diff --git a/code/notebooks/03_feature_extraction.ipynb b/code/notebooks/03_feature_extraction.ipynb index c32d240..4878537 100644 --- a/code/notebooks/03_feature_extraction.ipynb +++ b/code/notebooks/03_feature_extraction.ipynb @@ -325,7 +325,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 15, "metadata": {}, "outputs": [], "source": [ @@ -355,6 +355,7 @@ " all_features = []\n", " for nth_damage in os.listdir(input_dir):\n", " nth_damage_path = os.path.join(input_dir, nth_damage)\n", + " print(f'Extracting features from damage folder {nth_damage_path}')\n", " if os.path.isdir(nth_damage_path):\n", " for nth_test in os.listdir(nth_damage_path):\n", " nth_test_path = os.path.join(nth_damage_path, nth_test)\n", @@ -381,11 +382,30 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 16, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Extracting features from damage folder ../../data/raw\\DAMAGE_1\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_2\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_3\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_4\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_5\n", + "Extracting features from damage folder ../../data/raw\\README.md\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_1\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_2\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_3\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_4\n", + "Extracting features from damage folder ../../data/raw\\DAMAGE_5\n", + "Extracting features from damage folder ../../data/raw\\README.md\n" + ] + } + ], "source": [ - "data_dir = \"../../data/QUGS/raw\"\n", + "data_dir = \"../../data/raw\"\n", "# Extract features\n", "df1 = build_features(data_dir, sensor=1)\n", "df2 = build_features(data_dir, sensor=2)" @@ -400,7 +420,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 20, "metadata": {}, "outputs": [ { @@ -437,7 +457,7 @@ "Index: []" ] }, - "execution_count": 7, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" } @@ -827,6 +847,1435 @@ "sns.pairplot(subset_df, hue='label', diag_kind='kde')\n", "plt.show()" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## QUGS Data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To test the `FeatureExtractor` class from the `time_domain_features.py` script with real data from QUGS that has been converted purposed for the thesis." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Importing Modules\n", + "\n", + "Use relative imports or modify the path to include the directory where the module is stored. In this example, we’ll simulate the relative import setup." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Create Real DataFrame\n", + "\n", + "Create one DataFrame from one of the raw data file. Simulate importing the `FeatureExtractor` from its relative path in the notebooks directory." + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TimeReal.4
00.000000-0.002501
10.000977-0.005371
20.001953-0.003811
30.0029300.005464
40.003906-0.029412
\n", + "
" + ], + "text/plain": [ + " Time Real.4\n", + "0 0.000000 -0.002501\n", + "1 0.000977 -0.005371\n", + "2 0.001953 -0.003811\n", + "3 0.002930 0.005464\n", + "4 0.003906 -0.029412" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Convert to DataFrame (simulating processed data input)\n", + "single_data_dir = \"D:/thesis/data/converted/raw/DAMAGE_2/D2_TEST05_01.csv\"\n", + "df = pd.read_csv(single_data_dir)\n", + "df.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Visualize Data Points" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Plotting the data points\n", + "plt.figure(figsize=(8, 6))\n", + "plt.plot(df['Time'], df[df.columns[-1]], marker='o', color='blue', label='Data Points')\n", + "plt.title('Scatter Plot of Data Points')\n", + "plt.xlabel('Time')\n", + "plt.ylabel('Amp')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Downsampled Plot with Alpha Blending\n", + "\n", + "Reduce the number of data points by sampling a subset of the data and use transparency to help visualize the density of overlapping points." + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Downsample the data by taking every nth point\n", + "n = 1 # Adjust this value as needed\n", + "downsampled_df = df.iloc[::n, :]\n", + "\n", + "# Plotting the downsampled data points with alpha blending\n", + "plt.figure(figsize=(8, 6))\n", + "plt.plot(downsampled_df['Time'], downsampled_df[downsampled_df.columns[-1]], alpha=0.5, color='blue', label='Data Points')\n", + "plt.title('Scatter Plot of Downsampled Data Points')\n", + "plt.xlabel('Time')\n", + "plt.ylabel('Amp')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Line Plot with Rolling Avg" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Calculate the rolling average\n", + "window_size = 50 # Adjust this value as needed\n", + "rolling_avg = df[df.columns[-1]].rolling(window=window_size).mean()\n", + "\n", + "# Plotting the original data points and the rolling average\n", + "plt.figure(figsize=(8, 6))\n", + "plt.plot(df['Time'], df[df.columns[-1]], alpha=0.3, color='blue', label='Original Data')\n", + "plt.plot(df['Time'], rolling_avg, color='red', label='Rolling Average')\n", + "plt.title('Line Plot with Rolling Average')\n", + "plt.xlabel('Time')\n", + "plt.ylabel('Amp')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Print Time-domain Features (Single CSV Real Data)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
MeanMaxPeak (Pm)Peak-to-Peak (Pk)RMSVarianceStandard DeviationPowerCrest FactorForm FactorPulse IndicatorMarginKurtosisSkewness
0-4.594330e-110.6917690.6917691.3754040.1509150.0227750.1509160.0227754.583819-3.284819e+09-1.505702e+102.167343.0124590.008173
\n", + "
" + ], + "text/plain": [ + " Mean Max Peak (Pm) Peak-to-Peak (Pk) RMS Variance \\\n", + "0 -4.594330e-11 0.691769 0.691769 1.375404 0.150915 0.022775 \n", + "\n", + " Standard Deviation Power Crest Factor Form Factor Pulse Indicator \\\n", + "0 0.150916 0.022775 4.583819 -3.284819e+09 -1.505702e+10 \n", + "\n", + " Margin Kurtosis Skewness \n", + "0 2.16734 3.012459 0.008173 " + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import sys\n", + "import os\n", + "# Assuming the src directory is one level up from the notebooks directory\n", + "sys.path.append('../src/features')\n", + "from time_domain_features import FeatureExtractor\n", + "\n", + "\n", + "# Extract features\n", + "extracted = FeatureExtractor(df[df.columns[-1]])\n", + "\n", + "# Format with pandas DataFramw\n", + "features = pd.DataFrame(extracted.features, index=[0])\n", + "features\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Print Time-domain Features (Multiple CSV Real Data)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import sys\n", + "import os\n", + "import re\n", + "# Assuming the src directory is one level up from the notebooks directory\n", + "sys.path.append('../src/features')\n", + "from time_domain_features import ExtractTimeFeatures # use wrapper function instead of class for easy use\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### The function" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [], + "source": [ + "# Define a function to extract numbers from a filename that later used as labels features\n", + "def extract_numbers(filename):\n", + " '''\n", + " Extract numbers from a filename\n", + "\n", + " Parameters\n", + " ----------\n", + " filename : str\n", + " The filename to extract numbers from\n", + "\n", + " Returns\n", + " -------\n", + " list\n", + " A list of extracted numbers: [damage_number, test_number, sensor_number]\n", + " '''\n", + " # Find all occurrences of one or more digits in the filename\n", + " numbers = re.findall(r'\\d+', filename)\n", + " # Convert the list of number strings to integers\n", + " numbers = [int(num) for num in numbers]\n", + " # Convert to a tuple and return\n", + " return numbers\n", + "\n", + "def build_features(input_dir:str, sensor:int=None, verbose:bool=False):\n", + " all_features = []\n", + " for nth_damage in os.listdir(input_dir):\n", + " nth_damage_path = os.path.join(input_dir, nth_damage)\n", + " if verbose:\n", + " print(f'Extracting features from damage folder {nth_damage_path}')\n", + " if os.path.isdir(nth_damage_path):\n", + " for nth_test in os.listdir(nth_damage_path):\n", + " nth_test_path = os.path.join(nth_damage_path, nth_test)\n", + " # if verbose:\n", + " # print(f'Extracting features from {nth_test_path}')\n", + " if sensor is not None:\n", + " # Check if the file has the specified sensor suffix\n", + " if not nth_test.endswith(f'_{sensor:02}.csv'):\n", + " continue\n", + " # if verbose:\n", + " # print(f'Extracting features from {nth_test_path}')\n", + " features = ExtractTimeFeatures(nth_test_path) # return the one csv file feature in dictionary {}\n", + " if verbose:\n", + " print(features)\n", + " features['label'] = extract_numbers(nth_test)[0] # add labels to the dictionary\n", + " features['filename'] = nth_test # add filename to the dictionary\n", + " all_features.append(features)\n", + "\n", + " # Create a DataFrame from the list of dictionaries\n", + " df = pd.DataFrame(all_features)\n", + " return df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Execute the automation" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Extracting features from damage folder D:/thesis/data/converted/raw\\DAMAGE_1\n", + "{'Mean': 4.935794427560776e-09, 'Max': 0.5858288, 'Peak (Pm)': 0.6626305, 'Peak-to-Peak (Pk)': 1.2484593, 'RMS': 0.1362702190299897, 'Variance': 0.01856957259448133, 'Standard Deviation': 0.13627047894654068, 'Power': 0.018569572594481366, 'Crest Factor': 4.862621523006222, 'Form Factor': 27608568.596187092, 'Pulse Indicator': 134250019.87521306, 'Margin': 2.1849538435504186, 'Kurtosis': 3.022962308835951, 'Skewness': 0.0012958106685132709}\n", + "{'Mean': 1.0670429728482285e-07, 'Max': 0.7143209, 'Peak (Pm)': 0.7143209, 'Peak-to-Peak (Pk)': 1.2992979, 'RMS': 0.14557249700238117, 'Variance': 0.021191351883496887, 'Standard Deviation': 0.14557277466169877, 'Power': 0.021191351883508274, 'Crest Factor': 4.906977036935182, 'Form Factor': 1364260.8658375633, 'Pulse Indicator': 6694396.741054232, 'Margin': 2.2755535142432146, 'Kurtosis': 2.9896062310785814, 'Skewness': 0.0016697103771502017}\n", + "{'Mean': 1.9706693736568082e-08, 'Max': 0.7278727, 'Peak (Pm)': 0.7278727, 'Peak-to-Peak (Pk)': 1.4333739, 'RMS': 0.165006915629019, 'Variance': 0.027227282205401805, 'Standard Deviation': 0.1650072303568338, 'Power': 0.027227282205402194, 'Crest Factor': 4.411164812246163, 'Form Factor': 8373140.509248861, 'Pulse Indicator': 36935302.78239149, 'Margin': 2.1792802291177393, 'Kurtosis': 2.9812895758530917, 'Skewness': -0.006938824931332053}\n", + "{'Mean': 4.6400798331387123e-08, 'Max': 0.637569, 'Peak (Pm)': 0.637569, 'Peak-to-Peak (Pk)': 1.1512296000000002, 'RMS': 0.12090799377123415, 'Variance': 0.01461874295778264, 'Standard Deviation': 0.12090822438646137, 'Power': 0.014618742957784795, 'Crest Factor': 5.273174916840671, 'Form Factor': 2605730.8951395294, 'Pulse Indicator': 13740474.796286557, 'Margin': 2.226963805106291, 'Kurtosis': 2.9826863333977065, 'Skewness': -0.00442221557241219}\n", + "{'Mean': 2.7488388806731582e-08, 'Max': 0.5571427, 'Peak (Pm)': 0.5852444, 'Peak-to-Peak (Pk)': 1.1423871, 'RMS': 0.13144029417868638, 'Variance': 0.017276550933778858, 'Standard Deviation': 0.1314405448828225, 'Power': 0.017276550933779614, 'Crest Factor': 4.452549377319485, 'Form Factor': 4781666.000973408, 'Pulse Indicator': 21290603.975183897, 'Margin': 1.9649866646054637, 'Kurtosis': 3.015813008716952, 'Skewness': -0.000659001044647282}\n", + "Extracting features from damage folder D:/thesis/data/converted/raw\\DAMAGE_2\n", + "{'Mean': 1.3934612310944543e-08, 'Max': 0.7251477, 'Peak (Pm)': 0.7776651, 'Peak-to-Peak (Pk)': 1.5028128, 'RMS': 0.15703024768091647, 'Variance': 0.024658498686729775, 'Standard Deviation': 0.15703054719434353, 'Power': 0.024658498686729976, 'Crest Factor': 4.952326774521848, 'Form Factor': 11269079.051275905, 'Pulse Indicator': 55808161.909836926, 'Margin': 2.3914494217651483, 'Kurtosis': 3.065793079040563, 'Skewness': -0.011438874839155505}\n", + "{'Mean': -1.6040696913631207e-08, 'Max': 0.7163731, 'Peak (Pm)': 0.7801023, 'Peak-to-Peak (Pk)': 1.4964754, 'RMS': 0.1629113530481945, 'Variance': 0.026540108951993217, 'Standard Deviation': 0.1629116637790146, 'Power': 0.026540108951993477, 'Crest Factor': 4.788507893426066, 'Form Factor': -10156126.876866193, 'Pulse Indicator': -48632693.71651039, 'Margin': 2.3491353605498797, 'Kurtosis': 3.0095153805004067, 'Skewness': 0.0035459331148647265}\n", + "{'Mean': -3.6031959580527945e-08, 'Max': 0.7914127, 'Peak (Pm)': 0.8284533, 'Peak-to-Peak (Pk)': 1.619866, 'RMS': 0.18490495831144427, 'Variance': 0.034189843608155635, 'Standard Deviation': 0.18490531099201457, 'Power': 0.03418984360815694, 'Crest Factor': 4.480427715759771, 'Form Factor': -5131693.098683672, 'Pulse Indicator': -22992179.988115467, 'Margin': 2.343746706467838, 'Kurtosis': 3.002473556285487, 'Skewness': 0.016718729830412823}\n", + "{'Mean': 9.172816008257008e-09, 'Max': 0.6702775, 'Peak (Pm)': 0.7604433, 'Peak-to-Peak (Pk)': 1.4307208, 'RMS': 0.14168733498902872, 'Variance': 0.02007530089629316, 'Standard Deviation': 0.1416876052379772, 'Power': 0.020075300896293242, 'Crest Factor': 5.367052037917739, 'Form Factor': 15446438.134318551, 'Pulse Indicator': 82901837.26736467, 'Margin': 2.457804091403889, 'Kurtosis': 3.0023394577627944, 'Skewness': -0.01140764905780411}\n", + "{'Mean': 9.495013175985419e-09, 'Max': 0.6917691, 'Peak (Pm)': 0.6917691, 'Peak-to-Peak (Pk)': 1.375404, 'RMS': 0.1509157231480295, 'Variance': 0.022775555493292594, 'Standard Deviation': 0.15091601099884902, 'Power': 0.02277555549329269, 'Crest Factor': 4.583810656504364, 'Form Factor': 15894208.923240073, 'Pulse Indicator': 72856044.2390546, 'Margin': 2.167332528548143, 'Kurtosis': 3.012447483653337, 'Skewness': 0.008172550552215142}\n", + "Extracting features from damage folder D:/thesis/data/converted/raw\\DAMAGE_3\n", + "{'Mean': -5.125203652084519e-09, 'Max': 0.7967038, 'Peak (Pm)': 0.7967038, 'Peak-to-Peak (Pk)': 1.5589914999999999, 'RMS': 0.16884091104965937, 'Variance': 0.028507253244078955, 'Standard Deviation': 0.16884123309028998, 'Power': 0.028507253244078986, 'Crest Factor': 4.718665606854455, 'Form Factor': -32943258.943669196, 'Pulse Indicator': -155448222.95519227, 'Margin': 2.3556475344978147, 'Kurtosis': 3.0014048735916217, 'Skewness': 0.00016304631330188324}\n", + "{'Mean': -7.222874873547567e-09, 'Max': 0.8287752, 'Peak (Pm)': 0.8287752, 'Peak-to-Peak (Pk)': 1.5514018, 'RMS': 0.16929145862040224, 'Variance': 0.028659597961823314, 'Standard Deviation': 0.16929178152038984, 'Power': 0.02865959796182336, 'Crest Factor': 4.895552361317535, 'Form Factor': -23438237.76324863, 'Pulse Indicator': -114743120.22699365, 'Margin': 2.446085789562267, 'Kurtosis': 2.9631006088008798, 'Skewness': 0.010084718218560516}\n", + "{'Mean': -7.725628435660411e-09, 'Max': 0.7944632, 'Peak (Pm)': 0.7944632, 'Peak-to-Peak (Pk)': 1.5331682, 'RMS': 0.1625625135017677, 'Variance': 0.026426570796012346, 'Standard Deviation': 0.16256282356722532, 'Power': 0.02642657079601241, 'Crest Factor': 4.887124238463261, 'Form Factor': -21041979.284352075, 'Pulse Indicator': -102834766.98579885, 'Margin': 2.3967788349063155, 'Kurtosis': 3.0213181211381293, 'Skewness': 0.004488735052518127}\n", + "{'Mean': 9.120998409253091e-09, 'Max': 0.7135901, 'Peak (Pm)': 0.7135901, 'Peak-to-Peak (Pk)': 1.4117066, 'RMS': 0.16207233854213446, 'Variance': 0.026267442920516162, 'Standard Deviation': 0.16207264767265123, 'Power': 0.02626744292051624, 'Crest Factor': 4.402911110056487, 'Form Factor': 17769144.480687, 'Pulse Indicator': 78235963.6502157, 'Margin': 2.1564501310909345, 'Kurtosis': 2.998678121046115, 'Skewness': 0.006172057448616143}\n", + "{'Mean': -3.128234370585584e-08, 'Max': 0.6531574, 'Peak (Pm)': 0.7488455, 'Peak-to-Peak (Pk)': 1.4020029, 'RMS': 0.15292709505145338, 'Variance': 0.023386696400875272, 'Standard Deviation': 0.15292738673868306, 'Power': 0.02338669640087626, 'Crest Factor': 4.896748347623067, 'Form Factor': -4888607.339955366, 'Pulse Indicator': -23938279.914104436, 'Margin': 2.328524868575274, 'Kurtosis': 3.000210053435982, 'Skewness': -0.0029119433234809813}\n", + "Extracting features from damage folder D:/thesis/data/converted/raw\\DAMAGE_4\n", + "{'Mean': 1.55488128252111e-08, 'Max': 0.7442828, 'Peak (Pm)': 0.7442828, 'Peak-to-Peak (Pk)': 1.459784, 'RMS': 0.1690262994991522, 'Variance': 0.02856988992237687, 'Standard Deviation': 0.169026621893385, 'Power': 0.028569889922377106, 'Crest Factor': 4.403354993899828, 'Form Factor': 10870688.418416755, 'Pulse Indicator': 47867500.13436445, 'Margin': 2.2012696204227113, 'Kurtosis': 2.99056612619621, 'Skewness': -0.018603955930243943}\n", + "{'Mean': 1.292989200929343e-08, 'Max': 0.8217714, 'Peak (Pm)': 0.8217714, 'Peak-to-Peak (Pk)': 1.6252129000000002, 'RMS': 0.18214987905659388, 'Variance': 0.033178578440331605, 'Standard Deviation': 0.1821502264822355, 'Power': 0.03317857844033178, 'Crest Factor': 4.511512191258036, 'Form Factor': 14087501.96255875, 'Pulse Indicator': 63555936.8484553, 'Margin': 2.3449707893701555, 'Kurtosis': 3.0280857310588734, 'Skewness': 0.0009546518963361565}\n", + "{'Mean': -9.007574774122792e-09, 'Max': 0.8003945, 'Peak (Pm)': 0.8320401, 'Peak-to-Peak (Pk)': 1.6324345999999998, 'RMS': 0.1758869327443254, 'Variance': 0.03093621311020678, 'Standard Deviation': 0.17588726822426548, 'Power': 0.03093621311020685, 'Crest Factor': 4.730539597330285, 'Form Factor': -19526558.164092984, 'Pulse Indicator': -92371156.5948148, 'Margin': 2.4119301890810863, 'Kurtosis': 2.9844842979116764, 'Skewness': -0.011957880697579701}\n", + "{'Mean': 1.3813648390246642e-09, 'Max': 0.6532164, 'Peak (Pm)': 0.6532164, 'Peak-to-Peak (Pk)': 1.2857231, 'RMS': 0.14361795378567382, 'Variance': 0.020626116649583946, 'Standard Deviation': 0.14361822771701033, 'Power': 0.020626116649583946, 'Crest Factor': 4.54829206782056, 'Form Factor': 103968155.06544794, 'Pulse Indicator': 472877534.99011487, 'Margin': 2.096257507768814, 'Kurtosis': 2.9947520336358764, 'Skewness': -0.0031834515529559487}\n", + "{'Mean': -4.778003436297728e-08, 'Max': 0.6669507, 'Peak (Pm)': 0.6669507, 'Peak-to-Peak (Pk)': 1.3241321, 'RMS': 0.15547548985491688, 'Variance': 0.024172627945624078, 'Standard Deviation': 0.1554757864028522, 'Power': 0.02417262794562636, 'Crest Factor': 4.289748182317162, 'Form Factor': -3253984.4712918047, 'Pulse Indicator': -13958773.971012289, 'Margin': 2.0572986524988806, 'Kurtosis': 2.998294672107473, 'Skewness': -0.005900011198990793}\n", + "{'Mean': -1.4860702017497662e-08, 'Max': 0.5918152, 'Peak (Pm)': 0.5918152, 'Peak-to-Peak (Pk)': 1.1695822, 'RMS': 0.1273105747526182, 'Variance': 0.016207982443841768, 'Standard Deviation': 0.12731081757988907, 'Power': 0.016207982443841983, 'Crest Factor': 4.648594204762468, 'Form Factor': -8566928.70920344, 'Pulse Indicator': -39824175.150216326, 'Margin': 2.0169392631404075, 'Kurtosis': 3.02420106022748, 'Skewness': 0.0074253093438661905}\n", + "{'Mean': -1.7241842698455592e-08, 'Max': 0.6988725, 'Peak (Pm)': 0.6988725, 'Peak-to-Peak (Pk)': 1.3169399, 'RMS': 0.1422862926904231, 'Variance': 0.020245389087584442, 'Standard Deviation': 0.14228656408179957, 'Power': 0.020245389087584748, 'Crest Factor': 4.911734551412901, 'Form Factor': -8252383.180781955, 'Pulse Indicator': -40533515.60054543, 'Margin': 2.2528929044415698, 'Kurtosis': 3.006112425097173, 'Skewness': 0.0020457966428877265}\n", + "{'Mean': -4.1197091090896294e-09, 'Max': 0.9292531, 'Peak (Pm)': 0.9292531, 'Peak-to-Peak (Pk)': 1.7662965000000002, 'RMS': 0.17837248381965012, 'Variance': 0.03181674298399133, 'Standard Deviation': 0.17837282404043445, 'Power': 0.03181674298399135, 'Crest Factor': 5.209621350227732, 'Form Factor': -43297349.180817954, 'Pulse Indicator': -225562794.70065442, 'Margin': 2.6794066535741035, 'Kurtosis': 3.059551564691877, 'Skewness': -0.009642173835931916}\n", + "{'Mean': -1.1934879643152173e-08, 'Max': 0.707527, 'Peak (Pm)': 0.755228, 'Peak-to-Peak (Pk)': 1.462755, 'RMS': 0.15931024345213565, 'Variance': 0.025379753668778586, 'Standard Deviation': 0.15931054731433875, 'Power': 0.025379753668778728, 'Crest Factor': 4.7406116746466855, 'Form Factor': -13348290.742382344, 'Pulse Indicator': -63279062.92991602, 'Margin': 2.3013726266794055, 'Kurtosis': 2.9869035740941716, 'Skewness': 0.014359917561322237}\n", + "{'Mean': 7.395535928902504e-09, 'Max': 0.6920146, 'Peak (Pm)': 0.6920146, 'Peak-to-Peak (Pk)': 1.3443711, 'RMS': 0.1412843411260445, 'Variance': 0.019961265047420452, 'Standard Deviation': 0.14128461060633815, 'Power': 0.019961265047420507, 'Crest Factor': 4.898027583839816, 'Form Factor': 19104003.074867226, 'Pulse Indicator': 93571934.02246033, 'Margin': 2.236725107476516, 'Kurtosis': 2.9968041695990943, 'Skewness': 0.0034724073879618903}\n", + "{'Mean': 1.0422456716329221e-08, 'Max': 0.5713457, 'Peak (Pm)': 0.5797505, 'Peak-to-Peak (Pk)': 1.1510962, 'RMS': 0.12968834598537562, 'Variance': 0.016819067084422386, 'Standard Deviation': 0.12968859334791594, 'Power': 0.016819067084422497, 'Crest Factor': 4.470336140036637, 'Form Factor': 12443164.746579224, 'Pulse Indicator': 55625129.06306293, 'Margin': 1.9590883401151484, 'Kurtosis': 3.016023674055137, 'Skewness': 0.00852173949170516}\n", + "{'Mean': 8.107469372403859e-09, 'Max': 0.6199987, 'Peak (Pm)': 0.6756481, 'Peak-to-Peak (Pk)': 1.2956468, 'RMS': 0.1402657999449104, 'Variance': 0.019674494634185562, 'Standard Deviation': 0.14026606748247794, 'Power': 0.01967449463418563, 'Crest Factor': 4.816912606389881, 'Form Factor': 17300811.572886854, 'Pulse Indicator': 83336497.36621463, 'Margin': 2.1975471976374075, 'Kurtosis': 3.037578810042664, 'Skewness': -0.013613810169722728}\n", + "{'Mean': 4.262961079273146e-08, 'Max': 0.814953, 'Peak (Pm)': 0.814953, 'Peak-to-Peak (Pk)': 1.5565602, 'RMS': 0.16625709306754788, 'Variance': 0.027641420995269454, 'Standard Deviation': 0.1662574101798985, 'Power': 0.02764142099527128, 'Crest Factor': 4.901763798245265, 'Form Factor': 3900037.7900681063, 'Pulse Indicator': 19117064.05114431, 'Margin': 2.4308595525011776, 'Kurtosis': 3.0190362730354328, 'Skewness': 0.0022508235385028208}\n", + "{'Mean': 9.371075913619966e-10, 'Max': 0.7196078, 'Peak (Pm)': 0.7196078, 'Peak-to-Peak (Pk)': 1.3686654, 'RMS': 0.15299253723022288, 'Variance': 0.023406716448141136, 'Standard Deviation': 0.15299282904227765, 'Power': 0.023406716448141133, 'Crest Factor': 4.703548375808263, 'Form Factor': 163260375.47925827, 'Pulse Indicator': 767903073.9193124, 'Margin': 2.235990216835229, 'Kurtosis': 2.981834630537439, 'Skewness': 0.0007909124000460926}\n", + "{'Mean': 1.4493594366489167e-08, 'Max': 0.6528962, 'Peak (Pm)': 0.6528962, 'Peak-to-Peak (Pk)': 1.290172, 'RMS': 0.14220565540682817, 'Variance': 0.020222448429685333, 'Standard Deviation': 0.14220592664440052, 'Power': 0.020222448429685555, 'Crest Factor': 4.591211215420132, 'Form Factor': 9811621.038299773, 'Pulse Indicator': 45047224.552494034, 'Margin': 2.1038145838382705, 'Kurtosis': 2.9857388812869656, 'Skewness': -0.007918264333781077}\n", + "{'Mean': 1.031987296632552e-08, 'Max': 0.595708, 'Peak (Pm)': 0.6369753, 'Peak-to-Peak (Pk)': 1.2326833000000001, 'RMS': 0.12773594252827294, 'Variance': 0.01631647101358614, 'Standard Deviation': 0.12773618616687432, 'Power': 0.016316471013586246, 'Crest Factor': 4.986656749794699, 'Form Factor': 12377666.173322521, 'Pulse Indicator': 61723172.569904275, 'Margin': 2.166322112675606, 'Kurtosis': 3.012298419893727, 'Skewness': 0.004319132036356966}\n", + "{'Mean': 1.5924574521904461e-09, 'Max': 0.6533219, 'Peak (Pm)': 0.6533219, 'Peak-to-Peak (Pk)': 1.2685596000000001, 'RMS': 0.1471860602460746, 'Variance': 0.021663736330761102, 'Standard Deviation': 0.1471863409830795, 'Power': 0.021663736330761102, 'Crest Factor': 4.438748471884747, 'Form Factor': 92426997.05641633, 'Pulse Indicator': 410260191.945064, 'Margin': 2.0719719014709344, 'Kurtosis': 2.968632188312844, 'Skewness': -0.005134453231454551}\n", + "{'Mean': -2.47821254392403e-08, 'Max': 1.001901, 'Peak (Pm)': 1.001901, 'Peak-to-Peak (Pk)': 1.8490419, 'RMS': 0.19846256347765465, 'Variance': 0.03938738910212148, 'Standard Deviation': 0.19846294201747922, 'Power': 0.0393873891021221, 'Crest Factor': 5.048312298519747, 'Form Factor': -8008294.68659725, 'Pulse Indicator': -40428372.55651924, 'Margin': 2.736851348421886, 'Kurtosis': 3.0049833880728696, 'Skewness': 0.00472936527535124}\n", + "{'Mean': 1.1718091881137134e-08, 'Max': 0.6872381, 'Peak (Pm)': 0.764375, 'Peak-to-Peak (Pk)': 1.4516130999999999, 'RMS': 0.16163067307431705, 'Variance': 0.026124474478456623, 'Standard Deviation': 0.161630981362418, 'Power': 0.02612447447845676, 'Crest Factor': 4.729145684176814, 'Form Factor': 13793258.724528132, 'Pulse Indicator': 65230329.9678364, 'Margin': 2.3146302669231273, 'Kurtosis': 3.018968361591216, 'Skewness': -0.0027038961477170074}\n", + "{'Mean': 4.483916744688538e-09, 'Max': 0.5636284, 'Peak (Pm)': 0.6170025, 'Peak-to-Peak (Pk)': 1.1806309000000001, 'RMS': 0.13617995217916362, 'Variance': 0.018544979375519265, 'Standard Deviation': 0.1361802119235431, 'Power': 0.01854497937551929, 'Crest Factor': 4.530788050125378, 'Form Factor': 30370758.409035303, 'Pulse Indicator': 137603469.27290198, 'Margin': 2.033717161471145, 'Kurtosis': 2.9918743365839853, 'Skewness': -0.0004150140042344471}\n", + "{'Mean': 2.9766394349442996e-09, 'Max': 0.5311777, 'Peak (Pm)': 0.5506368, 'Peak-to-Peak (Pk)': 1.0818145000000001, 'RMS': 0.12818522987371672, 'Variance': 0.01643145315777759, 'Standard Deviation': 0.12818547436927183, 'Power': 0.0164314531577776, 'Crest Factor': 4.29563375236341, 'Form Factor': 43063741.06614474, 'Pulse Indicator': 184986059.62676963, 'Margin': 1.8701294186586008, 'Kurtosis': 2.9729630742257265, 'Skewness': -0.0017016004702273704}\n", + "{'Mean': -1.7561047037294235e-08, 'Max': 0.7885605, 'Peak (Pm)': 0.7885605, 'Peak-to-Peak (Pk)': 1.5711632, 'RMS': 0.1717757508437296, 'Variance': 0.029506908577926764, 'Standard Deviation': 0.17177607848215945, 'Power': 0.02950690857792707, 'Crest Factor': 4.590639226588979, 'Form Factor': -9781634.914987188, 'Pulse Indicator': -44903956.94091254, 'Margin': 2.313529340377086, 'Kurtosis': 2.999345507398793, 'Skewness': -0.0039902823350783535}\n", + "{'Mean': -7.485887050165297e-09, 'Max': 0.8665391, 'Peak (Pm)': 0.8665391, 'Peak-to-Peak (Pk)': 1.6968147, 'RMS': 0.19506420041417172, 'Variance': 0.03805004228322011, 'Standard Deviation': 0.19506457247209133, 'Power': 0.038050042283220155, 'Crest Factor': 4.442327696010408, 'Form Factor': -26057593.322873402, 'Pulse Indicator': -115756368.50957641, 'Margin': 2.385612230408672, 'Kurtosis': 2.9914497228644032, 'Skewness': -0.006119251854077776}\n", + "{'Mean': -1.065039840858949e-09, 'Max': 0.7413595, 'Peak (Pm)': 0.7413595, 'Peak-to-Peak (Pk)': 1.428194, 'RMS': 0.1555196869879253, 'Variance': 0.02418637304082225, 'Standard Deviation': 0.15551998362016786, 'Power': 0.024186373040822256, 'Crest Factor': 4.766981688032589, 'Form Factor': -146022412.51604208, 'Pulse Indicator': -696086166.5063134, 'Margin': 2.2912655142745573, 'Kurtosis': 3.0331285787830486, 'Skewness': -0.013338525795229992}\n", + "{'Mean': 2.033986356306842e-08, 'Max': 0.5774453, 'Peak (Pm)': 0.6074951, 'Peak-to-Peak (Pk)': 1.1849404, 'RMS': 0.13797500828702497, 'Variance': 0.019037102911804195, 'Standard Deviation': 0.1379752714552237, 'Power': 0.019037102911804608, 'Crest Factor': 4.402935774689337, 'Form Factor': 6783477.571479364, 'Pulse Indicator': 29867216.076269235, 'Margin': 1.9889851026106096, 'Kurtosis': 2.986310918941125, 'Skewness': 0.006731218798193905}\n" + ] + } + ], + "source": [ + "data_dir = \"D:/thesis/data/converted/raw\"\n", + "# Extract features\n", + "df1 = build_features(data_dir, sensor=1, verbose=True)\n", + "df2 = build_features(data_dir, sensor=2, verbose=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
MeanMaxPeak (Pm)Peak-to-Peak (Pk)RMSVarianceStandard DeviationPowerCrest FactorForm FactorPulse IndicatorMarginKurtosisSkewnesslabelfilename
04.935794e-090.5858290.6626311.2484590.1362700.0185700.1362700.0185704.8626222.760857e+071.342500e+082.1849543.0229620.0012961D1_TEST01_01.csv
11.067043e-070.7143210.7143211.2992980.1455720.0211910.1455730.0211914.9069771.364261e+066.694397e+062.2755542.9896060.0016701D1_TEST02_01.csv
21.970669e-080.7278730.7278731.4333740.1650070.0272270.1650070.0272274.4111658.373141e+063.693530e+072.1792802.981290-0.0069391D1_TEST03_01.csv
34.640080e-080.6375690.6375691.1512300.1209080.0146190.1209080.0146195.2731752.605731e+061.374047e+072.2269642.982686-0.0044221D1_TEST04_01.csv
42.748839e-080.5571430.5852441.1423870.1314400.0172770.1314410.0172774.4525494.781666e+062.129060e+071.9649873.015813-0.0006591D1_TEST05_01.csv
\n", + "
" + ], + "text/plain": [ + " Mean Max Peak (Pm) Peak-to-Peak (Pk) RMS Variance \\\n", + "0 4.935794e-09 0.585829 0.662631 1.248459 0.136270 0.018570 \n", + "1 1.067043e-07 0.714321 0.714321 1.299298 0.145572 0.021191 \n", + "2 1.970669e-08 0.727873 0.727873 1.433374 0.165007 0.027227 \n", + "3 4.640080e-08 0.637569 0.637569 1.151230 0.120908 0.014619 \n", + "4 2.748839e-08 0.557143 0.585244 1.142387 0.131440 0.017277 \n", + "\n", + " Standard Deviation Power Crest Factor Form Factor Pulse Indicator \\\n", + "0 0.136270 0.018570 4.862622 2.760857e+07 1.342500e+08 \n", + "1 0.145573 0.021191 4.906977 1.364261e+06 6.694397e+06 \n", + "2 0.165007 0.027227 4.411165 8.373141e+06 3.693530e+07 \n", + "3 0.120908 0.014619 5.273175 2.605731e+06 1.374047e+07 \n", + "4 0.131441 0.017277 4.452549 4.781666e+06 2.129060e+07 \n", + "\n", + " Margin Kurtosis Skewness label filename \n", + "0 2.184954 3.022962 0.001296 1 D1_TEST01_01.csv \n", + "1 2.275554 2.989606 0.001670 1 D1_TEST02_01.csv \n", + "2 2.179280 2.981290 -0.006939 1 D1_TEST03_01.csv \n", + "3 2.226964 2.982686 -0.004422 1 D1_TEST04_01.csv \n", + "4 1.964987 3.015813 -0.000659 1 D1_TEST05_01.csv " + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
MeanMaxPeak (Pm)Peak-to-Peak (Pk)RMSVarianceStandard DeviationPowerCrest FactorForm FactorPulse IndicatorMarginKurtosisSkewnesslabelfilename
0-1.486070e-080.5918150.5918151.1695820.1273110.0162080.1273110.0162084.648594-8.566929e+06-3.982418e+072.0169393.0242010.0074251D1_TEST1_02.csv
1-1.724184e-080.6988730.6988731.3169400.1422860.0202450.1422870.0202454.911735-8.252383e+06-4.053352e+072.2528933.0061120.0020461D1_TEST2_02.csv
2-4.119709e-090.9292530.9292531.7662970.1783720.0318170.1783730.0318175.209621-4.329735e+07-2.255628e+082.6794073.059552-0.0096421D1_TEST3_02.csv
3-1.193488e-080.7075270.7552281.4627550.1593100.0253800.1593110.0253804.740612-1.334829e+07-6.327906e+072.3013732.9869040.0143601D1_TEST4_02.csv
47.395536e-090.6920150.6920151.3443710.1412840.0199610.1412850.0199614.8980281.910400e+079.357193e+072.2367252.9968040.0034721D1_TEST5_02.csv
\n", + "
" + ], + "text/plain": [ + " Mean Max Peak (Pm) Peak-to-Peak (Pk) RMS Variance \\\n", + "0 -1.486070e-08 0.591815 0.591815 1.169582 0.127311 0.016208 \n", + "1 -1.724184e-08 0.698873 0.698873 1.316940 0.142286 0.020245 \n", + "2 -4.119709e-09 0.929253 0.929253 1.766297 0.178372 0.031817 \n", + "3 -1.193488e-08 0.707527 0.755228 1.462755 0.159310 0.025380 \n", + "4 7.395536e-09 0.692015 0.692015 1.344371 0.141284 0.019961 \n", + "\n", + " Standard Deviation Power Crest Factor Form Factor Pulse Indicator \\\n", + "0 0.127311 0.016208 4.648594 -8.566929e+06 -3.982418e+07 \n", + "1 0.142287 0.020245 4.911735 -8.252383e+06 -4.053352e+07 \n", + "2 0.178373 0.031817 5.209621 -4.329735e+07 -2.255628e+08 \n", + "3 0.159311 0.025380 4.740612 -1.334829e+07 -6.327906e+07 \n", + "4 0.141285 0.019961 4.898028 1.910400e+07 9.357193e+07 \n", + "\n", + " Margin Kurtosis Skewness label filename \n", + "0 2.016939 3.024201 0.007425 1 D1_TEST1_02.csv \n", + "1 2.252893 3.006112 0.002046 1 D1_TEST2_02.csv \n", + "2 2.679407 3.059552 -0.009642 1 D1_TEST3_02.csv \n", + "3 2.301373 2.986904 0.014360 1 D1_TEST4_02.csv \n", + "4 2.236725 2.996804 0.003472 1 D1_TEST5_02.csv " + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### Perform division" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Mean_relMax_relPeak (Pm)_relPeak-to-Peak (Pk)_relRMS_relVariance_relStandard Deviation_relPower_relCrest Factor_relForm Factor_relPulse Indicator_relMargin_relKurtosis_relSkewness_rellabel
0-3.0108021.0102190.8931300.9368200.9342510.8728250.9342510.8728250.955985-0.310300-0.2966420.9231041.0004105.7302421
1-0.1615850.9783730.9783731.0135780.9774260.9553610.9774260.9553611.000970-6.048977-6.0548420.9900421.0055211.2252401
2-0.2090511.2766701.2766701.2322651.0810001.1685611.0810001.1685611.181008-5.170981-6.1069701.2294921.0262511.3895981
3-0.2572131.1097261.1845431.2706021.3176151.7361111.3176151.7361110.899005-5.122667-4.6053041.0334131.001414-3.2472221
40.2690421.2420781.1824371.1768091.0748941.1553961.0748941.1553961.1000503.9952614.3949871.1382900.993697-5.2691991
50.7479550.7879030.7455020.7659610.8258810.6820800.8258810.6820800.9026741.1041860.9967200.8192050.983766-0.7449812
6-0.5054310.8654690.8661020.8657990.8609950.7413120.8609950.7413121.005932-1.703485-1.7135900.9354711.009325-3.8392742
7-1.1831061.0297450.9837040.9609190.8991490.8084690.8991490.8084691.094039-0.759990-0.8314591.0371681.0055160.1346292
80.1021611.0735970.9463000.9566261.0797901.1659461.0797901.1659460.87637510.5694519.2627990.9097510.993170-0.0693322
91.5264430.9438070.9438070.9380310.9422850.8879010.9422850.8879011.0016140.6173080.6183050.9706930.991134-0.9688852
10-2.0135540.7477160.7995130.7906930.7565460.5723620.7565460.5723621.056794-0.375727-0.3970660.9196291.00362926.4902163
11-0.2204740.7882980.7882980.8176860.8694240.7558980.8694240.7558980.906690-3.943428-3.5754670.8470561.001867-0.5091323
123.2077811.2611041.2611041.2060271.2208381.4904461.2208381.4904461.0329820.3805870.3931391.1418870.9945941.0536083
131.2847380.9630711.0711681.0282680.9972750.9945570.9972750.9945571.0740950.7762480.8337641.0733521.006766-0.4380873
14-0.1433370.8629290.8239380.8421030.8904890.7929710.8904890.7929710.925265-6.212558-5.7482610.8733930.9972220.1425213
150.1914380.7136770.7398220.7410780.7583740.5751320.7583740.5751320.9755373.9614553.8645440.8495690.9941140.0914644
16-1.3581740.9595860.9595860.9667430.9430460.8893360.9430460.8893361.017539-0.694348-0.7065270.9865920.990509-4.1798304
170.8310661.0826401.0414631.0394381.1090321.2299521.1090321.2299520.9390741.3344691.2531660.9890881.0023340.5117344
18-0.7710051.1349371.1349371.1108101.0828711.1726091.0828711.1726091.048082-1.404492-1.4720221.0930271.0128154.1899574
19-0.4256980.8657990.9108550.8948810.8874390.7875480.8874390.7875481.026386-2.084668-2.1396730.9667950.996003-1.1408824
\n", + "
" + ], + "text/plain": [ + " Mean_rel Max_rel Peak (Pm)_rel Peak-to-Peak (Pk)_rel RMS_rel \\\n", + "0 -3.010802 1.010219 0.893130 0.936820 0.934251 \n", + "1 -0.161585 0.978373 0.978373 1.013578 0.977426 \n", + "2 -0.209051 1.276670 1.276670 1.232265 1.081000 \n", + "3 -0.257213 1.109726 1.184543 1.270602 1.317615 \n", + "4 0.269042 1.242078 1.182437 1.176809 1.074894 \n", + "5 0.747955 0.787903 0.745502 0.765961 0.825881 \n", + "6 -0.505431 0.865469 0.866102 0.865799 0.860995 \n", + "7 -1.183106 1.029745 0.983704 0.960919 0.899149 \n", + "8 0.102161 1.073597 0.946300 0.956626 1.079790 \n", + "9 1.526443 0.943807 0.943807 0.938031 0.942285 \n", + "10 -2.013554 0.747716 0.799513 0.790693 0.756546 \n", + "11 -0.220474 0.788298 0.788298 0.817686 0.869424 \n", + "12 3.207781 1.261104 1.261104 1.206027 1.220838 \n", + "13 1.284738 0.963071 1.071168 1.028268 0.997275 \n", + "14 -0.143337 0.862929 0.823938 0.842103 0.890489 \n", + "15 0.191438 0.713677 0.739822 0.741078 0.758374 \n", + "16 -1.358174 0.959586 0.959586 0.966743 0.943046 \n", + "17 0.831066 1.082640 1.041463 1.039438 1.109032 \n", + "18 -0.771005 1.134937 1.134937 1.110810 1.082871 \n", + "19 -0.425698 0.865799 0.910855 0.894881 0.887439 \n", + "\n", + " Variance_rel Standard Deviation_rel Power_rel Crest Factor_rel \\\n", + "0 0.872825 0.934251 0.872825 0.955985 \n", + "1 0.955361 0.977426 0.955361 1.000970 \n", + "2 1.168561 1.081000 1.168561 1.181008 \n", + "3 1.736111 1.317615 1.736111 0.899005 \n", + "4 1.155396 1.074894 1.155396 1.100050 \n", + "5 0.682080 0.825881 0.682080 0.902674 \n", + "6 0.741312 0.860995 0.741312 1.005932 \n", + "7 0.808469 0.899149 0.808469 1.094039 \n", + "8 1.165946 1.079790 1.165946 0.876375 \n", + "9 0.887901 0.942285 0.887901 1.001614 \n", + "10 0.572362 0.756546 0.572362 1.056794 \n", + "11 0.755898 0.869424 0.755898 0.906690 \n", + "12 1.490446 1.220838 1.490446 1.032982 \n", + "13 0.994557 0.997275 0.994557 1.074095 \n", + "14 0.792971 0.890489 0.792971 0.925265 \n", + "15 0.575132 0.758374 0.575132 0.975537 \n", + "16 0.889336 0.943046 0.889336 1.017539 \n", + "17 1.229952 1.109032 1.229952 0.939074 \n", + "18 1.172609 1.082871 1.172609 1.048082 \n", + "19 0.787548 0.887439 0.787548 1.026386 \n", + "\n", + " Form Factor_rel Pulse Indicator_rel Margin_rel Kurtosis_rel \\\n", + "0 -0.310300 -0.296642 0.923104 1.000410 \n", + "1 -6.048977 -6.054842 0.990042 1.005521 \n", + "2 -5.170981 -6.106970 1.229492 1.026251 \n", + "3 -5.122667 -4.605304 1.033413 1.001414 \n", + "4 3.995261 4.394987 1.138290 0.993697 \n", + "5 1.104186 0.996720 0.819205 0.983766 \n", + "6 -1.703485 -1.713590 0.935471 1.009325 \n", + "7 -0.759990 -0.831459 1.037168 1.005516 \n", + "8 10.569451 9.262799 0.909751 0.993170 \n", + "9 0.617308 0.618305 0.970693 0.991134 \n", + "10 -0.375727 -0.397066 0.919629 1.003629 \n", + "11 -3.943428 -3.575467 0.847056 1.001867 \n", + "12 0.380587 0.393139 1.141887 0.994594 \n", + "13 0.776248 0.833764 1.073352 1.006766 \n", + "14 -6.212558 -5.748261 0.873393 0.997222 \n", + "15 3.961455 3.864544 0.849569 0.994114 \n", + "16 -0.694348 -0.706527 0.986592 0.990509 \n", + "17 1.334469 1.253166 0.989088 1.002334 \n", + "18 -1.404492 -1.472022 1.093027 1.012815 \n", + "19 -2.084668 -2.139673 0.966795 0.996003 \n", + "\n", + " Skewness_rel label \n", + "0 5.730242 1 \n", + "1 1.225240 1 \n", + "2 1.389598 1 \n", + "3 -3.247222 1 \n", + "4 -5.269199 1 \n", + "5 -0.744981 2 \n", + "6 -3.839274 2 \n", + "7 0.134629 2 \n", + "8 -0.069332 2 \n", + "9 -0.968885 2 \n", + "10 26.490216 3 \n", + "11 -0.509132 3 \n", + "12 1.053608 3 \n", + "13 -0.438087 3 \n", + "14 0.142521 3 \n", + "15 0.091464 4 \n", + "16 -4.179830 4 \n", + "17 0.511734 4 \n", + "18 4.189957 4 \n", + "19 -1.140882 4 " + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Separate the label column\n", + "label_column = df1.iloc[:, -2]\n", + "\n", + "# Perform the relative value by operate division on all the features\n", + "df_relative = df2.iloc[:, :-2] / df1.iloc[:, :-2]\n", + "\n", + "# Add the label column back to the resulting DataFrame\n", + "df_relative['label'] = label_column\n", + "\n", + "# Append a string to all column names\n", + "suffix = '_rel'\n", + "df_relative.columns = [col + suffix if col != 'label' else col for col in df_relative.columns]\n", + "\n", + "# Display the first 5 rows of the resulting DataFrame\n", + "df_relative" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Subsetting DataFrame to see the pair plots due to many features" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "\n", + "# Assuming your DataFrame is named 'df'\n", + "\n", + "# Subsetting the DataFrame to include only the first 3 columns and the label\n", + "subset_df = df_relative[['Mean_rel', 'Max_rel', 'Peak (Pm)_rel', 'label']]\n", + "\n", + "# Plotting the pairplot\n", + "g = sns.pairplot(subset_df, hue='label', diag_kind='kde')\n", + "\n", + "# Adjusting the axis limits\n", + "for ax in g.axes.flatten():\n", + " ax.set_xlim(-10, 10) # Adjust these limits based on your data\n", + " ax.set_ylim(-10, 10) # Adjust these limits based on your data\n", + "\n", + "plt.show()" + ] } ], "metadata": {