# Compute distance matrices
print_heading('CALCULATING DISTANCE MATRICES')
distances = {}
analysis_times = []
timer = Timer()
timer.start()
for ID in experiment_bouts.metadata['ID'].unique():
output_path, path_exists = create_filepath(output_directory, ID, '.npy', True)
if path_exists:
distances[ID] = np.load(output_path)
if not path_exists:
print ID + '...',
queries = experiment_bouts.list_bouts(IDs=[ID], values=True, ndims=n_dims)
fish_distances = calculate_distance_matrix_templates(queries, exemplars, fs=frame_rate)
distances[ID] = fish_distances
time_taken = timer.lap()
analysis_times.append(time_taken)
print timer.convert_time(time_taken)
np.save(output_path, fish_distances)
if len(analysis_times) > 0:
print 'Average time: {}'.format(timer.convert_time(timer.average))
# Assign exemplars
mapped_bouts = experiment_bouts.metadata.copy()
mapped_bouts['exemplar'] = None
for ID, fish_distances in distances.iteritems():
bout_idxs = mapped_bouts[mapped_bouts['ID'] == ID].index
nearest_exemplar = np.argmin(fish_distances, axis=1)
mapped_bouts.loc[bout_idxs, 'exemplar'] = nearest_exemplar
mapped_bouts.to_csv(os.path.join(experiment.subdirs['analysis'], 'mapped_bouts.csv'))
rand = np.load(os.path.join(stimulus_map_directory, 'random_frames.npy'))
subset_averages = []
subset_counts = []
for i in np.arange(0, len(rand), 1000):
subset = rand[i:i + 1000].astype('float64')
subset_averages.append(subset.mean(axis=0))
subset_counts.append(float(len(subset)))
subset_averages = np.array(subset_averages)
subset_counts = np.array(subset_counts)
average = np.einsum('i,ijk->jk', subset_counts, subset_averages)
average /= subset_counts.sum()
np.save(os.path.join(stimulus_map_directory, 'random_average.npy'),
average)
# Compute histogram
histogram = np.zeros((250, 250))
for img in rand:
img_points, img_orientations = find_paramecia(img)
img_counts, x, y = np.histogram2d(
*img_points.T, bins=[np.arange(0, 251),
np.arange(0, 251)])
histogram += img_counts
np.save(os.path.join(stimulus_map_directory, 'random_histogram.npy'),
histogram)
print 'Time taken:', timer.convert_time(timer.stop())
from behaviour_analysis.analysis.stimulus_mapping import BoutStimulusMapper
import os
import pandas as pd
if __name__ == "__main__":
for experiment in (blu, lak):
print_heading(os.path.basename(experiment.directory))
stimulus_map_directory = create_folder(experiment.subdirs['analysis'],
'stimulus_maps')
mapped_bouts = pd.read_csv(os.path.join(experiment.subdirs['analysis'],
'mapped_bouts.csv'),
index_col=0,
dtype={
'ID': str,
'video_code': str
})
# Calculate stimulus maps for each fish in parallel
timer = Timer()
timer.start()
mapper = BoutStimulusMapper(mapped_bouts,
experiment,
stimulus_map_directory,
n_threads=20)
mapper.run()
total_time = timer.stop()
print 'Total time:', timer.convert_time(total_time)
from datasets.main_dataset import experiment
from paths import paths, capture_strike_directory
from behaviour_analysis.analysis.stimulus_mapping import calculate_fish_sequences
from behaviour_analysis.manage_files import create_folder
from behaviour_analysis.miscellaneous import Timer
from joblib import Parallel, delayed
import numpy as np
import pandas as pd
import os
strike_sequence_directory = create_folder(capture_strike_directory, 'strike_sequences')
if __name__ == "__main__":
capture_strikes = pd.read_csv(paths['capture_strikes'], index_col=0, dtype={'ID': str, 'video_code': str})
complete_strikes = capture_strikes[(capture_strikes['start'] - 500) >= 0]
complete_strikes.to_csv(os.path.join(strike_sequence_directory, 'complete_strikes.csv'), index=True)
analysis_times = Parallel(4)(delayed(calculate_fish_sequences)(ID, complete_strikes, experiment, strike_sequence_directory)
for ID in complete_strikes['ID'].unique())
print 'Total time:', Timer.convert_time(np.sum(analysis_times))
print 'Average time:', Timer.convert_time(np.mean(analysis_times))
# Compare first antisymmetric transition mode
a1_dot_a = np.abs(np.dot(USVa1[0, :, 0], USVa2[0, :, 0]))
a1_dot_b = np.abs(np.dot(USVa1[0, :, 0], USVa2[0, :, 1]))
a1_dot = max(a1_dot_a, a1_dot_b)
# Append to output
dot_products.append((s1_dot, s2_dot, a1_dot))
i += 1
return np.array(dot_products)
if __name__ == "__main__":
transition_directory = os.path.join(experiment.subdirs['analysis'],
'transitions')
control_matrices = np.load(
os.path.join(transition_directory, 'control',
'transition_matrices.npy'))
ablated_matrices = np.load(
os.path.join(transition_directory, 'ablated',
'transition_matrices.npy'))
timer = Timer()
timer.start()
dot_products = compare_transition_modes(ablated_matrices,
control_matrices,
exact=False,
n_permutations=100)
np.save(os.path.join(transition_directory, 'compare_control_ablated.npy'),
dot_products)
print timer.convert_time(timer.stop())
# Transform
transformed_strikes = capture_strike_data.map(eigenfish, whiten=True, mean=mean_tail, std=std_tail)
transformed_strikes = transformed_strikes.list_bouts(values=True, ndims=3)
# Truncate
truncated_strikes = [bout[12:37] for bout in transformed_strikes]
bw = 0.006 # 3 frames
# Calculate distance matrix
print_heading('CALCULATING CAPTURE STRIKE DISTANCE MATRIX')
timer = Timer()
timer.start()
D_normal = calculate_distance_matrix(truncated_strikes, bw=bw)
D_flipped = calculate_distance_matrix(truncated_strikes, bw=bw, flip=True)
D = np.min([D_normal, D_flipped], axis=0)
np.save(paths['distance_matrix'], D)
time_taken = timer.stop()
print 'Time taken: {}'.format(timer.convert_time(time_taken))
# Perform embedding
D = squareform(D)
np.random.seed(1992)
isomap = IsomapPrecomputed(n_neighbors=5, n_components=2)
isomapped_strikes = isomap.fit_transform(D)
np.save(paths['isomapped_strikes'], isomapped_strikes)
# Cluster
cluster_labels = KMeans(2).fit_predict(isomapped_strikes)
capture_strikes['cluster_label'] = cluster_labels
capture_strikes.to_csv(paths['capture_strikes'], index=True)