt.show()\n"
    ]
   }
  ],

code/src/ml/model_selection.py

@@ -0,0 +1,57 @@
+import numpy as np
+import pandas as pd
+import os
+from sklearn.model_selection import train_test_split as sklearn_split
+
+
+def create_ready_data(
+    stft_data_path: str,
+    stratify: np.ndarray = None,
+) -> tuple:
+    """
+    Create a stratified train-test split from STFT data.
+
+    Parameters:
+    -----------
+    stft_data_path : str
+        Path to the directory containing STFT data files (e.g. 'data/converted/raw/sensor1')
+    stratify : np.ndarray, optional
+        Labels to use for stratified sampling
+
+    Returns:
+    --------
+    tuple
+        (X_train, X_test, y_train, y_test) - Split datasets
+    """
+    ready_data = []
+    for file in os.listdir(stft_data_path):
+        ready_data.append(pd.read_csv(os.path.join(stft_data_path, file)))
+
+    y_data = [i for i in range(len(ready_data))]
+
+    # Combine all dataframes in ready_data into a single dataframe
+    if ready_data:  # Check if the list is not empty
+        # Use pandas concat function instead of iterative concatenation
+        combined_data = pd.concat(ready_data, axis=0, ignore_index=True)
+
+        print(f"Type of combined data: {type(combined_data)}")
+        print(f"Shape of combined data: {combined_data.shape}")
+    else:
+        print("No data available in ready_data list")
+        combined_data = pd.DataFrame()
+
+    # Store the result in x1a for compatibility with subsequent code
+    X = combined_data
+
+    for i in range(len(y_data)):
+        y_data[i] = [y_data[i]] * ready_data[i].shape[0]
+        y_data[i] = np.array(y_data[i])
+
+    if y_data:
+        # Use numpy concatenate function instead of iterative concatenation
+        y = np.concatenate(y_data, axis=0)
+    else:
+        print("No labels available in y_data list")
+        y = np.array([])
+
+    return X, y

latex/frontmatter/glossaries.tex

@@ -0,0 +1,78 @@
+% % A new command that enables us to enter bi-lingual (Slovene and English) terms
+% % syntax: \addterm[options]{label}{Slovene}{Slovene first use}{English}{Slovene
+% % description}
+% \newcommand{\addterm}[6][]{
+%   \newglossaryentry{#2}{
+%     name={#3 (angl.\ #5)},
+%     first={#4 (\emph{#5})},
+%     text={#3},
+%     sort={#3},
+%     description={#6},
+%     #1 % pass additional options to \newglossaryentry
+%   }
+% }
+
+% % A new command that enables us to enter (English) acronyms with bi-lingual
+% % (Slovene and English) long versions
+% % syntax: \addacronym[options]{label}{abbreviation}{Slovene long}{Slovene first
+% % use long}{English long}{Slovene description}
+% \newcommand{\addacronym}[7][]{
+%   % Create the main glossary entry with \newacronym
+%   % \newacronym[key-val list]{label}{abbrv}{long}
+%   \newacronym[
+%     name={#4 (angl.\ #6,\ #3)},
+%     first={\emph{#5} (angl.\ \emph{#6},\ \emph{#3})},
+%     sort={#4},
+%     description={#7},
+%     #1 % pass additional options to \newglossaryentry
+%     ]
+%     {#2}{#3}{#4}
+%   % Create a cross-reference from the abbreviation to the main glossary entry by
+%   % creating an auxiliary glossary entry (note: we set the label of this entry
+%   % to '<original label>_auxiliary' to avoid clashes)
+%   \newglossaryentry{#2_auxiliary}{
+%     name={#3},
+%     sort={#3},
+%     description={\makefirstuc{#6}},
+%     see=[See:]{#2}
+%   }
+% }
+
+% % Change the text of the cross-reference links to the Slovene long version.
+% \renewcommand*{\glsseeitemformat}[1]{\emph{\acrlong{#1}}.}
+
+% Define the Indonesian term and link it to the English term
+\newglossaryentry{jaringansaraf}{
+  name=Jaringan Saraf,
+  description={The Indonesian term for \gls{nn}}
+}
+% \newglossaryentry{pemelajaranmesin}{
+%   name=Pemelajaran Mesin,
+%   description={Lihat \gls{machinelearning}}
+% }
+
+% Define the English term and link it to its acronym
+\newglossaryentry{neuralnetwork}{
+  name=Neural Network,
+  description={A computational model inspired by the human brain, see \gls{nn}}
+}
+
+% \newglossaryentry{machinelearning}{
+%   name=Machine Learning,
+%   description={A program or system that trains a model from input data. The trained model can make useful predictions from new (never-before-seen) data drawn from the same distribution as the one used to train the model.}}
+% \newglossaryentry{pemelajaranmesin}{
+%     name={pemelajaran mesin (angl.\ #5)},
+%     first={pemelajaran mesin (\emph{machine learning})},
+%     text={pemelajaran mesin},
+%     sort={ },
+%     description={#6},
+%     #1 % pass additional options to \newglossaryentry
+% }
+\longnewglossaryentry{machinelearning}{name={machine learning}}
+{A program or system that trains a model from input data. The trained model can make useful predictions from new (never-before-seen) data drawn from the same distribution as the one used to train the model.}
+\newterm[see={machinelearning}]{pemelajaranmesin}
+% \newglossaryentry{pemelajaran mesin}{}
+% \addterm{machinelearning}{pemelajaran mesin}{pemelajaran mesin}{machine learning}{A program or system that trains a model from input data. The trained model can make useful predictions from new (never-before-seen) data drawn from the same distribution as the one used to train the model.}
+\newacronym
+ [description={statistical pattern recognition technique}]
+ {svm}{SVM}{support vector machine}

latex/frontmatter/maketitle.tex

@@ -5,7 +5,7 @@
 {\fontsize{14pt}{16pt}\selectfont \textbf{\MakeUppercase{Tugas Akhir}}\par}
 \vspace{1.5cm}
 
-    {\fontsize{14pt}{16pt}\selectfont \textbf{\MakeUppercase{\thesistitle}}\par}
+{\fontsize{14pt}{16pt}\selectfont \textbf{\MakeUppercase{\thetitle}}\par}
 \vspace{1.5cm}
 
 \includegraphics[width=5cm]{frontmatter/img/logo.png}
@@ -13,7 +13,7 @@
 
 
 \textbf{Disusun oleh:} \\
-    {\fontsize{14pt}{16pt}\selectfont \textbf{\studentname}} \\
+{\fontsize{14pt}{16pt}\selectfont \textbf{\theauthor}} \\
 {\fontsize{14pt}{16pt}\selectfont \textbf{\studentid}} \\
 
 
@@ -28,4 +28,3 @@
 
 \end{titlepage}%
 
-    

latex/frontmatter/maketitle_secondary.tex

@@ -0,0 +1,29 @@
+\begin{titlepage}
+\centering
+{\fontsize{14pt}{16pt}\selectfont \textbf{\MakeUppercase{Tugas Akhir}}\par}
+\vspace{1.5cm}
+
+{\fontsize{14pt}{16pt}\selectfont \textbf{\MakeUppercase{\thetitle}}\par}
+\vspace{1cm}
+{\normalsize\selectfont Diajukan guna melengkapi persyaratan untuk memenuhi gelar Sarjana Teknik di Program Studi Teknik Sipil, Fakultas Teknik, Universitas Muhammadiyah Yogyakarta\par}
+\vspace{1.5cm}
+
+\includegraphics[width=5cm]{frontmatter/img/logo.png}
+\vspace{1.5cm}
+
+
+\textbf{Disusun oleh:} \\
+{\fontsize{14pt}{16pt}\selectfont \textbf{\theauthor}} \\
+{\fontsize{14pt}{16pt}\selectfont \textbf{\studentid}} \\
+
+
+\vfill
+
+{\fontsize{12pt}{14pt}\selectfont
+\textbf{\program} \\
+\textbf{\faculty} \\
+\textbf{\university} \\
+\textbf{\yearofsubmission}
+}
+
+\end{titlepage}%

latex/main.tex

@@ -16,22 +16,19 @@
 \input{preamble/macros}
 
 \begin{document}
-
+\input{frontmatter/maketitle}
-\maketitle
+\input{frontmatter/maketitle_secondary}
 \frontmatter
-\input{frontmatter/approval}\clearpage
+% \input{frontmatter/approval}\clearpage
-\input{frontmatter/originality}\clearpage
+% \input{frontmatter/originality}\clearpage
-\input{frontmatter/acknowledgement}\clearpage
+% \input{frontmatter/acknowledgement}\clearpage
 \tableofcontents
 \clearpage
 \mainmatter
 \pagestyle{fancyplain}
-% Include content
-\include{content/abstract}
-\include{content/introduction}
 \include{chapters/01_introduction}
-\include{content/chapter2}
+\include{chapters/id/02_literature_review/index}
-\include{content/conclusion}
+\include{chapters/id/03_methodology/index}
 
 % Bibliography
 % \bibliographystyle{IEEEtran}

latex/thesis.cls

@@ -21,17 +21,24 @@
 \RequirePackage{tocloft}
 \RequirePackage{tocbibind}
 \RequirePackage{amsmath,amsfonts,amssymb}
-
+\RequirePackage{svg}           % Allows including SVG images directly
+\RequirePackage{indentfirst}   % Makes first paragraph after headings indented
+\RequirePackage{float}         % Provides [H] option to force figure/table placement
+\RequirePackage[style=apa, backend=biber, language=indonesian]{biblatex}
 % Polyglossia set language
-\setmainlanguage{bahasai}
+\setdefaultlanguage[variant=indonesian]{malay}  % Proper Indonesian language setup
-% \setotherlanguage{english}
+\setotherlanguage{english}             % Enables English as secondary language
+\DefineBibliographyStrings{english}{%  % Customizes bibliography text
+  andothers={dkk\adddot},              % Changes "et al." to "dkk."
+  pages={hlm\adddot},                  % Changes "pp." to "hlm."
+}
 
 % Conditionally load the watermark package and settings
 \if@draftmark
   \RequirePackage{draftwatermark}
-  \SetWatermarkText{Draft: \today [wip]}
+  \SetWatermarkText{nuluh/thesis (wip) draft: \today}
-  \SetWatermarkColor[gray]{0.7}
+  \SetWatermarkColor[gray]{0.8}                    % Opacity: 0.8 = 20% transparent  
-  \SetWatermarkFontSize{2cm}
+  \SetWatermarkFontSize{1.5cm}
   \SetWatermarkAngle{90}
   \SetWatermarkHorCenter{1.5cm}
 \fi
@@ -48,8 +55,6 @@
 \setsansfont{Arial}
 \setmonofont{Courier New}
 
-% Metadata commands
-\input{metadata}
 
 \newcommand{\setthesisinfo}[7]{%
   \renewcommand{\thesistitle}{#1}%
@@ -79,7 +84,10 @@
 }
 
 % Chapter formatting
-\titlespacing{\chapter}{0pt}{0pt}{*1.5}
+\titlespacing{\chapter}{0pt}{0cm}{*1.5}    % 0pt→0cm: same value, different unit
+                                             % 0pt = no space above chapter title
+                                             % *1.5 = 1.5× line spacing after title
+
 \titleformat{\chapter}[display]
   {\normalsize\bfseries\centering}
   {BAB~\Roman{chapter}} % << display format
@@ -91,15 +99,16 @@
 \titleformat{\subsection}
     {\normalsize\bfseries}{\thesubsection}{1em}{}
 
+% Section numbering depth
+\setcounter{secnumdepth}{3}               % Enables numbering for:
+                                          % 1 = chapters, 2 = sections, 3 = subsections
+
 % Ensure chapter reference in TOC matches
 \renewcommand{\cftchappresnum}{BAB~}
 \renewcommand{\cftchapaftersnum}{\quad}
 
 % \titlespacing*{\chapter}{0pt}{-10pt}{20pt}
 
-% Redefine \maketitle
-\renewcommand{\maketitle}{\input{frontmatter/maketitle}}
-
 % Chapter & Section format
 \renewcommand{\cftchapfont}{\normalsize\MakeUppercase}
 % \renewcommand{\cftsecfont}{}
@@ -108,16 +117,22 @@
 
 
 % Dot leaders, spacing, indentation
+\setlength{\cftbeforetoctitleskip}{0cm}   % Space above "DAFTAR ISI" title
+\setlength{\cftbeforeloftitleskip}{0cm}   % Space above "DAFTAR GAMBAR" title  
+\setlength{\cftbeforelottitleskip}{0cm}   % Space above "DAFTAR TABEL" title
+
 \setlength{\cftbeforechapskip}{0em}
 \setlength{\cftchapindent}{0pt}
 \setlength{\cftsecindent}{0em}
-\setlength{\cftsubsecindent}{2.5em}
+\setlength{\cftsubsecindent}{2em}
 \setlength{\cftchapnumwidth}{3.5em}
-\setlength{\cftsecnumwidth}{3.5em}
+\setlength{\cftsecnumwidth}{2em}
 \setlength{\cftsubsecnumwidth}{2.5em}
 \setlength{\cftfignumwidth}{5em}
 \setlength{\cfttabnumwidth}{4em}
-\renewcommand \cftchapdotsep{4.5} % https://tex.stackexchange.com/a/273764
+\renewcommand \cftchapdotsep{1}           % Denser dots (closer together) https://tex.stackexchange.com/a/273764
+\renewcommand \cftsecdotsep{1}            % Apply to sections too
+\renewcommand \cftsubsecdotsep{1}         % Apply to subsections too
 \renewcommand{\cftchapleader}{\normalfont\cftdotfill{\cftsecdotsep}}
 \renewcommand{\cftchappagefont}{\normalfont}
 \renewcommand{\cftfigpresnum}{\figurename~}

setup.py

@@ -0,0 +1,8 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="thesisrepo",
+    version="0.1",
+    packages=find_packages(where="code"),
+    package_dir={"": "code"},
+)