148 lines
3.6 KiB
Plaintext
148 lines
3.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import sklearn\n",
|
|
"import sklearn.model_selection\n",
|
|
"from sklearn.metrics.pairwise import cosine_similarity\n",
|
|
"from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer\n",
|
|
"import pandas as pd\n",
|
|
"import scipy\n",
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"df_eng = pd.read_csv('raw_texts.csv')\n",
|
|
"df_akk = pd.read_csv('new.csv')\n",
|
|
"# akk_raw_train, akk_raw_test = sklearn.model_selection.train_test_split(df_akk, test_size=0.2, random_state=0)\n",
|
|
"# eng_raw_train, eng_raw_test = sklearn.model_selection.train_test_split(df_eng, test_size=0.2, random_state=0)\n",
|
|
"tf_vectorizer = TfidfVectorizer(analyzer='word')\n",
|
|
"# tf_vectorizer.fit(akk_raw_train['Text'].to_list())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"tf_vectorizer = TfidfVectorizer(analyzer='word')\n",
|
|
"save_vect = tf_vectorizer.fit_transform(df_akk['Text'].dropna().to_list())\n",
|
|
"# save_vect = tf_vectorizer.fit_transform(['The sun in the sky is bright', 'We can see the shining sun, the bright sun.'])\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"tfidf_tokens = tf_vectorizer.get_feature_names_out()\n",
|
|
"df_tfidfvect = pd.DataFrame(data=save_vect.toarray(), columns=tfidf_tokens)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"test_mat = tf_vectorizer.transform(df_akk['Text'].dropna().to_list())\n",
|
|
"cc = cosine_similarity(save_vect,save_vect)\n",
|
|
"bool_similarity = cc > 0.5\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"abcd = np.where((cc > 0.5)&( cc< 1))\n",
|
|
"abcd[0].tofile(\"data.csv\", sep = \",\", format = \"%d\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Using matplotlib backend: <object object at 0x00000212CB626CA0>\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%matplotlib\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"import seaborn as sns"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"f = sns.scatterplot(bool_similarity)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"Project P394767\n",
|
|
"Text x x x BAD₃-ku-ri-gal-zi x E₂ 44 ša₂ BAD₃-{d}su...\n",
|
|
"Genre lexical\n",
|
|
"Name: 4, dtype: object"
|
|
]
|
|
},
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df_akk.iloc[4,:]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.9.13"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|