--- license: mit library_name: sklearn tags: - sklearn - skops - tabular-classification model_format: skops model_file: local_compartment_classifier_bd_boxes.skops widget: - structuredData: area_nm2: - 693824.0 - 4852608.0 - 17088896.0 area_nm2_neighbor_mean: - 10181485.714285716 - 9884429.714285716 - 9010409.142857144 area_nm2_neighbor_std: - 8312409.263207569 - 8587259.418816902 - 8418630.640116522 max_dt_nm: - 69.0 - 543.0 - 1287.0 max_dt_nm_neighbor_mean: - 664.7142857142857 - 630.8571428571429 - 577.7142857142857 max_dt_nm_neighbor_std: - 479.64240342658945 - 504.9563358340017 - 468.41868657651344 mean_dt_nm: - 24.4375 - 156.5 - 416.0 mean_dt_nm_neighbor_mean: - 198.62946428571428 - 189.19642857142856 - 170.66071428571428 mean_dt_nm_neighbor_std: - 150.614304054458 - 157.4368957825056 - 143.32375093543624 pca_ratio_01: - 1.3849340770961909 - 1.181656878273399 - 1.128046800200765 pca_ratio_01_neighbor_mean: - 1.8575624906424115 - 1.8760422359899387 - 1.880915879451087 pca_ratio_01_neighbor_std: - 0.641580757345606 - 0.6228187048854344 - 0.6165585104590592 pca_unwrapped_0: - -0.0046539306640625 - -0.497314453125 - -0.258544921875 pca_unwrapped_0_neighbor_mean: - 0.039224624633789 - 0.0840119448575106 - 0.0623056238347833 pca_unwrapped_0_neighbor_std: - 0.3114910605258688 - 0.2573427692683507 - 0.296254177168357 pca_unwrapped_1: - 0.7392578125 - -0.11553955078125 - 0.2169189453125 pca_unwrapped_1_neighbor_mean: - 0.0941687497225674 - 0.1718776009299538 - 0.1416541012850674 pca_unwrapped_1_neighbor_std: - 0.3179467337379631 - 0.3628551035117971 - 0.372447324946889 pca_unwrapped_2: - -0.673828125 - -0.85986328125 - 0.94140625 pca_unwrapped_2_neighbor_mean: - 0.2258744673295454 - 0.2427867542613636 - 0.0790349786931818 pca_unwrapped_2_neighbor_std: - 0.9134250264562896 - 0.8928014788058292 - 0.9167197839332804 pca_unwrapped_3: - -0.0302886962890625 - -0.86572265625 - 0.57177734375 pca_unwrapped_3_neighbor_mean: - -0.2933238636363636 - -0.2173753218217329 - -0.3480571400035511 pca_unwrapped_3_neighbor_std: - 0.6203425764161097 - 0.5938304683645145 - 0.5600074530240728 pca_unwrapped_4: - 0.67333984375 - -0.0005474090576171 - 0.81982421875 pca_unwrapped_4_neighbor_mean: - 0.2915762121027166 - 0.3528386896306818 - 0.2782594507390802 pca_unwrapped_4_neighbor_std: - 0.6415192812587974 - 0.6430080201673403 - 0.6308895861182334 pca_unwrapped_5: - 0.73876953125 - 0.50048828125 - -0.03192138671875 pca_unwrapped_5_neighbor_mean: - 0.2028697620738636 - 0.2245316938920454 - 0.2729325727982954 pca_unwrapped_5_neighbor_std: - 0.265173781606759 - 0.2994363858938455 - 0.2968562365279343 pca_unwrapped_6: - 0.99951171875 - 0.05828857421875 - -0.77880859375 pca_unwrapped_6_neighbor_mean: - -0.2386505820534446 - -0.1530848416415128 - -0.0769850990988991 pca_unwrapped_6_neighbor_std: - 0.6776577717043619 - 0.7717860533115238 - 0.7447135522384378 pca_unwrapped_7: - 0.023834228515625 - -0.9931640625 - 0.52978515625 pca_unwrapped_7_neighbor_mean: - -0.4803272594105113 - -0.3878728693181818 - -0.5263227982954546 pca_unwrapped_7_neighbor_std: - 0.4799926318285017 - 0.4691567465869561 - 0.3891669942534205 pca_unwrapped_8: - 0.0192413330078125 - 0.0997314453125 - -0.3359375 pca_unwrapped_8_neighbor_mean: - -0.0384375832297585 - -0.0457548661665482 - -0.0061485984108664 pca_unwrapped_8_neighbor_std: - 0.3037878488292577 - 0.3010843368506175 - 0.2874409267860334 pca_val_unwrapped_0: - 15657.09765625 - 40668.40625 - 66863.0 pca_val_unwrapped_0_neighbor_mean: - 69378.52059659091 - 67104.76526988637 - 64723.43856534091 pca_val_unwrapped_0_neighbor_std: - 20242.245019019712 - 24702.906417865197 - 25959.16138296664 pca_val_unwrapped_1: - 11305.3017578125 - 34416.42578125 - 59273.25 pca_val_unwrapped_1_neighbor_mean: - 41190.40261008523 - 39089.39133522727 - 36829.68004261364 pca_val_unwrapped_1_neighbor_std: - 16625.870141811894 - 18875.56976212627 - 17666.778281657556 pca_val_unwrapped_2: - 1270.4095458984375 - 13551.6748046875 - 47764.625 pca_val_unwrapped_2_neighbor_mean: - 28717.50048828125 - 27601.021828391335 - 24490.75362881747 pca_val_unwrapped_2_neighbor_std: - 14988.204981576571 - 16601.48080038032 - 15622.078784778376 post_synapse_count: - 0.0 - 0.0 - 0.0 post_synapse_count_neighbor_mean: - 0.0 - 0.0 - 0.0 post_synapse_count_neighbor_std: - 0.0 - 0.0 - 0.0 pre_synapse_count: - 0.0 - 0.0 - 0.0 pre_synapse_count_neighbor_mean: - 0.0 - 0.0 - 0.0 pre_synapse_count_neighbor_std: - 0.0 - 0.0 - 0.0 size_nm3: - 12771840.0 - 697943040.0 - 7550330880.0 size_nm3_neighbor_mean: - 3233702034.285714 - 3184761234.285714 - 2695304960.0 size_nm3_neighbor_std: - 3650678969.7909584 - 3691650923.5639486 - 3518520747.0511127 --- # Model description This is a model trained to classify pieces of neuron as axon, dendrite, soma, or glia, based only on their local shape and synapse features.The model is a linear discriminant classifier which was trained on compartment labels generated by Bethanny Danskin for 3 6x6x6 um boxes in the Minnie65 Phase3 dataset. ## Intended uses & limitations This model could be used to predict some compartment labels in mouse cortical connectomes, but it is unclear to what extent this model will generalize. ## Training Procedure The model was trained on local (level 2 cache) and synapse count features from 3 6x6x6 um boxes in the Minnie65 Phase3 dataset. These features were also locally aggregated in 5-hop neighborhood windows and concatenated to each level 2 node's features. The labels were generated by Bethanny Danskin and include axon, dendrite, soma, and glia compartments. The classification model was trained using a linear discriminant classifier. ### Hyperparameters
Click to expand | Hyperparameter | Value | | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------- | | memory | | | steps | [('transformer', QuantileTransformer(output_distribution='normal')), ('lda', LinearDiscriminantAnalysis(n_components=3))] | | verbose | False | | transformer | QuantileTransformer(output_distribution='normal') | | lda | LinearDiscriminantAnalysis(n_components=3) | | transformer\_\_copy | True | | transformer\_\_ignore_implicit_zeros | False | | transformer\_\_n_quantiles | 1000 | | transformer\_\_output_distribution | normal | | transformer\_\_random_state | | | transformer\_\_subsample | 10000 | | lda\_\_covariance_estimator | | | lda\_\_n_components | 3 | | lda\_\_priors | | | lda\_\_shrinkage | | | lda\_\_solver | svd | | lda\_\_store_covariance | False | | lda\_\_tol | 0.0001 |
### Model Plot 
Pipeline(steps=[('transformer',QuantileTransformer(output_distribution='normal')),('lda', LinearDiscriminantAnalysis(n_components=3))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
## Evaluation Results ### Classification Report (overall) | type | precision | recall | f1-score | support | | ------------ | --------- | -------- | -------- | -------- | | accuracy | 0.944357 | 0.944357 | 0.944357 | 0.944357 | | macro avg | 0.854825 | 0.917289 | 0.878753 | 31307 | | weighted avg | 0.946879 | 0.944357 | 0.945155 | 31307 | ### Classification Report (by class) | class | precision | recall | f1-score | support | | -------- | --------- | -------- | -------- | ------- | | axon | 0.956309 | 0.964704 | 0.960488 | 16404 | | dendrite | 0.928038 | 0.911341 | 0.919614 | 6948 | | glia | 0.964442 | 0.935279 | 0.949636 | 7540 | | soma | 0.570513 | 0.857831 | 0.685274 | 415 | # How to Get Started with the Model [More Information Needed] # Model Card Authors Ben Pedigo Bethanny Danskin