nuluh/thesis
1
0
Fork 0
Code Issues 47 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

feat(notebooks): Enhance STFT notebook and model selection functionality

Browse Source 
- Updated paths in the STFT notebook to reflect new data files.
- Improved plotting aesthetics for combined plots and added grid lines.
- Introduced a 3D spectrogram visualization for better data representation.
- Refactored model training function to include error handling and model export functionality.
- Adjusted model training calls to include export paths for saved models. Closes #90
- Added additional markdown cells for better documentation and clarity in the notebook.
This commit is contained in:
nuluh
2025-06-12 03:35:21 +07:00
parent f5dada1b9c
commit 4b0819f94e
3 changed files with 217 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

152
code/notebooks/stft.ipynb
View File

@@ -17,8 +17,8 @@
"metadata": {},
"outputs": [],
"source": [
"sensor1 = pd.read_csv('D:/thesis/data/converted/raw/DAMAGE_1/DAMAGE_1_TEST1_01.csv',sep=',')\n",
"sensor2 = pd.read_csv('D:/thesis/data/converted/raw/DAMAGE_1/DAMAGE_1_TEST1_02.csv',sep=',')"
"sensor1 = pd.read_csv('D:/thesis/data/converted/raw/DAMAGE_1/DAMAGE_0_TEST1_01.csv',sep=',')\n",
"sensor2 = pd.read_csv('D:/thesis/data/converted/raw/DAMAGE_1/DAMAGE_0_TEST1_02.csv',sep=',')"
]
},
{
@@ -101,13 +101,16 @@
"source": [
"# 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', alpha=0.5)\n",
"plt.plot(df1['s2'], label='Sensor 1', color='C1', alpha=0.6)\n",
"plt.plot(df1['s1'], label='Sensor 2', color='C0', alpha=0.6)\n",
"plt.xlabel(\"Number of samples\")\n",
"plt.ylabel(\"Amplitude\")\n",
"plt.title(\"Raw vibration signal\")\n",
"plt.ylim(-7.5, 5)\n",
"plt.legend()\n",
"plt.locator_params(axis='x', nbins=8)\n",
"plt.ylim(-1, 1) # Adjust range as needed\n",
"plt.grid(True, linestyle='--', alpha=0.5)\n",
"plt.show()"
]
},
@@ -334,9 +337,44 @@
"metadata": {},
"outputs": [],
"source": [
"# len(ready_data1a)\n",
"# plt.pcolormesh(ready_data1[0])\n",
"ready_data1a[0].max().max()"
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from mpl_toolkits.mplot3d import Axes3D\n",
"\n",
"# Assuming ready_data1a[0] is a DataFrame or 2D array\n",
"spectrogram_data = ready_data1a[0].values # Convert to NumPy array if it's a DataFrame\n",
"\n",
"# Get the dimensions of the spectrogram\n",
"num_frequencies, num_time_frames = spectrogram_data.shape\n",
"\n",
"# Create frequency and time arrays\n",
"frequencies = np.arange(num_frequencies) # Replace with actual frequency values if available\n",
"time_frames = np.arange(num_time_frames) # Replace with actual time values if available\n",
"\n",
"# Create a meshgrid for plotting\n",
"T, F = np.meshgrid(time_frames, frequencies)\n",
"\n",
"# Create a 3D plot\n",
"fig = plt.figure(figsize=(12, 8))\n",
"ax = fig.add_subplot(111, projection='3d')\n",
"\n",
"# Plot the surface\n",
"surf = ax.plot_surface(T, F, spectrogram_data, cmap='bwr', edgecolor='none')\n",
"\n",
"# Add labels and a color bar\n",
"ax.set_xlabel('Time Frames')\n",
"ax.set_ylabel('Frequency [Hz]')\n",
"ax.set_zlabel('Magnitude')\n",
"ax.set_title('3D Spectrogram')\n",
"# Resize the z-axis (shrink it)\n",
"z_min, z_max = 0, 0.1 # Replace with your desired range\n",
"ax.set_zlim(z_min, z_max)\n",
"ax.get_proj = lambda: np.dot(Axes3D.get_proj(ax), np.diag([1, 1, 0.5, 1])) # Shrink z-axis by 50%\n",
"ax.set_facecolor('white')\n",
"fig.colorbar(surf, ax=ax, shrink=0.5, aspect=10)\n",
"\n",
"# Show the plot\n",
"plt.show()"
]
},
{
@@ -345,13 +383,32 @@
"metadata": {},
"outputs": [],
"source": [
"from cmcrameri import cm\n",
"# Create a figure and subplots\n",
"fig, axes = plt.subplots(2, 3, figsize=(15, 8), sharex=True, sharey=True)\n",
"\n",
"# Flatten the axes array for easier iteration\n",
"axes = axes.flatten()\n",
"\n",
"# Loop through each subplot and plot the data\n",
"for i in range(6):\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",
" plt.show()"
" pcm = axes[i].pcolormesh(ready_data1a[i].transpose(), cmap='bwr', vmax=0.03, vmin=0.0)\n",
" axes[i].set_title(f'Case {i} Sensor A', fontsize=12)\n",
"\n",
"# Add a single color bar for all subplots\n",
"# Use the first `pcolormesh` object (or any valid one) for the color bar\n",
"cbar = fig.colorbar(pcm, ax=axes, orientation='vertical')\n",
"# cbar.set_label('Magnitude')\n",
"\n",
"# Set shared labels\n",
"fig.text(0.5, 0.04, 'Time Frames', ha='center', fontsize=12)\n",
"fig.text(0.04, 0.5, 'Frequency [Hz]', va='center', rotation='vertical', fontsize=12)\n",
"\n",
"# Adjust layout\n",
"# plt.tight_layout(rect=[0.05, 0.05, 1, 1]) # Leave space for shared labels\n",
"plt.subplots_adjust(left=0.1, right=0.75, top=0.9, bottom=0.1, wspace=0.2, hspace=0.2)\n",
"\n",
"plt.show()"
]
},
{
@@ -576,6 +633,16 @@
"X2a, y = create_ready_data('D:/thesis/data/converted/raw/sensor2')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"X1a.iloc[-1,:]\n",
"# y[2565]"
]
},
{
"cell_type": "code",
"execution_count": null,
@@ -621,23 +688,8 @@
"metadata": {},
"outputs": [],
"source": [
"def train_and_evaluate_model(model, model_name, sensor_label, x_train, y_train, x_test, y_test):\n",
" model.fit(x_train, y_train)\n",
" y_pred = model.predict(x_test)\n",
" accuracy = accuracy_score(y_test, y_pred) * 100\n",
" return {\n",
" \"model\": model_name,\n",
" \"sensor\": sensor_label,\n",
" \"accuracy\": accuracy\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from src.ml.model_selection import train_and_evaluate_model\n",
"from sklearn.svm import SVC\n",
"# Define models for sensor1\n",
"models_sensor1 = {\n",
" # \"Random Forest\": RandomForestClassifier(),\n",
@@ -646,12 +698,12 @@
" # \"KNN\": KNeighborsClassifier(),\n",
" # \"LDA\": LinearDiscriminantAnalysis(),\n",
" \"SVM\": SVC(),\n",
" \"XGBoost\": XGBClassifier()\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",
" res = train_and_evaluate_model(model, name, \"sensor1\", x_train1, y_train, x_test1, y_test, export='D:/thesis/models/sensor1')\n",
" results_sensor1.append(res)\n",
" print(f\"{name} on sensor1: Accuracy = {res['accuracy']:.2f}%\")\n"
]
@@ -669,12 +721,12 @@
" # \"KNN\": KNeighborsClassifier(),\n",
" # \"LDA\": LinearDiscriminantAnalysis(),\n",
" \"SVM\": SVC(),\n",
" \"XGBoost\": XGBClassifier()\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",
" res = train_and_evaluate_model(model, name, \"sensor2\", x_train2, y_train, x_test2, y_test, export='D:/thesis/models/sensor2')\n",
" results_sensor2.append(res)\n",
" print(f\"{name} on sensor2: Accuracy = {res['accuracy']:.2f}%\")\n"
]
@@ -787,6 +839,8 @@
"source": [
"from sklearn.metrics import accuracy_score, classification_report\n",
"# 4. Validate on Dataset B\n",
"from joblib import load\n",
"svm_model = load('D:/thesis/models/sensor1/SVM.joblib')\n",
"y_pred_svm = svm_model.predict(X1b)\n",
"\n",
"# 5. Evaluate\n",
@@ -794,6 +848,30 @@
"print(classification_report(y, y_pred_svm))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Model sensor 1 to predict sensor 2 data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics import accuracy_score, classification_report\n",
"# 4. Validate on Dataset B\n",
"from joblib import load\n",
"svm_model = load('D:/thesis/models/sensor1/SVM.joblib')\n",
"y_pred_svm = svm_model.predict(X2b)\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,
@@ -853,7 +931,7 @@
"# 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.title(\"SVM Sensor1 CM Train w/ Dataset A Val w/ Dataset B from Sensor2 readings\")\n",
"plt.show()"
]
},
@@ -871,14 +949,14 @@
"outputs": [],
"source": [
"# 1. Predict sensor 1 on Dataset A\n",
"y_train_pred = svm_model.predict(x_train1)\n",
"y_test_pred = svm_model.predict(x_test1)\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",
"cm_train = confusion_matrix(y_test, y_test_pred)\n",
"labels = svm_model.classes_\n",
"\n",
"disp = ConfusionMatrixDisplay(confusion_matrix=cm_train, display_labels=labels)\n",