consensus_wd_t = df_con_matching.iloc[0]['weighted_neuron_distance_ave'] df_merge.loc[i] = [image,'consensus',consensus_wd_t] i= i+1 merged_csv= data_DIR+'/consensus_compare_wnd.csv' df_merge.to_csv(merged_csv, index=False) # plot # ## sort by sample size algorithms = np.unique(df_nd.algorithm) dfg = df_merge.groupby('algorithm') sample_size_per_algorithm = np.zeros(algorithms.size) for i in range( algorithms.size): sample_size_per_algorithm[i] = (dfg.get_group(algorithms[i]).shape[0]) order = sample_size_per_algorithm.argsort() algorithms_ordered = algorithms[order[::-1]] algorithms_ordered= np.append('consensus',algorithms_ordered) plt_dist.plot_compare_consensus_distance(merged_csv, data_DIR,algorithms_ordered,metric='weighted_ave_neuron_distance',CASE_BY_CASE_PLOT = 0, value_label='Weighted Average Neuron Distance (bidirectional)') plt_dist.plot_similarities(merged_csv, data_DIR,algorithms_ordered,metric='weighted_ave_neuron_distance',CASE_BY_CASE_PLOT = 0, value_label='Similarities on Weighted Average Neuron Distance (bidirectional)')
for i in range(algorithms.size): sample_size_per_algorithm[i] = (dfg.get_group(algorithms[i]).shape[0]) order = sample_size_per_algorithm.argsort() algorithms_ordered = algorithms[order[::-1]] # plot if BD: plt_dist.plot_blasneuron_distance(bn_csv, data_DIR, algorithms_ordered, CASE_BY_CASE_PLOT=1) plt_dist.plot_similarities( bn_csv, data_DIR, algorithms_ordered, metric='SSD', CASE_BY_CASE_PLOT=0, value_label='Similarity (0~1) on Global Morph Feature Score') plt_dist.plot_similarities( neuron_distance_csv, data_DIR, algorithms_ordered, metric='neuron_distance', CASE_BY_CASE_PLOT=0, value_label='Similarity (0~1) on Average Neuron Distance (D1)') plt_dist.plot_similarities( neuron_distance_csv, data_DIR, algorithms_ordered,
algorithms = np.unique(df_nd.algorithm) dfg = df_nd.groupby('algorithm') sample_size_per_algorithm = np.zeros(algorithms.size) for i in range( algorithms.size): sample_size_per_algorithm[i] = (dfg.get_group(algorithms[i]).shape[0]) order = sample_size_per_algorithm.argsort() algorithms_ordered = algorithms[order[::-1]] # plot if BD: plt_dist.plot_blasneuron_distance(bn_csv,data_DIR,algorithms_ordered,CASE_BY_CASE_PLOT=1) plt_dist.plot_similarities(bn_csv, data_DIR,algorithms_ordered,metric='SSD',CASE_BY_CASE_PLOT = 0,value_label='Similarity (0~1) on Global Morph Feature Score') plt_dist.plot_similarities(neuron_distance_csv, data_DIR,algorithms_ordered,metric='neuron_distance',CASE_BY_CASE_PLOT = 0,value_label='Similarity (0~1) on Average Neuron Distance (D1)') plt_dist.plot_similarities(neuron_distance_csv, data_DIR,algorithms_ordered,metric='neuron_difference',CASE_BY_CASE_PLOT = 0, value_label='Similarity (0~1) on Neuron Difference Score (D2*D3)') plt_dist.plot_similarities(neuron_distance_csv, data_DIR,algorithms_ordered,metric='neuron_distance_diff',CASE_BY_CASE_PLOT = 0, value_label='Similarity (0~1) on Average Neuron Distance on Different Structures (D2)') plt_dist.plot_similarities(neuron_distance_csv, data_DIR,algorithms_ordered,metric='neuron_distance_perc',CASE_BY_CASE_PLOT = 0, value_label='Similarity (0~1) on Neuron Different Structure Percentage (D3)') plt_dist.plot_neuron_distance(neuron_distance_csv, data_DIR,algorithms_ordered,CASE_BY_CASE_PLOT = 0) ######################################## for all generated reconstructions ############################ #plot runnign time
dfg = df_nd.groupby("algorithm") sample_size_per_algorithm = np.zeros(algorithms.size) for i in range(algorithms.size): sample_size_per_algorithm[i] = dfg.get_group(algorithms[i]).shape[0] order = sample_size_per_algorithm.argsort() algorithms_ordered = algorithms[order[::-1]] # plot if BD > 0: plt_dist.plot_blasneuron_distance(bn_csv, data_DIR, algorithms_ordered, CASE_BY_CASE_PLOT=1) plt_dist.plot_similarities( bn_csv, data_DIR, algorithms_ordered, metric="SSD", CASE_BY_CASE_PLOT=0, value_label="Similarity (0~1) on Global Morph Feature Score", ) plt_dist.plot_similarities( neuron_distance_csv, data_DIR, algorithms_ordered, metric="neuron_distance", CASE_BY_CASE_PLOT=0, value_label="Similarity (0~1) based on Average Neuron Distance (D1)", ) plt_dist.plot_similarities( neuron_distance_csv,
df_merge.to_csv(merged_csv, index=False) # plot # ## sort by sample size algorithms = np.unique(df_nd.algorithm) dfg = df_merge.groupby('algorithm') sample_size_per_algorithm = np.zeros(algorithms.size) for i in range(algorithms.size): sample_size_per_algorithm[i] = (dfg.get_group(algorithms[i]).shape[0]) order = sample_size_per_algorithm.argsort() algorithms_ordered = algorithms[order[::-1]] algorithms_ordered = np.append('consensus', algorithms_ordered) plt_dist.plot_compare_consensus_distance( merged_csv, data_DIR, algorithms_ordered, metric='weighted_ave_neuron_distance', CASE_BY_CASE_PLOT=0, value_label='Weighted Average Neuron Distance (bidirectional)') plt_dist.plot_similarities( merged_csv, data_DIR, algorithms_ordered, metric='weighted_ave_neuron_distance', CASE_BY_CASE_PLOT=0, value_label= 'Similarities on Weighted Average Neuron Distance (bidirectional)')