sklearn_knneighbours.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pandas\n",
    "from math import sqrt\n",
    "from brand_lists import *\n",
    "%matplotlib inline\n",
    "\n",
    "# scikit-learn modules\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn import metrics \n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report, confusion_matrix\n",
    "\n",
    "#caricamento dei due dataframe (True Gold Standard & USERS-TAGS table)\n",
    "user_tags_values = pd.read_csv('final_results/users_tags_values.csv')\n",
    "\n",
    "#SELEZIONE DEGLI UTENTI DA ANALIZZARE CON IL KNN (SCEGLIERE UNO DEI TRE)\n",
    "#gold_standard = pd.read_excel('final_results/true_gold_standard.xlsx')       #SOLO UTENTI FOLLOWERS DELLE PAGINE UFFICIALI\n",
    "gold_standard = pd.read_excel('final_results/sentiment_gold_standard.xlsx')    #SOLO UTENTI ETICHETTATI CON LA SENTIMENT ANALYSIS\n",
    "#gold_standard = pd.read_excel('final_results/strong_gold_standard.xlsx')      #UTENTI INTERSEZIONE TRA FOLLOWERS E ETICHETTATI CON LA SENTIMENT ANALYSIS\n",
    "\n",
    "\n",
    "#lista dei tags in ordine del dataframe \"user_tags_values\"\n",
    "all_tags_in_order = user_tags_values.drop(columns='User').columns.to_list()\n",
    "\n",
    "#Lista degli utenti del gold standard\n",
    "users_list = np.unique(gold_standard['User'].to_list())\n",
    "\n",
    "#Raggruppamento dei due dataframe in dizionari per facilitare la ricerca degli utenti/etichette interessati\n",
    "dict_1 = dict(tuple(gold_standard.groupby('Brand')))  #raggruppa gli utenti del gold standard per Brand\n",
    "dict_2 = dict(tuple(user_tags_values.groupby('User')))     #raggruppa gli utenti di USERS-TAGS table per VETTORI\n",
    "dict_3 = dict(tuple(gold_standard.groupby('User')))   #raggruppa gli utenti del gold standard per User\n",
    "\n",
    "#Restituisce il vettore di un utente\n",
    "def get_user_vector(user):\n",
    "    user_values = dict_2.get(user)                     #riga dei valori di sentiment\n",
    "    vector = []\n",
    "    for tag in all_brands_tags:                     #per ogni tag\n",
    "        vector.append(user_values[tag].values[0])   #copia il valore letto   \n",
    "    return np.array(vector)\n",
    "\n",
    "#Restituisce la/le classe/i di un utente\n",
    "def get_user_class(user):\n",
    "    return dict_3.get(user)['Brand'].to_list()\n",
    "\n",
    "#crea un dataframe di vettori etichettati\n",
    "def make_df():\n",
    "    cols = all_tags_in_order.copy()\n",
    "    cols.append('label')\n",
    "    df = pd.DataFrame(columns=cols)\n",
    "    for user in users_list:\n",
    "        v = get_user_vector(user)\n",
    "        for label in get_user_class(user):\n",
    "            row = v.tolist()\n",
    "            row.append(label)\n",
    "            df.loc[len(df)] = row\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>baby</th>\n",
       "      <th>car</th>\n",
       "      <th>chocolate</th>\n",
       "      <th>clothing</th>\n",
       "      <th>coffee</th>\n",
       "      <th>computer</th>\n",
       "      <th>fashion</th>\n",
       "      <th>home</th>\n",
       "      <th>household appliances</th>\n",
       "      <th>italian</th>\n",
       "      <th>licorice</th>\n",
       "      <th>office</th>\n",
       "      <th>pasta</th>\n",
       "      <th>scent</th>\n",
       "      <th>sporty</th>\n",
       "      <th>technology</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>armani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>adidas</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>armani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>326</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>ferrero</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>327</th>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>328</th>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>barilla</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>329</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>ferrero</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>330</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>amarelli</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>331 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     baby  car  chocolate  clothing  coffee  computer  fashion  home  \\\n",
       "0     1.0  1.0        0.5       0.5     0.5       0.5      0.5   0.0   \n",
       "1     0.5  0.5        0.5       1.0     0.5       0.5      1.0   0.5   \n",
       "2     0.5  0.5        0.5       1.0     0.5       0.5      1.0   0.5   \n",
       "3     0.5  1.0        0.5       0.5     0.5       0.5      1.0   1.0   \n",
       "4     0.5  1.0        0.5       0.5     0.5       0.5      1.0   1.0   \n",
       "..    ...  ...        ...       ...     ...       ...      ...   ...   \n",
       "326   1.0  1.0        0.5       0.0     0.0       0.5      1.0   1.0   \n",
       "327   0.5  1.0        0.5       0.5     0.5       0.5      0.5   1.0   \n",
       "328   0.5  1.0        0.5       0.5     0.5       0.5      0.5   1.0   \n",
       "329   1.0  0.0        1.0       1.0     0.5       0.5      0.5   0.0   \n",
       "330   1.0  0.0        1.0       1.0     0.5       0.5      0.5   0.0   \n",
       "\n",
       "     household appliances  italian  licorice  office  pasta  scent  sporty  \\\n",
       "0                     0.5      0.5       0.5     0.5    0.5    0.5     1.0   \n",
       "1                     0.5      0.5       0.5     0.5    0.5    0.5     0.5   \n",
       "2                     0.5      0.5       0.5     0.5    0.5    0.5     0.5   \n",
       "3                     0.5      1.0       0.5     0.5    1.0    0.5     0.5   \n",
       "4                     0.5      1.0       0.5     0.5    1.0    0.5     0.5   \n",
       "..                    ...      ...       ...     ...    ...    ...     ...   \n",
       "326                   0.5      1.0       0.5     0.0    0.5    0.5     1.0   \n",
       "327                   0.5      1.0       0.5     0.5    0.5    0.5     1.0   \n",
       "328                   0.5      1.0       0.5     0.5    0.5    0.5     1.0   \n",
       "329                   0.5      0.5       0.5     0.5    0.5    0.0     0.5   \n",
       "330                   0.5      0.5       0.5     0.5    0.5    0.0     0.5   \n",
       "\n",
       "     technology      label  \n",
       "0           0.5  alfaromeo  \n",
       "1           0.5     armani  \n",
       "2           0.5     adidas  \n",
       "3           1.0  alfaromeo  \n",
       "4           1.0     armani  \n",
       "..          ...        ...  \n",
       "326         0.5    ferrero  \n",
       "327         0.5  alfaromeo  \n",
       "328         0.5    barilla  \n",
       "329         0.5    ferrero  \n",
       "330         0.5   amarelli  \n",
       "\n",
       "[331 rows x 17 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#CREAZIONE DEI DATI PER L'ANALIDI DEL KNN\n",
    "\n",
    "#Crea il dataframe di vettori etichettati\n",
    "df = make_df()\n",
    "\n",
    "#Colonne per la variabile x (I VETTORI)\n",
    "features = ['baby','car','chocolate','clothing',\n",
    "            'coffee','computer','fashion','home',\n",
    "            'household appliances','italian','licorice',\n",
    "            'office','pasta','scent','sporty','technology']\n",
    "\n",
    "#VARIABILE x = I VETTORI\n",
    "#VARIABILE y = LE ETICHETTE \n",
    "x = df[features]\n",
    "y = df['label']\n",
    "\n",
    "# Splitting del dataset in training e test (80% training - 20% set)\n",
    "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.20)\n",
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#ESECUZIONE DEL KNN PER DIVERSI K\n",
    "#Mostra il tasso di errore\n",
    "\n",
    "error_rate = []\n",
    "k_min = 1\n",
    "k_max = 51\n",
    "for i in range(k_min,k_max):\n",
    "    \n",
    "    knn = KNeighborsClassifier(n_neighbors=i)\n",
    "    knn.fit(x_train,y_train)\n",
    "    pred_i = knn.predict(x_test)\n",
    "    error_rate.append(np.mean(pred_i != y_test))\n",
    "\n",
    "plt.figure(figsize=(15,6))\n",
    "plt.plot(range(k_min,k_max),error_rate,color='blue', linestyle='dashed', marker='o', markerfacecolor='red', markersize=5)\n",
    "plt.title('Error Rate vs. K Value')\n",
    "plt.xlabel('K')\n",
    "plt.xticks(range(k_min,k_max))\n",
    "plt.ylabel('Error Rate')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report (K = 27 )\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "      adidas       0.27      0.33      0.30         9\n",
      "   alfaromeo       0.39      0.54      0.45        13\n",
      "    amarelli       0.20      0.25      0.22         4\n",
      "      armani       0.43      0.43      0.43         7\n",
      "     barilla       1.00      0.00      0.00         8\n",
      "    delonghi       0.29      0.22      0.25         9\n",
      "     ferrero       0.25      0.50      0.33         6\n",
      "     lavazza       0.25      0.33      0.29         3\n",
      "   microsoft       0.33      0.20      0.25         5\n",
      "     samsung       1.00      0.00      0.00         3\n",
      "\n",
      "    accuracy                           0.31        67\n",
      "   macro avg       0.44      0.28      0.25        67\n",
      "weighted avg       0.43      0.31      0.28        67\n",
      "\n",
      "KNN Classification Accuracy of the model (K = 27 ): 31.34%\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#ESECUZIONE DEK KNN\n",
    "\n",
    "#valore di K \n",
    "K = 27\n",
    "\n",
    "# Fitting KNN Classifier to the Training set\n",
    "model = KNeighborsClassifier(n_neighbors = K, metric = 'euclidean', p = 2)\n",
    "model.fit(x_train, y_train)\n",
    "\n",
    "# Predicting the results\n",
    "y_pred = model.predict(x_test)\n",
    "\n",
    "# Classification Report\n",
    "print(\"\\nClassification Report (K =\",K,\")\")\n",
    "report = classification_report(y_test, y_pred,zero_division=1)\n",
    "print(report)\n",
    "\n",
    "# Accuracy of the model\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print('KNN Classification Accuracy of the model (K =',K,'): {:.2f}%'.format(accuracy*100))\n",
    "\n",
    "#Confusion matrix\n",
    "confusionmatrix = confusion_matrix(y_test, y_pred)\n",
    "fig, ax = plt.subplots()\n",
    "sns.heatmap(confusionmatrix, annot=True, linewidth=3, cmap='viridis')\n",
    "plt.xlabel(\"Confusion Matrix\", fontsize=18, labelpad=20)\n",
    "ax.xaxis.tick_top()\n",
    "plt.ylabel(\"True\", fontsize=14, rotation=0, labelpad=30)\n",
    "plt.yticks(rotation=0)\n",
    "plt.title(\"Predicted\", fontsize=14, pad=10)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>index</th>\n",
       "      <th>label</th>\n",
       "      <th>Predicted-label (K=27)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8</td>\n",
       "      <td>lavazza</td>\n",
       "      <td>ferrero</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>54</td>\n",
       "      <td>alfaromeo</td>\n",
       "      <td>adidas</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>307</td>\n",
       "      <td>armani</td>\n",
       "      <td>armani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11</td>\n",
       "      <td>delonghi</td>\n",
       "      <td>ferrero</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>236</td>\n",
       "      <td>delonghi</td>\n",
       "      <td>delonghi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>249</td>\n",
       "      <td>adidas</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>135</td>\n",
       "      <td>delonghi</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>111</td>\n",
       "      <td>alfaromeo</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>221</td>\n",
       "      <td>barilla</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>25</td>\n",
       "      <td>samsung</td>\n",
       "      <td>adidas</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>67 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    index      label Predicted-label (K=27)\n",
       "0       8    lavazza                ferrero\n",
       "1      54  alfaromeo                 adidas\n",
       "2     307     armani                 armani\n",
       "3      11   delonghi                ferrero\n",
       "4     236   delonghi               delonghi\n",
       "..    ...        ...                    ...\n",
       "62    249     adidas              alfaromeo\n",
       "63    135   delonghi              alfaromeo\n",
       "64    111  alfaromeo              alfaromeo\n",
       "65    221    barilla              alfaromeo\n",
       "66     25    samsung                 adidas\n",
       "\n",
       "[67 rows x 3 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.set_option('display.max_colwidth', None)\n",
    "pd.set_option('display.max_rows', 30)\n",
    "pd.set_option('display.max_columns', None)\n",
    "\n",
    "col_name = 'Predicted-label (K='+str(K)+\")\"\n",
    "predictions = pd.DataFrame({'label': y_test, col_name : y_pred}).reset_index()\n",
    "predictions.sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>index</th>\n",
       "      <th>User</th>\n",
       "      <th>label</th>\n",
       "      <th>Predicted-label (K=27)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>ABO_mondo</td>\n",
       "      <td>alfaromeo</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8</td>\n",
       "      <td>AnteaterButters</td>\n",
       "      <td>lavazza</td>\n",
       "      <td>ferrero</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>11</td>\n",
       "      <td>AnteaterButters</td>\n",
       "      <td>delonghi</td>\n",
       "      <td>ferrero</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>17</td>\n",
       "      <td>AshleyUGCsocial</td>\n",
       "      <td>delonghi</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>Biagio960</td>\n",
       "      <td>alfaromeo</td>\n",
       "      <td>alfaromeo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>292</td>\n",
       "      <td>mollyrperk</td>\n",
       "      <td>microsoft</td>\n",
       "      <td>microsoft</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>295</td>\n",
       "      <td>plathfan78</td>\n",
       "      <td>delonghi</td>\n",
       "      <td>delonghi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>296</td>\n",
       "      <td>pradhangyan</td>\n",
       "      <td>adidas</td>\n",
       "      <td>adidas</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>299</td>\n",
       "      <td>prettyjuls</td>\n",
       "      <td>barilla</td>\n",
       "      <td>armani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>307</td>\n",
       "      <td>saverio825</td>\n",
       "      <td>armani</td>\n",
       "      <td>armani</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>67 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    index             User      label Predicted-label (K=27)\n",
       "0       3        ABO_mondo  alfaromeo              alfaromeo\n",
       "1       8  AnteaterButters    lavazza                ferrero\n",
       "2      11  AnteaterButters   delonghi                ferrero\n",
       "3      17  AshleyUGCsocial   delonghi              alfaromeo\n",
       "4      18        Biagio960  alfaromeo              alfaromeo\n",
       "..    ...              ...        ...                    ...\n",
       "62    292       mollyrperk  microsoft              microsoft\n",
       "63    295       plathfan78   delonghi               delonghi\n",
       "64    296      pradhangyan     adidas                 adidas\n",
       "65    299       prettyjuls    barilla                 armani\n",
       "66    307       saverio825     armani                 armani\n",
       "\n",
       "[67 rows x 4 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#TABELLA DI COMPARAZIONE\n",
    "\n",
    "compare_df = df\n",
    "compare_df = compare_df.reset_index()\n",
    "user_df = gold_standard['User'].reset_index()\n",
    "compare_df = compare_df.merge(user_df, on=[\"index\"])\n",
    "compare_df = compare_df.merge(predictions, on=[\"index\",\"label\"])\n",
    "\n",
    "predict_col_name = compare_df.iloc[:,-1:].columns[0]\n",
    "compare_df = compare_df[['index','User','baby','car','chocolate',\n",
    "                        'clothing','coffee','computer','fashion',\n",
    "                        'home','household appliances','italian',\n",
    "                        'licorice','office','pasta','scent','sporty',\n",
    "                        'technology','label',predict_col_name]]\n",
    "                        \n",
    "clean_compare_df = compare_df[['index','User','label',predict_col_name]]\n",
    "\n",
    "#SALVA I RISULTATI\n",
    "#clean_compare_df.to_excel('final_results/sklearn_knn_predictions_compatc.xlsx',index=False)\n",
    "#compare_df.to_excel('final_results/sklearn_knn_predictions.xlsx',index=False)\n",
    "\n",
    "clean_compare_df"
   ]
  }
 ],
 "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": "3.10.8"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "510bf11c66312c57553c778e95194a8e30cff11d9b6d05cf8b0c105636ab8e90"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}