From e32fb824335ff32368d8d00966e95528efd73d0d Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Tue, 14 Nov 2017 14:49:51 -0500
Subject: [PATCH] change hyperparameters.json to hyperparameters.yaml
---
README.md | 2 +-
.../models_class1/GENERATE.sh | 4 +-
.../models_class1/hyperparameters.json | 37 -------------
.../models_class1/hyperparameters.yaml | 54 +++++++++++++++++++
4 files changed, 57 insertions(+), 40 deletions(-)
delete mode 100644 downloads-generation/models_class1/hyperparameters.json
create mode 100644 downloads-generation/models_class1/hyperparameters.yaml
diff --git a/README.md b/README.md
index 8bfc7c72..bf02a88b 100644
--- a/README.md
+++ b/README.md
@@ -129,7 +129,7 @@ notebook for an overview of the Python API, including fitting your own predictor
An ensemble of eight single-allele models was trained for each allele with at least
100 measurements in the training set (118 alleles). The models were trained on a
random 80% sample of the data for the allele and the remaining 20% was used for
-early stopping. All models use the same [architecture](downloads-generation/models_class1/hyperparameters.json). The
+early stopping. All models use the same [architecture](downloads-generation/models_class1/hyperparameters.yaml). The
predictions are taken to be the geometric mean of the nM binding affinity
predictions of the individual models. The training script is [here](downloads-generation/models_class1/GENERATE.sh).
diff --git a/downloads-generation/models_class1/GENERATE.sh b/downloads-generation/models_class1/GENERATE.sh
index ff06a043..ae98f51e 100755
--- a/downloads-generation/models_class1/GENERATE.sh
+++ b/downloads-generation/models_class1/GENERATE.sh
@@ -25,11 +25,11 @@ cd $SCRATCH_DIR/$DOWNLOAD_NAME
mkdir models
-cp $SCRIPT_DIR/hyperparameters.json .
+cp $SCRIPT_DIR/hyperparameters.yaml .
time mhcflurry-class1-train-allele-specific-models \
--data "$(mhcflurry-downloads path data_curated)/curated_training_data.csv.bz2" \
- --hyperparameters hyperparameters.json \
+ --hyperparameters hyperparameters.yaml \
--out-models-dir models \
--min-measurements-per-allele 200
diff --git a/downloads-generation/models_class1/hyperparameters.json b/downloads-generation/models_class1/hyperparameters.json
deleted file mode 100644
index 75fd5d64..00000000
--- a/downloads-generation/models_class1/hyperparameters.json
+++ /dev/null
@@ -1,37 +0,0 @@
-[
- {
- "n_models": 12,
- "max_epochs": 500,
- "patience": 10,
- "early_stopping": true,
- "validation_split": 0.2,
-
- "random_negative_rate": 0.0,
- "random_negative_constant": 25,
-
- "use_embedding": false,
- "kmer_size": 15,
- "batch_normalization": false,
- "locally_connected_layers": [
- {
- "filters": 8,
- "activation": "tanh",
- "kernel_size": 3
- },
- {
- "filters": 8,
- "activation": "tanh",
- "kernel_size": 3
- }
- ],
- "activation": "relu",
- "output_activation": "sigmoid",
- "layer_sizes": [
- 32
- ],
- "random_negative_affinity_min": 20000.0,
- "random_negative_affinity_max": 50000.0,
- "dense_layer_l1_regularization": 0.001,
- "dropout_probability": 0.0
- }
-]
diff --git a/downloads-generation/models_class1/hyperparameters.yaml b/downloads-generation/models_class1/hyperparameters.yaml
new file mode 100644
index 00000000..0e114b32
--- /dev/null
+++ b/downloads-generation/models_class1/hyperparameters.yaml
@@ -0,0 +1,54 @@
+[{
+##########################################
+# ENSEMBLE SIZE
+##########################################
+"n_models": 12,
+
+##########################################
+# OPTIMIZATION
+##########################################
+"max_epochs": 500,
+"patience": 10,
+"early_stopping": true,
+"validation_split": 0.2,
+
+##########################################
+# RANDOM NEGATIVE PEPTIDES
+##########################################
+"random_negative_rate": 0.0,
+"random_negative_constant": 25,
+"random_negative_affinity_min": 20000.0,
+"random_negative_affinity_max": 50000.0,
+
+##########################################
+# PEPTIDE REPRESENTATION
+##########################################
+# One of "one-hot", "embedding", or "BLOSUM62".
+"peptide_amino_acid_encoding": "BLOSUM62",
+"use_embedding": false, # maintained for backward compatability
+"kmer_size": 15,
+
+##########################################
+# NEURAL NETWORK ARCHITECTURE
+##########################################
+"locally_connected_layers": [
+ {
+ "filters": 8,
+ "activation": "tanh",
+ "kernel_size": 3
+ },
+ {
+ "filters": 8,
+ "activation": "tanh",
+ "kernel_size": 3
+ }
+],
+"activation": "relu",
+"output_activation": "sigmoid",
+"layer_sizes": [
+ 32
+],
+"dense_layer_l1_regularization": 0.001,
+"batch_normalization": false,
+"dropout_probability": 0.0,
+}]
--
GitLab