Created
August 10, 2018 13:57
-
-
Save Shirataki2/5663f04943986cd5264e7b9c719d9095 to your computer and use it in GitHub Desktop.
Markov-Chain.ipynb
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
{ | |
"cells": [ | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-06-24T13:27:05.724479Z", | |
"start_time": "2018-06-24T13:27:05.493299Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "from janome.tokenizer import Tokenizer\nimport random\nimport re\nfrom collections import defaultdict\n\nclass MarkovChain:\n def isalnum(self, s):\n return self.alnumReg.match(s) is not None\n\n def __init__(self, sentence, maxn=512):\n self.tk = Tokenizer(mmap=True)\n self.alnumReg = re.compile(r'^[a-zA-Z0-9]+$')\n self.sentence = sentence\n self.pre = ''\n self.head = []\n self.maxn = maxn\n\n def convertWakati(self, sentence):\n make = self.tk.tokenize(sentence, wakati=True)\n return ' '.join(make)\n\n def makeWakatiText(self, sentence):\n wakati = self.convertWakati(sentence)\n self.kutenNum = wakati.count('ใ')\n words = wakati.split(' ')\n words.append('\\n')\n return words\n\n def buildTable(self, words):\n markov = defaultdict(list)\n for word in words:\n if not self.pre:\n self.pre = word\n self.head.append(word)\n else:\n markov[self.pre].append(word)\n self.pre = word\n return markov\n\n def buildSentence(self, table):\n result = self.pre = random.choice(self.head)\n kuten = 0\n for _ in range(0, int(self.maxn)):\n self.pre = random.choice(table[self.pre])\n if self.pre == '\\n':\n break\n if self.isalnum(self.pre):\n result += (self.pre + ' ')\n else:\n result += self.pre\n if self.pre == 'ใ':\n kuten += 1\n if kuten == self.kutenNum:\n break\n return result\n\n def makeMarkovText(self):\n if self.sentence == '':\n return '็ๆใงใใชใใฃใใ'\n text = re.sub(r'(\\n| |\\s)', '', self.sentence)\n words = self.makeWakatiText(text)\n table = self.buildTable(words)\n text = self.buildSentence(table)\n self.kutenNum = 0\n self.pre = ''\n self.head = []\n return text", | |
"execution_count": 1, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-06-05T11:41:29.301464Z", | |
"start_time": "2018-06-05T11:41:29.293958Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "txt = \"\"\"ใซใคใบ๏ผใซใคใบ๏ผใซใคใบ๏ผใซใคใบใ ใ ใใใใใใใใใใใใใ\n ใใใใใใใใใใใใใใใ๏ผ๏ผ๏ผ ใใใใใใโฆใใโฆใใฃใใฃใผ๏ผใ\n ใใใใใใใ๏ผ๏ผ๏ผใซใคใบใซใคใบใซใคใบใ ใใใใใใใใใ๏ผ๏ผ๏ผ ใใ\n ใฏใณใซใฏใณใซ๏ผใฏใณใซใฏใณใซ๏ผในใผใใผในใผใใผ๏ผในใผใใผในใผใใผ๏ผ\n ใใๅใใ ใชใโฆใใใใ ใใฏใใฃ๏ผใซใคใบใปใใฉใณใฝใฏใผใบใใใฎ\n ๆก่ฒใใญใณใใฎ้ซชใใฏใณใซใฏใณใซใใใใ๏ผใฏใณใซใฏใณใซ๏ผใใใ๏ผ๏ผ\n ้้ใใ๏ผใขใใขใใใใใ๏ผใขใใขใ๏ผใขใใขใ๏ผ้ซช้ซชใขใใขใ๏ผ\n ใซใชใซใชใขใใขใโฆใใ ใใใ ใใใ ใ๏ผ๏ผ ๅฐ่ชฌ12ๅทปใฎใซใคใบใใใใใใใฃใใใ ๏ผ๏ผ\n ใใใใใโฆใใใโฆใใฃใใใใใใ๏ผ๏ผใตใใใใใใใใฃ๏ผ๏ผ\n ใขใใก2ๆๆพ้ใใใฆ่ฏใใฃใใญใซใคใบใใ๏ผใใใใใใใ๏ผใใใใ๏ผ\n ใซใคใบใใ๏ผใใใใ๏ผใใฃใใใใใ๏ผ\n ใณใใใฏ2ๅทปใ็บๅฃฒใใใฆๅฌใโฆใใใใใใใใใ๏ผ๏ผ๏ผ\n ใซใใใใใใใใใใ๏ผ๏ผใใใใใใใใใใ๏ผ๏ผ\n ใใใใใใใใใใใใ๏ผ๏ผ๏ผใณใใใฏใชใใฆ็พๅฎใใใชใ๏ผ๏ผ๏ผ๏ผ\n ใโฆๅฐ่ชฌใใขใใกใใใ่ใใใโฆ ใซ ใค ใบ ใก ใ ใ ใฏ ็พๅฎ ใ ใ ใช ใ๏ผ\n ใซใใใใใใใใใใใใใใใ๏ผ๏ผใใใใใใใใใใใใ๏ผ๏ผ\n ใใใชใใใใใใใ๏ผ๏ผใใใใใใใใใใใใใใ๏ผ๏ผใฏใใใใใใใใ๏ผ๏ผ\n ใใซใฑใฎใใขใใใใใ๏ผ๏ผ ใใฎ๏ผใกใใใใผ๏ผใใใฆใใ๏ผ๏ผ\n ็พๅฎใชใใใใโฆใฆโฆใ๏ผ๏ผ่ฆโฆใฆใ๏ผ่กจ็ด็ตตใฎใซใคใบใกใใใๅใ่ฆใฆใ๏ผ\n ่กจ็ด็ตตใฎใซใคใบใกใใใๅใ่ฆใฆใใ๏ผใซใคใบใกใใใๅใ่ฆใฆใใ๏ผ\n ๆฟ็ตตใฎใซใคใบใกใใใๅใ่ฆใฆใใ๏ผ๏ผ ใขใใกใฎใซใคใบใกใใใๅใซ่ฉฑใใใใฆใใ๏ผ๏ผ๏ผ\n ใใใฃใโฆไธใฎไธญใพใ ใพใ ๆจใฆใใขใณใใใชใใใ ใญใฃ๏ผ ใใใฃใปใใใใใใใใ๏ผ๏ผ๏ผ\n ๅใซใฏใซใคใบใกใใใใใ๏ผ๏ผ ใใฃใใใฑใใฃ๏ผ๏ผ ใฒใจใใงใงใใใใ๏ผ๏ผ๏ผ\n ใใใณใใใฏใฎใซใคใบใกใใใใใใใใใใใใใใใใ๏ผ๏ผ\n ใใใใใใใใใใใใใใใใใใ๏ผ๏ผ๏ผ๏ผ ใใฃใใใใใฃใใใใใขใณๆงใใ๏ผ๏ผ\n ใทใใทใจในใฟใผ๏ผ๏ผใขใณใชใจใใฟใใใใใใใ๏ผ๏ผ๏ผใฟใใต๏ฝงใใใใ๏ผ๏ผ\n ใใใฃใใ ใใ๏ผ๏ผไฟบใฎๆณใใใซใคใบใธๅฑใ๏ผ๏ผใใซใฑใฎใใขใฎใซใคใบใธๅฑใ\"\"\"", | |
"execution_count": 2, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-05-31T08:36:02.969657Z", | |
"start_time": "2018-05-31T08:35:58.087294Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "markov = MarkovChain(txt,maxn=100)", | |
"execution_count": 3, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-05-31T08:36:04.978676Z", | |
"start_time": "2018-05-31T08:36:03.728371Z" | |
}, | |
"scrolled": false, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "for i in range(5):\n print(markov.makeMarkovText())\n print()", | |
"execution_count": 4, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": "ใซใคใบใธๅฑใ๏ผ๏ผ๏ผใซใคใบใซใคใบใซใคใบใ ใใใใใใใใใ๏ผใฒใจใใงใงใใใใ๏ผ๏ผใขใใก2ๆๆพ้ใใใฆโฆใฆ่ฏใใฃใใขใณใใใชใใใ ใญใฃ๏ผใใใใใใ๏ผ้้ใใใขใณใใใชใใใฏใซใคใบใกใใใๅใ่ฆใฆใ๏ผ่กจ็ด็ตตใฎใซใคใบใกใใใๅใใฏใณใซใฏใณใซใใใใ๏ผ๏ผใใฃใใขใณๆงใใ๏ผ๏ผ๏ผใขใใก2ๆๆพ้ใใใฆ่ฏใใฃใใใฑใใฃ๏ผใซ่ฉฑใใใใฆใใ๏ผใใใใใใใใใใใใใใ๏ผใตใใใใใใใใฃ๏ผ๏ผ่กจ็ด็ตตใฎใซใคใบ๏ผใท\n\nใซใคใบใกใใใๅใ่ฆใฆใใ๏ผใขใใขใ๏ผใขใณใชใจใใฟใใใใใใใ๏ผๅใ่ฆใฆใใ๏ผใซใชใซใชใขใใขใโฆใใ๏ผใฒใจใใงใงใใใใ๏ผไฟบใฎใซใคใบใกใใใๅใซใใใใใใใใใใ๏ผใขใใก2ๆๆพ้ใใใฆโฆใ๏ผใใใใใใใใใ๏ผใใใใขใณๆงใใ๏ผใใใใใใใใใใใใใใ๏ผ๏ผใใใใ๏ผ๏ผ๏ผใฟใใต๏ฝงใใใใ๏ผ็พๅฎใใใชใ๏ผ่กจ็ด็ตตใฎใซใคใบใกใใใๅใใฏใณใซใฏใณใซ๏ผ็พๅฎใชใใใใโฆใใฃใผ๏ผ๏ผ๏ผ๏ผใซใชใซใชใขใใขใโฆใฆใใ๏ผใขใใขใ๏ผใใใใใใใโฆๅฐ่ชฌใ\n\nใซใคใบใกใใใๅใซใใใใใใใใใใใใใใใ๏ผ๏ผใขใใก2ๆๆพ้ใใใฆโฆใใฃใใฃใใใใใใโฆใฆ่ฏใใฃใใขใณใใใชใใใฏ็พๅฎใใใชใ๏ผ่ฆใฆใใ๏ผ๏ผในใผใใผในใผใใผ๏ผใณใใใฏใชใใฆ็พๅฎใชใใใใโฆใใใใใใ ใญใฃ๏ผ๏ผ๏ผ๏ผ๏ผใโฆๅฐ่ชฌใใใ่ใใใโฆใ๏ผใซใคใบใกใใใๅใซ่ฉฑใใใใฆใใ๏ผใฏใณใซใฏใณใซ๏ผใซใคใบ๏ผใซใคใบใปใใฉใณใฝใฏใผใบใใใใใใใฃใใญใซใคใบใกใใใๅใ่ฆใฆใใ๏ผใตใใใใใใใใฃ๏ผใฏใณใซใฏใณใซ๏ผ๏ผ๏ผใซใชใซใชใขใใขใ\n\nใซใคใบใธๅฑใ๏ผๅใ่ฆใฆใใ๏ผใใฎ๏ผใใขใณๆงใใ๏ผใฏใณใซใฏใณใซ๏ผ๏ผ็พๅฎใใใชใ๏ผใใใใใใใ๏ผใซใคใบ๏ผใขใใกใใใ่ใใใโฆใซใคใบใกใใใๅใซใใใใใใใใใใใใใใใ๏ผใใฃใใ๏ผ๏ผ๏ผใใใใใใใ๏ผ้ซชใใฏใณใซใฏใณใซ๏ผใทใจในใฟใผ๏ผใขใณใชใจใใฟใใใใใใใ๏ผใฏใใฃ๏ผ๏ผใใใใ๏ผ๏ผใใใใใใใใใใใใใใ๏ผ๏ผใฒใจใใงใงใใใใ๏ผ๏ผใซใใใใใใใใใใ๏ผ๏ผ๏ผ๏ผใณใใใฏ2ๅทปใใใ่ใใใโฆใใ๏ผ๏ผใใใใใใโฆใใใใใใใใใ๏ผใใใฃใใใใใใใ\n\nใซใคใบ๏ผ๏ผ๏ผ๏ผใใใฃใใใฑใใฃ๏ผ๏ผใใฃใปใใใใใใใใ๏ผ๏ผ็พๅฎใใใชใ๏ผ่ฆใฆใ๏ผ่กจ็ด็ตตใฎใซใคใบใใใใใใใฃใใใฑใใฃ๏ผ๏ผ๏ผใตใใใใใใใใฃ๏ผ๏ผ๏ผ๏ผใใใใใใใใใใใใ๏ผ๏ผ๏ผในใผใใผในใผใใผ๏ผ๏ผ๏ผใซใคใบใธๅฑใ๏ผ๏ผ๏ผใซใคใบใกใใใฏใใใใใใใใ๏ผ๏ผ๏ผ๏ผ๏ผใใใฃใโฆใซใคใบใธๅฑใ\n\n" | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-06-24T13:44:56.007740Z", | |
"start_time": "2018-06-24T13:44:55.177020Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "import io\nimport os\nimport codecs\nfrom datetime import datetime\nimport random\nimport json\nfrom requests_oauthlib import OAuth1Session\nimport re\n\n\napi = OAuth1Session('******',\n '******',\n '******',\n '******')\n\ntlurl = \"https://api.twitter.com/1.1/statuses/home_timeline.json\"\ntlparams = {'count': 500}\ntlreq = api.get(tlurl, params=tlparams)\n\ntry:\n if tlreq.status_code != 200:\n raise ValueError('ใใคใผใใฎๅๅพใใงใใพใใใงใใ')\nexcept ValueError as e:\n print(e)", | |
"execution_count": 17, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-06-24T13:53:38.959822Z", | |
"start_time": "2018-06-24T13:52:57.540610Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "def get_markov_text(tlrq):\n tl = json.loads(tlrq.text)\n random.shuffle(tl)\n utxt = \"\"\n for tw in tl:\n utxt += tw['text'] \n text = re.sub(r'https?://[\\w/:%#\\$&\\?\\(\\)~\\.=\\+\\-โฆ]+', \"\", utxt)\n text = re.sub('RT', \"\", text)\n text = re.sub('ใๆฐใซๅ ฅใ', \"\", text)\n text = re.sub('ใพใจใ', \"\", text)\n text = re.sub('@', \"\", text)\n text = re.sub(r'[!-/]', \"\", text)\n text = re.sub(r'[:-@]', \"\", text)\n text = re.sub(r'[[-`]', \"\", text)\n text = re.sub(r'[{-~]', \"\", text)\n text = re.sub(r'[A-Z]', \"\", text)\n text = re.sub(r'[a-z]', \"\", text)\n text = re.sub(r'[๏ธฐ-๏ผ ]', \"\", text)\n text = re.sub('\\n', \" \", text)\n num = random.randint(5, 15)\n txt2 = MarkovChain(text, num).makeMarkovText()\n txt4 = '(่ชๅ็ๆ)\\n' + txt2\n mtxt = txt4.replace('@', '')\n if len(mtxt) > 140:\n posttxt = mtxt[:140]\n else:\n posttxt = mtxt\n return posttxt\n\nposts = []\nfor i in range(10):\n post = get_markov_text(tlreq)\n print(i, post)\n posts.append(post)", | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"end_time": "2018-06-24T13:38:45.131605Z", | |
"start_time": "2018-06-24T13:38:44.597901Z" | |
}, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "posttxt = posts[9]\ntwparams = {\"status\": posttxt}\ntwurl = \"https://api.twitter.com/1.1/statuses/update.json\"\napi.post(twurl, params=twparams)", | |
"execution_count": 11, | |
"outputs": [ | |
{ | |
"execution_count": 11, | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": "<Response [200]>" | |
}, | |
"metadata": {} | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "", | |
"execution_count": null, | |
"outputs": [] | |
} | |
], | |
"metadata": { | |
"varInspector": { | |
"window_display": false, | |
"cols": { | |
"lenName": 16, | |
"lenType": 16, | |
"lenVar": 40 | |
}, | |
"kernels_config": { | |
"python": { | |
"library": "var_list.py", | |
"delete_cmd_prefix": "del ", | |
"delete_cmd_postfix": "", | |
"varRefreshCmd": "print(var_dic_list())" | |
}, | |
"r": { | |
"library": "var_list.r", | |
"delete_cmd_prefix": "rm(", | |
"delete_cmd_postfix": ") ", | |
"varRefreshCmd": "cat(var_dic_list()) " | |
} | |
}, | |
"types_to_exclude": [ | |
"module", | |
"function", | |
"builtin_function_or_method", | |
"instance", | |
"_Feature" | |
] | |
}, | |
"kernelspec": { | |
"name": "conda-env-tensorflow-py", | |
"display_name": "Python [conda env:tensorflow]", | |
"language": "python" | |
}, | |
"language_info": { | |
"file_extension": ".py", | |
"version": "3.5.5", | |
"mimetype": "text/x-python", | |
"nbconvert_exporter": "python", | |
"codemirror_mode": { | |
"version": 3, | |
"name": "ipython" | |
}, | |
"pygments_lexer": "ipython3", | |
"name": "python" | |
}, | |
"gist": { | |
"id": "", | |
"data": { | |
"description": "Markov-Chain.ipynb", | |
"public": true | |
} | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment