# HG changeset patch
# User Maria Panteli
# Date 1508071019 -3600
# Node ID edd82eb89b4b4990e9724d5d6bbdfc5f0d09166a
# Parent  2f6e687938e20b91b730dd1a97558549923313f1# Parent  0768d0589e7b054bba51a10ba0e4faf70ebb5dbf
Merge

diff -r 0768d0589e7b -r edd82eb89b4b notebooks/explain_components.ipynb
--- a/notebooks/explain_components.ipynb	Thu Oct 12 13:52:29 2017 +0100
+++ b/notebooks/explain_components.ipynb	Sun Oct 15 13:36:59 2017 +0100
@@ -32,7 +32,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -54,7 +56,9 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -85,6 +89,7 @@
    "cell_type": "code",
    "execution_count": 12,
    "metadata": {
+    "collapsed": false,
     "scrolled": false
    },
    "outputs": [
@@ -251,7 +256,9 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -289,7 +296,9 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -321,7 +330,9 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -389,7 +400,9 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -433,7 +446,9 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -451,7 +466,9 @@
   {
    "cell_type": "code",
    "execution_count": 28,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -472,7 +489,9 @@
   {
    "cell_type": "code",
    "execution_count": 29,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -547,7 +566,9 @@
   {
    "cell_type": "code",
    "execution_count": 30,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -582,7 +603,9 @@
   {
    "cell_type": "code",
    "execution_count": 31,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -622,7 +645,9 @@
   {
    "cell_type": "code",
    "execution_count": 32,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -704,7 +729,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "version": "2.7.11"
   }
  },
  "nbformat": 4,
diff -r 0768d0589e7b -r edd82eb89b4b scripts/add_collection.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scripts/add_collection.py	Sun Oct 15 13:36:59 2017 +0100
@@ -0,0 +1,21 @@
+import numpy as np
+import pandas as pd
+import pickle 
+import os
+
+
+METADATA_FILE = '../../music-outliers/data/metadata.csv'
+#METADATA_FILE = '../data/metadata.csv'
+
+df = pd.read_csv(METADATA_FILE)
+
+collection = []
+for audio in df['Audio']:
+    if 'SampleAudio' in audio:
+        collection.append('Smithsonian Folkways')
+    else:
+        collection.append('British Library')
+collection = np.array(collection)
+df['Collection'] = collection
+
+df.to_csv('../../music-outliers/data/metadata_2.csv', index=False)