{
"cells": [
{
"cell_type": "markdown",
"id": "a19216bf-7568-46b1-b55c-8c6cc970ee88",
"metadata": {},
"source": [
"# Part of Speech Tagging"
]
},
{
"cell_type": "markdown",
"id": "cae9ee33-f0a0-43a4-9373-c3c45b56cf7e",
"metadata": {},
"source": [
" ## Imports"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "6708d97c-f4fb-459d-bea0-8a1ddadab088",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np"
]
},
{
"cell_type": "markdown",
"id": "297f6b9c-e16c-44a2-9c4e-cc2f4c801053",
"metadata": {},
"source": [
"## Helix Problem"
]
},
{
"cell_type": "code",
"execution_count": 292,
"id": "a93acc9b-c125-4a37-93c6-48c7fd5a0ec4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 0, 1, 2, 3, 4, 5],\n",
" [ 6, 7, 8, 9, 10, 11],\n",
" [12, 13, 14, 15, 16, 17],\n",
" [18, 19, 20, 21, 22, 23],\n",
" [24, 25, 26, 27, 28, 29]])"
]
},
"execution_count": 292,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"start_pos = (2, 5) \n",
"i, j = start_pos\n",
"i_min = 0\n",
"j_min = 0\n",
"i_max = 4\n",
"j_max = 5\n",
"assert (i == i_min) |(i == i_max)| (j == j_min)| (j == j_max)\n",
"\n",
"mat = np.arange(0, (i_max+1)*(j_max+1),1).reshape((i_max+1),(j_max+1)); mat"
]
},
{
"cell_type": "code",
"execution_count": 327,
"id": "c02d2ce1-1522-4dd9-b687-ec36244f5d7e",
"metadata": {},
"outputs": [],
"source": [
"def right(i,j): return (i,j+1)\n",
"def down(i,j): return (i+1,j)\n",
"def left(i,j): return (i,j-1)\n",
"def up(i,j): return (i-1,j)\n",
"\n",
"directions = ['r', 'd', 'l', 'u']\n",
"\n",
"def get_initial_dir(start_pos, i_min, j_min, i_max, j_max):\n",
" i, j = start_pos\n",
" # assert i_min < i_max\n",
" # assert j_min < j_max\n",
" assert (i == i_min) |(i == i_max)| (j == j_min)| (j == j_max)\n",
" if (i == i_min) & (j<j_max): return 'r'\n",
" elif (i < i_max) & (j == j_max): return 'd'\n",
" elif (i == i_max) & (j > j_min): return 'l'\n",
" elif (i > i_min) & (j == j_min): return 'u'\n",
" elif (j_min >= j_max): return 'u'\n",
" elif (i_min >= i_max): return 'l'\n",
" else: raise Exception ('Not Implemented')\n",
"\n",
"\n",
"\n",
"def move(curr_pos, curr_dir, i_min, j_min, i_max, j_max):\n",
" new_pos = curr_pos\n",
" new_dir= curr_dir\n",
" i, j = curr_pos\n",
" if curr_dir == 'r':\n",
" if j < j_max : new_pos = right(i,j)\n",
" else: new_pos = down(i,j); new_dir = 'd'\n",
" elif curr_dir == 'd':\n",
" if i < i_max : new_pos = down(i,j)\n",
" else: new_pos = left(i,j); new_dir = 'l'\n",
" elif curr_dir == 'l':\n",
" if j > j_min : new_pos = left(i,j)\n",
" else: new_pos = up(i,j); new_dir = 'u'\n",
" elif curr_dir == 'u':\n",
" if i > i_min : new_pos = up(i,j)\n",
" else: new_pos = right(i,j); new_dir = 'r'\n",
" \n",
" return new_pos, new_dir\n",
"\n",
"\n",
"def move_inner(curr_pos, curr_dir):\n",
" new_pos = curr_pos\n",
" i, j = curr_pos\n",
" if curr_dir == 'r': new_pos = down(i,j)\n",
" elif curr_dir == 'd': new_pos = left(i,j)\n",
" elif curr_dir == 'l': new_pos = up(i,j)\n",
" elif curr_dir == 'u': new_pos = right(i,j)\n",
" return new_pos\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 328,
"id": "4c9ac123-085b-4a07-a8b0-67729a673ba3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(1, 5) d 0 0 4 5 29\n",
"(1, 3) r 1 1 3 4 11\n",
"(2, 2) l 2 2 2 3 1\n"
]
},
{
"data": {
"text/plain": [
"array([[ 0, 1, 2, 3, 4, 5],\n",
" [ 6, 7, 8, 9, 10, 11],\n",
" [12, 13, 14, 15, 16, 17],\n",
" [18, 19, 20, 21, 22, 23],\n",
" [24, 25, 26, 27, 28, 29]])"
]
},
"execution_count": 328,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def make_loop(start_pos, i_min, j_min, i_max, j_max, idx_list=[]):\n",
" curr_pos = start_pos\n",
" curr_dir = get_initial_dir(start_pos, i_min, j_min, i_max, j_max)\n",
" step = 0\n",
" max_steps = 2*((i_max-i_min+1)+(j_max -j_min+1)-1) -1; max_steps\n",
" while step < (max_steps-2):\n",
" new_pos, new_dir = move(curr_pos,curr_dir, i_min, j_min, i_max, j_max)\n",
" curr_pos, curr_dir = new_pos, new_dir\n",
" idx_list.append(curr_pos)\n",
" step +=1\n",
" # print(f\"IDX_LIST : {len(idx_list), mat[idx_list[0]], mat[idx_list[-1]]}\")\n",
" return curr_pos, curr_dir, step\n",
"\n",
"def do_helix(start_pos, i_min, j_min, i_max, j_max, idx_list=[]):\n",
" total_steps_max = (i_max-i_min+1)*(j_max-j_min+1) -1\n",
" curr_pos = start_pos\n",
" # print(mat[curr_pos[0], curr_pos[1]])\n",
" if (total_steps_max<=0): return idx_list\n",
" # elif (i_min >= i_max)|(j_min>=j_max): return idx_list.append(curr_pos)\n",
" else:\n",
" idx_list.append(curr_pos)\n",
" curr_pos, curr_dir, step = make_loop(curr_pos, i_min, j_min, i_max, j_max, idx_list)\n",
" print(curr_pos,curr_dir, i_min, j_min, i_max, j_max, total_steps_max)\n",
" \n",
" total_steps_max = total_steps_max - step +1\n",
" i_min +=1\n",
" i_max -=1\n",
" j_min +=1\n",
" j_max -=1\n",
" new_pos = move_inner(curr_pos, curr_dir)\n",
" \n",
" return do_helix(new_pos, i_min, j_min, i_max, j_max, idx_list)\n",
" \n",
"idx= np.array(do_helix(start_pos, i_min, j_min, i_max, j_max))\n",
"mat"
]
},
{
"cell_type": "code",
"execution_count": 322,
"id": "cea73394-6a26-48ef-a291-95fdabba76d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(30, 2)"
]
},
"execution_count": 322,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"idx.shape"
]
},
{
"cell_type": "code",
"execution_count": 323,
"id": "c418e4dd-c104-49fc-afa8-5ee78abc34d9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2 5 17\n",
"3 5 23\n",
"4 5 29\n",
"4 4 28\n",
"4 3 27\n",
"4 2 26\n",
"4 1 25\n",
"4 0 24\n",
"3 0 18\n",
"2 0 12\n",
"1 0 6\n",
"0 0 0\n",
"0 1 1\n",
"0 2 2\n",
"0 3 3\n",
"0 4 4\n",
"0 5 5\n",
"1 5 11\n",
"1 4 10\n",
"2 4 16\n",
"3 4 22\n",
"3 3 21\n",
"3 2 20\n",
"3 1 19\n",
"2 1 13\n",
"1 1 7\n",
"1 2 8\n",
"1 3 9\n",
"2 3 15\n",
"2 2 14\n"
]
}
],
"source": [
"for i,j in idx:\n",
" print(i, j, mat[i,j])"
]
},
{
"cell_type": "markdown",
"id": "aa3509e6-c609-4675-bb28-38ef287539df",
"metadata": {},
"source": [
"# Part of Speech Tagging"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "05cc4480-8039-4388-88d3-e23809743133",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "40ead112-59d1-4283-9576-68c901745a04",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "6869d068-3796-44d3-957c-cf4b4441915e",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}