From 16414ac3fe8c5f5aea5118cf141e5acdda073366 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Mon, 5 Feb 2018 11:40:39 -0500
Subject: [PATCH] Many more models in ensemble
---
.../models_class1/GENERATE.sh | 2 +-
.../models_class1/generate_hyperparameters.py | 35 ++++++++++---------
.../models_class1_no_mass_spec/GENERATE.sh | 2 +-
3 files changed, 21 insertions(+), 18 deletions(-)
diff --git a/downloads-generation/models_class1/GENERATE.sh b/downloads-generation/models_class1/GENERATE.sh
index 4d4bf210..275e5c1b 100755
--- a/downloads-generation/models_class1/GENERATE.sh
+++ b/downloads-generation/models_class1/GENERATE.sh
@@ -35,7 +35,7 @@ time mhcflurry-class1-train-allele-specific-models \
--data "$(mhcflurry-downloads path data_curated)/curated_training_data.with_mass_spec.csv.bz2" \
--hyperparameters hyperparameters.yaml \
--out-models-dir models \
- --percent-rank-calibration-num-peptides-per-length 1000000 \
+ --percent-rank-calibration-num-peptides-per-length 100000 \
--min-measurements-per-allele 75 \
--num-jobs 32 16
diff --git a/downloads-generation/models_class1/generate_hyperparameters.py b/downloads-generation/models_class1/generate_hyperparameters.py
index 995be20b..dcd48aa8 100644
--- a/downloads-generation/models_class1/generate_hyperparameters.py
+++ b/downloads-generation/models_class1/generate_hyperparameters.py
@@ -49,7 +49,7 @@ base_hyperparameters = {
"kernel_size": 3
}
],
- "activation": "relu",
+ "activation": "tanh",
"output_activation": "sigmoid",
"layer_sizes": [16],
"dense_layer_l1_regularization": 0.001,
@@ -58,19 +58,22 @@ base_hyperparameters = {
}
grid = []
-for dense_layer_size in [64, 16]:
- for num_lc in [0, 1, 2]:
- for lc_kernel_size in [3, 5]:
- new = deepcopy(base_hyperparameters)
- new["layer_sizes"] = [dense_layer_size]
- (lc_layer,) = new["locally_connected_layers"]
- lc_layer['kernel_size'] = lc_kernel_size
- if num_lc == 0:
- new["locally_connected_layers"] = []
- elif num_lc == 1:
- new["locally_connected_layers"] = [lc_layer]
- elif num_lc == 2:
- new["locally_connected_layers"] = [lc_layer, deepcopy(lc_layer)]
- grid.append(new)
+for dense_layer_size in [64, 32, 16]:
+ for l1 in [0.001, 0.01, 0.0]:
+ for num_lc in [0, 1, 2]:
+ for lc_kernel_size in [3, 5]:
+ new = deepcopy(base_hyperparameters)
+ new["layer_sizes"] = [dense_layer_size]
+ new["dense_layer_l1_regularization"] = l1
+ (lc_layer,) = new["locally_connected_layers"]
+ lc_layer['kernel_size'] = lc_kernel_size
+ if num_lc == 0:
+ new["locally_connected_layers"] = []
+ elif num_lc == 1:
+ new["locally_connected_layers"] = [lc_layer]
+ elif num_lc == 2:
+ new["locally_connected_layers"] = [lc_layer, deepcopy(lc_layer)]
+ if not grid or new not in grid:
+ grid.append(new)
-dump(grid, stdout)
\ No newline at end of file
+dump(grid, stdout)
diff --git a/downloads-generation/models_class1_no_mass_spec/GENERATE.sh b/downloads-generation/models_class1_no_mass_spec/GENERATE.sh
index b199cb6b..20b74978 100755
--- a/downloads-generation/models_class1_no_mass_spec/GENERATE.sh
+++ b/downloads-generation/models_class1_no_mass_spec/GENERATE.sh
@@ -35,7 +35,7 @@ time mhcflurry-class1-train-allele-specific-models \
--data "$(mhcflurry-downloads path data_curated)/curated_training_data.no_mass_spec.csv.bz2" \
--hyperparameters hyperparameters.yaml \
--out-models-dir models \
- --percent-rank-calibration-num-peptides-per-length 1000000 \
+ --percent-rank-calibration-num-peptides-per-length 100000 \
--min-measurements-per-allele 75 \
--num-jobs 32 16
--
GitLab