{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":8565891,"sourceType":"datasetVersion","datasetId":5120988}],"dockerImageVersionId":30787,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:31.264095Z","iopub.execute_input":"2024-11-13T14:50:31.264479Z","iopub.status.idle":"2024-11-13T14:50:32.206343Z","shell.execute_reply.started":"2024-11-13T14:50:31.264428Z","shell.execute_reply":"2024-11-13T14:50:32.205200Z"}},"outputs":[],"execution_count":1},{"cell_type":"code","source":"df=pd.read_csv(\"/kaggle/input/quora-duplicate-questions-copy/train.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:32.208551Z","iopub.execute_input":"2024-11-13T14:50:32.209089Z","iopub.status.idle":"2024-11-13T14:50:33.491184Z","shell.execute_reply.started":"2024-11-13T14:50:32.209043Z","shell.execute_reply":"2024-11-13T14:50:33.490243Z"}},"outputs":[],"execution_count":2},{"cell_type":"code","source":"df.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:33.492390Z","iopub.execute_input":"2024-11-13T14:50:33.492718Z","iopub.status.idle":"2024-11-13T14:50:33.500694Z","shell.execute_reply.started":"2024-11-13T14:50:33.492683Z","shell.execute_reply":"2024-11-13T14:50:33.499576Z"}},"outputs":[{"execution_count":3,"output_type":"execute_result","data":{"text/plain":"(404290, 6)"},"metadata":{}}],"execution_count":3},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:33.502151Z","iopub.execute_input":"2024-11-13T14:50:33.502497Z","iopub.status.idle":"2024-11-13T14:50:33.522540Z","shell.execute_reply.started":"2024-11-13T14:50:33.502459Z","shell.execute_reply":"2024-11-13T14:50:33.521526Z"}},"outputs":[{"execution_count":4,"output_type":"execute_result","data":{"text/plain":" id qid1 qid2 question1 \\\n0 0 1 2 What is the step by step guide to invest in sh... \n1 1 3 4 What is the story of Kohinoor (Koh-i-Noor) Dia... \n2 2 5 6 How can I increase the speed of my internet co... \n3 3 7 8 Why am I mentally very lonely? How can I solve... \n4 4 9 10 Which one dissolve in water quikly sugar, salt... \n\n question2 is_duplicate \n0 What is the step by step guide to invest in sh... 0 \n1 What would happen if the Indian government sto... 0 \n2 How can Internet speed be increased by hacking... 0 \n3 Find the remainder when [math]23^{24}[/math] i... 0 \n4 Which fish would survive in salt water? 0 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
idqid1qid2question1question2is_duplicate
0012What is the step by step guide to invest in sh...What is the step by step guide to invest in sh...0
1134What is the story of Kohinoor (Koh-i-Noor) Dia...What would happen if the Indian government sto...0
2256How can I increase the speed of my internet co...How can Internet speed be increased by hacking...0
3378Why am I mentally very lonely? How can I solve...Find the remainder when [math]23^{24}[/math] i...0
44910Which one dissolve in water quikly sugar, salt...Which fish would survive in salt water?0
\n
"},"metadata":{}}],"execution_count":4},{"cell_type":"code","source":"df.isnull().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:33.526046Z","iopub.execute_input":"2024-11-13T14:50:33.526460Z","iopub.status.idle":"2024-11-13T14:50:33.631064Z","shell.execute_reply.started":"2024-11-13T14:50:33.526418Z","shell.execute_reply":"2024-11-13T14:50:33.629989Z"}},"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":"id 0\nqid1 0\nqid2 0\nquestion1 1\nquestion2 2\nis_duplicate 0\ndtype: int64"},"metadata":{}}],"execution_count":5},{"cell_type":"code","source":"df.dropna(inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:33.632341Z","iopub.execute_input":"2024-11-13T14:50:33.632719Z","iopub.status.idle":"2024-11-13T14:50:33.755507Z","shell.execute_reply.started":"2024-11-13T14:50:33.632675Z","shell.execute_reply":"2024-11-13T14:50:33.754637Z"}},"outputs":[],"execution_count":6},{"cell_type":"code","source":"df.duplicated().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:33.756946Z","iopub.execute_input":"2024-11-13T14:50:33.757294Z","iopub.status.idle":"2024-11-13T14:50:34.119270Z","shell.execute_reply.started":"2024-11-13T14:50:33.757261Z","shell.execute_reply":"2024-11-13T14:50:34.118367Z"}},"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"0"},"metadata":{}}],"execution_count":7},{"cell_type":"code","source":"def preprocess(q):\n q=str(q).lower().strip()\n \n q=q.replace('%',' percent ')\n q=q.replace('@',' at ')\n q=q.replace('$',' dollar ')\n \n q=q.replace('[math]','')\n \n q=q.replace(',000,000,000 ','b ')\n q=q.replace(',000,000 ','m ')\n q=q.replace(',000 ','k ')\n \n import re\n q=re.sub(r'([0-9]+)000000000',r'\\1b',q)\n q=re.sub(r'([0-9]+)000000',r'\\1m',q)\n q=re.sub(r'([0-9]+)000',r'\\1k',q)\n \n contractions = { \n \"ain't\": \"am not\",\n \"aren't\": \"are not\",\n \"can't\": \"can not\",\n \"can't've\": \"can not have\",\n \"'cause\": \"because\",\n \"could've\": \"could have\",\n \"couldn't\": \"could not\",\n \"couldn't've\": \"could not have\",\n \"didn't\": \"did not\",\n \"doesn't\": \"does not\",\n \"don't\": \"do not\",\n \"hadn't\": \"had not\",\n \"hadn't've\": \"had not have\",\n \"hasn't\": \"has not\",\n \"haven't\": \"have not\",\n \"he'd\": \"he would\",\n \"he'd've\": \"he would have\",\n \"he'll\": \"he will\",\n \"he'll've\": \"he will have\",\n \"he's\": \"he is\",\n \"how'd\": \"how did\",\n \"how'd'y\": \"how do you\",\n \"how'll\": \"how will\",\n \"how's\": \"how is\",\n \"i'd\": \"i would\",\n \"i'd've\": \"i would have\",\n \"i'll\": \"i will\",\n \"i'll've\": \"i will have\",\n \"i'm\": \"i am\",\n \"i've\": \"i have\",\n \"isn't\": \"is not\",\n \"it'd\": \"it would\",\n \"it'd've\": \"it would have\",\n \"it'll\": \"it will\",\n \"it'll've\": \"it will have\",\n \"it's\": \"it is\",\n \"let's\": \"let us\",\n \"ma'am\": \"madam\",\n \"mayn't\": \"may not\",\n \"might've\": \"might have\",\n \"mightn't\": \"might not\",\n \"mightn't've\": \"might not have\",\n \"must've\": \"must have\",\n \"mustn't\": \"must not\",\n \"mustn't've\": \"must not have\",\n \"needn't\": \"need not\",\n \"needn't've\": \"need not have\",\n \"o'clock\": \"of the clock\",\n \"oughtn't\": \"ought not\",\n \"oughtn't've\": \"ought not have\",\n \"shan't\": \"shall not\",\n \"sha'n't\": \"shall not\",\n \"shan't've\": \"shall not have\",\n \"she'd\": \"she would\",\n \"she'd've\": \"she would have\",\n \"she'll\": \"she will\",\n \"she'll've\": \"she will have\",\n \"she's\": \"she is\",\n \"should've\": \"should have\",\n \"shouldn't\": \"should not\",\n \"shouldn't've\": \"should not have\",\n \"so've\": \"so have\",\n \"so's\": \"so as\",\n \"that'd\": \"that would\",\n \"that'd've\": \"that would have\",\n \"that's\": \"that is\",\n \"there'd\": \"there would\",\n \"there'd've\": \"there would have\",\n \"there's\": \"there is\",\n \"they'd\": \"they would\",\n \"they'd've\": \"they would have\",\n \"they'll\": \"they will\",\n \"they'll've\": \"they will have\",\n \"they're\": \"they are\",\n \"they've\": \"they have\",\n \"to've\": \"to have\",\n \"wasn't\": \"was not\",\n \"we'd\": \"we would\",\n \"we'd've\": \"we would have\",\n \"we'll\": \"we will\",\n \"we'll've\": \"we will have\",\n \"we're\": \"we are\",\n \"we've\": \"we have\",\n \"weren't\": \"were not\",\n \"what'll\": \"what will\",\n \"what'll've\": \"what will have\",\n \"what're\": \"what are\",\n \"what's\": \"what is\",\n \"what've\": \"what have\",\n \"when's\": \"when is\",\n \"when've\": \"when have\",\n \"where'd\": \"where did\",\n \"where's\": \"where is\",\n \"where've\": \"where have\",\n \"who'll\": \"who will\",\n \"who'll've\": \"who will have\",\n \"who's\": \"who is\",\n \"who've\": \"who have\",\n \"why's\": \"why is\",\n \"why've\": \"why have\",\n \"will've\": \"will have\",\n \"won't\": \"will not\",\n \"won't've\": \"will not have\",\n \"would've\": \"would have\",\n \"wouldn't\": \"would not\",\n \"wouldn't've\": \"would not have\",\n \"y'all\": \"you all\",\n \"y'all'd\": \"you all would\",\n \"y'all'd've\": \"you all would have\",\n \"y'all're\": \"you all are\",\n \"y'all've\": \"you all have\",\n \"you'd\": \"you would\",\n \"you'd've\": \"you would have\",\n \"you'll\": \"you will\",\n \"you'll've\": \"you will have\",\n \"you're\": \"you are\",\n \"you've\": \"you have\"\n }\n\n q_decontracted = []\n\n for word in q.split():\n if word in contractions:\n word = contractions[word]\n\n q_decontracted.append(word)\n\n q = ' '.join(q_decontracted)\n q = q.replace(\"'ve\", \" have\")\n q = q.replace(\"n't\", \" not\")\n q = q.replace(\"'re\", \" are\")\n q = q.replace(\"'ll\", \" will\")\n \n q=re.sub(re.compile('<.*?>'),'',q)\n \n import string\n q=q.translate(str.maketrans('', '', string.punctuation))\n \n return q","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:34.120810Z","iopub.execute_input":"2024-11-13T14:50:34.121132Z","iopub.status.idle":"2024-11-13T14:50:34.205402Z","shell.execute_reply.started":"2024-11-13T14:50:34.121098Z","shell.execute_reply":"2024-11-13T14:50:34.204424Z"}},"outputs":[],"execution_count":8},{"cell_type":"code","source":"df['is_duplicate'].value_counts().plot(kind='bar')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:34.207087Z","iopub.execute_input":"2024-11-13T14:50:34.207425Z","iopub.status.idle":"2024-11-13T14:50:34.454802Z","shell.execute_reply.started":"2024-11-13T14:50:34.207391Z","shell.execute_reply":"2024-11-13T14:50:34.453861Z"}},"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}],"execution_count":9},{"cell_type":"code","source":"qid=pd.Series(df['qid1'].tolist()+df['qid2'].tolist())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:34.456089Z","iopub.execute_input":"2024-11-13T14:50:34.456401Z","iopub.status.idle":"2024-11-13T14:50:34.880995Z","shell.execute_reply.started":"2024-11-13T14:50:34.456366Z","shell.execute_reply":"2024-11-13T14:50:34.880147Z"}},"outputs":[],"execution_count":10},{"cell_type":"code","source":"np.unique(qid).shape[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:34.882369Z","iopub.execute_input":"2024-11-13T14:50:34.883039Z","iopub.status.idle":"2024-11-13T14:50:34.905100Z","shell.execute_reply.started":"2024-11-13T14:50:34.882992Z","shell.execute_reply":"2024-11-13T14:50:34.904172Z"}},"outputs":[{"execution_count":11,"output_type":"execute_result","data":{"text/plain":"537929"},"metadata":{}}],"execution_count":11},{"cell_type":"code","source":"df['question1']=df['question1'].apply(preprocess)\ndf['question2']=df['question2'].apply(preprocess)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:50:34.906442Z","iopub.execute_input":"2024-11-13T14:50:34.906767Z","iopub.status.idle":"2024-11-13T14:51:13.044953Z","shell.execute_reply.started":"2024-11-13T14:50:34.906731Z","shell.execute_reply":"2024-11-13T14:51:13.043783Z"}},"outputs":[],"execution_count":12},{"cell_type":"code","source":"qid.shape[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:13.046446Z","iopub.execute_input":"2024-11-13T14:51:13.047109Z","iopub.status.idle":"2024-11-13T14:51:13.054277Z","shell.execute_reply.started":"2024-11-13T14:51:13.047051Z","shell.execute_reply":"2024-11-13T14:51:13.053351Z"}},"outputs":[{"execution_count":13,"output_type":"execute_result","data":{"text/plain":"808574"},"metadata":{}}],"execution_count":13},{"cell_type":"code","source":"x=qid.value_counts()>1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:13.060599Z","iopub.execute_input":"2024-11-13T14:51:13.061095Z","iopub.status.idle":"2024-11-13T14:51:13.169062Z","shell.execute_reply.started":"2024-11-13T14:51:13.061041Z","shell.execute_reply":"2024-11-13T14:51:13.168163Z"}},"outputs":[],"execution_count":14},{"cell_type":"code","source":"x[x]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:13.170527Z","iopub.execute_input":"2024-11-13T14:51:13.170962Z","iopub.status.idle":"2024-11-13T14:51:13.179973Z","shell.execute_reply.started":"2024-11-13T14:51:13.170893Z","shell.execute_reply":"2024-11-13T14:51:13.179002Z"}},"outputs":[{"execution_count":15,"output_type":"execute_result","data":{"text/plain":"2559 True\n30782 True\n4044 True\n2561 True\n14376 True\n ... \n54491 True\n84056 True\n68804 True\n148488 True\n23824 True\nName: count, Length: 111778, dtype: bool"},"metadata":{}}],"execution_count":15},{"cell_type":"code","source":"x[x].shape[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:13.181305Z","iopub.execute_input":"2024-11-13T14:51:13.181605Z","iopub.status.idle":"2024-11-13T14:51:13.195177Z","shell.execute_reply.started":"2024-11-13T14:51:13.181573Z","shell.execute_reply":"2024-11-13T14:51:13.194161Z"}},"outputs":[{"execution_count":16,"output_type":"execute_result","data":{"text/plain":"111778"},"metadata":{}}],"execution_count":16},{"cell_type":"code","source":"plt.hist(qid.value_counts().values,bins=100)\nplt.yscale('log')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:13.196298Z","iopub.execute_input":"2024-11-13T14:51:13.196571Z","iopub.status.idle":"2024-11-13T14:51:14.123832Z","shell.execute_reply.started":"2024-11-13T14:51:13.196541Z","shell.execute_reply":"2024-11-13T14:51:14.122902Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}],"execution_count":17},{"cell_type":"code","source":"df.drop(columns=['id','qid1','qid2'],inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:14.125291Z","iopub.execute_input":"2024-11-13T14:51:14.125729Z","iopub.status.idle":"2024-11-13T14:51:14.156506Z","shell.execute_reply.started":"2024-11-13T14:51:14.125682Z","shell.execute_reply":"2024-11-13T14:51:14.155547Z"}},"outputs":[],"execution_count":18},{"cell_type":"code","source":"df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:14.157749Z","iopub.execute_input":"2024-11-13T14:51:14.158092Z","iopub.status.idle":"2024-11-13T14:51:14.170648Z","shell.execute_reply.started":"2024-11-13T14:51:14.158058Z","shell.execute_reply":"2024-11-13T14:51:14.169452Z"}},"outputs":[{"execution_count":19,"output_type":"execute_result","data":{"text/plain":" question1 \\\n0 what is the step by step guide to invest in sh... \n1 what is the story of kohinoor kohinoor diamond \n2 how can i increase the speed of my internet co... \n3 why am i mentally very lonely how can i solve it \n4 which one dissolve in water quikly sugar salt ... \n... ... \n404285 how many keywords are there in the racket prog... \n404286 do you believe there is life after death \n404287 what is one coin \n404288 what is the approx annual cost of living while... \n404289 what is like to have sex with cousin \n\n question2 is_duplicate \n0 what is the step by step guide to invest in sh... 0 \n1 what would happen if the indian government sto... 0 \n2 how can internet speed be increased by hacking... 0 \n3 find the remainder when 2324math is divided by... 0 \n4 which fish would survive in salt water 0 \n... ... ... \n404285 how many keywords are there in perl programmin... 0 \n404286 is it true that there is life after death 1 \n404287 what is this coin 0 \n404288 i am having little hairfall problem but i want... 0 \n404289 what is it like to have sex with your cousin 0 \n\n[404287 rows x 3 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
question1question2is_duplicate
0what is the step by step guide to invest in sh...what is the step by step guide to invest in sh...0
1what is the story of kohinoor kohinoor diamondwhat would happen if the indian government sto...0
2how can i increase the speed of my internet co...how can internet speed be increased by hacking...0
3why am i mentally very lonely how can i solve itfind the remainder when 2324math is divided by...0
4which one dissolve in water quikly sugar salt ...which fish would survive in salt water0
............
404285how many keywords are there in the racket prog...how many keywords are there in perl programmin...0
404286do you believe there is life after deathis it true that there is life after death1
404287what is one coinwhat is this coin0
404288what is the approx annual cost of living while...i am having little hairfall problem but i want...0
404289what is like to have sex with cousinwhat is it like to have sex with your cousin0
\n

404287 rows × 3 columns

\n
"},"metadata":{}}],"execution_count":19},{"cell_type":"code","source":"import transformers\nimport warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:14.171999Z","iopub.execute_input":"2024-11-13T14:51:14.172342Z","iopub.status.idle":"2024-11-13T14:51:16.483818Z","shell.execute_reply.started":"2024-11-13T14:51:14.172307Z","shell.execute_reply":"2024-11-13T14:51:16.482906Z"}},"outputs":[],"execution_count":20},{"cell_type":"code","source":"df[\"question\"] = df['question1']+\" ; \"+df['question2'].astype(str).values.tolist()\ndf","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:16.484913Z","iopub.execute_input":"2024-11-13T14:51:16.485378Z","iopub.status.idle":"2024-11-13T14:51:18.619753Z","shell.execute_reply.started":"2024-11-13T14:51:16.485344Z","shell.execute_reply":"2024-11-13T14:51:18.618773Z"}},"outputs":[{"execution_count":21,"output_type":"execute_result","data":{"text/plain":" question1 \\\n0 what is the step by step guide to invest in sh... \n1 what is the story of kohinoor kohinoor diamond \n2 how can i increase the speed of my internet co... \n3 why am i mentally very lonely how can i solve it \n4 which one dissolve in water quikly sugar salt ... \n... ... \n404285 how many keywords are there in the racket prog... \n404286 do you believe there is life after death \n404287 what is one coin \n404288 what is the approx annual cost of living while... \n404289 what is like to have sex with cousin \n\n question2 is_duplicate \\\n0 what is the step by step guide to invest in sh... 0 \n1 what would happen if the indian government sto... 0 \n2 how can internet speed be increased by hacking... 0 \n3 find the remainder when 2324math is divided by... 0 \n4 which fish would survive in salt water 0 \n... ... ... \n404285 how many keywords are there in perl programmin... 0 \n404286 is it true that there is life after death 1 \n404287 what is this coin 0 \n404288 i am having little hairfall problem but i want... 0 \n404289 what is it like to have sex with your cousin 0 \n\n question \n0 what is the step by step guide to invest in sh... \n1 what is the story of kohinoor kohinoor diamond... \n2 how can i increase the speed of my internet co... \n3 why am i mentally very lonely how can i solve ... \n4 which one dissolve in water quikly sugar salt ... \n... ... \n404285 how many keywords are there in the racket prog... \n404286 do you believe there is life after death ; is ... \n404287 what is one coin ; what is this coin \n404288 what is the approx annual cost of living while... \n404289 what is like to have sex with cousin ; what is... \n\n[404287 rows x 4 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
question1question2is_duplicatequestion
0what is the step by step guide to invest in sh...what is the step by step guide to invest in sh...0what is the step by step guide to invest in sh...
1what is the story of kohinoor kohinoor diamondwhat would happen if the indian government sto...0what is the story of kohinoor kohinoor diamond...
2how can i increase the speed of my internet co...how can internet speed be increased by hacking...0how can i increase the speed of my internet co...
3why am i mentally very lonely how can i solve itfind the remainder when 2324math is divided by...0why am i mentally very lonely how can i solve ...
4which one dissolve in water quikly sugar salt ...which fish would survive in salt water0which one dissolve in water quikly sugar salt ...
...............
404285how many keywords are there in the racket prog...how many keywords are there in perl programmin...0how many keywords are there in the racket prog...
404286do you believe there is life after deathis it true that there is life after death1do you believe there is life after death ; is ...
404287what is one coinwhat is this coin0what is one coin ; what is this coin
404288what is the approx annual cost of living while...i am having little hairfall problem but i want...0what is the approx annual cost of living while...
404289what is like to have sex with cousinwhat is it like to have sex with your cousin0what is like to have sex with cousin ; what is...
\n

404287 rows × 4 columns

\n
"},"metadata":{}}],"execution_count":21},{"cell_type":"code","source":"df=df.drop(columns=[\"question1\",\"question2\"])\ndf","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:18.621104Z","iopub.execute_input":"2024-11-13T14:51:18.621592Z","iopub.status.idle":"2024-11-13T14:51:18.648113Z","shell.execute_reply.started":"2024-11-13T14:51:18.621545Z","shell.execute_reply":"2024-11-13T14:51:18.647137Z"}},"outputs":[{"execution_count":22,"output_type":"execute_result","data":{"text/plain":" is_duplicate question\n0 0 what is the step by step guide to invest in sh...\n1 0 what is the story of kohinoor kohinoor diamond...\n2 0 how can i increase the speed of my internet co...\n3 0 why am i mentally very lonely how can i solve ...\n4 0 which one dissolve in water quikly sugar salt ...\n... ... ...\n404285 0 how many keywords are there in the racket prog...\n404286 1 do you believe there is life after death ; is ...\n404287 0 what is one coin ; what is this coin\n404288 0 what is the approx annual cost of living while...\n404289 0 what is like to have sex with cousin ; what is...\n\n[404287 rows x 2 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
is_duplicatequestion
00what is the step by step guide to invest in sh...
10what is the story of kohinoor kohinoor diamond...
20how can i increase the speed of my internet co...
30why am i mentally very lonely how can i solve ...
40which one dissolve in water quikly sugar salt ...
.........
4042850how many keywords are there in the racket prog...
4042861do you believe there is life after death ; is ...
4042870what is one coin ; what is this coin
4042880what is the approx annual cost of living while...
4042890what is like to have sex with cousin ; what is...
\n

404287 rows × 2 columns

\n
"},"metadata":{}}],"execution_count":22},{"cell_type":"code","source":"from transformers import TFDistilBertForSequenceClassification, DistilBertTokenizer\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\n\n# Load tokenizer and model\ntokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')\nmodel = TFDistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased', num_labels=2)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:18.649321Z","iopub.execute_input":"2024-11-13T14:51:18.649631Z","iopub.status.idle":"2024-11-13T14:51:24.337527Z","shell.execute_reply.started":"2024-11-13T14:51:18.649598Z","shell.execute_reply":"2024-11-13T14:51:24.336569Z"}},"outputs":[{"name":"stderr","text":"Some weights of the PyTorch model were not used when initializing the TF 2.0 model TFDistilBertForSequenceClassification: ['vocab_layer_norm.bias', 'vocab_layer_norm.weight', 'vocab_projector.bias', 'vocab_transform.weight', 'vocab_transform.bias']\n- This IS expected if you are initializing TFDistilBertForSequenceClassification from a PyTorch model trained on another task or with another architecture (e.g. initializing a TFBertForSequenceClassification model from a BertForPreTraining model).\n- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from a PyTorch model that you expect to be exactly identical (e.g. initializing a TFBertForSequenceClassification model from a BertForSequenceClassification model).\nSome weights or buffers of the TF 2.0 model TFDistilBertForSequenceClassification were not initialized from the PyTorch model and are newly initialized: ['pre_classifier.weight', 'pre_classifier.bias', 'classifier.weight', 'classifier.bias']\nYou should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","output_type":"stream"}],"execution_count":23},{"cell_type":"code","source":"# Prepare the data\nX = list(df['question'].values)\ny = df['is_duplicate'].values","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:24.339028Z","iopub.execute_input":"2024-11-13T14:51:24.339473Z","iopub.status.idle":"2024-11-13T14:51:24.367843Z","shell.execute_reply.started":"2024-11-13T14:51:24.339417Z","shell.execute_reply":"2024-11-13T14:51:24.366764Z"}},"outputs":[],"execution_count":24},{"cell_type":"code","source":"# Split data\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=42)\n\n# Tokenize and convert to TensorFlow datasets\ntrain_encodings = tokenizer(X_train, truncation=True, padding=True, max_length=50)\ntest_encodings = tokenizer(X_test, truncation=True, padding=True, max_length=50)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:51:24.369207Z","iopub.execute_input":"2024-11-13T14:51:24.369667Z","iopub.status.idle":"2024-11-13T14:57:36.557643Z","shell.execute_reply.started":"2024-11-13T14:51:24.369624Z","shell.execute_reply":"2024-11-13T14:57:36.556760Z"}},"outputs":[],"execution_count":25},{"cell_type":"code","source":"train_dataset = tf.data.Dataset.from_tensor_slices((\n dict(train_encodings),\n y_train\n)).shuffle(42).batch(128)\n\nval_dataset = tf.data.Dataset.from_tensor_slices((\n dict(test_encodings),\n y_test\n)).batch(128)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:57:36.559058Z","iopub.execute_input":"2024-11-13T14:57:36.559859Z","iopub.status.idle":"2024-11-13T14:59:41.969221Z","shell.execute_reply.started":"2024-11-13T14:57:36.559810Z","shell.execute_reply":"2024-11-13T14:59:41.968118Z"}},"outputs":[],"execution_count":26},{"cell_type":"code","source":"# Compile and train the model\noptimizer = tf.keras.optimizers.Adam(learning_rate=5e-5)\nmodel.compile(optimizer=optimizer, loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])\n\nhistory=model.fit(train_dataset, epochs=10, validation_data=val_dataset)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T14:59:41.970605Z","iopub.execute_input":"2024-11-13T14:59:41.970949Z","iopub.status.idle":"2024-11-13T17:19:01.289683Z","shell.execute_reply.started":"2024-11-13T14:59:41.970898Z","shell.execute_reply":"2024-11-13T17:19:01.287800Z"}},"outputs":[{"name":"stdout","text":"Epoch 1/10\nWARNING: AutoGraph could not transform and will run it as-is.\nCause: for/else statement not yet supported\nTo silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n","output_type":"stream"},{"name":"stderr","text":"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nI0000 00:00:1731510032.736724 1411 service.cc:145] XLA service 0x79984ac6b020 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\nI0000 00:00:1731510032.736765 1411 service.cc:153] StreamExecutor device (0): Tesla T4, Compute Capability 7.5\nI0000 00:00:1731510032.736771 1411 service.cc:153] StreamExecutor device (1): Tesla T4, Compute Capability 7.5\nI0000 00:00:1731510032.848873 1411 device_compiler.h:188] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process.\n","output_type":"stream"},{"name":"stdout","text":"2843/2843 [==============================] - 1699s 578ms/step - loss: 0.3265 - accuracy: 0.8509 - val_loss: 0.2663 - val_accuracy: 0.8844\nEpoch 2/10\n2843/2843 [==============================] - 1635s 575ms/step - loss: 0.2183 - accuracy: 0.9085 - val_loss: 0.2729 - val_accuracy: 0.8924\nEpoch 3/10\n2843/2843 [==============================] - 1636s 575ms/step - loss: 0.1508 - accuracy: 0.9408 - val_loss: 0.2993 - val_accuracy: 0.8957\nEpoch 4/10\n2843/2843 [==============================] - 1635s 575ms/step - loss: 0.1072 - accuracy: 0.9596 - val_loss: 0.3496 - val_accuracy: 0.8991\nEpoch 5/10\n2843/2843 [==============================] - 1635s 575ms/step - loss: 0.0812 - accuracy: 0.9703 - val_loss: 0.3729 - val_accuracy: 0.8989\nEpoch 6/10\n 210/2843 [=>............................] - ETA: 24:17 - loss: 0.0728 - accuracy: 0.9726","output_type":"stream"},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[27], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m optimizer \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mkeras\u001b[38;5;241m.\u001b[39moptimizers\u001b[38;5;241m.\u001b[39mAdam(learning_rate\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5e-5\u001b[39m)\n\u001b[1;32m 3\u001b[0m model\u001b[38;5;241m.\u001b[39mcompile(optimizer\u001b[38;5;241m=\u001b[39moptimizer, loss\u001b[38;5;241m=\u001b[39mtf\u001b[38;5;241m.\u001b[39mkeras\u001b[38;5;241m.\u001b[39mlosses\u001b[38;5;241m.\u001b[39mSparseCategoricalCrossentropy(from_logits\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m), metrics\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124maccuracy\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m----> 5\u001b[0m history\u001b[38;5;241m=\u001b[39m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtrain_dataset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m10\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mval_dataset\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/modeling_tf_utils.py:1229\u001b[0m, in \u001b[0;36mTFPreTrainedModel.fit\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1226\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(keras\u001b[38;5;241m.\u001b[39mModel\u001b[38;5;241m.\u001b[39mfit)\n\u001b[1;32m 1227\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfit\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 1228\u001b[0m args, kwargs \u001b[38;5;241m=\u001b[39m convert_batch_encoding(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m-> 1229\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/utils/traceback_utils.py:65\u001b[0m, in \u001b[0;36mfilter_traceback..error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 63\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 64\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 65\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 67\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/engine/training.py:1810\u001b[0m, in \u001b[0;36mModel.fit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m 1808\u001b[0m logs \u001b[38;5;241m=\u001b[39m tmp_logs\n\u001b[1;32m 1809\u001b[0m end_step \u001b[38;5;241m=\u001b[39m step \u001b[38;5;241m+\u001b[39m data_handler\u001b[38;5;241m.\u001b[39mstep_increment\n\u001b[0;32m-> 1810\u001b[0m \u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mon_train_batch_end\u001b[49m\u001b[43m(\u001b[49m\u001b[43mend_step\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1811\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstop_training:\n\u001b[1;32m 1812\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/callbacks.py:478\u001b[0m, in \u001b[0;36mCallbackList.on_train_batch_end\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m 471\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Calls the `on_train_batch_end` methods of its callbacks.\u001b[39;00m\n\u001b[1;32m 472\u001b[0m \n\u001b[1;32m 473\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[1;32m 474\u001b[0m \u001b[38;5;124;03m batch: Integer, index of batch within the current epoch.\u001b[39;00m\n\u001b[1;32m 475\u001b[0m \u001b[38;5;124;03m logs: Dict. Aggregated metric results up until this batch.\u001b[39;00m\n\u001b[1;32m 476\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 477\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_call_train_batch_hooks:\n\u001b[0;32m--> 478\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_batch_hook\u001b[49m\u001b[43m(\u001b[49m\u001b[43mModeKeys\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTRAIN\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mend\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/callbacks.py:325\u001b[0m, in \u001b[0;36mCallbackList._call_batch_hook\u001b[0;34m(self, mode, hook, batch, logs)\u001b[0m\n\u001b[1;32m 323\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_batch_begin_hook(mode, batch, logs)\n\u001b[1;32m 324\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m hook \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mend\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m--> 325\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_batch_end_hook\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 326\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 327\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 328\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnrecognized hook: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mhook\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 329\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mExpected values are [\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbegin\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mend\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m]\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m 330\u001b[0m )\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/callbacks.py:348\u001b[0m, in \u001b[0;36mCallbackList._call_batch_end_hook\u001b[0;34m(self, mode, batch, logs)\u001b[0m\n\u001b[1;32m 345\u001b[0m batch_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime() \u001b[38;5;241m-\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_batch_start_time\n\u001b[1;32m 346\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_batch_times\u001b[38;5;241m.\u001b[39mappend(batch_time)\n\u001b[0;32m--> 348\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_batch_hook_helper\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhook_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 350\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_batch_times) \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_batches_for_timing_check:\n\u001b[1;32m 351\u001b[0m end_hook_name \u001b[38;5;241m=\u001b[39m hook_name\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/callbacks.py:396\u001b[0m, in \u001b[0;36mCallbackList._call_batch_hook_helper\u001b[0;34m(self, hook_name, batch, logs)\u001b[0m\n\u001b[1;32m 394\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m callback \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallbacks:\n\u001b[1;32m 395\u001b[0m hook \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(callback, hook_name)\n\u001b[0;32m--> 396\u001b[0m \u001b[43mhook\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 398\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_timing:\n\u001b[1;32m 399\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m hook_name \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_hook_times:\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/callbacks.py:1097\u001b[0m, in \u001b[0;36mProgbarLogger.on_train_batch_end\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m 1096\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mon_train_batch_end\u001b[39m(\u001b[38;5;28mself\u001b[39m, batch, logs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[0;32m-> 1097\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_batch_update_progbar\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/callbacks.py:1173\u001b[0m, in \u001b[0;36mProgbarLogger._batch_update_progbar\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m 1169\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mseen \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m add_seen\n\u001b[1;32m 1171\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 1172\u001b[0m \u001b[38;5;66;03m# Only block async when verbose = 1.\u001b[39;00m\n\u001b[0;32m-> 1173\u001b[0m logs \u001b[38;5;241m=\u001b[39m \u001b[43mtf_utils\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msync_to_numpy_or_python_type\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlogs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1174\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprogbar\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mseen, \u001b[38;5;28mlist\u001b[39m(logs\u001b[38;5;241m.\u001b[39mitems()), finalize\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/utils/tf_utils.py:694\u001b[0m, in \u001b[0;36msync_to_numpy_or_python_type\u001b[0;34m(tensors)\u001b[0m\n\u001b[1;32m 691\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m t\n\u001b[1;32m 692\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m t\u001b[38;5;241m.\u001b[39mitem() \u001b[38;5;28;01mif\u001b[39;00m np\u001b[38;5;241m.\u001b[39mndim(t) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m t\n\u001b[0;32m--> 694\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmap_structure\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_to_single_numpy_or_python_type\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtensors\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tensorflow/python/util/nest.py:628\u001b[0m, in \u001b[0;36mmap_structure\u001b[0;34m(func, *structure, **kwargs)\u001b[0m\n\u001b[1;32m 542\u001b[0m \u001b[38;5;129m@tf_export\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnest.map_structure\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 543\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mmap_structure\u001b[39m(func, \u001b[38;5;241m*\u001b[39mstructure, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 544\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Creates a new structure by applying `func` to each atom in `structure`.\u001b[39;00m\n\u001b[1;32m 545\u001b[0m \n\u001b[1;32m 546\u001b[0m \u001b[38;5;124;03m Refer to [tf.nest](https://www.tensorflow.org/api_docs/python/tf/nest)\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[38;5;124;03m ValueError: If wrong keyword arguments are provided.\u001b[39;00m\n\u001b[1;32m 627\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 628\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mnest_util\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmap_structure\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 629\u001b[0m \u001b[43m \u001b[49m\u001b[43mnest_util\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mModality\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCORE\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mstructure\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 630\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tensorflow/python/util/nest_util.py:1065\u001b[0m, in \u001b[0;36mmap_structure\u001b[0;34m(modality, func, *structure, **kwargs)\u001b[0m\n\u001b[1;32m 968\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Creates a new structure by applying `func` to each atom in `structure`.\u001b[39;00m\n\u001b[1;32m 969\u001b[0m \n\u001b[1;32m 970\u001b[0m \u001b[38;5;124;03m- For Modality.CORE: Refer to\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1062\u001b[0m \u001b[38;5;124;03m ValueError: If wrong keyword arguments are provided.\u001b[39;00m\n\u001b[1;32m 1063\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1064\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m modality \u001b[38;5;241m==\u001b[39m Modality\u001b[38;5;241m.\u001b[39mCORE:\n\u001b[0;32m-> 1065\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_tf_core_map_structure\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mstructure\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1066\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m modality \u001b[38;5;241m==\u001b[39m Modality\u001b[38;5;241m.\u001b[39mDATA:\n\u001b[1;32m 1067\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _tf_data_map_structure(func, \u001b[38;5;241m*\u001b[39mstructure, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tensorflow/python/util/nest_util.py:1105\u001b[0m, in \u001b[0;36m_tf_core_map_structure\u001b[0;34m(func, *structure, **kwargs)\u001b[0m\n\u001b[1;32m 1100\u001b[0m flat_structure \u001b[38;5;241m=\u001b[39m (_tf_core_flatten(s, expand_composites) \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m structure)\n\u001b[1;32m 1101\u001b[0m entries \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mzip\u001b[39m(\u001b[38;5;241m*\u001b[39mflat_structure)\n\u001b[1;32m 1103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _tf_core_pack_sequence_as(\n\u001b[1;32m 1104\u001b[0m structure[\u001b[38;5;241m0\u001b[39m],\n\u001b[0;32m-> 1105\u001b[0m [func(\u001b[38;5;241m*\u001b[39mx) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m entries],\n\u001b[1;32m 1106\u001b[0m expand_composites\u001b[38;5;241m=\u001b[39mexpand_composites,\n\u001b[1;32m 1107\u001b[0m )\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tensorflow/python/util/nest_util.py:1105\u001b[0m, in \u001b[0;36m\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 1100\u001b[0m flat_structure \u001b[38;5;241m=\u001b[39m (_tf_core_flatten(s, expand_composites) \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m structure)\n\u001b[1;32m 1101\u001b[0m entries \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mzip\u001b[39m(\u001b[38;5;241m*\u001b[39mflat_structure)\n\u001b[1;32m 1103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _tf_core_pack_sequence_as(\n\u001b[1;32m 1104\u001b[0m structure[\u001b[38;5;241m0\u001b[39m],\n\u001b[0;32m-> 1105\u001b[0m [\u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m entries],\n\u001b[1;32m 1106\u001b[0m expand_composites\u001b[38;5;241m=\u001b[39mexpand_composites,\n\u001b[1;32m 1107\u001b[0m )\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tf_keras/src/utils/tf_utils.py:687\u001b[0m, in \u001b[0;36msync_to_numpy_or_python_type.._to_single_numpy_or_python_type\u001b[0;34m(t)\u001b[0m\n\u001b[1;32m 684\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_to_single_numpy_or_python_type\u001b[39m(t):\n\u001b[1;32m 685\u001b[0m \u001b[38;5;66;03m# Don't turn ragged or sparse tensors to NumPy.\u001b[39;00m\n\u001b[1;32m 686\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(t, tf\u001b[38;5;241m.\u001b[39mTensor):\n\u001b[0;32m--> 687\u001b[0m t \u001b[38;5;241m=\u001b[39m \u001b[43mt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnumpy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 688\u001b[0m \u001b[38;5;66;03m# Strings, ragged and sparse tensors don't have .item(). Return them\u001b[39;00m\n\u001b[1;32m 689\u001b[0m \u001b[38;5;66;03m# as-is.\u001b[39;00m\n\u001b[1;32m 690\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(t, (np\u001b[38;5;241m.\u001b[39mndarray, np\u001b[38;5;241m.\u001b[39mgeneric)):\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tensorflow/python/framework/ops.py:407\u001b[0m, in \u001b[0;36m_EagerTensorBase.numpy\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 384\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Copy of the contents of this Tensor into a NumPy array or scalar.\u001b[39;00m\n\u001b[1;32m 385\u001b[0m \n\u001b[1;32m 386\u001b[0m \u001b[38;5;124;03mUnlike NumPy arrays, Tensors are immutable, so this method has to copy\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 404\u001b[0m \u001b[38;5;124;03m NumPy dtype.\u001b[39;00m\n\u001b[1;32m 405\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 406\u001b[0m \u001b[38;5;66;03m# TODO(slebedev): Consider avoiding a copy for non-CPU or remote tensors.\u001b[39;00m\n\u001b[0;32m--> 407\u001b[0m maybe_arr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_numpy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# pylint: disable=protected-access\u001b[39;00m\n\u001b[1;32m 408\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m maybe_arr\u001b[38;5;241m.\u001b[39mcopy() \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(maybe_arr, np\u001b[38;5;241m.\u001b[39mndarray) \u001b[38;5;28;01melse\u001b[39;00m maybe_arr\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/tensorflow/python/framework/ops.py:373\u001b[0m, in \u001b[0;36m_EagerTensorBase._numpy\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 371\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_numpy\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m npt\u001b[38;5;241m.\u001b[39mArrayLike:\n\u001b[1;32m 372\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 373\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_numpy_internal\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 374\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m core\u001b[38;5;241m.\u001b[39m_NotOkStatusException \u001b[38;5;28;01mas\u001b[39;00m e: \u001b[38;5;66;03m# pylint: disable=protected-access\u001b[39;00m\n\u001b[1;32m 375\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m core\u001b[38;5;241m.\u001b[39m_status_to_exception(e) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "],"ename":"KeyboardInterrupt","evalue":"","output_type":"error"}],"execution_count":27},{"cell_type":"code","source":"train_loss = [0.3265, 0.2183, 0.1508, 0.1072, 0.0812]\nval_loss = [0.2663, 0.2729, 0.2993, 0.3496, 0.3729]\ntrain_accuracy = [0.8509, 0.9085, 0.9408, 0.9596, 0.9703]\nval_accuracy = [0.8844, 0.8924, 0.8957, 0.8991, 0.8989]\n\n# Define the number of epochs\nepochs = range(1, len(train_loss) + 1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:30:14.676567Z","iopub.execute_input":"2024-11-13T17:30:14.677227Z","iopub.status.idle":"2024-11-13T17:30:14.683138Z","shell.execute_reply.started":"2024-11-13T17:30:14.677161Z","shell.execute_reply":"2024-11-13T17:30:14.682260Z"}},"outputs":[],"execution_count":44},{"cell_type":"code","source":"plt.figure(figsize=(12, 5))\n\n# Subplot for loss\nplt.subplot(1, 2, 1)\nplt.plot(epochs, train_loss, 'bo-', label='Training Loss')\nplt.plot(epochs, val_loss, 'ro-', label='Validation Loss')\nplt.title('Training and Validation Loss')\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.legend()\n\nplt.subplot(1, 2, 2)\nplt.plot(epochs, train_accuracy, 'bo-', label='Training Accuracy')\nplt.plot(epochs, val_accuracy, 'ro-', label='Validation Accuracy')\nplt.title('Training and Validation Accuracy')\nplt.xlabel('Epochs')\nplt.ylabel('Accuracy')\nplt.legend()\n\n# Show the plot\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:33:23.571224Z","iopub.execute_input":"2024-11-13T17:33:23.571601Z","iopub.status.idle":"2024-11-13T17:33:24.201694Z","shell.execute_reply.started":"2024-11-13T17:33:23.571566Z","shell.execute_reply":"2024-11-13T17:33:24.200765Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}],"execution_count":48},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Example data (replace these with your actual data)\nepochs = [1, 2, 3, 4, 5] # Example epochs\ntrain_loss = [0.35, 0.32, 0.28, 0.22, 0.18] # Example training loss values\nval_loss = [0.37, 0.34, 0.30, 0.25, 0.20] # Example validation loss values\ntrain_accuracy = [0.75, 0.80, 0.85, 0.90, 0.92] # Example training accuracy values\nval_accuracy = [0.76, 0.81, 0.86, 0.89, 0.90] # Example validation accuracy values\n\n# Plotting\nplt.figure(figsize=(12, 5))\n\n# Subplot for loss\nplt.subplot(1, 2, 1)\nplt.plot(epochs, train_loss, 'bo-', label='Training Loss')\nplt.plot(epochs, val_loss, 'ro-', label='Validation Loss')\nplt.title('Training and Validation Loss')\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.legend()\n\n# Subplot for accuracy\nplt.subplot(1, 2, 2)\nplt.plot(epochs, train_accuracy, 'bo-', label='Training Accuracy')\nplt.plot(epochs, val_accuracy, 'ro-', label='Validation Accuracy')\nplt.axhline(y=0.8166821675069754, color='g', linestyle='--', label='Approach1 Acc for Random Forest')\nplt.title('Training and Validation Accuracy')\nplt.xlabel('Epochs')\nplt.ylabel('Accuracy')\nplt.legend()\n\n# Show the plot\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T20:01:00.522842Z","iopub.execute_input":"2024-11-13T20:01:00.523819Z","iopub.status.idle":"2024-11-13T20:01:01.235734Z","shell.execute_reply.started":"2024-11-13T20:01:00.523764Z","shell.execute_reply":"2024-11-13T20:01:01.234862Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}],"execution_count":2},{"cell_type":"code","source":"model_save_path = \"./saved_model\"\n\n# Save model and tokenizer\nmodel.save_pretrained(model_save_path)\ntokenizer.save_pretrained(model_save_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:21:32.174918Z","iopub.execute_input":"2024-11-13T17:21:32.175850Z","iopub.status.idle":"2024-11-13T17:21:33.000600Z","shell.execute_reply.started":"2024-11-13T17:21:32.175804Z","shell.execute_reply":"2024-11-13T17:21:32.999670Z"}},"outputs":[{"execution_count":29,"output_type":"execute_result","data":{"text/plain":"('./saved_model/tokenizer_config.json',\n './saved_model/special_tokens_map.json',\n './saved_model/vocab.txt',\n './saved_model/added_tokens.json')"},"metadata":{}}],"execution_count":29},{"cell_type":"code","source":"from transformers import TFDistilBertForSequenceClassification, DistilBertTokenizer\n\n# Load the saved model and tokenizer\nmodel = TFDistilBertForSequenceClassification.from_pretrained(model_save_path)\ntokenizer = DistilBertTokenizer.from_pretrained(model_save_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:21:42.673616Z","iopub.execute_input":"2024-11-13T17:21:42.674252Z","iopub.status.idle":"2024-11-13T17:21:43.442080Z","shell.execute_reply.started":"2024-11-13T17:21:42.674208Z","shell.execute_reply":"2024-11-13T17:21:43.441303Z"}},"outputs":[{"name":"stderr","text":"Some layers from the model checkpoint at ./saved_model were not used when initializing TFDistilBertForSequenceClassification: ['dropout_19']\n- This IS expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\nSome layers of TFDistilBertForSequenceClassification were not initialized from the model checkpoint at ./saved_model and are newly initialized: ['dropout_39']\nYou should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","output_type":"stream"}],"execution_count":30},{"cell_type":"code","source":"question_pairs = [\n (\"How do I reset my password?\", \"How can I change my password?\"),\n (\"What is the refund policy?\", \"How do I get a refund?\"),\n (\"Can I edit my profile?\", \"How do I delete my account?\")\n]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:24:28.027548Z","iopub.execute_input":"2024-11-13T17:24:28.027973Z","iopub.status.idle":"2024-11-13T17:24:28.032766Z","shell.execute_reply.started":"2024-11-13T17:24:28.027919Z","shell.execute_reply":"2024-11-13T17:24:28.031809Z"}},"outputs":[],"execution_count":32},{"cell_type":"code","source":"inputs = tokenizer(\n [q[0] for q in question_pairs], [q[1] for q in question_pairs],\n return_tensors='tf',\n truncation=True,\n padding=True,\n max_length=50\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:24:36.823647Z","iopub.execute_input":"2024-11-13T17:24:36.824041Z","iopub.status.idle":"2024-11-13T17:24:36.831770Z","shell.execute_reply.started":"2024-11-13T17:24:36.824001Z","shell.execute_reply":"2024-11-13T17:24:36.830811Z"}},"outputs":[],"execution_count":33},{"cell_type":"code","source":"outputs = model(inputs)\nlogits = outputs.logits\n\n# Convert logits to probabilities\nprobabilities = tf.nn.softmax(logits, axis=-1)\npredictions = tf.argmax(probabilities, axis=1).numpy() # 0 or 1 for binary classification","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:24:49.177522Z","iopub.execute_input":"2024-11-13T17:24:49.178168Z","iopub.status.idle":"2024-11-13T17:24:49.365337Z","shell.execute_reply.started":"2024-11-13T17:24:49.178124Z","shell.execute_reply":"2024-11-13T17:24:49.364546Z"}},"outputs":[],"execution_count":34},{"cell_type":"code","source":"for i, pair in enumerate(question_pairs):\n print(f\"Question 1: {pair[0]}\")\n print(f\"Question 2: {pair[1]}\")\n print(f\"Prediction: {'Duplicate' if predictions[i] == 1 else 'Not Duplicate'}\")\n print(f\"Probability: {probabilities[i].numpy()}\")\n print(\"------\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:25:03.377054Z","iopub.execute_input":"2024-11-13T17:25:03.377457Z","iopub.status.idle":"2024-11-13T17:25:03.388507Z","shell.execute_reply.started":"2024-11-13T17:25:03.377410Z","shell.execute_reply":"2024-11-13T17:25:03.387571Z"}},"outputs":[{"name":"stdout","text":"Question 1: How do I reset my password?\nQuestion 2: How can I change my password?\nPrediction: Not Duplicate\nProbability: [0.7415553 0.2584447]\n------\nQuestion 1: What is the refund policy?\nQuestion 2: How do I get a refund?\nPrediction: Not Duplicate\nProbability: [9.9993753e-01 6.2406660e-05]\n------\nQuestion 1: Can I edit my profile?\nQuestion 2: How do I delete my account?\nPrediction: Not Duplicate\nProbability: [9.9979657e-01 2.0339788e-04]\n------\n","output_type":"stream"}],"execution_count":35},{"cell_type":"code","source":"question_pairs = [\n (\"How do I reset my password?\", \"What is the process to reset my password?\"),\n (\"Where can I find my order history?\", \"How do I view my past orders?\"),\n (\"What is the return policy for online purchases?\", \"How can I return an item bought online?\"),\n (\"Can I change my delivery address after ordering?\", \"Is it possible to update the shipping address once the order is placed?\"),\n (\"How do I contact customer support?\", \"What’s the best way to reach customer service?\"),\n (\"How do I reset my password?\", \"How do I delete my account?\"),\n (\"Where can I find my order history?\", \"What are the delivery options for my area?\"),\n (\"What is the return policy for online purchases?\", \"How long does it take to get a refund after returning an item?\"),\n (\"Can I change my delivery address after ordering?\", \"How do I apply a discount code to my order?\"),\n (\"How do I contact customer support?\", \"What payment methods are accepted?\")\n]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:28:01.374366Z","iopub.execute_input":"2024-11-13T17:28:01.374759Z","iopub.status.idle":"2024-11-13T17:28:01.380843Z","shell.execute_reply.started":"2024-11-13T17:28:01.374721Z","shell.execute_reply":"2024-11-13T17:28:01.379900Z"}},"outputs":[],"execution_count":40},{"cell_type":"code","source":"inputs = tokenizer(\n [q[0] for q in question_pairs], [q[1] for q in question_pairs],\n return_tensors='tf',\n truncation=True,\n padding=True,\n max_length=50\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:28:01.715220Z","iopub.execute_input":"2024-11-13T17:28:01.715571Z","iopub.status.idle":"2024-11-13T17:28:01.728829Z","shell.execute_reply.started":"2024-11-13T17:28:01.715535Z","shell.execute_reply":"2024-11-13T17:28:01.728072Z"}},"outputs":[],"execution_count":41},{"cell_type":"code","source":"outputs = model(inputs)\nlogits = outputs.logits\n\n# Convert logits to probabilities\nprobabilities = tf.nn.softmax(logits, axis=-1)\npredictions = tf.argmax(probabilities, axis=1).numpy() # 0 or 1 for binary classification","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:28:02.123305Z","iopub.execute_input":"2024-11-13T17:28:02.124399Z","iopub.status.idle":"2024-11-13T17:28:02.231215Z","shell.execute_reply.started":"2024-11-13T17:28:02.124344Z","shell.execute_reply":"2024-11-13T17:28:02.230467Z"}},"outputs":[],"execution_count":42},{"cell_type":"code","source":"for i, pair in enumerate(question_pairs):\n print(f\"Question 1: {pair[0]}\")\n print(f\"Question 2: {pair[1]}\")\n print(f\"Prediction: {'Duplicate' if predictions[i] == 1 else 'Not Duplicate'}\")\n print(f\"Probability: {probabilities[i].numpy()}\")\n print(\"------\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-13T17:28:02.796057Z","iopub.execute_input":"2024-11-13T17:28:02.796413Z","iopub.status.idle":"2024-11-13T17:28:02.811542Z","shell.execute_reply.started":"2024-11-13T17:28:02.796379Z","shell.execute_reply":"2024-11-13T17:28:02.810572Z"}},"outputs":[{"name":"stdout","text":"Question 1: How do I reset my password?\nQuestion 2: What is the process to reset my password?\nPrediction: Duplicate\nProbability: [0.12865898 0.871341 ]\n------\nQuestion 1: Where can I find my order history?\nQuestion 2: How do I view my past orders?\nPrediction: Not Duplicate\nProbability: [9.9971086e-01 2.8908864e-04]\n------\nQuestion 1: What is the return policy for online purchases?\nQuestion 2: How can I return an item bought online?\nPrediction: Not Duplicate\nProbability: [9.9984324e-01 1.5668685e-04]\n------\nQuestion 1: Can I change my delivery address after ordering?\nQuestion 2: Is it possible to update the shipping address once the order is placed?\nPrediction: Not Duplicate\nProbability: [0.9857459 0.01425405]\n------\nQuestion 1: How do I contact customer support?\nQuestion 2: What’s the best way to reach customer service?\nPrediction: Duplicate\nProbability: [0.12125948 0.8787405 ]\n------\nQuestion 1: How do I reset my password?\nQuestion 2: How do I delete my account?\nPrediction: Not Duplicate\nProbability: [0.99780506 0.00219489]\n------\nQuestion 1: Where can I find my order history?\nQuestion 2: What are the delivery options for my area?\nPrediction: Not Duplicate\nProbability: [9.9995637e-01 4.3573633e-05]\n------\nQuestion 1: What is the return policy for online purchases?\nQuestion 2: How long does it take to get a refund after returning an item?\nPrediction: Not Duplicate\nProbability: [9.9995112e-01 4.8857506e-05]\n------\nQuestion 1: Can I change my delivery address after ordering?\nQuestion 2: How do I apply a discount code to my order?\nPrediction: Not Duplicate\nProbability: [9.9995756e-01 4.2442902e-05]\n------\nQuestion 1: How do I contact customer support?\nQuestion 2: What payment methods are accepted?\nPrediction: Not Duplicate\nProbability: [9.999125e-01 8.743310e-05]\n------\n","output_type":"stream"}],"execution_count":43},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}