Skip to content

Instantly share code, notes, and snippets.

@angelormrl

angelormrl/dataset_generation.ipynb

Created May 12, 2019 21:18
Show Gist options
  • Save angelormrl/09bdad0b20b05b721198341c10d94d54 to your computer and use it in GitHub Desktop.
Save angelormrl/09bdad0b20b05b721198341c10d94d54 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
dataset_generation.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 74,
"metadata": {},
"outputs": [],
"source": [
"## ================ INCLUDES ================ ##\n",
"\n",
"# control and rendering of vst plugins\n",
"import librenderman as rm\n",
"\n",
"# mel-frequency cepstrum extraction\n",
"import librosa\n",
"\n",
"# math operations\n",
"import numpy as np\n",
"\n",
"# retries list of filenames in a directory\n",
"from os import listdir\n",
"\n",
"# clears output and will allow us to create a progress indicator\n",
"from IPython.display import clear_output"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
"## ================ FUNCTION DEFINITIONS ================ ##\n",
"\n",
"\n",
"# returns means mfcc values across render duration\n",
"def mean_mfccs(note, velocity, n_mfcc):\n",
"\n",
" engine.render_patch(note, velocity, 3.0, 4.0)\n",
"\n",
" audio_frames = np.asarray(engine.get_audio_frames())\n",
" \n",
" mfccs = librosa.feature.mfcc(y=audio_frames, sr=44100, hop_length=512, n_mfcc=n_mfcc)\n",
" \n",
" means = [np.mean(coefficient) for coefficient in mfccs]\n",
" \n",
" return means\n",
"\n",
"\n",
"def indicate_progress(current, total, label, clear=True):\n",
" \n",
" progress = str(current) + \"/\" + str(total) + \" \" + label\n",
" \n",
" if(clear):\n",
" \n",
" clear_output(wait = True)\n",
" \n",
" return progress\n",
"\n",
"\n",
"# creates input data from patch at all midi notes and for some velocities\n",
"def patch_examples(path, file_num, total_files):\n",
" \n",
" data = []\n",
" \n",
" velocities = [0, 63, 127]\n",
" \n",
" n_notes = 128\n",
" \n",
" n_mfcc = 20\n",
" \n",
" engine.load_preset(path)\n",
" \n",
" for note in range(n_notes):\n",
" \n",
" for i in range(len(velocities)):\n",
" \n",
" means = mean_mfccs(note, velocities[i], n_mfcc)\n",
" \n",
" data.append(means)\n",
" \n",
" current = i + note * len(velocities)\n",
" \n",
" total = n_notes * len(velocities)\n",
" \n",
" line_1 = indicate_progress(current, total, \"examples extracted from current patch!\")\n",
" \n",
" line_2 = indicate_progress(file_num, total_files, \"files searched!\", clear = False)\n",
" \n",
" print line_1 + \"\\n\" + line_2\n",
" \n",
" return data\n",
"\n",
"\n",
"# generates input and target data from each preset in a directory\n",
"def generate_dataset(load_path, patch_types):\n",
" \n",
" X = []\n",
" y = []\n",
" \n",
" file_names = os.listdir(load_path)\n",
" \n",
" for i in range(len(file_names)):\n",
" \n",
" for j in range(len(patch_types)):\n",
" \n",
" if(patch_types[j] in file_names[i]):\n",
" \n",
" target_index = j\n",
" \n",
" concatenated_path = load_path + file_names[i]\n",
" \n",
" data = patch_examples(concatenated_path, i, len(file_names))\n",
" \n",
" targets = np.full(len(data), target_index)\n",
" \n",
" X.extend(data)\n",
" \n",
" y.extend(targets)\n",
" \n",
" clear_output()\n",
" \n",
" print(\"*** dataset generated! ***\")\n",
" \n",
" return X, y"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"*** plugin loaded succesfully! ***\n"
]
}
],
"source": [
"## ================ SETUP ================ ##\n",
"\n",
"\n",
"engine = rm.RenderEngine(44100, 512)\n",
"\n",
"plugin_path = '/Library/Audio/Plug-Ins/VST/KORG/MonoPoly.vst'\n",
"\n",
"if engine.load_plugin(plugin_path):\n",
" \n",
" print '*** plugin loaded succesfully! ***'\n",
" \n",
"load_path = \"/Users/angelorussell/Downloads/monopoly_presets\"\n",
"\n",
"# list of all file names in a directory\n",
"files = listdir(load_path)\n",
"\n",
"# titles of each class as substrings to be found in file name strings\n",
"patch_types = ['Bass', 'Pad', 'Lead']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"110/384 examples extracted from current patch!\n",
"43/86 files searched!\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-77-d432cb546adc>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgenerate_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mload_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpatch_types\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m<ipython-input-75-c8588dba7b32>\u001b[0m in \u001b[0;36mgenerate_dataset\u001b[0;34m(load_path, patch_types)\u001b[0m\n\u001b[1;32m 79\u001b[0m \u001b[0mconcatenated_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_path\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mfile_names\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 80\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 81\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpatch_examples\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconcatenated_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile_names\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 82\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 83\u001b[0m \u001b[0mtargets\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfull\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget_index\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-75-c8588dba7b32>\u001b[0m in \u001b[0;36mpatch_examples\u001b[0;34m(path, file_num, total_files)\u001b[0m\n\u001b[1;32m 44\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvelocities\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 45\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 46\u001b[0;31m \u001b[0mmeans\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmean_mfccs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnote\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvelocities\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_mfcc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 47\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 48\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmeans\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-75-c8588dba7b32>\u001b[0m in \u001b[0;36mmean_mfccs\u001b[0;34m(note, velocity, n_mfcc)\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mmean_mfccs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnote\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvelocity\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_mfcc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 7\u001b[0;31m \u001b[0mengine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrender_patch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnote\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvelocity\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3.0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m4.0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 8\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0maudio_frames\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mengine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_audio_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"## ================ GENERATE DATA ================ ##\n",
"\n",
"\n",
"X, y = generate_dataset(load_path, patch_types)"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"12288 samples in dataset.\n",
"\n",
"6912 Bass patch examples.\n",
"\n",
"1536 Pad patch examples.\n",
"\n",
"3840 Lead patch examples.\n"
]
}
],
"source": [
"## ================ DATA DESCRIPTION ================ ##\n",
"\n",
"\n",
"print str(len(X)) + \" samples in dataset.\"\n",
"\n",
"counts = np.bincount(y)\n",
"\n",
"for i in range(len(patch_types)):\n",
" \n",
" print \"\\n\" + str(counts[i]) + \" \" + patch_types[i] + \" patch examples.\""
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[-313.54278582 106.84572427 -25.429015 30.08328347 -5.32818981\n",
" 0.75808556 6.27498085 5.00479316 6.84010424 5.36592338\n",
" 4.11957381 4.11169945 5.2659075 4.35764479 4.77529445\n",
" 3.490972 3.73166278 3.76179877 4.60956964 3.5109039 ]\n",
"[-313.37309742 106.8237494 -25.3588622 30.12473205 -5.3326032\n",
" 0.74215542 6.28365495 4.96143867 6.86089893 5.36243742\n",
" 4.06786453 4.11844223 5.27006533 4.30207667 4.79911608\n",
" 3.49508771 3.74554194 3.77495628 4.62650527 3.51819289]\n",
"[-313.37724166 106.76919212 -25.37837269 30.10655499 -5.3370088\n",
" 0.72270189 6.28541453 4.9766507 6.86226075 5.38604629\n",
" 4.08843162 4.10583529 5.27744382 4.31883936 4.80139762\n",
" 3.49578531 3.72388733 3.76674386 4.62119455 3.49729737]\n"
]
}
],
"source": [
"## ================ DATA ANALYSIS ================ ##\n",
"\n",
"n_mfcc = 20\n",
"\n",
"totals = np.zeros([len(patch_types), n_mfcc])\n",
"\n",
"for i in range(len(X)):\n",
" \n",
" for j in range(len(X[0])):\n",
" \n",
" totals[y[i]][j] += X[i][j]\n",
" \n",
"means = [totals[i] / counts[i] for i in range(len(patch_types))]\n",
"\n",
"for class_mean in means:\n",
" \n",
" print class_mean"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"## ================ NETWOR TRAINING ================ ##\n",
"\n",
"\n",
"from sklearn import datasets\n",
"from sklearn.neural_network import MLPClassifier\n",
"\n",
"\n",
"def normalize_data(x):\n",
" data = zeros(shape(x))\n",
" for i in range(len(x[0])):\n",
" feature = [example[i] for example in x]\n",
" max_val = np.max(feature)\n",
" min_val = np.min(feature)\n",
" val_range = max_val - min_val\n",
" for j in range(len(x)):\n",
" data[j][i] = (x[j][i] - min_val) / val_range\n",
" return data\n",
"\n",
"\n",
"def accuracy_score(pred, true):\n",
" correct = np.sum(pred==true)\n",
" accuracy = correct/len(pred)\n",
" return accuracy\n",
"\n",
"\n",
"#X = normalize_data(X)\n",
"\n",
"\n",
"X = np.asarray(X)\n",
"\n",
"y = np.asarray(y)\n",
"\n",
"indices = np.random.permutation(len(X))\n",
"\n",
"train, test = indices[200:], indices[:200]\n",
"\n",
"net = MLPClassifier(activation='logistic', solver = 'sgd', hidden_layer_sizes=([100, 4]), learning_rate='invscaling', learning_rate_init=0.01)\n",
"\n",
"net.fit(X[train], y[train])\n",
"\n",
"preds = net.predict(X[test])\n",
"\n",
"accuracy = accuracy_score(preds, y[test])\n",
"print(accuracy)\n",
"print(preds)\n",
"print(y[test])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.14"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment