def run_model(data_set, kmer_size, norm_input, encoding_dim_1, encoding_dim_2,
encoded_activation, input_dropout_pct, dropout_pct, num_epochs,
batch_size, n_splits, n_repeats, compute_informative_features,
plot_iteration, graph_dir, outFile):
# format strings for outputting the paramters associated with this run:
summary_string, plotting_string = stats_utils.format_input_parameters_printing_2layers(
data_set, kmer_size, norm_input, encoding_dim_1, encoding_dim_2,
encoded_activation, input_dropout_pct, dropout_pct, num_epochs,
batch_size, n_splits, n_repeats, compute_informative_features,
plot_iteration)
outFile_header = 'data_set\tkmer_size\tnorm_input\tencoding_dim_1\tencoding_dim_2\tencoded_activation\tinput_dropout_pct\tdropout_pct\tnum_epochs\tbatch_size\tn_splits\tn_repeats\t'
#################
# Load the data #
#################
print('Loading data...')
data_normalized, labels, rskf = load_kmer_cnts_jf.load_single_disease(
data_set, kmer_size, n_splits, n_repeats, precomputed_kfolds=False)
# rskf = repeated stratified k fold. This contains all the kfold-by-iteration combos.
###################################################
# iterate through the data kfolds and iterations #
###################################################
# Create a dictionary to store the metrics of each fold
aggregated_statistics = {} # key=n_repeat, values= dictionary with stats
for n_repeat in range(0, len(rskf[0])):
print('Iteration %s...' % n_repeat)
aggregated_statistics[n_repeat] = {}
train_idx = rskf[0][n_repeat]
test_idx = rskf[1][n_repeat]
x_train, y_train = data_normalized[train_idx], labels[train_idx]
x_test, y_test = data_normalized[test_idx], labels[test_idx]
#standardize the data, mean=0, std=1
if norm_input:
x_train, x_test = stats_utils.standardize_data(x_train, x_test)
###########################################
# set up a model (supervised learning) #
###########################################
# note that the model has to be instantiated each time a new fold is started otherwise the weights will not start from scratch.
input_dim = len(
data_normalized[0]) # this is the number of input kmers
model = deep_learning_models.create_supervised_model_2layers(
input_dim, encoding_dim_1, encoding_dim_2, encoded_activation,
input_dropout_pct, dropout_pct)
#weightFile = os.environ['HOME'] + '/deep_learning_microbiome/data/weights.txt'
##################################################
# Fit the model with the train data of this fold #
##################################################
history = History()
# history is a dictionary. To get the keys, type print(history.history.keys())
model.fit(x_train,
y_train,
epochs=num_epochs,
batch_size=len(x_train),
shuffle=True,
validation_data=(x_test, y_test),
verbose=0,
callbacks=[history])
# predict using the held out data
y_pred = model.predict(x_test)
# save the weights of this model. TODO
################################################################
# Compute summary statistics #
################################################################
# Store the results of this fold in aggregated_statistics
aggregated_statistics = stats_utils.compute_summary_statistics(
y_test, y_pred, history, aggregated_statistics, n_repeat)
# could plot everything (roc, accuracy vs epoch, loss vs epoch, confusion matrix, precision recall) for each fold, but this will produce a lot of graphs.
if compute_informative_features:
shap_values, shap_values_summed = stats_utils.compute_shap_values_deeplearning(
input_dim, model, x_test)
aggregated_statistics[n_repeat][
'shap_values_summed'] = shap_values_summed
aggregated_statistics[n_repeat]['shap_values'] = shap_values
# also plot:
#shap.summary_plot(shap_values, X, plot_type="bar")
#shap.summary_plot(shap_values, X)
##############################################
# aggregate the results from all the k-folds #
# Print and Plot #
##############################################
print('Aggregating statistics across iterations and printing/plotting...')
stats_utils.aggregate_statistics_across_folds(aggregated_statistics, rskf,
n_splits, outFile,
summary_string,
plotting_string,
outFile_header)
###################
# Aggregate shap: #
###################
if compute_informative_features:
print('Computing informative features with Shap...')
stats_utils.aggregate_shap(aggregated_statistics, rskf)
tmp_intermediate_directory = config_file.tmp_intermediate_directory
for kmer_size in [5, 6, 7, 8, 10]:
print(kmer_size)
#################
# Load the data #
#################
print('Loading data...')
data_set = 'Qin_et_al'
data_normalized, kmer_cnts, labels, rskf = load_kmer_cnts_jf.load_single_disease(
data_set,
kmer_size,
n_splits,
n_repeats,
precomputed_kfolds=False,
bootstrap=True)
num_replicates = 100
num_kmers = 100000
bootstrapped_data = stats_utils.bootstrap_data(data_normalized, kmer_cnts,
num_replicates, num_kmers)
pickle.dump(
bootstrapped_data,
open(
"%skmer_size_%s_Qin_bootstrap.p" %
(tmp_intermediate_directory, kmer_size), "wb"))