Upload files to ''

GroupLASSONN.py

+import tensorflow as tf
+import numpy as np
+import pandas as pd
+from pylab import rcParams
+import matplotlib.pyplot as plt
+import warnings
+from mlxtend.plotting import plot_decision_regions
+from matplotlib.colors import ListedColormap
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+from sklearn.model_selection import train_test_split
+from group_lasso import BaseGroupLasso, GroupLasso
+from tensorflow import keras
+import math
+#using https://github.com/yngvem/group-lasso/
+warnings.filterwarnings('ignore')
+
+nd_path = ['nds/allnds_case.txt', 'nds/allnds_control.txt']
+
+X, y = load_dataset(nd_path)
+#https://github.com/bhattbhavesh91/regularization-neural-networks/blob/master/regularization-notebook.ipynb
+X_train, X_test, y_train, y_test = train_test_split(X, y,
+                                                    test_size=0.33,
+                                                    random_state=42)
+reg_model = Sequential()
+reg_model.add(Dense(math.sqrt(X_train.shape[1]), input_dim= X_train.shape[1], activation='relu'))
+reg_model.add(Dense(1, activation='sigmoid'))
+reg_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+reg_history = reg_model.fit(X_train, y_train,
+                            validation_data=(X_test, y_test),
+                            epochs=4000, verbose=1)
+
+
+# serialize model to JSON
+model_json = model.to_json()
+with open('model.json', 'w') as json_file:
+    json_file.write(model_json)
+# serialize weights to HDF5
+model.save_weights('model.h5')
+print('Saved model to disk')
+
+# load json and create model
+json_file = open('model.json', 'r')
+loaded_model_json = json_file.read()
+json_file.close()
+loaded_model = model_from_json(loaded_model_json)
+# load weights into new model
+loaded_model.load_weights("model.h5")
+print("Loaded model from disk")
+
+# evaluate loaded model on test data
+# loaded_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
+
+asd_path = ['nds/asd_case.txt', 'nds/asd_control.txt']
+
+X, y = load_dataset(asd_path)
+#https://github.com/bhattbhavesh91/regularization-neural-networks/blob/master/regularization-notebook.ipynb
+X_train, X_test, y_train, y_test = train_test_split(X, y,
+                                                    test_size=0.33,
+                                                    random_state=42)
+reg_model = Sequential()
+model.layers[0].set_weights(loaded_model[0])
+reg_model.add(Dense(math.sqrt(X_train.shape[1]), input_dim= X_train.shape[1], activation='relu',  kernel_regularizer='group_lasso'))
+reg_model.add(Dense(1, activation='ReLU'))
+reg_model.add(Dense(1, activation='sigmoid'))
+reg_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+reg_history = reg_model.fit(X_train, y_train,
+                            validation_data=(X_test, y_test),
+                            epochs=4000, verbose=1)
+
+
+
+model = keras.models.load_model('path/to/saved/model')
+weights = model.get_layer('input').get_weights()
+
+values = weights[0]
+for indx, v in enumerate(values):
+    if v!=0:
+        print('nonzero input', indx)