Datasets
Models
Downloads: 1
312 lines (312 with data), 19.5 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "-oTEyfkwNdmj"
},
"outputs": [],
"source": [
"# from transformers import pipeline, BertForMaskedLM, BertTokenizer, BertModel\n",
"# from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n",
"# import time\n",
"# import torch\n",
"# import math\n",
"# import re"
]
},
{
"cell_type": "code",
"source": [
"# Ref 1: Hugging Face, Rostlab/prot_bert. https://huggingface.co/Rostlab/prot_bert\n",
"# Ref 2: Hayes, J. Medium, 2023 https://medium.com/labs-notebook/large-language-models-for-drug-discovery-7ddfc005e0bb\n",
"# Ref 3: HF Intro, AssemblyAI 2022 https://www.youtube.com/watch?v=QEaBAZQCtwE&t=4s\n",
"# Ref 4: ChatGPT3.5 Coding assistance 2024 https://chat.openai.com/"
],
"metadata": {
"id": "jzr3h73L1w-7"
},
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since beginning of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "2K0dcoVBuBGy",
"outputId": "8a904c07-4c64-41e8-94d1-0ec72d15c425"
},
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712858775.0148897\n",
"Thu Apr 11 18:06:15 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Load tokenizer and model\n",
"tokenizer = BertTokenizer.from_pretrained(\"Rostlab/prot_bert\", do_lower_case=False)\n",
"model = BertForMaskedLM.from_pretrained(\"Rostlab/prot_bert\")\n",
"unmasker = pipeline('fill-mask', model=model, tokenizer=tokenizer)\n",
"\n",
"# Define the sequence with two masked tokens\n",
"sequence = 'FYLSITIHRPLRP[MASK]SSSSFLSLCLSLLSISIYYPS\\nLLIRRFTSISSCSSITIYHPLLYPSPSSLFLSLSHTYIYISPLHPSSLLLSISLLFYLSI\\nYIIYPLQPSSLLLSI[MASK]SLPLSISIYLSYPPLSSPSPSLSLYLTPFLLIPSLSIYLSLPFPY\\nHSYLYLRLLFHPPLPLHICHLPHSLTLFIFLLPPHLSHLPILFSRLQPFYPSTSPSSYRP\\nLPCIPSASYFSYHPLSPPPSLHPHPLSYPSVSRPSPPYLSIHLHSPPPPPPPSPFSSIHP\\nPFLSSTLPLPSSTSSLPPSSSPFSSTHLIPSPSSPPPPSLLPSSLPL'\n",
"\n",
"# Predict and print top 10 predictions for each mask\n",
"result = unmasker(sequence, top_k=10)\n",
"for predictions in result:\n",
" for prediction in predictions:\n",
" print(prediction)\n",
" print(\"------\")"
],
"metadata": {
"id": "YX05PGDZNImk",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "25f2ab86-fc66-4279-cf8f-a1621d267e6f"
},
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Some weights of the model checkpoint at Rostlab/prot_bert were not used when initializing BertForMaskedLM: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']\n",
"- This IS expected if you are initializing BertForMaskedLM 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 BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"{'score': 0.9999492168426514, 'token': 25, 'token_str': 'X', 'sequence': '[CLS] [UNK] X [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 7.70106453273911e-06, 'token': 13, 'token_str': 'R', 'sequence': '[CLS] [UNK] R [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 6.548679721163353e-06, 'token': 5, 'token_str': 'L', 'sequence': '[CLS] [UNK] L [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 4.85780628878274e-06, 'token': 19, 'token_str': 'F', 'sequence': '[CLS] [UNK] F [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 4.367872861621436e-06, 'token': 18, 'token_str': 'Q', 'sequence': '[CLS] [UNK] Q [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 4.232546871207887e-06, 'token': 7, 'token_str': 'G', 'sequence': '[CLS] [UNK] G [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 3.1130280149227474e-06, 'token': 12, 'token_str': 'K', 'sequence': '[CLS] [UNK] K [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 2.9373295546974987e-06, 'token': 16, 'token_str': 'P', 'sequence': '[CLS] [UNK] P [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 2.8243982796993805e-06, 'token': 6, 'token_str': 'A', 'sequence': '[CLS] [UNK] A [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 2.3990457975742174e-06, 'token': 15, 'token_str': 'T', 'sequence': '[CLS] [UNK] T [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"------\n",
"{'score': 0.9999690055847168, 'token': 25, 'token_str': 'X', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] X [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 4.743668341689045e-06, 'token': 5, 'token_str': 'L', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] L [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 4.336807705840329e-06, 'token': 13, 'token_str': 'R', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] R [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 4.116420768696116e-06, 'token': 18, 'token_str': 'Q', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] Q [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 3.6834383081441047e-06, 'token': 6, 'token_str': 'A', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] A [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 2.364193051107577e-06, 'token': 7, 'token_str': 'G', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] G [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 2.1007083432778018e-06, 'token': 16, 'token_str': 'P', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] P [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 1.6038892454162124e-06, 'token': 15, 'token_str': 'T', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] T [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 1.3503024547389941e-06, 'token': 10, 'token_str': 'S', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] S [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"{'score': 1.272862732548674e-06, 'token': 12, 'token_str': 'K', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] K [UNK] [UNK] [UNK] [UNK] [SEP]'}\n",
"------\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Load tokenizer and model\n",
"tokenizer = BertTokenizer.from_pretrained(\"Rostlab/prot_bert\", do_lower_case=False)\n",
"model = BertForMaskedLM.from_pretrained(\"Rostlab/prot_bert\")\n",
"unmasker = pipeline('fill-mask', model=model, tokenizer=tokenizer)\n",
"\n",
"# Define the sequence with two masked tokens\n",
"sequence = 'FYLSITIHRPLRP[MASK]SSSSFLSLCLSLLSISIYYPS\\nLLIRRFTSISSCSSITIYHPLLYPSPSSLFLSLSHTYIYISPLHPSSLLLSISLLFYLSI\\nYIIYPLQPSSLLLSI[MASK]SLPLSISIYLSYPPLSSPSPSLSLYLTPFLLIPSLSIYLSLPFPY\\nHSYLYLRLLFHPPLPLHICHLPHSLTLFIFLLPPHLSHLPILFSRLQPFYPSTSPSSYRP\\nLPCIPSASYFSYHPLSPPPSLHPHPLSYPSVSRPSPPYLSIHLHSPPPPPPPSPFSSIHP\\nPFLSSTLPLPSSTSSLPPSSSPFSSTHLIPSPSSPPPPSLLP[MASK]SSLPL'\n",
"\n",
"# Predict and print top 10 predictions for each mask\n",
"result = unmasker(sequence, top_k=10)\n",
"for predictions in result:\n",
" for prediction in predictions:\n",
" print(prediction)\n",
" print(\"------\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "McDmgTTdNlA9",
"outputId": "551fd198-7b8b-4601-cf93-40dc5da22f95"
},
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Some weights of the model checkpoint at Rostlab/prot_bert were not used when initializing BertForMaskedLM: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']\n",
"- This IS expected if you are initializing BertForMaskedLM 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 BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"{'score': 0.9999243021011353, 'token': 25, 'token_str': 'X', 'sequence': '[CLS] [UNK] X [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 9.95707159745507e-06, 'token': 5, 'token_str': 'L', 'sequence': '[CLS] [UNK] L [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 7.378088412224315e-06, 'token': 7, 'token_str': 'G', 'sequence': '[CLS] [UNK] G [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 7.330473636102397e-06, 'token': 9, 'token_str': 'E', 'sequence': '[CLS] [UNK] E [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 6.249400939850602e-06, 'token': 12, 'token_str': 'K', 'sequence': '[CLS] [UNK] K [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 6.2195363170758355e-06, 'token': 19, 'token_str': 'F', 'sequence': '[CLS] [UNK] F [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 6.003328053338919e-06, 'token': 6, 'token_str': 'A', 'sequence': '[CLS] [UNK] A [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 5.373394287744304e-06, 'token': 13, 'token_str': 'R', 'sequence': '[CLS] [UNK] R [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 4.275994342606282e-06, 'token': 20, 'token_str': 'Y', 'sequence': '[CLS] [UNK] Y [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 3.627200385381002e-06, 'token': 8, 'token_str': 'V', 'sequence': '[CLS] [UNK] V [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"------\n",
"{'score': 0.9996041655540466, 'token': 25, 'token_str': 'X', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] X [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 5.5235712352441624e-05, 'token': 6, 'token_str': 'A', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] A [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 5.422084723250009e-05, 'token': 5, 'token_str': 'L', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] L [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 4.226986857247539e-05, 'token': 7, 'token_str': 'G', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] G [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 3.9134716644184664e-05, 'token': 13, 'token_str': 'R', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] R [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 3.062105315621011e-05, 'token': 18, 'token_str': 'Q', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] Q [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 2.8334136004559696e-05, 'token': 9, 'token_str': 'E', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] E [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 2.7488824343890883e-05, 'token': 12, 'token_str': 'K', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] K [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 1.9406317733228207e-05, 'token': 16, 'token_str': 'P', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] P [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"{'score': 1.778588557499461e-05, 'token': 19, 'token_str': 'F', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] F [UNK] [UNK] [UNK] [UNK] [MASK] [UNK] [SEP]'}\n",
"------\n",
"{'score': 0.9990819692611694, 'token': 25, 'token_str': 'X', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] X [UNK] [SEP]'}\n",
"{'score': 0.00016688588948454708, 'token': 6, 'token_str': 'A', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] A [UNK] [SEP]'}\n",
"{'score': 8.889797754818574e-05, 'token': 5, 'token_str': 'L', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] L [UNK] [SEP]'}\n",
"{'score': 8.658925071358681e-05, 'token': 12, 'token_str': 'K', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] K [UNK] [SEP]'}\n",
"{'score': 6.849779310869053e-05, 'token': 18, 'token_str': 'Q', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] Q [UNK] [SEP]'}\n",
"{'score': 6.579031469300389e-05, 'token': 20, 'token_str': 'Y', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] Y [UNK] [SEP]'}\n",
"{'score': 6.401719292625785e-05, 'token': 7, 'token_str': 'G', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] G [UNK] [SEP]'}\n",
"{'score': 5.076546221971512e-05, 'token': 9, 'token_str': 'E', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] E [UNK] [SEP]'}\n",
"{'score': 4.9771988415159285e-05, 'token': 13, 'token_str': 'R', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] R [UNK] [SEP]'}\n",
"{'score': 4.564020491670817e-05, 'token': 19, 'token_str': 'F', 'sequence': '[CLS] [UNK] [MASK] [UNK] [UNK] [UNK] [MASK] [UNK] [UNK] [UNK] [UNK] F [UNK] [SEP]'}\n",
"------\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Load tokenizer and model\n",
"tokenizer = BertTokenizer.from_pretrained(\"Rostlab/prot_bert\", do_lower_case=False)\n",
"model = BertModel.from_pretrained(\"Rostlab/prot_bert\")\n",
"\n",
"# Example protein sequence\n",
"sequence_Example = \"FYLSITIHRPLRPSSSSFLSLCLSLLSISIYYPS\\nLLIRRFTSISSCSSITIYHPLLYPSPSSLFLSLSHTYIYISPLHPSSLLLSISLLFYLSI\\nYIIYPLQPSSLLLSISLPLSISIYLSYPPLSSPSPSLSLYLTPFLLIPSLSIYLSLPFPY\\nHSYLYLRLLFHPPLPLHICHLPHSLTLFIFLLPPHLSHLPILFSRLQPFYPSTSPSSYRP\\nLPCIPSASYFSYHPLSPPPSLHPHPLSYPSVSRPSPPYLSIHLHSPPPPPPPSPFSSIHP\\nPFLSSTLPLPSSTSSLPPSSSPFSSTHLIPSPSSPPPPSLLPSSLPL\"\n",
"sequence_Example = re.sub(r\"[UZOB]\", \"X\", sequence_Example)\n",
"\n",
"# Tokenize input sequence\n",
"encoded_input = tokenizer(sequence_Example, return_tensors='pt')\n",
"\n",
"# Forward pass through the model\n",
"output = model(**encoded_input)\n",
"\n",
"print(output)\n",
"\n",
"# Extract last hidden states\n",
"last_hidden_state = output.last_hidden_state\n",
"\n",
"# Calculate additional metrics\n",
"mean_tensor = torch.mean(last_hidden_state, dim=1) # Mean along sequence length\n",
"std_tensor = torch.std(last_hidden_state, dim=1) # Standard deviation along sequence length\n",
"max_tensor = torch.max(last_hidden_state, dim=1).values # Maximum value along sequence length\n",
"\n",
"# Print additional metrics\n",
"print(\"Mean tensor shape:\", mean_tensor.shape)\n",
"print(\"Standard deviation tensor shape:\", std_tensor.shape)\n",
"print(\"Maximum tensor shape:\", max_tensor.shape)"
],
"metadata": {
"id": "tiXjSEo2MfrD",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "55f75b62-24fc-4524-c3fe-04c076842cdd"
},
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"BaseModelOutputWithPoolingAndCrossAttentions(last_hidden_state=tensor([[[-0.1217, 0.0759, -0.2128, ..., 0.0417, -0.0052, 0.1067],\n",
" [-0.0694, 0.1312, -0.1388, ..., -0.0231, 0.0595, 0.0174],\n",
" [-0.1399, 0.0801, -0.1725, ..., 0.0329, -0.0341, 0.0568],\n",
" ...,\n",
" [-0.1345, 0.0499, -0.1611, ..., 0.0035, -0.0035, 0.0531],\n",
" [-0.1569, 0.0764, -0.1574, ..., -0.0122, -0.0043, 0.0533],\n",
" [-0.1272, 0.0725, -0.1479, ..., -0.0294, 0.0445, -0.0033]]],\n",
" grad_fn=<NativeLayerNormBackward0>), pooler_output=tensor([[-0.1908, 0.2020, -0.1812, ..., 0.1921, 0.1790, -0.1964]],\n",
" grad_fn=<TanhBackward0>), hidden_states=None, past_key_values=None, attentions=None, cross_attentions=None)\n",
"Mean tensor shape: torch.Size([1, 1024])\n",
"Standard deviation tensor shape: torch.Size([1, 1024])\n",
"Maximum tensor shape: torch.Size([1, 1024])\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since end of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "TkiND_HHuERP",
"outputId": "c8fbb5be-e846-42ef-d6bc-6347d9a3ba87"
},
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712858783.8144772\n",
"Thu Apr 11 18:06:23 2024\n"
]
}
]
}
]
}