From f9a97757299b30957cb38c18503863549287451b Mon Sep 17 00:00:00 2001
From: Giulia Menichetti <giulia.menichetti2@unibo.it>
Date: Sun, 5 Mar 2023 21:02:14 -0500
Subject: [PATCH] Added zip file

---
 Open_Food_Facts_SISection6.ipynb | 79 +++++++++++++++++---------------
 1 file changed, 41 insertions(+), 38 deletions(-)

diff --git a/Open_Food_Facts_SISection6.ipynb b/Open_Food_Facts_SISection6.ipynb
index ecf8894..b8b1768 100644
--- a/Open_Food_Facts_SISection6.ipynb
+++ b/Open_Food_Facts_SISection6.ipynb
@@ -2,8 +2,8 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "df8dac46",
+   "execution_count": 12,
+   "id": "e18d139a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,6 +15,7 @@
     "import joblib\n",
     "import matplotlib\n",
     "import operator\n",
+    "from zipfile import ZipFile\n",
     "# Set \n",
     "matplotlib.rcParams['font.serif'] = 'Times New Roman'\n",
     "matplotlib.rcParams['font.family'] = \"serif\"\n",
@@ -26,8 +27,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "dc2d945d",
+   "execution_count": 13,
+   "id": "e9b9cb68",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -39,7 +40,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5ee07c54",
+   "id": "267994f6",
    "metadata": {},
    "source": [
     "# Load Data"
@@ -47,8 +48,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "bd61b473",
+   "execution_count": 18,
+   "id": "4d40a822",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -57,8 +58,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "08d4a7b1",
+   "execution_count": 19,
+   "id": "58610a77",
    "metadata": {
     "scrolled": true
    },
@@ -472,7 +473,7 @@
        "[233831 rows x 25 columns]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -483,7 +484,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "55d99365",
+   "id": "60843900",
    "metadata": {},
    "source": [
     "# Missing Data in Nutrition Facts"
@@ -491,8 +492,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "cc1321c3",
+   "execution_count": 20,
+   "id": "f077ef2b",
    "metadata": {},
    "outputs": [
     {
@@ -514,7 +515,7 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -538,7 +539,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "89c1573d",
+   "id": "f5f8f81d",
    "metadata": {},
    "source": [
     "# Keep 11 nutrients including Trans-Fats"
@@ -546,8 +547,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "46f43497",
+   "execution_count": 21,
+   "id": "0c99130a",
    "metadata": {},
    "outputs": [
     {
@@ -583,8 +584,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "41f05700",
+   "execution_count": 22,
+   "id": "4d1bddda",
    "metadata": {},
    "outputs": [
     {
@@ -608,20 +609,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "ab6334c1",
+   "execution_count": 23,
+   "id": "00dd1eab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# zip file\n",
+    "with ZipFile(pathdir2+'OpenFoodFacts11p_Performance.pkl.zip', 'r') as zObject:\n",
+    "    zObject.extractall(path=pathdir2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "847c8adc",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/giulia/anaconda/lib/python3.6/site-packages/sklearn/base.py:315: UserWarning: Trying to unpickle estimator DecisionTreeClassifier from version 0.23.2 when using version 0.24.2. This might lead to breaking code or invalid results. Use at your own risk.\n",
-      "  UserWarning)\n",
-      "/Users/giulia/anaconda/lib/python3.6/site-packages/sklearn/base.py:315: UserWarning: Trying to unpickle estimator RandomForestClassifier from version 0.23.2 when using version 0.24.2. This might lead to breaking code or invalid results. Use at your own risk.\n",
-      "  UserWarning)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -647,7 +650,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "abe4947c",
+   "id": "bc3c1be8",
    "metadata": {},
    "source": [
     "# Including Additives Information"
@@ -656,7 +659,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "2b98cd81",
+   "id": "18f4e736",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -668,7 +671,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "d37d6468",
+   "id": "eca1ce17",
    "metadata": {},
    "outputs": [
     {
@@ -690,7 +693,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "1c039feb",
+   "id": "243cdff5",
    "metadata": {},
    "outputs": [
     {
@@ -710,7 +713,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "08a11251",
+   "id": "0b467541",
    "metadata": {},
    "source": [
     "# Using just the Number of Additives"
@@ -719,7 +722,7 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "e381bf68",
+   "id": "7cde3081",
    "metadata": {},
    "outputs": [
     {
@@ -741,7 +744,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "0ac64460",
+   "id": "d3efbb21",
    "metadata": {},
    "outputs": [
     {