feat(notebook): Add evaluation metrics and confusion matrix visualizations for model predictions on Dataset B. Remove commented-out code and integrate data preparation using create_ready_data function.

.gitignore

@@ -1,4 +1,5 @@
 # Ignore CSV files in the data directory and all its subdirectories
 data/**/*.csv
 .venv/
-*.pyc
+*.pyc
+*.egg-info/

.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 +334,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ready_data1[0]\n",
-    "plt.pcolormesh(ready_data1[0])"
+    "len(ready_data1a)\n",
+    "# plt.pcolormesh(ready_data1[0])"
    ]
   },
   {
@@ -345,7 +345,7 @@
    "outputs": [],
    "source": [
     "for i in range(6):\n",
-    "    plt.pcolormesh(ready_data1[i])\n",
+    "    plt.pcolormesh(ready_data1a[i])\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 +358,9 @@
    "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 +369,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(len(ready_data1))\n",
-    "print(len(ready_data2))"
+    "print(len(ready_data1a))\n",
+    "print(len(ready_data2a))"
    ]
   },
   {
@@ -379,10 +379,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x1 = 0\n",
-    "print(type(ready_data1[0]))\n",
-    "ready_data1[0].iloc[:,0]\n",
-    "# x1 = x1 + ready_data1[0].shape[0]"
+    "x1a = 0\n",
+    "print(type(ready_data1a[0]))\n",
+    "ready_data1a[0].iloc[:,0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Checking length of the total array"
    ]
   },
   {
@@ -391,16 +397,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x1 = 0\n",
-    "print(type(x1))\n",
-    "for i in range(len(ready_data1)):\n",
-    "    # print(ready_data1[i].shape)\n",
-    "    # print(ready_data1[i].)\n",
-    "    print(type(ready_data1[i].shape[0]))\n",
-    "    x1 = x1 + ready_data1[i].shape[0]\n",
-    "    print(type(x1))\n",
+    "x1a = 0\n",
+    "print(type(x1a))\n",
+    "for i in range(len(ready_data1a)):\n",
+    "    print(type(ready_data1a[i].shape[0]))\n",
+    "    x1a = x1a + ready_data1a[i].shape[0]\n",
+    "    print(type(x1a))\n",
     "\n",
-    "print(x1)"
+    "print(x1a)"
    ]
   },
   {
@@ -409,13 +413,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x2 = 0\n",
+    "x2a = 0\n",
     "\n",
-    "for i in range(len(ready_data2)):\n",
-    "    print(ready_data2[i].shape)\n",
-    "    x2 = x2 + ready_data2[i].shape[0]\n",
+    "for i in range(len(ready_data2a)):\n",
+    "    print(ready_data2a[i].shape)\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 +435,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "x1 = ready_data1[0]\n",
-    "# print(x1)\n",
-    "print(type(x1))\n",
-    "for i in range(len(ready_data1) - 1):\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",
+    "# Combine all dataframes in ready_data1a into a single dataframe\n",
+    "if ready_data1a:  # Check if the list is not empty\n",
+    "    # Use pandas concat function instead of iterative concatenation\n",
+    "    combined_data = pd.concat(ready_data1a, 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",
-    "for i in range(len(ready_data2) - 1):\n",
-    "    #print(i)\n",
-    "    x2 = np.concatenate((x2, ready_data2[i + 1]), axis=0)\n",
-    "pd.DataFrame(x2)"
+    "# Store the result in x1a for compatibility with subsequent code\n",
+    "x1a = combined_data"
    ]
   },
   {
@@ -454,20 +459,29 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(x1.shape)\n",
-    "print(x2.shape)"
+    "# Combine all dataframes in ready_data1a into a single dataframe\n",
+    "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",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "y_1 = [1,1,1,1]\n",
-    "y_2 = [0,1,1,1]\n",
-    "y_3 = [1,0,1,1]\n",
-    "y_4 = [1,1,0,0]"
+    "### Creating the label"
    ]
   },
   {
@@ -490,7 +504,8 @@
    "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",
+    "y_data"
    ]
   },
   {
@@ -500,7 +515,7 @@
    "outputs": [],
    "source": [
     "for i in range(len(y_data)):\n",
-    "    print(ready_data1[i].shape[0])"
+    "    print(ready_data1a[i].shape[0])"
    ]
   },
   {
@@ -509,9 +524,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import numpy as np\n",
     "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])"
+    "    y_data[i] = [y_data[i]]*ready_data1a[i].shape[0]"
    ]
   },
   {
@@ -520,6 +535,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# len(y_data[0])\n",
     "y_data"
    ]
   },
@@ -552,10 +568,10 @@
    "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",
-    "x_train2, x_test2, y_train, y_test = train_test_split(x2, y, test_size=0.2, random_state=2)"
+    "X1a, y = create_ready_data('D:/thesis/data/converted/raw/sensor1')\n",
+    "X2a, y = create_ready_data('D:/thesis/data/converted/raw/sensor2')"
    ]
   },
   {
@@ -565,6 +581,17 @@
    "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",
@@ -597,16 +624,17 @@
     "\n",
     "\n",
     "# 1. Random Forest\n",
-    "rf_model = RandomForestClassifier()\n",
-    "rf_model.fit(x_train1, y_train)\n",
-    "rf_pred1 = rf_model.predict(x_test1)\n",
+    "rf_model1 = RandomForestClassifier()\n",
+    "rf_model1.fit(x_train1, y_train)\n",
+    "rf_pred1 = rf_model1.predict(x_test1)\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",
+    "rf_model2 = RandomForestClassifier()\n",
+    "rf_model2.fit(x_train2, y_train)\n",
+    "rf_pred2 = rf_model2.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",
@@ -616,16 +644,17 @@
     "# 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",
+    "bagged_model1 = BaggingClassifier(estimator=DecisionTreeClassifier(), n_estimators=10)\n",
+    "bagged_model1.fit(x_train1, y_train)\n",
+    "bagged_pred1 = bagged_model1.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",
+    "bagged_model2 = BaggingClassifier(estimator=DecisionTreeClassifier(), n_estimators=10)\n",
+    "bagged_model2.fit(x_train2, y_train)\n",
+    "bagged_pred2 = bagged_model2.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",
@@ -641,8 +670,9 @@
     "# 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",
+    "dt_model2 = DecisionTreeClassifier()\n",
+    "dt_model2.fit(x_train2, y_train)\n",
+    "dt_pred2 = dt_model2.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",
@@ -658,8 +688,9 @@
     "# 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",
+    "knn_model2 = KNeighborsClassifier()\n",
+    "knn_model2.fit(x_train2, y_train)\n",
+    "knn_pred2 = knn_model2.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",
@@ -675,8 +706,9 @@
     "# 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",
+    "lda_model2 = LinearDiscriminantAnalysis()\n",
+    "lda_model2.fit(x_train2, y_train)\n",
+    "lda_pred2 = lda_model2.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",
@@ -692,8 +724,9 @@
     "# 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",
+    "svm_model2 = SVC()\n",
+    "svm_model2.fit(x_train2, y_train)\n",
+    "svm_pred2 = svm_model2.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",
@@ -709,8 +742,9 @@
     "# 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",
+    "xgboost_model2 = XGBClassifier()\n",
+    "xgboost_model2.fit(x_train2, y_train)\n",
+    "xgboost_pred2 = xgboost_model2.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",
@@ -787,51 +821,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def spectograph(data_dir: str):\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",
+    "from src.ml.model_selection import create_ready_data\n",
     "\n",
-    "            # df1 = pd.DataFrame()\n",
-    "\n",
-    "            # 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()"
+    "X1b, y = create_ready_data('D:/thesis/data/converted/raw_B/sensor1')\n",
+    "X2b, y = create_ready_data('D:/thesis/data/converted/raw_B/sensor2')"
    ]
   },
   {
@@ -840,7 +833,115 @@
    "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

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"},
+)