#!/usr/bin/env python
# coding: utf-8

# Start by creating a new `conda` environment:
# 
# ```bash
# $ conda create -n pyannote python=3.6 anaconda
# $ source activate pyannote
# ```
# 
# Then, install `pyannote-video` and its dependencies:
# 
# ```bash
# $ pip install pyannote-video
# ```
# 
# Finally, download sample video and `dlib` models:
# 
# ```bash
# $ git clone https://github.com/pyannote/pyannote-data.git
# $ git clone https://github.com/davisking/dlib-models.git
# $ bunzip2 dlib-models/dlib_face_recognition_resnet_model_v1.dat.bz2
# $ bunzip2 dlib-models/shape_predictor_68_face_landmarks.dat.bz2
# ```
# 
# To execute this notebook locally:
# ```bash
# $ git clone https://github.com/pyannote/pyannote-video.git
# $ jupyter notebook --notebook-dir="pyannote-video/doc"
# ```
# 

# In[4]:


get_ipython().run_line_magic('pylab', 'inline')


# # Shot segmentation

# In[5]:


get_ipython().system('pyannote-structure.py --help')


# In[7]:


get_ipython().system('pyannote-structure.py shot --verbose ../../pyannote-data/TheBigBangTheory.mkv                                        ../../pyannote-data/TheBigBangTheory.shots.json')


# Detected shot boundaries can be visualized using `pyannote.core` notebook support:

# In[8]:


from pyannote.core.json import load_from
shots = load_from('../../pyannote-data/TheBigBangTheory.shots.json')
shots


# # Face processing

# In[9]:


get_ipython().system('pyannote-face.py --help')


# ### Face tracking

# In[10]:


get_ipython().system('pyannote-face.py track --verbose --every=0.5 ../../pyannote-data/TheBigBangTheory.mkv                                                ../../pyannote-data/TheBigBangTheory.shots.json                                                ../../pyannote-data/TheBigBangTheory.track.txt')


# Face tracks can be visualized using `demo` mode:

# In[12]:


get_ipython().system('pyannote-face.py demo ../../pyannote-data/TheBigBangTheory.mkv                         ../../pyannote-data/TheBigBangTheory.track.txt                         ../../pyannote-data/TheBigBangTheory.track.mp4')


# In[14]:


import io
import base64
from IPython.display import HTML
video = io.open('../../pyannote-data/TheBigBangTheory.track.mp4', 'r+b').read()
encoded = base64.b64encode(video)
HTML(data='''<video alt="test" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii')))


# ### Facial landmarks and face embedding

# In[15]:


get_ipython().system('pyannote-face.py extract --verbose ../../pyannote-data/TheBigBangTheory.mkv                                      ../../pyannote-data/TheBigBangTheory.track.txt                                      ../../dlib-models/shape_predictor_68_face_landmarks.dat                                      ../../dlib-models/dlib_face_recognition_resnet_model_v1.dat                                      ../../pyannote-data/TheBigBangTheory.landmarks.txt                                      ../../pyannote-data/TheBigBangTheory.embedding.txt')


# ### Face clustering

# Once embeddings are extracted, let's apply face track hierarchical agglomerative clustering.  
# The distance between two clusters is defined as the average euclidean distance between all embeddings.  

# In[16]:


from pyannote.video.face.clustering import FaceClustering
clustering = FaceClustering(threshold=0.6)


# In[17]:


face_tracks, embeddings = clustering.model.preprocess('../../pyannote-data/TheBigBangTheory.embedding.txt')
face_tracks.get_timeline()


# In[18]:


result = clustering(face_tracks, features=embeddings)


# In[19]:


from pyannote.core import notebook, Segment
notebook.reset()
notebook.crop = Segment(0, 30)
mapping = {9: 'Leonard', 6: 'Sheldon', 14: 'Receptionist', 5: 'False_alarm'}
result = result.rename_labels(mapping=mapping)
result


# In[21]:


with open('../../pyannote-data/TheBigBangTheory.labels.txt', 'w') as fp:
    for _, track_id, cluster in result.itertracks(yield_label=True):
        fp.write(f'{track_id} {cluster}\n')


# In[23]:


get_ipython().system('pyannote-face.py demo ../../pyannote-data/TheBigBangTheory.mkv                         ../../pyannote-data/TheBigBangTheory.track.txt                         --label=../../pyannote-data/TheBigBangTheory.labels.txt                         ../../pyannote-data/TheBigBangTheory.final.mp4')


# In[25]:


import io
import base64
from IPython.display import HTML
video = io.open('../../pyannote-data/TheBigBangTheory.final.mp4', 'r+b').read()
encoded = base64.b64encode(video)
HTML(data='''<video alt="test" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii')))