GSoC evaluation test updated as per suggestion.

Jayanta_Banik_AWAKE_GSoC_EvaL.ipynb

@@ -0,0 +1,200 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#importing libraries\n",
+    "from os import listdir\n",
+    "import h5py\n",
+    "\n",
+    "#defining variables\n",
+    "input_path = \"C:\\\\Users\\\\scien\\\\Desktop\\\\AWAKE\\\\\" #change to path of where files are stored\n",
+    "output_path = input_path\n",
+    "data = [] \n",
+    "records = []\n",
+    "\n",
+    "#reading files\n",
+    "files_list = listdir(input_path) #reading all available files\n",
+    "file = h5py.File(input_path+files_list[0], 'r') #reading file\n",
+    "key_s = list(file.keys())\n",
+    "for i in key_s:\n",
+    "    data.append(file[i])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CERN Local time - CEST\n",
+      "2018-11-11 19:48:28 CET+0100\n",
+      "UTC time\n",
+      "2018-11-11 18:48:28 UTC+0000\n"
+     ]
+    }
+   ],
+   "source": [
+    "import datetime\n",
+    "import pytz\n",
+    "#defining a datetime object    \n",
+    "cern_local = pytz.timezone('Europe/Zurich') \n",
+    "\n",
+    "#reading the files atributes of time as first 19 digits\n",
+    "nano_time = int((files_list[0])[:19])\n",
+    "    \n",
+    "#assuming the nanoseconds is in UTC timezone converting nanoseconds to seconds and then converting into datetime object and then converting into utc\n",
+    "utc_dt = pytz.utc.localize(datetime.datetime.utcfromtimestamp(nano_time/pow(10,9))) #converting nanoseconds to seconds\n",
+    "#converting to cern local time\n",
+    "loc_dt = utc_dt.astimezone(cern_local)\n",
+    "print(\"CERN Local time - CEST\")\n",
+    "print(loc_dt.strftime('%Y-%m-%d %H:%M:%S %Z%z'))\n",
+    "print(\"UTC time\")\n",
+    "print(utc_dt.strftime('%Y-%m-%d %H:%M:%S %Z%z'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#defining a function to explore all nodes of dataset\n",
+    "def explorer(data):\n",
+    "    try:\n",
+    "        t = list(data.keys())\n",
+    "        for i in range(0,len(t)):\n",
+    "            b = data.get(t[i])\n",
+    "            explorer(b)\n",
+    "    except:\n",
+    "        records.append([str(data.name)])\n",
+    "        #saving size, shape and type of data\n",
+    "        try:\n",
+    "            records[-1].append(str(data.size))\n",
+    "            records[-1].append(str(data.shape))\n",
+    "            records[-1].append(str(data.dtype))\n",
+    "            \n",
+    "        except:\n",
+    "            records[-1].append(str(type(data)))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#exploring all the groups and datasets\n",
+    "def data_tree():\n",
+    "    for subfiles in data:\n",
+    "        explorer(subfiles)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import csv\n",
+    "def wrritter():\n",
+    "    #converting to dataframe\n",
+    "    df = pd.DataFrame(np.array(records))\n",
+    "    #saving into csv\n",
+    "    with open(output_path + 'output_box.csv', 'w') as csvFile:\n",
+    "        writer = csv.writer(csvFile)\n",
+    "        writer.writerows([[\"path\",\"size\",\"shape\",\"type\"]])\n",
+    "        writer.writerows(df[0])\n",
+    "    csvFile.close()  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wrritter()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#reading dataset\n",
+    "image_1D = list(data[0].__getitem__(\"/AwakeEventData/XMPP-STREAK/StreakImage/streakImageData\"))\n",
+    "\n",
+    "img_height = list(data[0].__getitem__(\"/AwakeEventData/XMPP-STREAK/StreakImage/streakImageHeight\"))\n",
+    "\n",
+    "img_width = list(data[0].__getitem__(\"/AwakeEventData/XMPP-STREAK/StreakImage/streakImageWidth\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#reshape !D into 2D image\n",
+    "image_2D =np.reshape(image_1D, (img_height[0],img_width[0]))\n",
+    "#print(image_2D.shape)\n",
+    "#print(image_2D.ndim)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy.signal import medfilt\n",
+    "#using filter\n",
+    "image_ = (medfilt(image_2D))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from matplotlib import pyplot as plt\n",
+    "#visualising image\n",
+    "imgplot = plt.imshow(image_)\n",
+    "#saving image\n",
+    "plt.imsave(output_path + \"test_2D_image.png\", image_)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}