saret/DH
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

summery

Browse Source
This commit is contained in:
Benny Saret
2023-08-12 18:19:37 +03:00
parent 0e26118247
commit 8352a0a097
2 changed files with 61 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
datat.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -12,6 +12,7 @@
"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",
@@ -23,7 +24,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -34,7 +35,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -44,7 +45,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@@ -55,26 +56,63 @@
},
{
"cell_type": "code",
"execution_count": 22,
"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": [
{
"ename": "ValueError",
"evalue": "Cannot set a DataFrame with multiple columns to the single column Genre",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[22], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m df_genre \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mread_csv(\u001b[39m'\u001b[39m\u001b[39mgenre.csv\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m----> 2\u001b[0m df_akk[\u001b[39m\"\u001b[39;49m\u001b[39mGenre\u001b[39;49m\u001b[39m\"\u001b[39;49m] \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mconcat([df_genre, df_akk], axis\u001b[39m=\u001b[39m\u001b[39m1\u001b[39m, join\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39minner\u001b[39m\u001b[39m'\u001b[39m, keys\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mProject\u001b[39m\u001b[39m'\u001b[39m)\n",
"File \u001b[1;32mc:\\Users\\Saret\\Programming\\C#\\DH\\venv\\lib\\site-packages\\pandas\\core\\frame.py:3949\u001b[0m, in \u001b[0;36mDataFrame.__setitem__\u001b[1;34m(self, key, value)\u001b[0m\n\u001b[0;32m 3947\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_setitem_array(key, value)\n\u001b[0;32m 3948\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39misinstance\u001b[39m(value, DataFrame):\n\u001b[1;32m-> 3949\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_set_item_frame_value(key, value)\n\u001b[0;32m 3950\u001b[0m \u001b[39melif\u001b[39;00m (\n\u001b[0;32m 3951\u001b[0m is_list_like(value)\n\u001b[0;32m 3952\u001b[0m \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcolumns\u001b[39m.\u001b[39mis_unique\n\u001b[0;32m 3953\u001b[0m \u001b[39mand\u001b[39;00m \u001b[39m1\u001b[39m \u001b[39m<\u001b[39m \u001b[39mlen\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcolumns\u001b[39m.\u001b[39mget_indexer_for([key])) \u001b[39m==\u001b[39m \u001b[39mlen\u001b[39m(value)\n\u001b[0;32m 3954\u001b[0m ):\n\u001b[0;32m 3955\u001b[0m \u001b[39m# Column to set is duplicated\u001b[39;00m\n\u001b[0;32m 3956\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_setitem_array([key], value)\n",
"File \u001b[1;32mc:\\Users\\Saret\\Programming\\C#\\DH\\venv\\lib\\site-packages\\pandas\\core\\frame.py:4103\u001b[0m, in \u001b[0;36mDataFrame._set_item_frame_value\u001b[1;34m(self, key, value)\u001b[0m\n\u001b[0;32m 4100\u001b[0m \u001b[39mreturn\u001b[39;00m\n\u001b[0;32m 4102\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(value\u001b[39m.\u001b[39mcolumns) \u001b[39m!=\u001b[39m \u001b[39m1\u001b[39m:\n\u001b[1;32m-> 4103\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[0;32m 4104\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mCannot set a DataFrame with multiple columns to the single \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m 4105\u001b[0m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mcolumn \u001b[39m\u001b[39m{\u001b[39;00mkey\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m\n\u001b[0;32m 4106\u001b[0m )\n\u001b[0;32m 4108\u001b[0m \u001b[39mself\u001b[39m[key] \u001b[39m=\u001b[39m value[value\u001b[39m.\u001b[39mcolumns[\u001b[39m0\u001b[39m]]\n",
"\u001b[1;31mValueError\u001b[0m: Cannot set a DataFrame with multiple columns to the single column Genre"
"name": "stdout",
"output_type": "stream",
"text": [
"Using matplotlib backend: <object object at 0x00000212CB626CA0>\n"
]
}
],
"source": [
"df_genre = pd.read_csv('genre.csv')\n",
"df_akk[\"Genre\"] = pd.concat([df_genre, df_akk], axis=1, join='inner', keys='Project')"
"%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,:]"
]
},
{
@@ -87,7 +125,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@@ -102,8 +140,7 @@
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
},
"orig_nbformat": 4
}
},
"nbformat": 4,
"nbformat_minor": 2