def main(args, facebook_id, facebook_token):
# There are three function choices: browse, build, like
# browse: review new tinder profiles and store them in your database
# train: use machine learning to create a new model that likes and dislikes profiles based on your historical preference
# like: use your machine leanring model to like new tinder profiles
if args.function == 'browse':
my_sess = client(facebook_id, facebook_token, args.distance)
my_sess.browse()
elif args.function == 'train':
# align the database
tindetheus_align.main()
# export the embeddinggs from the aligned database
export_embeddings.main()
# calculate the 128 average embedding per profiles
X, y = calc_avg_emb()
# fit and save a logistic regression model to the database
fit_log_reg(X, y)
elif args.function == 'like':
my_sess = client(facebook_id, facebook_token, args.distance)
my_sess.like()
else:
text = '''You must specify a function. Your choices are either
tindetheus browse
tindetheus train
tindetheus like'''
print(text)
def main(args, facebook_token):
# There are three function choices: browse, build, like
# browse: review new tinder profiles and store them in your database
# train: use machine learning to create a new model that likes and dislikes
# profiles based on your historical preference
# like: use your machine leanring model to like new tinder profiles
if args.function == 'browse':
my_sess = client(facebook_token, args.distance, args.model_dir,
likes_left=args.likes)
my_sess.browse()
elif args.function == 'train':
# align the database
tindetheus_align.main()
# export the embeddings from the aligned database
export_embeddings.main(model_dir=args.model_dir,
image_batch=args.image_batch)
# calculate the n average embedding per profiles
X, y = calc_avg_emb()
# fit and save a logistic regression model to the database
fit_log_reg(X, y)
elif args.function == 'validate':
print('\n\nAttempting to validate the dataset...\n\n')
valdir = 'validation'
# align the validation dataset
tindetheus_align.main(input_dir=valdir,
output_dir=valdir+'_aligned')
# export embeddings
# y is the image list, X is the embedding_array
image_list, emb_array = export_embeddings.main(model_dir=args.model_dir, # noqa: E501
data_dir=valdir+'_aligned',
image_batch=args.image_batch,
embeddings_name='val_embeddings.npy',
labels_name='val_labels.npy',
labels_strings_name='val_label_strings.npy', # noqa: E501
return_image_list=True)
# print(image_list)
# convert the image list to a numpy array to take advantage of
# numpy array slicing
image_list = np.array(image_list)
print('\n\nEvaluating trained model\n \n')
model = joblib.load('log_reg_model.pkl')
yhat = model.predict(emb_array)
# print(yhat)
# 0 should be dislike, and 1 should be like
# if this is backwards, there is probablly a bug...
dislikes = yhat == 0
likes = yhat == 1
show_images(image_list[dislikes], holdon=True, title='Dislike')
print('\n\nGenerating plots...\n\n')
plt.title('Dislike')
show_images(image_list[likes], holdon=True, title='Like')
plt.title('Like')
cols = ['Image name', 'Model prediction (0=Dislike, 1=Like)']
results = np.array((image_list, yhat)).T
print('\n\nSaving results to validation.csv\n\n')
my_results_DF = pd.DataFrame(results, columns=cols)
my_results_DF.to_csv('validation.csv')
plt.show()
elif args.function == 'like':
print('... Loading the facenet model ...')
print('... be patient this may take some time ...')
with tf.Graph().as_default():
with tf.Session() as sess:
# pass the tf session into client object
my_sess = client(facebook_token, args.distance, args.model_dir,
likes_left=args.likes, tfsess=sess)
# Load the facenet model
facenet.load_model(my_sess.model_dir)
print('Facenet model loaded successfully!!!')
# automatically like users
my_sess.like()
else:
text = '''You must specify a function. Your choices are either
tindetheus browse
tindetheus train
tindetheus like
tindetheus validate'''
print(text)