forked from info-ruc/tm23projects
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
332 additions
and
0 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,332 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 71, | ||
"id": "ba5fb3f7", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"import torch\n", | ||
"import torch.nn as nn\n", | ||
"import math\n", | ||
"import re\n", | ||
"from torch.utils.data import Dataset, DataLoader\n", | ||
"import collections\n", | ||
"\n", | ||
"class CosineSimilarity(nn.Module):\n", | ||
" def forward(self, tensor_1,tensor_2):\n", | ||
" normalized_tensor_1=tensor_1/tensor_1.norm(dim=-1,keepdim=True)\n", | ||
" normalized_tensor_2=tensor_2/tensor_2.norm(dim=-1,keepdim=True)\n", | ||
" return (normalized_tensor_1*normalized_tensor_2).sum(dim=-1)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 73, | ||
"id": "b8330127", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"name": "stdout", | ||
"output_type": "stream", | ||
"text": [ | ||
"tensor([-0.0021], grad_fn=<SumBackward1>)\n", | ||
"tensor([1.0000], grad_fn=<SumBackward1>)\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"#for test\n", | ||
"input1 = torch.randn(1,200,requires_grad=True)\n", | ||
"input2 = torch.randn(1,200,requires_grad=True)\n", | ||
"con = CosineSimilarity()\n", | ||
"s1 = con(input1,input2)\n", | ||
"s2 = torch.cosine_similarity(input1,input1)\n", | ||
"print(s1)\n", | ||
"print(s2)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 74, | ||
"id": "0b278674", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# dealwith text\n", | ||
"def tokenize(text):\n", | ||
" fileters = ['!', '\"', '#', '$', '%', '&', '\\(', '\\)', '\\*', '\\+', ',', '-', '\\.', '/', ':', ';', '<', '=', '>', '\\?', '@'\n", | ||
" , '\\[', '\\\\', '\\]', '^', '_', '`', '\\{', '\\|', '\\}', '~', '\\t', '\\n', '\\x97', '\\x96', '”', '“', '0', '1', '2',\n", | ||
" '3', '4', '5', '6', '7', '8', '9', '10']\n", | ||
" text = re.sub(\"<.*?>\", \" \", text, flags=re.S)\n", | ||
" text = re.sub(\"|\".join(fileters), \" \", text, flags=re.S)\n", | ||
" return [i.strip() for i in text.split()]" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 75, | ||
"id": "416c777e", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"name": "stdout", | ||
"output_type": "stream", | ||
"text": [ | ||
"['a', 'dnjsdf']\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"#test \n", | ||
"res = tokenize(\"a3dnjsdf99099_\")\n", | ||
"print(res)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 124, | ||
"id": "358ce47d", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"#gen dict\n", | ||
"def gendict(x,y):\n", | ||
" z = x + '!' + y\n", | ||
" t = tokenize(z)\n", | ||
" li = list(set(t))\n", | ||
" print('diction:')\n", | ||
" print(li)\n", | ||
" tinydict = {}\n", | ||
" it = 1;\n", | ||
" for i in li:\n", | ||
" tinydict[i] = it\n", | ||
" it = it + 1\n", | ||
" for i in li:\n", | ||
" tinydict[i] = tinydict[i]/(len(li)+1)\n", | ||
" print('kv:')\n", | ||
" print(tinydict)\n", | ||
" xx = []\n", | ||
" yy = []\n", | ||
" for ix in tokenize(x):\n", | ||
" xx.append(tinydict[ix])\n", | ||
" for iy in tokenize(y):\n", | ||
" yy.append(tinydict[iy])\n", | ||
" #print(xx)\n", | ||
" #print(yy)\n", | ||
" zz = (xx,yy)\n", | ||
" #print('text to number:')\n", | ||
" #print(zz)\n", | ||
" return (xx,yy)\n" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 125, | ||
"id": "d73f236e", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"name": "stdout", | ||
"output_type": "stream", | ||
"text": [ | ||
"diction:\n", | ||
"['a', 'aa', 'dnjsdf']\n", | ||
"kv:\n", | ||
"{'a': 0.25, 'aa': 0.5, 'dnjsdf': 0.75}\n", | ||
"([0.25, 0.75], [0.25, 0.75, 0.5])\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"#test gendict\n", | ||
"z = gendict(\"a3dnjsdf99099_\",\"a3dnjsdf99099aa_\")\n", | ||
"print(z)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 126, | ||
"id": "03552361", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"#f(x,y)\n", | ||
"def f(x,y):\n", | ||
" dic_x = tokenize(x)\n", | ||
" dic_x_count = len(dic_x)\n", | ||
" print(dic_x)\n", | ||
" dic_y = tokenize(y)\n", | ||
" dic_y_count = len(dic_y)\n", | ||
" print(dic_y)\n", | ||
" sx = 0.0\n", | ||
" sy = 0.0\n", | ||
" for xx in dic_x:\n", | ||
" if xx in dic_y:\n", | ||
" sx = sx + 1.0/dic_x_count\n", | ||
" for yy in dic_y:\n", | ||
" if yy in dic_x:\n", | ||
" sy = sy + 1.0/dic_y_count\n", | ||
" print(sx)\n", | ||
" print(sy)\n", | ||
" return max(sx,sy)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 127, | ||
"id": "4657d7f2", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"name": "stdout", | ||
"output_type": "stream", | ||
"text": [ | ||
"['dqn', 'n', 'j', 's']\n", | ||
"['dqn', 'js']\n", | ||
"0.25\n", | ||
"0.5\n", | ||
"0.5\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"#test f(x,y)\n", | ||
"x = \"3dqn1n1j1s99099_\"\n", | ||
"y = \"3dqn1js99099_\"\n", | ||
"test_f = f(x,y)\n", | ||
"print(test_f)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 128, | ||
"id": "bbbd7911", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"def embed(x,y):\n", | ||
" dic_x = tokenize(x)\n", | ||
" dic_x_count = len(dic_x)\n", | ||
" dic_y = tokenize(y)\n", | ||
" dic_y_count = len(dic_y)\n", | ||
" emb = torch.nn.Embedding(dic_x_count + dic_y_count,5)\n", | ||
" " | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 132, | ||
"id": "0ba94e55", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"#g(x,y)\n", | ||
"def g(x,y):\n", | ||
" (xx,yy) = gendict(x,y)\n", | ||
" count = min(len(xx),len(yy))\n", | ||
" print(count)\n", | ||
" tx = []\n", | ||
" ty = []\n", | ||
" for i in range(0,count):\n", | ||
" tx.append(xx[i])\n", | ||
" ty.append(yy[i])\n", | ||
" print(tx)\n", | ||
" print(ty)\n", | ||
" return con(torch.tensor(tx),torch.tensor(ty))" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 134, | ||
"id": "1b17ae28", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"name": "stdout", | ||
"output_type": "stream", | ||
"text": [ | ||
"diction:\n", | ||
"['j', 'n', 's', 'js', 'dqn']\n", | ||
"kv:\n", | ||
"{'j': 0.16666666666666666, 'n': 0.3333333333333333, 's': 0.5, 'js': 0.6666666666666666, 'dqn': 0.8333333333333334}\n", | ||
"2\n", | ||
"[0.8333333333333334, 0.3333333333333333]\n", | ||
"[0.8333333333333334, 0.6666666666666666]\n", | ||
"tensor(0.9570)\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"#test g(x,y)\n", | ||
"x = \"3dqn1n1j1s99099_\"\n", | ||
"y = \"3dqn1js99099_\"\n", | ||
"test_g = g(x,y)\n", | ||
"print(test_g)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 144, | ||
"id": "1db58b72", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"name": "stdout", | ||
"output_type": "stream", | ||
"text": [ | ||
"['int', 'sum', 'int', 'x', 'int', 'y', 'return', 'x', 'y']\n", | ||
"['int', 'summary', 'float', 'z', 'return', 'z']\n", | ||
"0.4444444444444444\n", | ||
"0.3333333333333333\n", | ||
"diction:\n", | ||
"['y', 'return', 'x', 'summary', 'sum', 'int', 'z', 'float']\n", | ||
"kv:\n", | ||
"{'y': 0.1111111111111111, 'return': 0.2222222222222222, 'x': 0.3333333333333333, 'summary': 0.4444444444444444, 'sum': 0.5555555555555556, 'int': 0.6666666666666666, 'z': 0.7777777777777778, 'float': 0.8888888888888888}\n", | ||
"6\n", | ||
"[0.6666666666666666, 0.5555555555555556, 0.6666666666666666, 0.3333333333333333, 0.6666666666666666, 0.1111111111111111]\n", | ||
"[0.6666666666666666, 0.4444444444444444, 0.8888888888888888, 0.7777777777777778, 0.2222222222222222, 0.7777777777777778]\n", | ||
"tensor(0.8156)\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"#result\n", | ||
"x = \"int sum(int x,int y){return x - y;}\"\n", | ||
"y = \"int summary(float z){return z;}\"\n", | ||
"s = max(f(x,y), g(x,y))\n", | ||
"print(s)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "c8b1a5ce", | ||
"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": "3.8.10" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 5 | ||
} |
Empty file.