2177 lines
89 KiB
Plaintext
2177 lines
89 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "051c5726",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"from matplotlib import pyplot as plt\n",
|
|
"import numpy as np\n",
|
|
"from wordcloud import WordCloud\n",
|
|
"\n",
|
|
"from sklearn.feature_extraction.text import CountVectorizer\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from sklearn.linear_model import LogisticRegression\n",
|
|
"from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix\n",
|
|
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
|
|
"from sklearn.pipeline import Pipeline\n",
|
|
"from sklearn.model_selection import KFold, StratifiedShuffleSplit\n",
|
|
"from sklearn.metrics import confusion_matrix\n",
|
|
"from sklearn.metrics import ConfusionMatrixDisplay\n",
|
|
"\n",
|
|
"import re\n",
|
|
"import string\n",
|
|
"from stop_words import get_stop_words\n",
|
|
"\n",
|
|
"from imblearn.over_sampling import RandomOverSampler\n",
|
|
"\n",
|
|
"import spacy\n",
|
|
"\n",
|
|
"from nltk import ngrams\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "310c031d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"pd.set_option(\"display.max_colwidth\", 255)\n",
|
|
"pd.set_option('display.max_rows', 255)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "cc6821d0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df = pd.read_excel(\"training-nltk-mapping3.xlsx\")\n",
|
|
"cnt = df.groupby(\"CASISTICA_MOTIVAZIONE\").count() \\\n",
|
|
".rename(columns={\"Unnamed: 0\": \"count\"})[\"count\"]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4b8cbd26",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def prune_infrequent_classes(input_df: pd.DataFrame):\n",
|
|
" card_thresh = 10\n",
|
|
" cnt = input_df[[\"CASISTICA_MOTIVAZIONE\",\"NOTE_OPERATORE\"]].groupby([\"CASISTICA_MOTIVAZIONE\"]).count().rename({\"NOTE_OPERATORE\":\"count\"},axis=1)\n",
|
|
" res = input_df.merge(cnt, on=\"CASISTICA_MOTIVAZIONE\")\n",
|
|
" res = res[res[\"count\"] >= card_thresh]\n",
|
|
" res = res.drop(\"count\", axis=1)\n",
|
|
" return res\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "3903d9da",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def unique_str(l:list[str]):\n",
|
|
" return list(set(l))\n",
|
|
"\n",
|
|
"def apply_ngram(l:list[str], n:int):\n",
|
|
" return list(ngrams(l, n))\n",
|
|
"\n",
|
|
"def join_string_list(l:list[tuple[str]]):\n",
|
|
" return [\" \".join(list(i)) for i in l]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c0d08201",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"C:\\Users\\a.torchi\\AppData\\Local\\Temp\\ipykernel_31116\\2333237563.py:5: SettingWithCopyWarning: \n",
|
|
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
|
|
"Try using .loc[row_indexer,col_indexer] = value instead\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",
|
|
" df_cp[\"NOTE_OPERATORE_lower\"] = df_cp[\"NOTE_OPERATORE\"].str.lower()\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>CASISTICA_MOTIVAZIONE</th>\n",
|
|
" <th>NOTE_OPERATORE_2gram_unique_words</th>\n",
|
|
" <th>ngram_occurrencies</th>\n",
|
|
" <th>record_per_class</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>allega vers</td>\n",
|
|
" <td>28</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>veicolo intestato</td>\n",
|
|
" <td>15</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>essere mai</td>\n",
|
|
" <td>14</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>periodi tributari</td>\n",
|
|
" <td>14</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>scansiona versamento</td>\n",
|
|
" <td>14</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>5</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>furto trascritto</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>116</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>6</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>relativa vers.</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>7</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>versamento periodo</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>8</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>relativa anno</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>9</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>dichiara vendita</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>10</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>intestato società</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>11</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>modalità pagamento</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>12</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>scrive essere</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>13</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>diverso periodo</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>14</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>lombardo mese</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>257</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>15</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>successivo versamento</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>831</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>16</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>annotazione carta</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>17</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>demolizione annotata</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>18</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>dichiara demolizione</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>19</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>documentazione carente</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>20</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>nessun atto</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>21</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>risulta intestatario</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>22</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>documento didentità</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>23</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>on line</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>2763</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>24</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>venduta dopo</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>257</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" CASISTICA_MOTIVAZIONE NOTE_OPERATORE_2gram_unique_words \\\n",
|
|
"0 Periodo diverso allega vers \n",
|
|
"1 Generica veicolo intestato \n",
|
|
"2 Generica essere mai \n",
|
|
"3 Periodo diverso periodi tributari \n",
|
|
"4 Periodo diverso scansiona versamento \n",
|
|
"5 Furto non annotato furto trascritto \n",
|
|
"6 Periodo diverso relativa vers. \n",
|
|
"7 Periodo diverso versamento periodo \n",
|
|
"8 Periodo diverso relativa anno \n",
|
|
"9 Generica dichiara vendita \n",
|
|
"10 Generica intestato società \n",
|
|
"11 Generica modalità pagamento \n",
|
|
"12 Generica scrive essere \n",
|
|
"13 Periodo diverso diverso periodo \n",
|
|
"14 Vendita tardiva lombardo mese \n",
|
|
"15 Periodo diverso successivo versamento \n",
|
|
"16 Generica annotazione carta \n",
|
|
"17 Generica demolizione annotata \n",
|
|
"18 Generica dichiara demolizione \n",
|
|
"19 Generica documentazione carente \n",
|
|
"20 Generica nessun atto \n",
|
|
"21 Generica risulta intestatario \n",
|
|
"22 Generica documento didentità \n",
|
|
"23 Generica on line \n",
|
|
"24 Vendita tardiva venduta dopo \n",
|
|
"\n",
|
|
" ngram_occurrencies record_per_class \n",
|
|
"0 28 831 \n",
|
|
"1 15 2763 \n",
|
|
"2 14 2763 \n",
|
|
"3 14 831 \n",
|
|
"4 14 831 \n",
|
|
"5 12 116 \n",
|
|
"6 12 831 \n",
|
|
"7 12 831 \n",
|
|
"8 11 831 \n",
|
|
"9 10 2763 \n",
|
|
"10 10 2763 \n",
|
|
"11 10 2763 \n",
|
|
"12 10 2763 \n",
|
|
"13 10 831 \n",
|
|
"14 9 257 \n",
|
|
"15 9 831 \n",
|
|
"16 9 2763 \n",
|
|
"17 9 2763 \n",
|
|
"18 9 2763 \n",
|
|
"19 9 2763 \n",
|
|
"20 9 2763 \n",
|
|
"21 9 2763 \n",
|
|
"22 8 2763 \n",
|
|
"23 8 2763 \n",
|
|
"24 8 257 "
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"def get_unique_ngrams(df: pd.DataFrame, n:int):\n",
|
|
" df_cp = df[[\"CASISTICA_LAVORAZIONE\",\"NOTE_OPERATORE\",\"CASISTICA_MOTIVAZIONE\"]]\n",
|
|
"\n",
|
|
" #make all strings lowercase\n",
|
|
" df_cp[\"NOTE_OPERATORE_lower\"] = df_cp[\"NOTE_OPERATORE\"].str.lower()\n",
|
|
"\n",
|
|
" #make column as a list of words (1-gram)\n",
|
|
" splitted_col_name = \"NOTE_OPERATORE_split_{}gram\".format(str(n))\n",
|
|
" df_cp[\"NOTE_OPERATORE_split_1gram\"] = df_cp[\"NOTE_OPERATORE_lower\"].str.split(\" \")\n",
|
|
"\n",
|
|
" #if n!=1 make a column as a list of n-grams\n",
|
|
" if(n!=1):\n",
|
|
" df_cp[splitted_col_name] = df_cp[\"NOTE_OPERATORE_split_1gram\"].apply(lambda x: apply_ngram(x, n))\n",
|
|
"\n",
|
|
" ngram_col_name = \"NOTE_OPERATORE_{}gram_unique_words\".format(str(n))\n",
|
|
"\n",
|
|
" #make sure every n-gram in every row is not repeated\n",
|
|
" df_cp[ngram_col_name] = df_cp[splitted_col_name].apply(lambda x: unique_str(x))\n",
|
|
"\n",
|
|
" #concat every word composing a n-gram, transforming the column from a list[tuple[str]] to list[str]\n",
|
|
" if(n!=1):\n",
|
|
" df_cp[ngram_col_name] = df_cp[ngram_col_name].apply(lambda x: join_string_list(x))\n",
|
|
"\n",
|
|
"\n",
|
|
" #explode the df, to make a row for every n-gram - then groupBy [class, n-gram] to find how many records contain every n-gram\n",
|
|
" df_cp_ngram = df_cp[[ngram_col_name, \"CASISTICA_MOTIVAZIONE\", \"CASISTICA_LAVORAZIONE\"]].explode(ngram_col_name) \\\n",
|
|
" .groupby([\"CASISTICA_MOTIVAZIONE\",ngram_col_name]).count()\\\n",
|
|
" .sort_values(by=[\"CASISTICA_MOTIVAZIONE\", \"CASISTICA_LAVORAZIONE\"], ascending=[True,False])\\\n",
|
|
" .reset_index() \\\n",
|
|
" .rename(columns={\"CASISTICA_LAVORAZIONE\":\"count\"})\n",
|
|
"\n",
|
|
"\n",
|
|
" #self-join the df to find every n-gram occurring in just one class\n",
|
|
" df_cp_ngram_mrg = df_cp_ngram.merge(df_cp_ngram, how=\"left\", on=ngram_col_name)\n",
|
|
" df_cp_ngram_mrg = df_cp_ngram_mrg.rename(columns={\"count_x\":\"ngram_occurrencies\"})\n",
|
|
"\n",
|
|
" df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE = df_cp_ngram_mrg.groupby([\"CASISTICA_MOTIVAZIONE_x\", ngram_col_name]).count()\n",
|
|
" \n",
|
|
" df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE = df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE.reset_index()\n",
|
|
" df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE = df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE[[\"CASISTICA_MOTIVAZIONE_x\", ngram_col_name, \"count_y\"]] \\\n",
|
|
" .rename(columns={\"count_y\":\"ngram_occurrencies_in_CASISTICA_MOTIVAZIONE\", \"CASISTICA_MOTIVAZIONE_x\": \"CASISTICA_MOTIVAZIONE\"})\n",
|
|
" \n",
|
|
" # find every n-gram occurring in just one class (it was groupedBy + count by [class,n-gram])\n",
|
|
" df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE = df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE[df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE[\"ngram_occurrencies_in_CASISTICA_MOTIVAZIONE\"] == 1]\n",
|
|
"\n",
|
|
" #merge the new DF to produce the final result\n",
|
|
" res = df_cp_ngram_mrg.merge(df_cp_ngram_mrg_uniqueCASISTICAMOTIVAZIONE, on=ngram_col_name)\n",
|
|
"\n",
|
|
" res = res[[\"CASISTICA_MOTIVAZIONE_x\", ngram_col_name, \"ngram_occurrencies\"]] #\"ngram_occurrencies_in_CASISTICA_MOTIVAZIONE\"\n",
|
|
" res = res.rename(columns={\"CASISTICA_MOTIVAZIONE_x\":\"CASISTICA_MOTIVAZIONE\"})\n",
|
|
"\n",
|
|
" res = res.sort_values(by = \"ngram_occurrencies\", ascending=False)\n",
|
|
"\n",
|
|
" #groupBy and merge the original DF to create the column \"record_per_class\", indicating how many record occurr in every class\n",
|
|
" df_grp_class = df.groupby(\"CASISTICA_MOTIVAZIONE\").count().reset_index()\n",
|
|
" df_grp_class = df_grp_class.rename(columns={\"Unnamed: 0\":\"record_per_class\"})\n",
|
|
" df_grp_class = df_grp_class[[\"CASISTICA_MOTIVAZIONE\", \"record_per_class\"]]\n",
|
|
"\n",
|
|
" res = res.merge(df_grp_class, on=\"CASISTICA_MOTIVAZIONE\")\n",
|
|
"\n",
|
|
" return res\n",
|
|
"\n",
|
|
"\n",
|
|
"gram_dim = 2\n",
|
|
"res= get_unique_ngrams(df, gram_dim)\n",
|
|
"\n",
|
|
"res.iloc[:25]\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f05a5897",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>CASISTICA_MOTIVAZIONE</th>\n",
|
|
" <th>NOTE_OPERATORE_split_3gram</th>\n",
|
|
" <th>count_placeholder</th>\n",
|
|
" <th>CASISTICA_MOTIVAZIONE_selfjoin</th>\n",
|
|
" <th>count_selfjoin</th>\n",
|
|
" <th>sum_selfjoin</th>\n",
|
|
" <th>tf_idf</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>2627</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(mai, stato, proprietario)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>3.666667</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2626</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(mai, stato, proprietario)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>No esenzione PH</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>3.666667</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2625</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(manca, vers, allega)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>3.666667</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2587</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(annotata, pra, già)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2588</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(annotata, pra, già)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2386</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(periodo, tributario, versamento)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2335</th>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>(versamento, favore, regione)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2347</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(furto, allega, denuncia)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2356</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(vendita, bollo, dovuto)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2384</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versamento, allegato, relativo)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2379</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(periodo, tributario, già)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2345</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(denuncia, furto, mai)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2302</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(allega, bollo, pagato)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2340</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(presa, carico, demolitore)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Fermo</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2315</th>\n",
|
|
" <td>No esenzione PH</td>\n",
|
|
" <td>(invalidità, idoneo, rilascio)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2295</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, presente, bollo)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2296</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(altra, regione, periodo)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; concessionario</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2317</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(nessun, versamento, presente)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2316</th>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>(presente, cliente, avvisato)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2336</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, presente, ricevuta)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Ricevuta non valida</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2355</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(domiciliazione, bancaria, attiva)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Domiciliazione tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2282</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(visura, pra, risulta)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2280</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(veicolo, venduto, mese)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2273</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(bollo, dovuto, cliente)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Demolizione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2277</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(perdita, possesso, trascritta)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Sequestro non annotato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2330</th>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>(versamento, effettuato, favore)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2383</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(utile, atto, di)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2272</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, congruo, versamento)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2270</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(pratica, lavorata, nuovo)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2309</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(veicolo, demolito, periodo)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Demolizione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2279</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(targa, errata, targa)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2304</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(presente, allega, versamenti)</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2645</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(vendita, tardivo, veicolo)</td>\n",
|
|
" <td>13</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; concessionario</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>4.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2646</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(vendita, tardivo, veicolo)</td>\n",
|
|
" <td>13</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>4.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2607</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(veicolo, targato, targa)</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>No esenzione PH</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>4.500000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2608</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(veicolo, targato, targa)</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>4.500000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2463</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(regione, versamento, non)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2616</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versamento, riferito, altra)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2615</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versamento, riferito, altra)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2467</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(richiesta, versamento, non)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2462</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(atto, altra, regione)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2390</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(bollo, dovuto, vendita)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Generica 2_non allegata documentazione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2612</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(perdita, possesso, furto)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Rientro in possesso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2395</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(rientro, possesso, data)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Rientro in possesso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2394</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(presente, aci/tabaccaio/agenzia, versamento)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Ricevuta non valida</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2476</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(allega, ricevuta, pagamento)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2448</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(dichiara, aver, pagato)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2446</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(disabile, fiscalmente, carico)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>No esenzione PH</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2420</th>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>(disabile, respinta, manca)</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>No esenzione PH</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2611</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(perdita, possesso, furto)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>5.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2662</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(cliente, dichiara, aver)</td>\n",
|
|
" <td>16</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>5.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2664</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(allega, carta, circolazione)</td>\n",
|
|
" <td>16</td>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>5.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2665</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(allega, carta, circolazione)</td>\n",
|
|
" <td>16</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>5.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2666</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(allega, carta, circolazione)</td>\n",
|
|
" <td>16</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>5.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2663</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(cliente, dichiara, aver)</td>\n",
|
|
" <td>16</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>5.333333</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2635</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, presente, versamento)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>5.500000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2636</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, presente, versamento)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>5.500000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2483</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(documentazione, allegata, targa)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2639</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(allega, certificato, storico)</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2534</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(x, periodo, tributario)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2512</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versamento, allegato, anno)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2533</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(carta, circolazione, annotazione)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2518</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(pagamento, atto, di)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2482</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, presente, allegato)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Esenzione PH senza istanza</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2642</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(bollo, allegato, corrisponde)</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2644</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(bollo, pagato, x)</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2643</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(bollo, pagato, x)</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2479</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(allegato, anno, manca)</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>6.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2652</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(atto, data, certa)</td>\n",
|
|
" <td>13</td>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>6.500000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2651</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(atto, data, certa)</td>\n",
|
|
" <td>13</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>6.500000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2683</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(presente, non, congruo)</td>\n",
|
|
" <td>27</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>6.750000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2680</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versam, presente, non)</td>\n",
|
|
" <td>27</td>\n",
|
|
" <td>Versamento annullato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>6.750000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2682</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(presente, non, congruo)</td>\n",
|
|
" <td>27</td>\n",
|
|
" <td>Versamento annullato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>6.750000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2681</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versam, presente, non)</td>\n",
|
|
" <td>27</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>6.750000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2737</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Domiciliazione tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2740</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>No minivoltura</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2745</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2744</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2743</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Demolizione</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2739</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Generica 2_non allegata documentazione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2738</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2742</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; concessionario</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2741</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, di, vendita)</td>\n",
|
|
" <td>152</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>22</td>\n",
|
|
" <td>6.909091</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2654</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(dovuto, versamento, non)</td>\n",
|
|
" <td>14</td>\n",
|
|
" <td>Perdita possesso con DS successiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2653</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(dovuto, versamento, non)</td>\n",
|
|
" <td>14</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2579</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(allega, presa, carico)</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>Fermo</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2572</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(presente, allega, versamento)</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2576</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(corrisponde, periodo, richiesto)</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2578</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(pagato, x, periodo)</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2566</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(ricevuta, allegata, riferita)</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>7.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2731</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>Domiciliazione tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2733</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2732</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>No minivoltura</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2735</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>6</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2734</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; concessionario</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2736</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2730</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(di, vendita, tardivo)</td>\n",
|
|
" <td>147</td>\n",
|
|
" <td>Demolizione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>19</td>\n",
|
|
" <td>7.736842</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2591</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(riferito, periodo, tributario)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2589</th>\n",
|
|
" <td>Fermo</td>\n",
|
|
" <td>(fermo, amministrativo, fermo)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2583</th>\n",
|
|
" <td>Furto non annotato</td>\n",
|
|
" <td>(furto, mai, trascritto)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2586</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(atto, vendita, atto)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Generica 2_non allegata documentazione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2590</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(manca, carta, circolazione)</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Esportazione non annotata</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>8.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2602</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(ricevuta, relativa, diverso)</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>9.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2610</th>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>(regione, bollo, pagato)</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>9.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2609</th>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>(dichiara, aver, venduto)</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>9.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2614</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(tardivo, veicolo, venduto)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>10.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2621</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(allegato, corrisponde, periodo)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Regione diversa</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>10.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2613</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(dovuto, atto, di)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>10.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2620</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(non, congruo, allega)</td>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>10.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2637</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(allega, versamento, anno)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>11.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2624</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(allegata, ricevuta, relativa)</td>\n",
|
|
" <td>11</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>11.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2650</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versamento, riferito, periodo)</td>\n",
|
|
" <td>13</td>\n",
|
|
" <td>Generica</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>13.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2661</th>\n",
|
|
" <td>Periodo diverso</td>\n",
|
|
" <td>(versamento, allegato, riferito)</td>\n",
|
|
" <td>15</td>\n",
|
|
" <td>Veicolo diverso</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>15.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2671</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(vendita, atto, di)</td>\n",
|
|
" <td>17</td>\n",
|
|
" <td>Generica 2_non allegata documentazione</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>17.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2693</th>\n",
|
|
" <td>Vendita tardiva</td>\n",
|
|
" <td>(vendita, tardivo, atto)</td>\n",
|
|
" <td>29</td>\n",
|
|
" <td>Acquisto nel mese di rinnovo; privato</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>29.000000</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" CASISTICA_MOTIVAZIONE \\\n",
|
|
"2627 Generica \n",
|
|
"2626 Generica \n",
|
|
"2625 Periodo diverso \n",
|
|
"2587 Furto non annotato \n",
|
|
"2588 Furto non annotato \n",
|
|
"2386 Periodo diverso \n",
|
|
"2335 Regione diversa \n",
|
|
"2347 Furto non annotato \n",
|
|
"2356 Vendita tardiva \n",
|
|
"2384 Periodo diverso \n",
|
|
"2379 Vendita tardiva \n",
|
|
"2345 Furto non annotato \n",
|
|
"2302 Periodo diverso \n",
|
|
"2340 Generica \n",
|
|
"2315 No esenzione PH \n",
|
|
"2295 Periodo diverso \n",
|
|
"2296 Generica \n",
|
|
"2317 Generica \n",
|
|
"2316 Esenzione PH senza istanza \n",
|
|
"2336 Periodo diverso \n",
|
|
"2355 Generica \n",
|
|
"2282 Generica \n",
|
|
"2280 Vendita tardiva \n",
|
|
"2273 Generica \n",
|
|
"2277 Generica \n",
|
|
"2330 Regione diversa \n",
|
|
"2383 Vendita tardiva \n",
|
|
"2272 Periodo diverso \n",
|
|
"2270 Generica \n",
|
|
"2309 Generica \n",
|
|
"2279 Generica \n",
|
|
"2304 Periodo diverso \n",
|
|
"2645 Vendita tardiva \n",
|
|
"2646 Vendita tardiva \n",
|
|
"2607 Generica \n",
|
|
"2608 Generica \n",
|
|
"2463 Periodo diverso \n",
|
|
"2616 Periodo diverso \n",
|
|
"2615 Periodo diverso \n",
|
|
"2467 Periodo diverso \n",
|
|
"2462 Generica \n",
|
|
"2390 Vendita tardiva \n",
|
|
"2612 Furto non annotato \n",
|
|
"2395 Generica \n",
|
|
"2394 Periodo diverso \n",
|
|
"2476 Periodo diverso \n",
|
|
"2448 Generica \n",
|
|
"2446 Generica \n",
|
|
"2420 Esenzione PH senza istanza \n",
|
|
"2611 Furto non annotato \n",
|
|
"2662 Generica \n",
|
|
"2664 Generica \n",
|
|
"2665 Generica \n",
|
|
"2666 Generica \n",
|
|
"2663 Generica \n",
|
|
"2635 Periodo diverso \n",
|
|
"2636 Periodo diverso \n",
|
|
"2483 Generica \n",
|
|
"2639 Generica \n",
|
|
"2534 Periodo diverso \n",
|
|
"2512 Periodo diverso \n",
|
|
"2533 Generica \n",
|
|
"2518 Vendita tardiva \n",
|
|
"2482 Periodo diverso \n",
|
|
"2642 Periodo diverso \n",
|
|
"2644 Periodo diverso \n",
|
|
"2643 Periodo diverso \n",
|
|
"2479 Periodo diverso \n",
|
|
"2652 Generica \n",
|
|
"2651 Generica \n",
|
|
"2683 Periodo diverso \n",
|
|
"2680 Periodo diverso \n",
|
|
"2682 Periodo diverso \n",
|
|
"2681 Periodo diverso \n",
|
|
"2737 Vendita tardiva \n",
|
|
"2740 Vendita tardiva \n",
|
|
"2745 Vendita tardiva \n",
|
|
"2744 Vendita tardiva \n",
|
|
"2743 Vendita tardiva \n",
|
|
"2739 Vendita tardiva \n",
|
|
"2738 Vendita tardiva \n",
|
|
"2742 Vendita tardiva \n",
|
|
"2741 Vendita tardiva \n",
|
|
"2654 Vendita tardiva \n",
|
|
"2653 Vendita tardiva \n",
|
|
"2579 Generica \n",
|
|
"2572 Periodo diverso \n",
|
|
"2576 Periodo diverso \n",
|
|
"2578 Periodo diverso \n",
|
|
"2566 Periodo diverso \n",
|
|
"2731 Vendita tardiva \n",
|
|
"2733 Vendita tardiva \n",
|
|
"2732 Vendita tardiva \n",
|
|
"2735 Vendita tardiva \n",
|
|
"2734 Vendita tardiva \n",
|
|
"2736 Vendita tardiva \n",
|
|
"2730 Vendita tardiva \n",
|
|
"2591 Periodo diverso \n",
|
|
"2589 Fermo \n",
|
|
"2583 Furto non annotato \n",
|
|
"2586 Vendita tardiva \n",
|
|
"2590 Generica \n",
|
|
"2602 Periodo diverso \n",
|
|
"2610 Regione diversa \n",
|
|
"2609 Generica \n",
|
|
"2614 Vendita tardiva \n",
|
|
"2621 Periodo diverso \n",
|
|
"2613 Vendita tardiva \n",
|
|
"2620 Periodo diverso \n",
|
|
"2637 Periodo diverso \n",
|
|
"2624 Periodo diverso \n",
|
|
"2650 Periodo diverso \n",
|
|
"2661 Periodo diverso \n",
|
|
"2671 Vendita tardiva \n",
|
|
"2693 Vendita tardiva \n",
|
|
"\n",
|
|
" NOTE_OPERATORE_split_3gram count_placeholder \\\n",
|
|
"2627 (mai, stato, proprietario) 11 \n",
|
|
"2626 (mai, stato, proprietario) 11 \n",
|
|
"2625 (manca, vers, allega) 11 \n",
|
|
"2587 (annotata, pra, già) 8 \n",
|
|
"2588 (annotata, pra, già) 8 \n",
|
|
"2386 (periodo, tributario, versamento) 4 \n",
|
|
"2335 (versamento, favore, regione) 4 \n",
|
|
"2347 (furto, allega, denuncia) 4 \n",
|
|
"2356 (vendita, bollo, dovuto) 4 \n",
|
|
"2384 (versamento, allegato, relativo) 4 \n",
|
|
"2379 (periodo, tributario, già) 4 \n",
|
|
"2345 (denuncia, furto, mai) 4 \n",
|
|
"2302 (allega, bollo, pagato) 4 \n",
|
|
"2340 (presa, carico, demolitore) 4 \n",
|
|
"2315 (invalidità, idoneo, rilascio) 4 \n",
|
|
"2295 (non, presente, bollo) 4 \n",
|
|
"2296 (altra, regione, periodo) 4 \n",
|
|
"2317 (nessun, versamento, presente) 4 \n",
|
|
"2316 (presente, cliente, avvisato) 4 \n",
|
|
"2336 (non, presente, ricevuta) 4 \n",
|
|
"2355 (domiciliazione, bancaria, attiva) 4 \n",
|
|
"2282 (visura, pra, risulta) 4 \n",
|
|
"2280 (veicolo, venduto, mese) 4 \n",
|
|
"2273 (bollo, dovuto, cliente) 4 \n",
|
|
"2277 (perdita, possesso, trascritta) 4 \n",
|
|
"2330 (versamento, effettuato, favore) 4 \n",
|
|
"2383 (utile, atto, di) 4 \n",
|
|
"2272 (non, congruo, versamento) 4 \n",
|
|
"2270 (pratica, lavorata, nuovo) 4 \n",
|
|
"2309 (veicolo, demolito, periodo) 4 \n",
|
|
"2279 (targa, errata, targa) 4 \n",
|
|
"2304 (presente, allega, versamenti) 4 \n",
|
|
"2645 (vendita, tardivo, veicolo) 13 \n",
|
|
"2646 (vendita, tardivo, veicolo) 13 \n",
|
|
"2607 (veicolo, targato, targa) 9 \n",
|
|
"2608 (veicolo, targato, targa) 9 \n",
|
|
"2463 (regione, versamento, non) 5 \n",
|
|
"2616 (versamento, riferito, altra) 10 \n",
|
|
"2615 (versamento, riferito, altra) 10 \n",
|
|
"2467 (richiesta, versamento, non) 5 \n",
|
|
"2462 (atto, altra, regione) 5 \n",
|
|
"2390 (bollo, dovuto, vendita) 5 \n",
|
|
"2612 (perdita, possesso, furto) 10 \n",
|
|
"2395 (rientro, possesso, data) 5 \n",
|
|
"2394 (presente, aci/tabaccaio/agenzia, versamento) 5 \n",
|
|
"2476 (allega, ricevuta, pagamento) 5 \n",
|
|
"2448 (dichiara, aver, pagato) 5 \n",
|
|
"2446 (disabile, fiscalmente, carico) 5 \n",
|
|
"2420 (disabile, respinta, manca) 5 \n",
|
|
"2611 (perdita, possesso, furto) 10 \n",
|
|
"2662 (cliente, dichiara, aver) 16 \n",
|
|
"2664 (allega, carta, circolazione) 16 \n",
|
|
"2665 (allega, carta, circolazione) 16 \n",
|
|
"2666 (allega, carta, circolazione) 16 \n",
|
|
"2663 (cliente, dichiara, aver) 16 \n",
|
|
"2635 (non, presente, versamento) 11 \n",
|
|
"2636 (non, presente, versamento) 11 \n",
|
|
"2483 (documentazione, allegata, targa) 6 \n",
|
|
"2639 (allega, certificato, storico) 12 \n",
|
|
"2534 (x, periodo, tributario) 6 \n",
|
|
"2512 (versamento, allegato, anno) 6 \n",
|
|
"2533 (carta, circolazione, annotazione) 6 \n",
|
|
"2518 (pagamento, atto, di) 6 \n",
|
|
"2482 (non, presente, allegato) 6 \n",
|
|
"2642 (bollo, allegato, corrisponde) 12 \n",
|
|
"2644 (bollo, pagato, x) 12 \n",
|
|
"2643 (bollo, pagato, x) 12 \n",
|
|
"2479 (allegato, anno, manca) 6 \n",
|
|
"2652 (atto, data, certa) 13 \n",
|
|
"2651 (atto, data, certa) 13 \n",
|
|
"2683 (presente, non, congruo) 27 \n",
|
|
"2680 (versam, presente, non) 27 \n",
|
|
"2682 (presente, non, congruo) 27 \n",
|
|
"2681 (versam, presente, non) 27 \n",
|
|
"2737 (atto, di, vendita) 152 \n",
|
|
"2740 (atto, di, vendita) 152 \n",
|
|
"2745 (atto, di, vendita) 152 \n",
|
|
"2744 (atto, di, vendita) 152 \n",
|
|
"2743 (atto, di, vendita) 152 \n",
|
|
"2739 (atto, di, vendita) 152 \n",
|
|
"2738 (atto, di, vendita) 152 \n",
|
|
"2742 (atto, di, vendita) 152 \n",
|
|
"2741 (atto, di, vendita) 152 \n",
|
|
"2654 (dovuto, versamento, non) 14 \n",
|
|
"2653 (dovuto, versamento, non) 14 \n",
|
|
"2579 (allega, presa, carico) 7 \n",
|
|
"2572 (presente, allega, versamento) 7 \n",
|
|
"2576 (corrisponde, periodo, richiesto) 7 \n",
|
|
"2578 (pagato, x, periodo) 7 \n",
|
|
"2566 (ricevuta, allegata, riferita) 7 \n",
|
|
"2731 (di, vendita, tardivo) 147 \n",
|
|
"2733 (di, vendita, tardivo) 147 \n",
|
|
"2732 (di, vendita, tardivo) 147 \n",
|
|
"2735 (di, vendita, tardivo) 147 \n",
|
|
"2734 (di, vendita, tardivo) 147 \n",
|
|
"2736 (di, vendita, tardivo) 147 \n",
|
|
"2730 (di, vendita, tardivo) 147 \n",
|
|
"2591 (riferito, periodo, tributario) 8 \n",
|
|
"2589 (fermo, amministrativo, fermo) 8 \n",
|
|
"2583 (furto, mai, trascritto) 8 \n",
|
|
"2586 (atto, vendita, atto) 8 \n",
|
|
"2590 (manca, carta, circolazione) 8 \n",
|
|
"2602 (ricevuta, relativa, diverso) 9 \n",
|
|
"2610 (regione, bollo, pagato) 9 \n",
|
|
"2609 (dichiara, aver, venduto) 9 \n",
|
|
"2614 (tardivo, veicolo, venduto) 10 \n",
|
|
"2621 (allegato, corrisponde, periodo) 10 \n",
|
|
"2613 (dovuto, atto, di) 10 \n",
|
|
"2620 (non, congruo, allega) 10 \n",
|
|
"2637 (allega, versamento, anno) 11 \n",
|
|
"2624 (allegata, ricevuta, relativa) 11 \n",
|
|
"2650 (versamento, riferito, periodo) 13 \n",
|
|
"2661 (versamento, allegato, riferito) 15 \n",
|
|
"2671 (vendita, atto, di) 17 \n",
|
|
"2693 (vendita, tardivo, atto) 29 \n",
|
|
"\n",
|
|
" CASISTICA_MOTIVAZIONE_selfjoin count_selfjoin \\\n",
|
|
"2627 Periodo diverso 2 \n",
|
|
"2626 No esenzione PH 1 \n",
|
|
"2625 Generica 3 \n",
|
|
"2587 Esportazione non annotata 1 \n",
|
|
"2588 Generica 1 \n",
|
|
"2386 Generica 1 \n",
|
|
"2335 Periodo diverso 1 \n",
|
|
"2347 Generica 1 \n",
|
|
"2356 Generica 1 \n",
|
|
"2384 Vendita tardiva 1 \n",
|
|
"2379 Periodo diverso 1 \n",
|
|
"2345 Generica 1 \n",
|
|
"2302 Generica 1 \n",
|
|
"2340 Fermo 1 \n",
|
|
"2315 Generica 1 \n",
|
|
"2295 Vendita tardiva 1 \n",
|
|
"2296 Acquisto nel mese di rinnovo; concessionario 1 \n",
|
|
"2317 Periodo diverso 1 \n",
|
|
"2316 Generica 1 \n",
|
|
"2336 Ricevuta non valida 1 \n",
|
|
"2355 Domiciliazione tardiva 1 \n",
|
|
"2282 Vendita tardiva 1 \n",
|
|
"2280 Generica 1 \n",
|
|
"2273 Demolizione 1 \n",
|
|
"2277 Sequestro non annotato 1 \n",
|
|
"2330 Periodo diverso 1 \n",
|
|
"2383 Acquisto nel mese di rinnovo; privato 1 \n",
|
|
"2272 Veicolo diverso 1 \n",
|
|
"2270 Periodo diverso 1 \n",
|
|
"2309 Demolizione 1 \n",
|
|
"2279 Regione diversa 1 \n",
|
|
"2304 Veicolo diverso 1 \n",
|
|
"2645 Acquisto nel mese di rinnovo; concessionario 1 \n",
|
|
"2646 Acquisto nel mese di rinnovo; privato 2 \n",
|
|
"2607 No esenzione PH 1 \n",
|
|
"2608 Veicolo diverso 1 \n",
|
|
"2463 Regione diversa 1 \n",
|
|
"2616 Veicolo diverso 1 \n",
|
|
"2615 Generica 1 \n",
|
|
"2467 Esenzione PH senza istanza 1 \n",
|
|
"2462 Acquisto nel mese di rinnovo; privato 1 \n",
|
|
"2390 Generica 2_non allegata documentazione 1 \n",
|
|
"2612 Rientro in possesso 1 \n",
|
|
"2395 Rientro in possesso 1 \n",
|
|
"2394 Ricevuta non valida 1 \n",
|
|
"2476 Generica 1 \n",
|
|
"2448 Vendita tardiva 1 \n",
|
|
"2446 No esenzione PH 1 \n",
|
|
"2420 No esenzione PH 1 \n",
|
|
"2611 Generica 1 \n",
|
|
"2662 Vendita tardiva 1 \n",
|
|
"2664 Esenzione PH senza istanza 1 \n",
|
|
"2665 Esportazione non annotata 1 \n",
|
|
"2666 Vendita tardiva 1 \n",
|
|
"2663 Esportazione non annotata 2 \n",
|
|
"2635 Regione diversa 1 \n",
|
|
"2636 Veicolo diverso 1 \n",
|
|
"2483 Periodo diverso 1 \n",
|
|
"2639 Esenzione PH senza istanza 2 \n",
|
|
"2534 Generica 1 \n",
|
|
"2512 Generica 1 \n",
|
|
"2533 Esenzione PH senza istanza 1 \n",
|
|
"2518 Acquisto nel mese di rinnovo; privato 1 \n",
|
|
"2482 Esenzione PH senza istanza 1 \n",
|
|
"2642 Generica 2 \n",
|
|
"2644 Regione diversa 1 \n",
|
|
"2643 Generica 1 \n",
|
|
"2479 Generica 1 \n",
|
|
"2652 Furto non annotato 1 \n",
|
|
"2651 Esportazione non annotata 1 \n",
|
|
"2683 Veicolo diverso 3 \n",
|
|
"2680 Versamento annullato 1 \n",
|
|
"2682 Versamento annullato 1 \n",
|
|
"2681 Veicolo diverso 3 \n",
|
|
"2737 Domiciliazione tardiva 1 \n",
|
|
"2740 No minivoltura 1 \n",
|
|
"2745 Acquisto nel mese di rinnovo; privato 7 \n",
|
|
"2744 Periodo diverso 6 \n",
|
|
"2743 Demolizione 2 \n",
|
|
"2739 Generica 2_non allegata documentazione 1 \n",
|
|
"2738 Esportazione non annotata 1 \n",
|
|
"2742 Acquisto nel mese di rinnovo; concessionario 2 \n",
|
|
"2741 Veicolo diverso 1 \n",
|
|
"2654 Perdita possesso con DS successiva 1 \n",
|
|
"2653 Esportazione non annotata 1 \n",
|
|
"2579 Fermo 1 \n",
|
|
"2572 Veicolo diverso 1 \n",
|
|
"2576 Regione diversa 1 \n",
|
|
"2578 Generica 1 \n",
|
|
"2566 Veicolo diverso 1 \n",
|
|
"2731 Domiciliazione tardiva 1 \n",
|
|
"2733 Veicolo diverso 1 \n",
|
|
"2732 No minivoltura 1 \n",
|
|
"2735 Periodo diverso 6 \n",
|
|
"2734 Acquisto nel mese di rinnovo; concessionario 2 \n",
|
|
"2736 Acquisto nel mese di rinnovo; privato 7 \n",
|
|
"2730 Demolizione 1 \n",
|
|
"2591 Generica 1 \n",
|
|
"2589 Generica 1 \n",
|
|
"2583 Generica 1 \n",
|
|
"2586 Generica 2_non allegata documentazione 1 \n",
|
|
"2590 Esportazione non annotata 1 \n",
|
|
"2602 Veicolo diverso 1 \n",
|
|
"2610 Generica 1 \n",
|
|
"2609 Vendita tardiva 1 \n",
|
|
"2614 Generica 1 \n",
|
|
"2621 Regione diversa 1 \n",
|
|
"2613 Periodo diverso 1 \n",
|
|
"2620 Veicolo diverso 1 \n",
|
|
"2637 Veicolo diverso 1 \n",
|
|
"2624 Veicolo diverso 1 \n",
|
|
"2650 Generica 1 \n",
|
|
"2661 Veicolo diverso 1 \n",
|
|
"2671 Generica 2_non allegata documentazione 1 \n",
|
|
"2693 Acquisto nel mese di rinnovo; privato 1 \n",
|
|
"\n",
|
|
" sum_selfjoin tf_idf \n",
|
|
"2627 3 3.666667 \n",
|
|
"2626 3 3.666667 \n",
|
|
"2625 3 3.666667 \n",
|
|
"2587 2 4.000000 \n",
|
|
"2588 2 4.000000 \n",
|
|
"2386 1 4.000000 \n",
|
|
"2335 1 4.000000 \n",
|
|
"2347 1 4.000000 \n",
|
|
"2356 1 4.000000 \n",
|
|
"2384 1 4.000000 \n",
|
|
"2379 1 4.000000 \n",
|
|
"2345 1 4.000000 \n",
|
|
"2302 1 4.000000 \n",
|
|
"2340 1 4.000000 \n",
|
|
"2315 1 4.000000 \n",
|
|
"2295 1 4.000000 \n",
|
|
"2296 1 4.000000 \n",
|
|
"2317 1 4.000000 \n",
|
|
"2316 1 4.000000 \n",
|
|
"2336 1 4.000000 \n",
|
|
"2355 1 4.000000 \n",
|
|
"2282 1 4.000000 \n",
|
|
"2280 1 4.000000 \n",
|
|
"2273 1 4.000000 \n",
|
|
"2277 1 4.000000 \n",
|
|
"2330 1 4.000000 \n",
|
|
"2383 1 4.000000 \n",
|
|
"2272 1 4.000000 \n",
|
|
"2270 1 4.000000 \n",
|
|
"2309 1 4.000000 \n",
|
|
"2279 1 4.000000 \n",
|
|
"2304 1 4.000000 \n",
|
|
"2645 3 4.333333 \n",
|
|
"2646 3 4.333333 \n",
|
|
"2607 2 4.500000 \n",
|
|
"2608 2 4.500000 \n",
|
|
"2463 1 5.000000 \n",
|
|
"2616 2 5.000000 \n",
|
|
"2615 2 5.000000 \n",
|
|
"2467 1 5.000000 \n",
|
|
"2462 1 5.000000 \n",
|
|
"2390 1 5.000000 \n",
|
|
"2612 2 5.000000 \n",
|
|
"2395 1 5.000000 \n",
|
|
"2394 1 5.000000 \n",
|
|
"2476 1 5.000000 \n",
|
|
"2448 1 5.000000 \n",
|
|
"2446 1 5.000000 \n",
|
|
"2420 1 5.000000 \n",
|
|
"2611 2 5.000000 \n",
|
|
"2662 3 5.333333 \n",
|
|
"2664 3 5.333333 \n",
|
|
"2665 3 5.333333 \n",
|
|
"2666 3 5.333333 \n",
|
|
"2663 3 5.333333 \n",
|
|
"2635 2 5.500000 \n",
|
|
"2636 2 5.500000 \n",
|
|
"2483 1 6.000000 \n",
|
|
"2639 2 6.000000 \n",
|
|
"2534 1 6.000000 \n",
|
|
"2512 1 6.000000 \n",
|
|
"2533 1 6.000000 \n",
|
|
"2518 1 6.000000 \n",
|
|
"2482 1 6.000000 \n",
|
|
"2642 2 6.000000 \n",
|
|
"2644 2 6.000000 \n",
|
|
"2643 2 6.000000 \n",
|
|
"2479 1 6.000000 \n",
|
|
"2652 2 6.500000 \n",
|
|
"2651 2 6.500000 \n",
|
|
"2683 4 6.750000 \n",
|
|
"2680 4 6.750000 \n",
|
|
"2682 4 6.750000 \n",
|
|
"2681 4 6.750000 \n",
|
|
"2737 22 6.909091 \n",
|
|
"2740 22 6.909091 \n",
|
|
"2745 22 6.909091 \n",
|
|
"2744 22 6.909091 \n",
|
|
"2743 22 6.909091 \n",
|
|
"2739 22 6.909091 \n",
|
|
"2738 22 6.909091 \n",
|
|
"2742 22 6.909091 \n",
|
|
"2741 22 6.909091 \n",
|
|
"2654 2 7.000000 \n",
|
|
"2653 2 7.000000 \n",
|
|
"2579 1 7.000000 \n",
|
|
"2572 1 7.000000 \n",
|
|
"2576 1 7.000000 \n",
|
|
"2578 1 7.000000 \n",
|
|
"2566 1 7.000000 \n",
|
|
"2731 19 7.736842 \n",
|
|
"2733 19 7.736842 \n",
|
|
"2732 19 7.736842 \n",
|
|
"2735 19 7.736842 \n",
|
|
"2734 19 7.736842 \n",
|
|
"2736 19 7.736842 \n",
|
|
"2730 19 7.736842 \n",
|
|
"2591 1 8.000000 \n",
|
|
"2589 1 8.000000 \n",
|
|
"2583 1 8.000000 \n",
|
|
"2586 1 8.000000 \n",
|
|
"2590 1 8.000000 \n",
|
|
"2602 1 9.000000 \n",
|
|
"2610 1 9.000000 \n",
|
|
"2609 1 9.000000 \n",
|
|
"2614 1 10.000000 \n",
|
|
"2621 1 10.000000 \n",
|
|
"2613 1 10.000000 \n",
|
|
"2620 1 10.000000 \n",
|
|
"2637 1 11.000000 \n",
|
|
"2624 1 11.000000 \n",
|
|
"2650 1 13.000000 \n",
|
|
"2661 1 15.000000 \n",
|
|
"2671 1 17.000000 \n",
|
|
"2693 1 29.000000 "
|
|
]
|
|
},
|
|
"execution_count": 91,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"n=3\n",
|
|
"splitted_col_name = \"NOTE_OPERATORE_split_{}gram\".format(str(n))\n",
|
|
"df_cp=df.copy()\n",
|
|
"\n",
|
|
"#concatenate every string within the same class\n",
|
|
"df_cp = df_cp.sort_values(by=\"CASISTICA_MOTIVAZIONE\")\n",
|
|
"df_cp[\"cat\"] = df_cp.groupby(['CASISTICA_MOTIVAZIONE'])['NOTE_OPERATORE'].transform(lambda x : ' '.join(x))\n",
|
|
"df_cp[\"cat\"] = df_cp[\"cat\"].str.lower()\n",
|
|
"df_cp = df_cp.groupby([\"CASISTICA_MOTIVAZIONE\", \"cat\"]).count().reset_index()\n",
|
|
"\n",
|
|
"#make column as a list of words (1-gram), then create a column of n-grams\n",
|
|
"df_cp[splitted_col_name] = df_cp[\"cat\"].str.split(\" \").apply(lambda x: apply_ngram(x, n))\n",
|
|
"\n",
|
|
"#count the occurrences for every n-gram for every class\n",
|
|
"df_cp[\"count_placeholder\"] = 1\n",
|
|
"df_cp = df_cp[[\"CASISTICA_MOTIVAZIONE\", splitted_col_name, \"count_placeholder\"]].explode(splitted_col_name)\\\n",
|
|
" .groupby([\"CASISTICA_MOTIVAZIONE\", splitted_col_name]).count() \\\n",
|
|
" .reset_index() \\\n",
|
|
" .sort_values(by=\"count_placeholder\")\n",
|
|
"\n",
|
|
"#self-join to find which classes (except the currently considerated one) have a given n-gram, for every n-gram and every class\n",
|
|
"df_cp_selfjoin = df_cp[[\"CASISTICA_MOTIVAZIONE\", splitted_col_name, \"count_placeholder\"]].rename(columns={\"CASISTICA_MOTIVAZIONE\": \"CASISTICA_MOTIVAZIONE_selfjoin\", \"count_placeholder\":\"count_selfjoin\"})\n",
|
|
"df_cp = df_cp.merge(df_cp_selfjoin, on=splitted_col_name)\n",
|
|
"df_cp = df_cp[df_cp[\"CASISTICA_MOTIVAZIONE\"] != df_cp[\"CASISTICA_MOTIVAZIONE_selfjoin\"]]\n",
|
|
"\n",
|
|
"# find how many occurrences of a given n-gram exist in every other class (except the currently considerated one), for every n-gram and every class\n",
|
|
"df_cp_tfidf = df_cp[[\"CASISTICA_MOTIVAZIONE\", splitted_col_name, \"count_selfjoin\"]].groupby([\"CASISTICA_MOTIVAZIONE\", splitted_col_name]).sum(\"count_selfjoin\") \\\n",
|
|
" .rename(columns={\"count_selfjoin\": \"sum_selfjoin\"})\n",
|
|
"df_cp = df_cp.merge(df_cp_tfidf, on=[\"CASISTICA_MOTIVAZIONE\", splitted_col_name])\n",
|
|
"\n",
|
|
"#for every n-gram and every class, divide the occurrences of that n-gram in that class by the sum of the occurrences of that n-gram in every other class\n",
|
|
"df_cp[\"tf_idf\"] = df_cp[\"count_placeholder\"] / df_cp[\"sum_selfjoin\"]\n",
|
|
"\n",
|
|
"df_cp = df_cp.sort_values(by=\"tf_idf\")\n",
|
|
"\n",
|
|
"df_cp.iloc[-115:]\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "venv",
|
|
"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": "3.13.3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|