diff --git a/data_exploration.ipynb b/data_exploration.ipynb index ccedac8..20e095d 100644 --- a/data_exploration.ipynb +++ b/data_exploration.ipynb @@ -2,138 +2,9 @@ "cells": [ { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: get_duration() keyword argument 'filename' has been renamed to 'path' in version 0.10.0.\n", - "\tThis alias will be removed in version 1.0.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n", - "C:\\Users\\chris\\AppData\\Local\\Temp\\ipykernel_24960\\2693969370.py:23: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " df = df.append({'filename': file, 'length': librosa.get_duration(filename=filepath), 'size': os.path.getsize(filepath)}, ignore_index=True)\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Total length of all files: 10116.067625000001 seconds\n", - "Total length of all files: 168.60112708333335 minutes\n", - "Total size of all files: 161858220 bytes\n", - "Average length of all files: 562.0037569444445 seconds\n", - "Average length of all files: 9.366729282407409 minutes\n", - "Average size of all files: 8992123.333333334 bytes\n" - ] - } - ], + "outputs": [], "source": [ "import pandas as pd\n", "import os\n", @@ -223,107 +94,18 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": null, "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", - "
length
count36.000000
mean557.044358
std92.890642
min247.552000
25%581.285750
50%594.606375
75%599.680000
max599.808000
\n", - "
" - ], - "text/plain": [ - " length\n", - "count 36.000000\n", - "mean 557.044358\n", - "std 92.890642\n", - "min 247.552000\n", - "25% 581.285750\n", - "50% 594.606375\n", - "75% 599.680000\n", - "max 599.808000" - ] - }, - "execution_count": 34, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.describe()" ] }, { "cell_type": "code", - "execution_count": 32, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# load csv as dataframe\n", "df_explore = pd.read_csv('CGN_data_exploration.csv')\n",