Remove useless dirs

CPLUOS · Nov 27, 2017 · c790d63 · c790d63
1 parent c8e41aa
commit c790d63
Show file tree

Hide file tree

Showing 7 changed files with 696 additions and 0 deletions.
diff --git a/...points/nb_naive_training-checkpoint.ipynb → ...ynb_checkpoints/Untitled-checkpoint.ipynb b/...points/nb_naive_training-checkpoint.ipynb → ...ynb_checkpoints/Untitled-checkpoint.ipynb
diff --git a/SJ-Keras/Proj-ChannelImportance/.training.py.swp b/SJ-Keras/Proj-ChannelImportance/.training.py.swp
diff --git a/SJ-Keras/Proj-ChannelImportance/Untitled.ipynb b/SJ-Keras/Proj-ChannelImportance/Untitled.ipynb
@@ -0,0 +1,34 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/SJ-Keras/Proj-ChannelImportance/evaluation.py b/SJ-Keras/Proj-ChannelImportance/evaluation.py
@@ -0,0 +1,131 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os.path
+
+import argparse
+from datetime import datetime
+from tqdm import tqdm
+#import numpy as np
+import matplotlib as mpl
+mpl.use('Agg')
+
+#import tensorflow as tf
+
+import keras
+#from keras import (
+#    optimizers,
+#    losses,
+#    metrics)
+from keras.models import load_model
+from keras.utils import multi_gpu_model 
+
+#import keras.backend as K
+
+from models import add_an_sigmoid_layer
+from pipeline import DataLodaer
+
+#from custom_losses import binary_cross_entropy_with_logits
+#from custom_metrics import accuracy_with_logits
+from meters import ROCMeter, OutHist
+from utils import (
+    get_log_dir,
+    get_saved_model_paths
+)
+
+
+
+def evaluate(saved_model_path,
+             step,
+             log_dir):
+    # TEST
+    logger = Logger(log_dir.path, "READ")
+
+    model_logit = load_model(saved_model_path)
+    model_sigmoid = add_an_sigmoid_layer(model_logit)
+
+    model = multi_gpu_model(model_sigmoid, 2)
+
+    out_hist = OutHist(
+        dpath=log_dir.output_histogram.path,
+        step=step,
+        dname_list=["train", "test_dijet", "test_zjet"])
+
+    # on training data
+    train_data_loader = DataLodaer(
+        path=logger["train_data"],
+        batch_size=1000,
+        cyclic=False)
+
+    for x, y in train_data_loader:
+        preds = model.predict_on_batch(x)
+        out_hist.fill(dname="train", labels=y, preds=preds)
+
+    # Test on dijet dataset
+    test_dijet_loader = DataLodaer(
+        path=logger["val_dijet_data"],
+        batch_size=1000,
+        cyclic=False)
+
+    roc_dijet = ROCMeter(
+        dpath=log_dir.roc.path,
+        step=step,
+        title="Test on Dijet",
+        prefix="dijet_"
+    )
+
+    for x, y in test_dijet_loader:
+        preds = model.predict_on_batch(x)
+
+        roc_dijet.append(labels=y, preds=preds)
+        out_hist.fill(dname="test_dijet", labels=y, preds=preds)
+
+    roc_dijet.finish()
+
+    # Test on Z+jet dataset
+    test_zjet_loader = DataLodaer(
+        path=logger["val_zjet_data"],
+        batch_size=1000,
+        cyclic=False)
+
+    roc_zjet = ROCMeter(
+        dpath=log_dir.roc.path,
+        step=step,
+        title="Test on Z+jet",
+        prefix="zjet_"
+    )
+
+    for x, y in test_zjet_loader:
+        preds = model.predict_on_batch(x)
+        roc_zjet.append(labels=y, preds=preds)
+        out_hist.fill("test_zjet", labels=y, preds=preds)
+
+    roc_zjet.finish()
+
+    out_hist.finish()
+
+
+def main():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+	    '--log_dir', type=str, required=True,
+    	help='the directory path of dataset')
+
+    args = parser.parse_args()
+
+    log_dir = get_log_dir(path=args.log_dir, creation=False)
+
+    path_and_step = get_saved_model_paths(log_dir.saved_models.path)
+    for i, (saved_model_path, step) in enumerate(path_and_step):
+        print("\n\n\n[{i}/{total}]: {path}".format(
+            i=i, total=len(path_and_step), path=saved_model_path))
+        evaluate(
+            saved_model_path,
+            step,
+            log_dir)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/SJ-Keras/Proj-ChannelImportance/pipeline.py b/SJ-Keras/Proj-ChannelImportance/pipeline.py
@@ -0,0 +1,104 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import ROOT
+import numpy as np
+
+
+class DataLoader(object):
+    def __init__(self, path, channel, batch_size, cyclic, image_shape=(1, 33, 33)):
+        self.path = path
+        self.channel = channel
+        self.batch_size = batch_size
+        self.cyclic = cyclic
+        self._image_shape = image_shape
+
+        c, h, w = image_shpae
+
+        channel = channel.lower()
+        if channel == "cpt":
+            self._slicing = slice(0, h*w)
+        elif channel == "npt":
+            self._slicing = slice(h*w, 2*h*w)
+        elif channel == "cmu":
+            self._slicing = slice(2*h*w, 3*h*w)
+        else:
+            raise ValueError("")
+
+
+        self.root_file = ROOT.TFile(path, "READ")
+        self.tree = self.root_file.Get("jet")
+
+        self._start = 0
+
+    def __len__(self):
+        return int(self.tree.GetEntries())
+
+    def _get_data(self, idx):
+        self.tree.GetEntry(idx)
+        image = np.array(self.tree.image, dtype=np.float32)
+        image = image[self._slicing].reshape(self._image_shape)
+        label = np.int64(self.tree.label[1])
+        return (image, label)
+
+
+    def __getitem__(self, key):
+        if isinstance(key, int):
+            if key < 0 or key >= len(self):
+                raise IndexError
+            return self._get_data(key)
+        elif isinstance(key, slice):
+            x = []
+            y = []
+            for idx in xrange(*key.indices(len(self))):
+                image, label = self._get_data(idx)
+                x.append(image)
+                y.append(label)
+            x = np.array(x)
+            y = np.array(y)
+            return (x, y)
+        else:
+            raise TypeError
+
+    def next(self):
+        if self.cyclic:
+            if self._start + 1 < len(self):
+                end = self._start + self.batch_size
+                slicing = slice(self._start, end)
+                if end <= len(self):
+                    self._start = end
+                    return self[slicing]
+                else:
+                    x, y = self[slicing]
+
+                    self._start = 0
+                    end = end - len(self)
+
+                    x1, y1 = self[slice(self._start, end)]
+                    self._start = end
+
+                    np.append(x, x1, axis=0)
+                    np.append(y, y1, axis=0)
+                    return x, y
+            else:
+                self._start = 0
+                return self.next()
+        else:
+            if self._start + 1 < len(self):
+                end = self._start + self.batch_size
+                slicing = slice(self._start, end)
+                self._start = end
+                return self[slicing]
+            else:
+                raise StopIteration
+
+    def __next__(self):
+        return self.next()
+
+    def __iter__(self):
+        for start in xrange(0, len(self), self.batch_size): 
+            yield self[slice(start, start+self.batch_size)]
+
+
+