systemy_dialogowe/eval.ipynb

378 lines
12 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\macty\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\tensorflow_addons\\utils\\tfa_eol_msg.py:23: UserWarning: \n",
"\n",
"TensorFlow Addons (TFA) has ended development and introduction of new features.\n",
"TFA has entered a minimal maintenance and release mode until a planned end of life in May 2024.\n",
"Please modify downstream libraries to take dependencies from other repositories in our TensorFlow community (e.g. Keras, Keras-CV, and Keras-NLP). \n",
"\n",
"For more information see: https://github.com/tensorflow/addons/issues/2807 \n",
"\n",
" warnings.warn(\n"
]
}
],
"source": [
"import pickle\n",
"import pandas as pd\n",
"import tensorflow as tf\n",
"from tensorflow.keras.models import load_model\n",
"import tensorflow_addons as tfa\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"loaded_model = tf.keras.models.load_model('model')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"tf_bert_for_sequence_classification\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" bert (Custom>TFBertMainLaye multiple 132121344 \n",
" r) \n",
" \n",
" dropout_37 (Dropout) multiple 0 \n",
" \n",
" classifier (Dense) multiple 13073 \n",
" \n",
"=================================================================\n",
"Total params: 132,134,417\n",
"Trainable params: 132,134,417\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"loaded_model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"acts=pd.read_csv('user_acts_one_hot.csv', index_col=\"Unnamed: 0\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"acts=acts.drop([\"Agent\"],axis=1)\n",
"acts=acts.drop([\"Act\"],axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\macty\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n",
"c:\\Users\\macty\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\transformers\\generation_utils.py:24: FutureWarning: Importing `GenerationMixin` from `src/transformers/generation_utils.py` is deprecated and will be removed in Transformers v5. Import as `from transformers import GenerationMixin` instead.\n",
" warnings.warn(\n",
"c:\\Users\\macty\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\transformers\\generation_tf_utils.py:24: FutureWarning: Importing `TFGenerationMixin` from `src/transformers/generation_tf_utils.py` is deprecated and will be removed in Transformers v5. Import as `from transformers import TFGenerationMixin` instead.\n",
" warnings.warn(\n",
"loading file vocab.txt from cache at C:\\Users\\macty/.cache\\huggingface\\hub\\models--dkleczek--bert-base-polish-uncased-v1\\snapshots\\62be9821055981deafb23f217b68cc41f38cdb76\\vocab.txt\n",
"loading file added_tokens.json from cache at None\n",
"loading file special_tokens_map.json from cache at C:\\Users\\macty/.cache\\huggingface\\hub\\models--dkleczek--bert-base-polish-uncased-v1\\snapshots\\62be9821055981deafb23f217b68cc41f38cdb76\\special_tokens_map.json\n",
"loading file tokenizer_config.json from cache at C:\\Users\\macty/.cache\\huggingface\\hub\\models--dkleczek--bert-base-polish-uncased-v1\\snapshots\\62be9821055981deafb23f217b68cc41f38cdb76\\tokenizer_config.json\n",
"loading configuration file config.json from cache at C:\\Users\\macty/.cache\\huggingface\\hub\\models--dkleczek--bert-base-polish-uncased-v1\\snapshots\\62be9821055981deafb23f217b68cc41f38cdb76\\config.json\n",
"Model config BertConfig {\n",
" \"_name_or_path\": \"dkleczek/bert-base-polish-uncased-v1\",\n",
" \"architectures\": [\n",
" \"BertForMaskedLM\",\n",
" \"BertForPreTraining\"\n",
" ],\n",
" \"attention_probs_dropout_prob\": 0.1,\n",
" \"classifier_dropout\": null,\n",
" \"hidden_act\": \"gelu\",\n",
" \"hidden_dropout_prob\": 0.1,\n",
" \"hidden_size\": 768,\n",
" \"initializer_range\": 0.02,\n",
" \"intermediate_size\": 3072,\n",
" \"layer_norm_eps\": 1e-12,\n",
" \"max_position_embeddings\": 512,\n",
" \"model_type\": \"bert\",\n",
" \"num_attention_heads\": 12,\n",
" \"num_hidden_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"position_embedding_type\": \"absolute\",\n",
" \"transformers_version\": \"4.28.1\",\n",
" \"type_vocab_size\": 2,\n",
" \"use_cache\": true,\n",
" \"vocab_size\": 60000\n",
"}\n",
"\n"
]
}
],
"source": [
"from transformers import *\n",
"tokenizer = BertTokenizer.from_pretrained(\"dkleczek/bert-base-polish-uncased-v1\")\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"80/80 [==============================] - 14s 170ms/step\n"
]
}
],
"source": [
"input_data = acts[\"text\"].tolist()\n",
"encoded_input = tokenizer.batch_encode_plus(input_data, padding=True, truncation=True, return_tensors='tf')\n",
"dataset = tf.data.Dataset.from_tensor_slices({\n",
" 'input_ids': encoded_input['input_ids'],\n",
" 'attention_mask': encoded_input['attention_mask'],\n",
" 'token_type_ids': encoded_input['token_type_ids']\n",
"}).batch(2)\n",
"\n",
"# make predictions\n",
"predictions = loaded_model.predict(dataset)\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"def predict(text):\n",
" input = [ text ]\n",
" encoded_input = tokenizer.batch_encode_plus(input, padding=True, truncation=True, return_tensors='tf')\n",
" dataset = tf.data.Dataset.from_tensor_slices({\n",
" 'input_ids': encoded_input['input_ids'],\n",
" 'attention_mask': encoded_input['attention_mask'],\n",
" 'token_type_ids': encoded_input['token_type_ids']\n",
" }).batch(2)\n",
" predictions = loaded_model.predict(dataset)\n",
" return predictions\n",
" \n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"for prediction in predictions:\n",
" predicted_classes = (predictions[prediction]> 0.5).astype(\"int32\")\n"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0, 0, 0, ..., 0, 0, 0],\n",
" [0, 0, 0, ..., 0, 0, 1],\n",
" [0, 0, 0, ..., 0, 1, 0],\n",
" ...,\n",
" [0, 0, 0, ..., 0, 0, 0],\n",
" [0, 0, 0, ..., 0, 0, 0],\n",
" [0, 0, 1, ..., 0, 0, 0]])"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"predicted_classes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"classes = [\"ack\",\"affirm\",\"bye\",\"hello\",\"help\",\"negate\",\"null\",\"repeat\",\"reqalts\",\"reqmore\",\"restart\",\"silence\",\"thankyou\",\"confirm\",\"deny\",\"inform\",\"request\"]"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"true_acts = acts.drop(acts.columns[0],axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"true= true_acts.to_numpy()"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"results = abs(predicted_classes-true)"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"23"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
"all=results.size"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"not_predicted = results.sum()"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
"accuracy = (all-not_predicted)/all"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\macty\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1609: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no true nor predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, \"true nor predicted\", \"F-score is\", len(true_sum))\n"
]
}
],
"source": [
"from sklearn.metrics import f1_score\n",
"micro_f1 = f1_score(true, predicted_classes, average='micro')\n",
"macro_f1 = f1_score(true, predicted_classes, average='macro')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.9362880886426593\n"
]
}
],
"source": [
"print(micro_f1)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.2"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}