{"cells":[{"metadata":{"nbpresent":{"id":"42344751-df85-4fa9-af08-b4bf50b41e05"},"_uuid":"f1663ba4fce0025fb99a54443b79ca6cac6e9752"},"cell_type":"markdown","source":"# Part 2 - Extracting Audio Features\n\nEu Jin Lok\n<br>Kernel post for __[Speech Accent Archive](https://www.kaggle.com/rtatman/speech-accent-archive)__ on Kaggle\n<br>20 January 2019\n\n\n## Introduction \n#### To understand the various features we can extract from audio, and use it to predict gender and accents\n\n\nIn part 2 of this series, I'll introduce the various types of features from audio and we can see how these features differ when we compare between genders and accent types. I'm hoping one of these features will be distinctive enough that we could use it for predictive modelling in the next part. \n\nI would also like to acknowledge 2 people whom I've learnt alot from: \n- __[Jayesh Saita](https://towardsdatascience.com/ok-google-how-to-do-speech-recognition-f77b5d7cbe0b)__, whose blog I really liked and helped me understand audio features and MFCCs in the early stages of my journey   \n- __[Zafarullah Mahmood](https://www.kaggle.com/fizzbuzz/beginner-s-guide-to-audio-data)__, whose Kaggle Kernel basically became the canvas for all audio work that I do at work and outside work. Please do check out his kernels whom I've drawn lots of inspiration from! \n\nThis part 2 kernel will cover quite a few items so I'll provide a brief agenda: \n- [Core concepts in Audio](#core)\n- [Time domain features](#time) \n    - [1. Audio wave](#time)\n- [Frequency domain features](#mfcc)\n    - [2. MFCC](#mfcc)\n    - [3. Log Mel-spectogram](#melspec)\n    - [4. Harmonic-percussive source separation (HPSS)](#hpss)\n    - [5. Chroma](#chroma)\n- [Final thoughts](#final)\n\nAgain, thanks to the awesome Kaggle community, and the broader data science community. Without further ado, lets begin!"},{"metadata":{"nbpresent":{"id":"6b931974-2fc8-4fdc-9f32-a93d21ec08ef"},"trusted":true,"_uuid":"ceae2fd72a471482cd9a27660142e00c3d4a5092","_kg_hide-output":false,"_kg_hide-input":false},"cell_type":"code","source":"import pandas as pd       \nimport os \nimport math \nimport numpy as np\nimport matplotlib.pyplot as plt  \nimport IPython.display as ipd  # To play sound in the notebook\nimport librosa\nimport librosa.display\n!apt install -y ffmpeg\n# os.chdir(\"/kaggle/input/freesound-audio-tagging/audio_train\")\n#os.getcwd()\nos.chdir(\"/kaggle/input/speech-accent-archive/recordings\")\n# print(os.listdir(\"/kaggle/input/freesound-audio-tagging/audio_train/audio_train/\"))\n# print(os.listdir(\"recordings\"))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"2860232f43eddd276da420eebd4e76ac962362e0"},"cell_type":"markdown","source":"------------------------------\nAfter loading the libraries and setting our directory path, we're going to use the two Kentucky accent speakers that we heard from __[Part 1](https://www.kaggle.com/ejlok1/part-1-data-exploration-deep-learning-series)__. Here's another quick replay of how they sound if you've forgotten:"},{"metadata":{"trusted":true,"_uuid":"c74492e1d66d967d0bbe8adc4172e0581be996ac"},"cell_type":"code","source":"# Play female from Kentucky\nfname_f = 'recordings/' + 'english385.mp3'   \nipd.Audio(fname_f)","execution_count":null,"outputs":[]},{"metadata":{"scrolled":true,"trusted":true,"_uuid":"09a86f5f46b2508302cf0d7198366906db0de2cb"},"cell_type":"code","source":"# Play male from Kentucky\nfname_m = 'recordings/' + 'english381.mp3'\nipd.Audio(fname_m)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"66de8fc9a744ed8e1f2818ba929b31d546f85900"},"cell_type":"markdown","source":"<a id=\"core\"></a>\n##  Core concepts in Audio"},{"metadata":{"_uuid":"131b16e2d446d815bd653fff4f46094b2632cb51"},"cell_type":"markdown","source":"Before diving straight to the meaty bits, I'm going to quickly introduce a few key concepts to anyone who's new to audio \n- Duration\n- sampling rate\n- Amplitude \n- Frequency\n\n\n__Duration__ is the length of the audio call in terms of time. \n\n__Sampling rate__ is the number of samples of audio per second, measured in Hz / KHz. This is similar to resolution in images, where the higher the resolution (or more pixels), the clearer it is. A full sampling rate is 44100 Hz (44.1 KHz) but, you don't always need to have it in at 'High Fidelity' format. A more reasonable sampling rate is 22050 Hz (22 KHz), because that is the audible sound to a human. \n\n__Amplitude__ is the fluctuation of the soud wave. The shorter and more frequent the waves are, the higher the pitch or frequency. Plotting the audio by time against amplitute is probably the most intuitive way of understanding the audio. However, its not the only way to represent the data or used as feature. Another equally good way of doing this is to look at it by the frequency domain, which is a nice segway to our final concept. \n\n__Frequency__, the best way of understanding it is through visualising it. Imagining the audio in terms of time is probably the most intutive way of thinking about it. But frequency, although not as intuitive, is actually much more efficient as signal in the frequency domain requires much less computational space for storage. Below is a nice visualisation of how to differentiate the Time vs Frequency domain"},{"metadata":{"_uuid":"8f1d17d0cfe13782b57b587c73a04a44f476f9bf"},"cell_type":"markdown","source":"![Audio%20wave.png](attachment:Audio%20wave.png)\nThe time vs frequency domain sourced from __[here](https://docs.google.com/presentation/d/1zzgNu_HbKL2iPkHS8-qhtDV20QfWt9lC3ZwPVZo8Rw0/pub?start=false&loop=false&delayms=3000&slide=id.g5a7a9806e_0_84)__ ","attachments":{"Audio%20wave.png":{"image/png":"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"}}},{"metadata":{"_uuid":"776aaf7ce1560cfa0e9830c772b636c7cc8acb65"},"cell_type":"markdown","source":"So what we're going to do is use the same audio file but plot the 2 different sampling rates to see how they differ, one at the full 44100 Hz and the other at 6000 Hz. We're also going to down sample them and chop the audio file at 5 seconds just so the differences are more perceptible"},{"metadata":{"_uuid":"a601ec84f26c0ec2fb8b592af1dd0ed3eb5406a5"},"cell_type":"markdown","source":"<a id=\"time\"></a>\n## 1. Audio wave\n\nAudio wave is our first feature. This is of course the first most common form of the data, and is the only time domain feature that I am aware off. Lets use this opportunity to plot the two audio files again at their most native format, which is the wave form. To start off, I'm going to plot them in 3 different sampling rates, at 44kHz, 6kHz and 1000kHz and see how they differ, using the female version of the audio (_fname = english385.mp3_)\n\nNote that I'm only taking the first 5 seconds of audio for illustration purposes."},{"metadata":{"trusted":true,"_uuid":"4c1b1386249cb977337826eebb4027e6751a91cd"},"cell_type":"code","source":"# The full 'high fidelity' sampling rate of 44k \nSAMPLE_RATE = 44100\nfname_f = 'recordings/' + 'english385.mp3' \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5)\n\nplt.figure(figsize=(12, 3))\nplt.figure()\nlibrosa.display.waveplot(y, sr=sr)\nplt.title('Audio sampled at 44100 hrz')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a7cf3597edb62abf2d32818d3caaa4932014922a"},"cell_type":"code","source":"# The very 'low fidelity' sampling rate of 6k \nSAMPLE_RATE = 6000\nfname_f = 'recordings/' + 'english385.mp3' \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5)\n\nplt.figure(figsize=(12, 3))\nplt.figure()\nlibrosa.display.waveplot(y, sr=sr)\nplt.title('Audio sampled at 6000 hrz')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a6a7745ab6d89f8e50d62ae05650688cbf6a6828"},"cell_type":"code","source":"# The very very 'low fidelity' sampling rate of 1k \nSAMPLE_RATE = 1000\nfname_f = 'recordings/' + 'english385.mp3' \ny, sr = librosa.core.load(fname_f, sr=SAMPLE_RATE, duration = 5)\n\nplt.figure(figsize=(12, 3))\nplt.figure()\nlibrosa.display.waveplot(y, sr=sr)\nplt.title('Audio sampled at 1000 hrz')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6843d8c3fd6f51aedd36ebb98b8cb122865a14ca"},"cell_type":"markdown","source":"Note the minor differences between the 44100 Hz and the 6000 Hz? Things start to change once you go down to sampling rate of 1000 Hz, and audio becomes more blurry. Generally 21500 Hz sampling rate is the most common as previously mentioned. And the difference with 44 KHz is very minor. For now, we're going to use a sampling rate of 6000 Hz, to compare the male and female speakers from Kentucky. \n\nSince we've plotted the female version, lets hear the male version now (_fname = english381.mp3_)... at 6000 Hz and chopped at 5 seconds. You can see has some distinctive pattern over the female equivalent"},{"metadata":{"trusted":true,"_uuid":"900b7a550bd34357e6f219fd9bcdc5941909ad52"},"cell_type":"code","source":"# The 'low fidelity' sampling rate of 6k \nSAMPLE_RATE = 6000\nfname_m = 'recordings/' + 'english381.mp3' \ny, sr = librosa.load(fname_m, sr=SAMPLE_RATE, duration = 5)\n\nplt.figure(figsize=(12, 3))\nplt.figure()\nlibrosa.display.waveplot(y, sr=sr)\nplt.title('Audio sampled at 6000 hrz')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"There's some distinctive differences in the wave pattern between male and female but we don't really know what information it is capturing. It could be capturing the supposedly higher pitch voice that female has, or it could just be the different accent pronoucation between the 2 speakers. And that's why we use machine learning right? \n\nI suppose if there's one thing that's clear between the 2 audio file is that, the male speaker seems to have a more consistent pitch overtime versus the female counter part, whom we can clearly see an obvious huge spike in amplitude. "},{"metadata":{"_uuid":"27de424bb4cc554ce4f4d2c7557dd3f210622911"},"cell_type":"markdown","source":"<a id=\"mfcc\"></a>\n## 2. MFCC\nNow moving into the Frequency domain feature, this is my favourite which is MFCC, short for Mel-Frequency Cepstral Coefficient. MFCC is a sentence, is a \"representation\" of the vocal tract that produces the sound. Think of it like an x-ray of your mouth. The processing steps to get MFCC is quite lengthy but  in my simple mind, that is how I understand it, or explain to my wife. A more indepth and technical explanation can be found __[here](http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/)__. \n\nSo we're now going to compare males and female voices via the MFCC coefficient plots"},{"metadata":{"trusted":true,"_uuid":"ee3c2e2ecf6e383624795a6c858cbf8a9e8e9d09"},"cell_type":"code","source":"# MFCC for female \nSAMPLE_RATE = 22050\nfname_f = 'recordings/' + 'english385.mp3'  \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5) # Chop audio at 5 secs... \nmfcc = librosa.feature.mfcc(y=y, sr=SAMPLE_RATE, n_mfcc = 5) # 5 MFCC components\n\nplt.figure(figsize=(12, 6))\nplt.subplot(3,1,1)\nlibrosa.display.specshow(mfcc)\nplt.ylabel('MFCC')\nplt.colorbar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b1c8bc39cf36151813c2711f4093d04cba809085"},"cell_type":"code","source":"# MFCC for male  \nSAMPLE_RATE = 22050\nfname_m = 'recordings/' + 'english381.mp3'  \ny, sr = librosa.load(fname_m, sr=SAMPLE_RATE, duration = 5)\nmfcc = librosa.feature.mfcc(y=y, sr=SAMPLE_RATE, n_mfcc = 5)\n\nplt.figure(figsize=(12, 6))\nplt.subplot(3,1,1)\nlibrosa.display.specshow(mfcc)\nplt.ylabel('MFCC')\nplt.colorbar()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b4ec7d43ba9a1f09a92c25e59e329fc2dd284dec"},"cell_type":"markdown","source":"Notice the difference? Seems like there could be something here. Generally in practice one would use not just the entire duration of the audio, but also set a higher number of MFCC components, usually between 20 and 40. Here I used 5 MFCC components just so its easier to visualise the difference. We will use the optimal settings later in the actual modelling component. In my limited experience so far with audio, I have gotten the most success in using MFCC as the feature choice for supervise learning"},{"metadata":{"_uuid":"31ddb0bc02646fe488659a1fbae4eade0472e6f8"},"cell_type":"markdown","source":"<a id=\"melspec\"></a>\n## 3. Log Mel-spectogram\n\nOther than MFCC, the next most popular, if not the most popular audio feature is the Mel-spectogram. A time by frequency representation of the audio wave form is called a spectogram. That spectogram is then mapped to the Mel-scales thus giving us the Mel-spectogram. But because human perception of sound intensity is logarithmic in nature, the log form of the Mel-spectogram is the better one in theory. Thou I admit I haven't research this in alot of depth. \n\nLike MFCC, Log Mel-spectogram are well known to be discriminative features in audio. So once again, lets see how the Log Mel-spectogram varies between male and female."},{"metadata":{"trusted":true,"_uuid":"419d5d78bc3feb5d5305fa3a856d3c437d2e42ab"},"cell_type":"code","source":"# Log Mel-spectogram for female \nSAMPLE_RATE = 22050\nfname_f = 'recordings/' + 'english385.mp3'  \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5) # Chop audio at 5 secs... \nmelspec = librosa.feature.melspectrogram(y, sr=sr, n_mels=128)\n\n# Convert to log scale (dB). We'll use the peak power (max) as reference.\nlog_S = librosa.amplitude_to_db(melspec)\n\n# Display the log mel spectrogram\nplt.figure(figsize=(12,4))\nlibrosa.display.specshow(log_S, sr=sr, x_axis='time', y_axis='mel')\nplt.title('Log mel spectrogram for female')\nplt.colorbar(format='%+02.0f dB')\nplt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"973e344664556e70a3c5a69e2da00b35453e9a61"},"cell_type":"code","source":"# Log Mel-spectogram for male \nSAMPLE_RATE = 22050\nfname_m = 'recordings/' + 'english381.mp3'  \ny, sr = librosa.load(fname_m, sr=SAMPLE_RATE, duration = 5) # Chop audio at 5 secs... \nmelspec = librosa.feature.melspectrogram(y, sr=sr, n_mels=128)\n\n# Convert to log scale (dB). We'll use the peak power (max) as reference.\nlog_S = librosa.amplitude_to_db(melspec)\n\n# Display the log mel spectrogram\nplt.figure(figsize=(12,4))\nlibrosa.display.specshow(log_S, sr=sr, x_axis='time', y_axis='mel')\nplt.title('Log mel spectrogram for male')\nplt.colorbar(format='%+02.0f dB')\nplt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ebe7624594efd3ee8330f6e0af5888f62c8956e7"},"cell_type":"markdown","source":"The difference may not be as obvious but is definitely noticable after careful inspection. In particular, the female version  reaches a higher frequency compared to the male counterpart. \n\nI've also heard about a Mel Power spectogram as another feature, thou I haven't had any experience using it, hence I really can't comment how good it is compared to a Log Mel spectogram. Perhaps someone else who's a real expert can elaborate further. Leave the comments down below!"},{"metadata":{"_uuid":"ec3bd57e8e9cc239978ee630f463cb96a3d06101"},"cell_type":"markdown","source":"<a id=\"hpss\"></a>\n## 4. Harmonic-percussive source separation\n\nIts a mouthful to pronounce, but it's really easy to remember and I rarely use its short form of HPSS. Despite the complex description, it is essentially quite literal in what it means. This feature seperates the harmonic and the percussive source of an audio file. There's a really good notebook that explains how this works __[here](https://musicinformationretrieval.com/hpss.html)__\n\nLets take one of the audio files and __seperate its harmonic and perussive source__ (see told you its easy to remember), then listen to it too see how different they are..."},{"metadata":{"trusted":true,"_uuid":"0965dc603b959dbae59e295331420960ae7a43e9"},"cell_type":"code","source":"SAMPLE_RATE = 22050\nfname_f = 'recordings/' + 'english385.mp3'  \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5) \ny_harmonic, y_percussive = librosa.effects.hpss(y)\n\nipd.Audio(y_harmonic, rate=sr)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a9807f6322b256600c0afbe85db4b34432423888"},"cell_type":"code","source":"ipd.Audio(y_percussive, rate=sr)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e6e15e1d6c6c857ffc4fcef36235c86eafdb286f"},"cell_type":"markdown","source":"It's a pity that playing these audio files aren't the best way to really get a feel for how different the harmonic and percussive source sounds like. Generally its really obvious for music as it seperates out the beats from drums. In either case, maybe converting the source to a Mel spectogram may shed abit more light..."},{"metadata":{"trusted":true,"_uuid":"48b164278dbdb4142f9d34324fcf2115a57d58ec"},"cell_type":"code","source":"# harmonic \nmelspec = librosa.feature.melspectrogram(y_harmonic, sr=sr, n_mels=128)\nlog_h = librosa.amplitude_to_db(melspec)\n\n# percussive\nmelspec = librosa.feature.melspectrogram(y_percussive, sr=sr, n_mels=128)\nlog_p = librosa.amplitude_to_db(melspec)\n\n# Display the log mel spectrogram of both harmonic and percussive\nplt.figure(figsize=(12,6))\n\nplt.subplot(2,1,1)\nlibrosa.display.specshow(log_h, sr=sr, x_axis='time', y_axis='mel')\nplt.title('Log mel spectrogram for female harmonic')\nplt.colorbar(format='%+02.0f dB')\n\nplt.subplot(2,1,2)\nlibrosa.display.specshow(log_p, sr=sr, x_axis='time', y_axis='mel')\nplt.title('Log mel spectrogram for female percussive')\nplt.colorbar(format='%+02.0f dB')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Here's another alternative way to go about getting HPSS which is the decompose route. Output's the same but just a shortcut"},{"metadata":{"trusted":true,"_uuid":"e4222f4698007f37ad8428e138c929c0cda4632b"},"cell_type":"code","source":"# Lets use this one for the male \nSAMPLE_RATE = 22050\nfname_f = 'recordings/' + 'english381.mp3'  \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5)\nX = librosa.stft(y)\nH, P = librosa.decompose.hpss(X)  # Both Harmonic and Percussive as spectogram \nHmag = librosa.amplitude_to_db(H) # Get log mel-spectogram \nPmag = librosa.amplitude_to_db(P)\n\n# Have a listen to male harmonic \nh = librosa.istft(H)\nipd.Audio(h, rate=SAMPLE_RATE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"29499988f43ca26d02a41fbf9de78a3b00bfc487"},"cell_type":"code","source":"# Have a listen to male percussive \np = librosa.istft(P)\nipd.Audio(p, rate=SAMPLE_RATE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b272bfe45d811b3ee023147325e98d64124192e0"},"cell_type":"code","source":"# Display the log mel spectrogram of both harmonic and percussive\nplt.figure(figsize=(12,6))\n\nplt.subplot(2,1,1)\nlibrosa.display.specshow(Hmag, sr=sr, x_axis='time', y_axis='mel')\nplt.title('Log mel spectrogram for male harmonic')\nplt.colorbar(format='%+02.0f dB')\n\nplt.subplot(2,1,2)\nlibrosa.display.specshow(Pmag, sr=sr, x_axis='time', y_axis='mel')\nplt.title('Log mel spectrogram for male percussive')\nplt.colorbar(format='%+02.0f dB')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Notice how the HPSS for both female and male are quite diffferent? It sort of looks like the male version is abit rough? I'm no expert in interpreting the outputs of the HPSS but safe to say it will serve as a good feature for the machine learning model"},{"metadata":{"_uuid":"3f1d3e2a11bbec4e1685ee772df8d326cc42e291"},"cell_type":"markdown","source":"<a id=\"chroma\"></a>\n## 5. Chroma\n\nThis feature is still pretty new to me. But the way I understand it is that it classifies the pitches into 12 distinct classes called 'pitch profiles. Often used in music but again, I haven't done much research on this feature and have never tried it on a deep learning architecture before, at least not yet. I'll aim to give this a try in this series! \n\nBut before we do, lets compare how female and male differs in Chroma"},{"metadata":{"trusted":true,"_uuid":"93b58f17900b19c82ded4c97c4cf7546a47dd0c9"},"cell_type":"code","source":"SAMPLE_RATE = 22050\nfname_f = 'recordings/' + 'english381.mp3'  \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5)\nC = librosa.feature.chroma_cqt(y=y, sr=sr)\n\n# Make a new figure\nplt.figure(figsize=(12,4))\n# To make sure that the colors span the full range of chroma values, set vmin and vmax\nlibrosa.display.specshow(C, sr=sr, x_axis='time', y_axis='chroma', vmin=0, vmax=1)\nplt.title('Chromagram')\nplt.colorbar()\nplt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d0ccb74b4527a04425257e5efee8c991fbd76b42"},"cell_type":"code","source":"SAMPLE_RATE = 22050\nfname_f = 'recordings/' + 'english385.mp3'  \ny, sr = librosa.load(fname_f, sr=SAMPLE_RATE, duration = 5)\nC = librosa.feature.chroma_cqt(y=y, sr=sr)\n\n# Make a new figure\nplt.figure(figsize=(12,4))\nlibrosa.display.specshow(C, sr=sr, x_axis='time', y_axis='chroma', vmin=0, vmax=1)\nplt.title('Chromagram')\nplt.colorbar()\nplt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"917cf6c3b42a6adfe1714492e4be123dc3aa0cbd"},"cell_type":"markdown","source":"Quite surprisingly, Chroma seems to be the most discriminative feature between male and female, or at least visually. We should definitely try and use Chroma for our deep learning.  "},{"metadata":{"_uuid":"1d28c6fd42f8c141ea3e1ad05de4ebc8e2fd333b"},"cell_type":"markdown","source":"------------------------------\n<a id=\"final\"></a>\n## Final thoughts\n\nAnd there you have it! The 5 features you can extract from audio. Note that there are more features you can extract such as Beat Tracking, spectogram, spectral informations and etc. But I'm not familiar with them. So I'll let the experts elaborate on those other features.\n\nNow moving on, part 3 we will go into the actual modelling. First up, I will show how you could use the traditional machine learning models first such as Gradient Boosting and Random Forest, before jumping into deep learning. Then at Part 4 we'll go into Deep Learning. \n\nStay Tuned!"}],"metadata":{"anaconda-cloud":{},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}