update training process

workspace/2-data_csv.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -10,41 +10,43 @@
     "import numpy as np\n",
     "import pandas as pd\n",
     "from tqdm import tqdm\n",
-    "import utils.samplefiles"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "train_wnum = 50\n",
-    "train_nnum = 50\n",
-    "test_wnum = 50\n",
-    "test_nnum = 50"
+    "import utils.samplefiles\n",
+    "import h5py"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
     "data = utils.samplefiles.SampleFile()\n",
-    "data.read_hdf('./output/train.hdf')"
+    "data.read_hdf('./output/train.hdf')\n",
+    "\n",
+    "wave, noise = data.as_dataframe(injection_parameters=True, \n",
+    "                  static_arguments=False, \n",
+    "                  command_line_arguments=False, \n",
+    "                  split_injections_noise=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 23,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4096"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "wave, noise = data.as_dataframe(injection_parameters=True, \n",
-    "                  static_arguments=False, \n",
-    "                  command_line_arguments=False, \n",
-    "                  split_injections_noise=True)"
+    "wave['h1_strain'][0].size"
    ]
   },
   {
@@ -56,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -66,6 +68,26 @@
     "nary = np.array(h1n)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4096"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "h1w[0].size"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -75,16 +97,41 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
+    "train_wnum = 50\n",
+    "train_nnum = 50\n",
+    "test_wnum = 50\n",
+    "test_nnum = 50\n",
+    "\n",
     "wtrain = wary[:train_wnum,:]\n",
     "ntrain = nary[:train_nnum,:]\n",
     "wtest = wary[train_wnum:,:]\n",
     "ntest = nary[train_nnum:,:]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(50, 4096)"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wtrain.shape"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -94,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -108,25 +155,25 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Training set name"
+    "# Training set"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:00<00:00, 299593.14it/s]\n"
+      "100%|██████████| 4096/4096 [00:00<00:00, 774600.71it/s]\n"
      ]
     }
    ],
    "source": [
     "train_name = []\n",
-    "num = 50\n",
+    "num = wtrain.shape[1]-1 # 4096\n",
     "train_name.append('label')\n",
     "for i in tqdm(range(0,num)):\n",
     "    train_name.append('point{s1}'.format(s1=i))"
@@ -134,14 +181,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:00<00:00, 63.12it/s]\n"
+      "100%|██████████| 50/50 [00:00<00:00, 120.83it/s]\n"
      ]
     }
    ],
@@ -156,29 +203,58 @@
     "        writer.writerow(ntrain[i])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_set = pd.read_csv(\"./output/train.csv\", dtype=np.float32)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(100, 4097)"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_set.shape"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "testing set name"
+    "# Testing set"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:00<00:00, 394201.50it/s]\n"
+      "100%|██████████| 4096/4096 [00:00<00:00, 457568.56it/s]\n"
      ]
     }
    ],
    "source": [
     "test_name = []\n",
-    "num = 50\n",
+    "num = wtrain.shape[1]-1 # 4096\n",
     "test_name.append('label')\n",
     "for i in tqdm(range(0,num)):\n",
     "    test_name.append('point{s1}'.format(s1=i))"
@@ -186,14 +262,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:00<00:00, 60.24it/s]\n"
+      "100%|██████████| 50/50 [00:00<00:00, 120.86it/s]\n"
      ]
     }
    ],
@@ -208,6 +284,35 @@
     "        writer.writerow(ntest[i])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_set = pd.read_csv(\"./output/test.csv\", dtype=np.float32)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(100, 4097)"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_set.shape"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -232,7 +337,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,

workspace/config_files/default.json

@@ -8,5 +8,5 @@
   "n_injection_samples": 100,
   "n_noise_samples": 100,
   "n_processes": 4,
-  "output_file_name": "train.hdf"
+  "output_file_name": "test.hdf"
 }

workspace/config_files/waveform_params.ini

@@ -13,7 +13,7 @@ injection_snr =
 [static_args]
 approximant = SEOBNRv4
 domain = time
-f_lower = 18
+f_lower = 10
 distance = 100
 waveform_length = 128
 
@@ -31,8 +31,8 @@ target_sampling_rate = 2048
 ; Define parameters for the whitening procedure. See documentation of the
 ; pycbc.types.TimeSeries.whiten() method for an explanation of what these
 ; values exactly mean.
-whitening_segment_duration = 4
-whitening_max_filter_duration = 4
+whitening_segment_duration = 1
+whitening_max_filter_duration = 1
 
 ; Define the lower and upper bound for the bandpass filter (in Hertz)
 bandpass_lower = 20
@@ -41,8 +41,8 @@ bandpass_upper = 2048
 ; Define how to align the sample around the event time. By convention, the
 ; event time is the H1 time!
 ; The sum of these values will be the the sample_length!
-seconds_before_event = 5.5
-seconds_after_event = 2.5
+seconds_before_event = 1.5
+seconds_after_event = 0.5
 
 ; alpha for the Tukey window that is used to "fade on" the waveforms
 ; It represents the fraction of the window inside the cosine tapered region.