Defeat Recording Data

Main Behavior Pickle File: <br> Overall dictionary from (mouse,defeat_day)--&gt;data data.keys() # body_part_tracking, extracted_features, fiber_photometry <br> data['body_part_tracking] is a dictionary from body part to x,y coordinates over time (T frame, 120 Hz) <br> data['extracted_features'] is a 12xT matrix of feature traces (120 Hz) <br> data['fiber_photometry'] is a dictionary from 'fpts' or 'fpnac' to raw GCaMP recordings from the tail striatum or nucleus accumbens respectively (1017 Hz) <br> <br> Model Pickle Files: - 2 sets of random forest classifiers (trained RF model, cutoff for probability of behavior ocurring) dictionary of behavior name: (trained <code><strong>sklearn.ensemble</strong></code><strong>.RandomForestClassifier</strong>, classification probability cutoff) <br> - t-SNE model: dictionary: 'training': features in training set 'projection': <code><strong>sklearn.neural_network</strong></code><strong>.MLPClassifier </strong>maps raw features to t-SNE space 'labeled_map': where clusters are in t-SNE space <br> <br>