{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "83c66bad-e9bb-4ea7-9f6b-be842df821f0",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import json\n",
"import re\n",
"import unicodedata\n",
"import numpy as np\n",
"data = pd.read_csv(\"./quotations.csv\", on_bad_lines='skip',sep=\";\")\n",
"\n",
"# Filter to just “Fensterreinigung” and drop rows missing requirements_textual\n",
"data = data.loc[\n",
" data['requirements_textual'].notna()\n",
" & data['price'].notna()\n",
"]\n",
"\n",
"\n",
"# (booking['product_name'] == \"Fensterreinigung\")\n",
"# & booking['quotation_info_request'].isna()\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d78b8f4a-f140-463f-8369-163f520dca4b",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_3260376/2893397658.py:27: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" shortened.loc[len(shortened)] = [othersFreq,othersRelFreq,\"Sonstige\",othersCumRelFreq]\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" freq | \n",
" relFreq | \n",
" name | \n",
" cumRelFreq | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 5169 | \n",
" 0.41 | \n",
" Umzugsreinigung | \n",
" 0.41 | \n",
"
\n",
" \n",
" | 1 | \n",
" 2448 | \n",
" 0.19 | \n",
" Intensivreinigung | \n",
" 0.60 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2124 | \n",
" 0.17 | \n",
" Fensterreinigung | \n",
" 0.77 | \n",
"
\n",
" \n",
" | 3 | \n",
" 2940 | \n",
" 0.23 | \n",
" Sonstige | \n",
" 1.00 | \n",
"
\n",
" \n",
"
\n",
"