{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import os\n",
"\n",
"import pickle"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def ones_to_zeros(ET_inner_dict, ET_outer_dict):\n",
" \n",
" for k in range(0,len(ET_inner_dict)):\n",
" for i in range(ET_inner_dict[k].shape[0]):\n",
" equal_inner = np.array_equal(ET_inner_dict[k][i],np.ones_like(ET_inner_dict[k][i]))\n",
" equal_outer = np.array_equal(ET_outer_dict[k][i],np.ones_like(ET_outer_dict[k][i]))\n",
" if equal_inner or equal_outer:\n",
" ET_inner_dict[k][i]=np.zeros_like(ET_inner_dict[k][i])\n",
" ET_outer_dict[k][i]=np.zeros_like(ET_outer_dict[k][i])\n",
" \n",
" return ET_inner_dict, ET_outer_dict"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def double_size(X_in):\n",
"\n",
" X_out = np.zeros(\n",
" shape=(2*X_in.shape[0],2*X_in.shape[1],1),\n",
" dtype=np.float32\n",
" )\n",
" \n",
" for i in range(X_in.shape[0]):\n",
" for j in range(X_in.shape[1]):\n",
" \n",
" if X_in[i,j]!=0:\n",
" value = X_in[i,j]/4\n",
" X_out[2*i,2*j]=value\n",
" X_out[2*i+1,2*j]=value\n",
" X_out[2*i,2*j+1]=value\n",
" X_out[2*i+1,2*j+1]=value\n",
" return X_out"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def insert(X_inner, X_outer):\n",
" X=X_outer\n",
" \n",
" for i in range(12,40):\n",
" for j in range(16,48):\n",
" X[i,j]=X_inner[i-12,j-16]\n",
" \n",
" return X"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def generate_HCAL_images(ET_inner_dict, ET_outer_dict):\n",
" \n",
" output_pics = {}\n",
" \n",
" pic = np.array(np.zeros(shape=(52,64,1), dtype=np.float32))\n",
" \n",
" for j in range(len(ET_inner_dict)):\n",
" \n",
" \n",
" output_pics[j]=np.array([pic for i in range(len(ET_inner_dict[j]))]) \n",
" \n",
" \n",
" for j in range(len(ET_inner_dict)):\n",
" \n",
" for k in range(len(ET_inner_dict[j])):\n",
" \n",
" ET_image = insert(ET_inner_dict[j][k], double_size(ET_outer_dict[j][k]))\n",
" ET_image = np.flip(ET_image, axis = 0)\n",
" \n",
" output_pics[j][k]= ET_image\n",
" \n",
" print('Done batch {0}'.format(j+1))\n",
" \n",
" return output_pics"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"ET_inner_dict={}\n",
"ET_outer_dict={}\n",
"\n",
"i=0\n",
"#while os.path.exists('/disk/lhcb_data/davide/HCAL_project_full_event/npy/DplusMuNu_Full/ET_inner/batch_'+str(i)+'.npy'):\n",
"while i < 2:\n",
" ET_inner_dict[i]=np.load('/disk/lhcb_data/davide/HCAL_project_full_event/npy/DplusMuNu_Full/ET_inner/batch_'+str(i)+'.npy')\n",
" ET_outer_dict[i]=np.load('/disk/lhcb_data/davide/HCAL_project_full_event/npy/DplusMuNu_Full/ET_outer/batch_'+str(i)+'.npy')\n",
"\n",
" i+=1\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1008x432 with 2 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"mean_inner_ET=np.mean(ET_inner_dict[0], axis=0, keepdims=True).reshape(32,32)\n",
"plt.subplot(1,2,1)\n",
"plt.imshow(mean_inner_ET[2:mean_inner_ET.shape[0]-2,0:mean_inner_ET.shape[0]])\n",
"plt.subplot(1,2,2)\n",
"mean_outer_ET=np.mean(ET_outer_dict[0], axis=0, keepdims=True).reshape(32,32)\n",
"plt.imshow(mean_outer_ET[3:mean_outer_ET.shape[0]-3,0:mean_outer_ET.shape[0]])\n",
"fig = plt.gcf()\n",
"fig.set_size_inches(14,6)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"ET_inner_dict, ET_outer_dict = ones_to_zeros(ET_inner_dict, ET_outer_dict)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"#cutting out useless pixels\n",
"for i in range(len(ET_inner_dict)):\n",
" ET_inner_dict[i]=ET_inner_dict[i][:,2:ET_inner_dict[i].shape[1]-2,:]\n",
" ET_outer_dict[i]=ET_outer_dict[i][:,3:ET_outer_dict[i].shape[1]-3,:]\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"((25000, 28, 32), (25000, 26, 32))\n"
]
}
],
"source": [
"#Check cut dict dimensions\n",
"print(ET_inner_dict[0].shape, ET_outer_dict[0].shape)\n",
"#is\n",
"#(?, 28, 32), (?,26, 32)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"def delete_undetected_events(X_inner, X_outer):\n",
"\n",
" pos_rejected={}\n",
" \n",
" for i in range(len(X_inner)):\n",
" pos_rejected[i]=[]\n",
" \n",
" for j in range(X_inner[i].shape[0]):\n",
" \n",
" equal_inner = np.array_equal(X_inner[i][j],np.zeros_like(X_inner[i][j]))\n",
" equal_outer = np.array_equal(X_outer[i][j],np.zeros_like(X_outer[i][j]))\n",
" \n",
" \n",
" X_inner_filtered={}\n",
" X_outer_filtered={}\n",
" for i in range(len(X_inner)):\n",
" \n",
" X_inner_filtered[i]=np.delete(X_inner[i],pos_rejected[i],axis=0)\n",
" X_outer_filtered[i]=np.delete(X_outer[i],pos_rejected[i],axis=0)\n",
" \n",
" return X_inner_filtered, X_outer_filtered"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"ET_inner_filtered, ET_outer_filtered = delete_undetected_events(ET_inner_dict,ET_outer_dict)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.image.AxesImage at 0x7fb56b8f0350>"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 2 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"plt.subplot(1,2,1)\n",
"plt.imshow(ET_inner_filtered[0][1].reshape(28,32),cmap='gray')\n",
"plt.subplot(1,2,2)\n",
"plt.imshow(ET_outer_filtered[0][1].reshape(26,32),cmap='gray')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.image.AxesImage at 0x7fb56b884b90>"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"i=1\n",
"plt.imshow(np.flip(insert(ET_inner_filtered[0][i],double_size(ET_outer_filtered[0][i])).reshape(52,64),axis=0))"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done batch 1\n",
"Done batch 2\n"
]
}
],
"source": [
"output_pics = generate_HCAL_images(ET_inner_filtered,ET_outer_filtered)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(25000, 52, 64, 1)"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"output_pics[0].shape"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"for i in range(len(output_pics)):\n",
" with open('/disk/lhcb_data/davide/HCAL_project_full_event/reco/sample'+str(i)+'.pickle', 'wb') as handle:\n",
" pickle.dump(output_pics[i], handle, protocol=pickle.HIGHEST_PROTOCOL)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"a=np.array([output_pics[0][i].sum() for i in range(len(output_pics[0]))])"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"plt.hist(a/1000,bins=70);"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"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": "2.7.15"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Davide Lancierini