Add Audio_classification_ML project

Audi_Classification_ML/.ipynb_checkpoints/predict-checkpoint.ipynb

@@ -0,0 +1,166 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import numpy as np\n",
+    "import pickle\n",
+    "from tqdm import tqdm\n",
+    "from scipy.io import wavfile\n",
+    "from python_speech_features import mfcc\n",
+    "from keras.models import load_model\n",
+    "import pandas as pd\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def build_predictions(audio_dir):\n",
+    "    \"\"\"\n",
+    "    Function which takes an audio directory as input (which should contain a series of wav files), \n",
+    "    and returns true labels, predicted labels, and a dictionary of probabilites corrosponding to labels\n",
+    "    for each file.\n",
+    "    \n",
+    "    Arguments:\n",
+    "    ----------\n",
+    "    audio_dir : location of folder containing wav files\n",
+    "    \n",
+    "    Returns:\n",
+    "    --------\n",
+    "    y_true : A list containing the true labels for each file\n",
+    "    \n",
+    "    y_pred : A list contianing predicted labels for each file\n",
+    "    \n",
+    "    fn_prob : A dict containing the probabilities  of each label for each file\n",
+    "    \n",
+    "    \"\"\"\n",
+    "    \n",
+    "    y_true = [] # List containing actual labels\n",
+    "    y_pred = [] # List containing predicted labels\n",
+    "    fn_prob = {} # Dict containing probability of given label\n",
+    "    \n",
+    "    print('Extracting features from audio')\n",
+    "    for fn in tqdm(os.listdir(audio_dir)):\n",
+    "        rate, wav = wavfile.read(os.path.join(audio_dir, fn))\n",
+    "        label = fn2class[fn]\n",
+    "        c = classes.index(label) # Grab true label\n",
+    "        y_prob = []\n",
+    "        \n",
+    "        # Step through audio file in chunks\n",
+    "        for i in range(0, wav.shape[0]-config.step, config.step):\n",
+    "            sample = wav[i:i+config.step] # Take chunk of audio file\n",
+    "            x = mfcc(sample, rate, numcep=config.nfeat,\n",
+    "                     nfilt=config.nfilt, nfft = config.nfft) # Take mfcc of our sample\n",
+    "            x = (x - config.min) / (config.max - config.min) # Normalize based on max/min\n",
+    "            \n",
+    "            if config.mode == 'conv':\n",
+    "                x = x.reshape(1, x.shape[0], x.shape[1], 1)\n",
+    "            elif config.mode == 'time':\n",
+    "                x = np.expand_dims(x, axis=0)\n",
+    "            y_hat = model.predict(x)\n",
+    "            y_prob.append(y_hat)\n",
+    "            y_pred.append(np.argmax(y_hat))\n",
+    "            y_true.append(c)\n",
+    "            \n",
+    "        fn_prob[fn] = np.mean(y_prob, axis=0).flatten()\n",
+    "        \n",
+    "    return y_true, y_pred, fn_prob"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Extracting features from audio\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 300/300 [01:08<00:00,  4.36it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('data/instruments.csv')\n",
+    "classes = list(np.unique(df.label))\n",
+    "fn2class = dict(zip(df.fname, df.label))\n",
+    "p_path = os.path.join('pickles', 'conv.p')\n",
+    "\n",
+    "with open(p_path, 'rb') as handle:\n",
+    "    config = pickle.load(handle)\n",
+    "    \n",
+    "model = load_model(config.model_path)\n",
+    "\n",
+    "y_true, y_pred, fn_prob = build_predictions('data/clean')\n",
+    "\n",
+    "\n",
+    "acc_score = accuracy_score(y_true=y_true, y_pred=y_pred)\n",
+    "\n",
+    "y_probs = []\n",
+    "# Iterate through each sample\n",
+    "for i, row in df.iterrows():\n",
+    "    y_prob = fn_prob[row.fname] # Grab probabilities for each class for the sample\n",
+    "    y_probs.append(y_prob)\n",
+    "    for c, p in zip(classes, y_prob):\n",
+    "        df.at[i, c] = p # add probabilities to dataframe\n",
+    "    \n",
+    "y_pred = [classes[np.argmax(y)] for y in y_probs]\n",
+    "df['y_pred'] = y_pred\n",
+    "\n",
+    "# Save as csv file which now contains all samples along with true label, predicted label, and probabilities for each class\n",
+    "df.to_csv('predictions.csv', index=False) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Audi_Classification_ML/cfg.py

@@ -0,0 +1,12 @@
+import os
+
+class config:
+    def __init__(self, mode='conv', nfilt=26, nfeat=13, nfft=512, rate=16000):
+        self.mode = mode
+        self.nfilt = nfilt
+        self.nfeat = nfeat
+        self.nfft = nfft
+        self.rate = rate
+        self.step = int(rate/10)
+        self.model_path = os.path.join('models', mode + '.model')
+        self.p_path = os.path.join('pickles', mode + '.p')