towards_a_programmable_dataverse_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "91b27fda",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting package metadata (current_repodata.json): ...working... done\n",
      "Solving environment: ...working... done\n",
      "\n",
      "# All requested packages already installed.\n",
      "\n",
      "Collecting package metadata (current_repodata.json): ...working... done\n",
      "Solving environment: ...working... done\n",
      "\n",
      "# All requested packages already installed.\n",
      "\n",
      "Collecting package metadata (current_repodata.json): ...working... done\n",
      "Solving environment: ...working... done\n",
      "\n",
      "# All requested packages already installed.\n",
      "\n",
      "Collecting package metadata (current_repodata.json): ...working... done\n",
      "Solving environment: ...working... done\n",
      "\n",
      "# All requested packages already installed.\n",
      "\n",
      "Collecting package metadata (current_repodata.json): ...working... done\n",
      "Solving environment: ...working... done\n",
      "\n",
      "# All requested packages already installed.\n",
      "\n",
      "Requirement already satisfied: pyDataverse in c:\\users\\au591635\\anaconda3\\lib\\site-packages (0.3.1)\n",
      "Requirement already satisfied: jsonschema>=3.2.0 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from pyDataverse) (3.2.0)\n",
      "Requirement already satisfied: requests>=2.12.0 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from pyDataverse) (2.26.0)\n",
      "Requirement already satisfied: six>=1.11.0 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from jsonschema>=3.2.0->pyDataverse) (1.16.0)\n",
      "Requirement already satisfied: setuptools in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from jsonschema>=3.2.0->pyDataverse) (58.0.4)\n",
      "Requirement already satisfied: attrs>=17.4.0 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from jsonschema>=3.2.0->pyDataverse) (21.2.0)\n",
      "Requirement already satisfied: pyrsistent>=0.14.0 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from jsonschema>=3.2.0->pyDataverse) (0.18.0)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from requests>=2.12.0->pyDataverse) (2021.10.8)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from requests>=2.12.0->pyDataverse) (1.26.7)\n",
      "Requirement already satisfied: charset-normalizer~=2.0.0 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from requests>=2.12.0->pyDataverse) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\au591635\\anaconda3\\lib\\site-packages (from requests>=2.12.0->pyDataverse) (3.2)\n"
     ]
    }
   ],
   "source": [
    "### Example code to show how data can be retrieved from the AUSSDA repository\n",
    "### You will learn how to navigate to the repository and download a datafile, and how to use different \n",
    "### datafiles.\n",
    "\n",
    "\n",
    "# This installs the packages so Jupyter Notebook can execute the code. \n",
    "# Version info: python 3.9.7\n",
    "# If you run this in a mybinder.org environment, you do not need to execute this chunk of code. \n",
    "import sys\n",
    "!conda install --yes --prefix {sys.prefix} requests \n",
    "!conda install --yes --prefix {sys.prefix} jsonschema \n",
    "!conda install --yes --prefix {sys.prefix} pandas \n",
    "!conda install --yes --prefix {sys.prefix} numpy \n",
    "!conda install --yes --prefix {sys.prefix} matplotlib\n",
    "\n",
    "!{sys.executable} -m pip install pyDataverse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "upset-hepatitis",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Start by installing and loading the packages you need. \n",
    "# The package pyDataverse handles everything you need to connect and retrieve files from a Dataverse \n",
    "# installation.\n",
    "# Check out the documentation: \n",
    "# https://pydataverse.readthedocs.io/en/latest/user/basic-usage.html#download-and-save-a-dataset-to-disk\n",
    "\n",
    "from pyDataverse.api import NativeApi, DataAccessApi\n",
    "import io\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "banned-crest",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Decide which data repository you want to use, and which dataset you want to download. \n",
    "## This example is based on the AUSSDA Dataverse. AUSSDA - The Austrian Social Science Data Archive is \n",
    "## a rich source for data for research purposes. Some data can also be used for other purposes under the \n",
    "## specified license conditions.\n",
    "## You will learn how to download the Social Survey Austria 2016 from the Dataverse.\n",
    "\n",
    "# Data citation: Bacher, Johann; Beham-Rabanser, Martina; Grausgruber, Alfred; Haller, Max; Höllinger, Franz; \n",
    "# Muckenhuber, Johanna; Prandner, Dimitri; Verwiebe, Roland, 2018, \"Social Survey Austria 2016\", \n",
    "# https://doi.org/10.11587/EHJHFJ, AUSSDA, V3\n",
    "# The data files under the above citation are licensed under a Creative Commons Attribution 4.0 International \n",
    "# License.\n",
    "# see source for more: https://doi.org/10.11587/EHJHFJ\n",
    "\n",
    "# Step 1: Define and connect to repository API\n",
    "repository_url = 'https://data.aussda.at/' \n",
    "native_api = NativeApi(repository_url)\n",
    "\n",
    "# Step 2: Define and download dataset\n",
    "DOI = \"doi:10.11587/EHJHFJ\"\n",
    "dataset = native_api.get_dataset(DOI)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "3bec2a05",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[{'description': 'Codebook', 'label': '10007_co_de_v1_0.pdf', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Codebook', 'Documentation'], 'dataFile': {'id': 181, 'persistentId': '', 'pidURL': '', 'filename': '10007_co_de_v1_0.pdf', 'contentType': 'application/pdf', 'filesize': 8871474, 'description': 'Codebook', 'storageIdentifier': 'file://1624de0b568-41d22a2eaf98', 'rootDataFileId': -1, 'md5': 'bdd1bb23ff05b38df06ffa93175639bf', 'checksum': {'type': 'MD5', 'value': 'bdd1bb23ff05b38df06ffa93175639bf'}, 'creationDate': '2018-03-22'}}, {'description': 'Core data file - STATA format - 373 Variables, 2021 Observations', 'label': '10007_da_de_v1_2-1.tab', 'restricted': False, 'directoryLabel': 'data', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Data', 'STATA'], 'dataFile': {'id': 188, 'persistentId': '', 'pidURL': '', 'filename': '10007_da_de_v1_2-1.tab', 'contentType': 'text/tab-separated-values', 'filesize': 2193585, 'description': 'Core data file - STATA format - 373 Variables, 2021 Observations', 'storageIdentifier': 'file://1626273a9c4-9af3e8eb1b7f', 'originalFileFormat': 'application/x-stata-14', 'originalFormatLabel': 'Stata 14 Binary', 'originalFileSize': 1454620, 'originalFileName': '10007_da_de_v1_2-1.dta', 'UNF': 'UNF:6:nt65SRLPdY1HW7gzczTtSA==', 'rootDataFileId': -1, 'md5': '822a4eb2b634116916d10d64a5b01bdc', 'checksum': {'type': 'MD5', 'value': '822a4eb2b634116916d10d64a5b01bdc'}, 'creationDate': '2018-03-26'}}, {'description': 'Core data file - SPSS format - 373 Variables, 2021 Observations', 'label': '10007_da_de_v1_2.tab', 'restricted': False, 'directoryLabel': 'data', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Data', 'SPSS'], 'dataFile': {'id': 189, 'persistentId': '', 'pidURL': '', 'filename': '10007_da_de_v1_2.tab', 'contentType': 'text/tab-separated-values', 'filesize': 2195532, 'description': 'Core data file - SPSS format - 373 Variables, 2021 Observations', 'storageIdentifier': 'file://1626278599d-2d1c8ca4ef09', 'originalFileFormat': 'text/tab-separated-values', 'originalFormatLabel': 'Tab-Delimited', 'originalFileSize': 1185535, 'originalFileName': '10007_da_de_v1_2.tsv', 'UNF': 'UNF:6:w0DkerN4YRg+TgfU9QMEww==', 'rootDataFileId': -1, 'md5': 'f1ed6d91dbbe83f029c7b5c15007e039', 'checksum': {'type': 'MD5', 'value': 'f1ed6d91dbbe83f029c7b5c15007e039'}, 'creationDate': '2018-03-26'}}, {'description': 'Core data file - compressed SPSS format - 373 Variables, 2021 Observations', 'label': '10007_da_de_v1_2.zsav', 'restricted': False, 'directoryLabel': 'data', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Data', 'SPSS'], 'dataFile': {'id': 187, 'persistentId': '', 'pidURL': '', 'filename': '10007_da_de_v1_2.zsav', 'contentType': 'application/octet-stream', 'filesize': 514242, 'description': 'Core data file - compressed SPSS format - 373 Variables, 2021 Observations', 'storageIdentifier': 'file://162626ac4f4-1ac57caf8d25', 'rootDataFileId': -1, 'md5': 'c27fcfad554b65271758729a39c6ac00', 'checksum': {'type': 'MD5', 'value': 'c27fcfad554b65271758729a39c6ac00'}, 'creationDate': '2018-03-26'}}, {'description': 'Method report', 'label': '10007_mr_de_v1_0.pdf', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Documentation', 'Method report'], 'dataFile': {'id': 182, 'persistentId': '', 'pidURL': '', 'filename': '10007_mr_de_v1_0.pdf', 'contentType': 'application/pdf', 'filesize': 543298, 'description': 'Method report', 'storageIdentifier': 'file://1624de0b8fe-c8a2d1208739', 'rootDataFileId': -1, 'md5': '979330f9b2b8f05b7e31e4b76220ebf0', 'checksum': {'type': 'MD5', 'value': '979330f9b2b8f05b7e31e4b76220ebf0'}, 'creationDate': '2018-03-22'}}, {'description': 'Differences between dataset and questionnaire as well as additional information about this open access version', 'label': '10007_om1_de_v1_0.pdf', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Documentation'], 'dataFile': {'id': 177, 'persistentId': '', 'pidURL': '', 'filename': '10007_om1_de_v1_0.pdf', 'contentType': 'application/pdf', 'filesize': 458701, 'description': 'Differences between dataset and questionnaire as well as additional information about this open access version', 'storageIdentifier': 'file://1624de0a63d-0753ce306f96', 'rootDataFileId': -1, 'md5': '81b9d7423f109c4d4fe096f27741da11', 'checksum': {'type': 'MD5', 'value': '81b9d7423f109c4d4fe096f27741da11'}, 'creationDate': '2018-03-22'}}, {'description': 'Weighting information', 'label': '10007_om2_de_v1_0.pdf', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Documentation'], 'dataFile': {'id': 178, 'persistentId': '', 'pidURL': '', 'filename': '10007_om2_de_v1_0.pdf', 'contentType': 'application/pdf', 'filesize': 242055, 'description': 'Weighting information', 'storageIdentifier': 'file://1624de0a8d8-8a697648a3cc', 'rootDataFileId': -1, 'md5': '09a0a2a4a3dc6718d99ff90f10516c84', 'checksum': {'type': 'MD5', 'value': '09a0a2a4a3dc6718d99ff90f10516c84'}, 'creationDate': '2018-03-22'}}, {'description': 'Variable list of this open access version', 'label': '10007_om3_de_v1_0.pdf', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Documentation'], 'dataFile': {'id': 179, 'persistentId': '', 'pidURL': '', 'filename': '10007_om3_de_v1_0.pdf', 'contentType': 'application/pdf', 'filesize': 383881, 'description': 'Variable list of this open access version', 'storageIdentifier': 'file://1624de0ab66-b98ecb9970a0', 'rootDataFileId': -1, 'md5': '885f8e83352e47459fa8ea93a25b2fb3', 'checksum': {'type': 'MD5', 'value': '885f8e83352e47459fa8ea93a25b2fb3'}, 'creationDate': '2018-03-22'}}, {'description': 'Variable identifiers and descriptions - machine-readable', 'label': '10007_om4_de_v1_0.tab', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Documentation'], 'dataFile': {'id': 186, 'persistentId': '', 'pidURL': '', 'filename': '10007_om4_de_v1_0.tab', 'contentType': 'text/tab-separated-values', 'filesize': 40164, 'description': 'Variable identifiers and descriptions - machine-readable', 'storageIdentifier': 'file://162534bc1af-86f7ead32fe2', 'originalFileFormat': 'text/tab-separated-values', 'originalFormatLabel': 'Tab-Delimited', 'originalFileSize': 40202, 'originalFileName': '10007_om4_de_v1_0.tsv', 'UNF': 'UNF:6:bf02jOXr7Pi6pxR+iwv5tg==', 'rootDataFileId': -1, 'md5': 'f2480df0e33bb8c5e97dd0791e76ea79', 'checksum': {'type': 'MD5', 'value': 'f2480df0e33bb8c5e97dd0791e76ea79'}, 'creationDate': '2018-03-23'}}, {'description': 'Questionnaire', 'label': '10007_qu_de_v1_0.pdf', 'restricted': False, 'directoryLabel': 'documentation', 'version': 2, 'datasetVersionId': 2227, 'categories': ['Documentation', 'Questionnaire'], 'dataFile': {'id': 180, 'persistentId': '', 'pidURL': '', 'filename': '10007_qu_de_v1_0.pdf', 'contentType': 'application/pdf', 'filesize': 1248733, 'description': 'Questionnaire', 'storageIdentifier': 'file://1624de0ae70-7369ca77d06e', 'rootDataFileId': -1, 'md5': 'c248232b0dd1b0bbd6dcf3b85b3d5d6e', 'checksum': {'type': 'MD5', 'value': 'c248232b0dd1b0bbd6dcf3b85b3d5d6e'}, 'creationDate': '2018-03-22'}}]\n",
      "188\n"
     ]
    }
   ],
   "source": [
    "## To download the data file automatically, the following code proceeeds in several steps.\n",
    "## First, you create a list of available files. Then, you download the first datafile.\n",
    "## In Dataverse, there are several files saved under each DOI: datafiles (usually .tab files), and \n",
    "## documentation as pdf-files. The following code saves a list of all these files. \n",
    "## \n",
    "## The following code first goes through all files in the file list (i.e. all files in the dataset), \n",
    "## and identifies all files that are tab-delimited files. These are the datafiles you want to download. \n",
    "## Then, it picks the first of these tab-delimited files which is usually the original datafile by default. \n",
    "## Then you download this file.  \n",
    "\n",
    "\n",
    "# Create a list of files that are available in the dataset\n",
    "files_list = dataset.json()['data']['latestVersion']['files']\n",
    "print(files_list)\n",
    "\n",
    "# Find the first tab-file\n",
    "ident = []\n",
    "\n",
    "for file in files_list:\n",
    "    filename = file[\"dataFile\"][\"filename\"]\n",
    "    file_id = file[\"dataFile\"][\"id\"]\n",
    "    if filename.endswith('.tab'):\n",
    "        ident.append(file_id)\n",
    "\n",
    "# Save the ID of the first tab file that occurs in the list\n",
    "datafile_id = ident[0] \n",
    "print(datafile_id)\n",
    "\n",
    "# Step 3: Connect to API for data access at the repository\n",
    "data_access_api = DataAccessApi(repository_url)\n",
    "\n",
    "# Step 4: Download data file using its id\n",
    "response = data_access_api.get_datafile(datafile_id)\n",
    "with open(\"data.dta\", \"xb\") as f:\n",
    "    f.write(response.content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "wooden-joyce",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Working with the datafile Pt. 1\n",
    "## Now that you have downloaded the datafile, you can work with it: It needs to be transformed into a format \n",
    "## that can be used by the Pandas package.\n",
    "\n",
    "# Transform the response into a Pandas data frame\n",
    "data = io.StringIO(str(response.content,'utf-8'))\n",
    "\n",
    "# The file is a tab-delimited file in the repository, i.e. the seperator between columns (variables) is a tab.\n",
    "# The first line consists of the variable names.\n",
    "data = pd.read_csv(data, sep=\"\\t\", index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "color-angola",
   "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>doi</th>\n",
       "      <th>NR_2016</th>\n",
       "      <th>ISSP_Version</th>\n",
       "      <th>Gewicht_DES</th>\n",
       "      <th>Gewicht_POS</th>\n",
       "      <th>Gewicht_GES</th>\n",
       "      <th>SEX_2016</th>\n",
       "      <th>af1</th>\n",
       "      <th>af5</th>\n",
       "      <th>bf14</th>\n",
       "      <th>...</th>\n",
       "      <th>Matura</th>\n",
       "      <th>city</th>\n",
       "      <th>Matura_vater</th>\n",
       "      <th>Matura_mutter</th>\n",
       "      <th>Nationalitaet</th>\n",
       "      <th>Geburtsland</th>\n",
       "      <th>Partnerschaft</th>\n",
       "      <th>Matura_partner</th>\n",
       "      <th>Messgang</th>\n",
       "      <th>Wohnverhaeltnis</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>version</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1.2 (2018-03-26)</th>\n",
       "      <td>doi:10.11587/EHJHFJ</td>\n",
       "      <td>1172</td>\n",
       "      <td>2</td>\n",
       "      <td>1.28212</td>\n",
       "      <td>0.80073</td>\n",
       "      <td>1.15048</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.2 (2018-03-26)</th>\n",
       "      <td>doi:10.11587/EHJHFJ</td>\n",
       "      <td>1857</td>\n",
       "      <td>2</td>\n",
       "      <td>0.38161</td>\n",
       "      <td>0.80682</td>\n",
       "      <td>0.20884</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>-99</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.2 (2018-03-26)</th>\n",
       "      <td>doi:10.11587/EHJHFJ</td>\n",
       "      <td>1946</td>\n",
       "      <td>2</td>\n",
       "      <td>0.41640</td>\n",
       "      <td>0.95263</td>\n",
       "      <td>0.37300</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>-99</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.2 (2018-03-26)</th>\n",
       "      <td>doi:10.11587/EHJHFJ</td>\n",
       "      <td>1102</td>\n",
       "      <td>2</td>\n",
       "      <td>1.28212</td>\n",
       "      <td>0.92258</td>\n",
       "      <td>1.30632</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.2 (2018-03-26)</th>\n",
       "      <td>doi:10.11587/EHJHFJ</td>\n",
       "      <td>1352</td>\n",
       "      <td>2</td>\n",
       "      <td>0.41640</td>\n",
       "      <td>0.86337</td>\n",
       "      <td>0.43237</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 372 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  doi  NR_2016  ISSP_Version  Gewicht_DES  \\\n",
       "version                                                                     \n",
       "1.2 (2018-03-26)  doi:10.11587/EHJHFJ     1172             2      1.28212   \n",
       "1.2 (2018-03-26)  doi:10.11587/EHJHFJ     1857             2      0.38161   \n",
       "1.2 (2018-03-26)  doi:10.11587/EHJHFJ     1946             2      0.41640   \n",
       "1.2 (2018-03-26)  doi:10.11587/EHJHFJ     1102             2      1.28212   \n",
       "1.2 (2018-03-26)  doi:10.11587/EHJHFJ     1352             2      0.41640   \n",
       "\n",
       "                  Gewicht_POS  Gewicht_GES  SEX_2016  af1  af5  bf14  ...  \\\n",
       "version                                                               ...   \n",
       "1.2 (2018-03-26)      0.80073      1.15048         1    1   -1     1  ...   \n",
       "1.2 (2018-03-26)      0.80682      0.20884         2    1   10     1  ...   \n",
       "1.2 (2018-03-26)      0.95263      0.37300         1    1   15     1  ...   \n",
       "1.2 (2018-03-26)      0.92258      1.30632         2    4    1     1  ...   \n",
       "1.2 (2018-03-26)      0.86337      0.43237         2    1   -1     1  ...   \n",
       "\n",
       "                  Matura  city  Matura_vater  Matura_mutter  Nationalitaet  \\\n",
       "version                                                                      \n",
       "1.2 (2018-03-26)       1     1             1              1              1   \n",
       "1.2 (2018-03-26)       2     1             2              2              1   \n",
       "1.2 (2018-03-26)       2     2             2              2              0   \n",
       "1.2 (2018-03-26)       1     1             1              1              1   \n",
       "1.2 (2018-03-26)       1     1             0              1              1   \n",
       "\n",
       "                  Geburtsland  Partnerschaft  Matura_partner  Messgang  \\\n",
       "version                                                                  \n",
       "1.2 (2018-03-26)            1              2               1         0   \n",
       "1.2 (2018-03-26)            1              3             -99         4   \n",
       "1.2 (2018-03-26)            0              3             -99         5   \n",
       "1.2 (2018-03-26)            1              1               1         5   \n",
       "1.2 (2018-03-26)            1              1               0         4   \n",
       "\n",
       "                  Wohnverhaeltnis  \n",
       "version                            \n",
       "1.2 (2018-03-26)                1  \n",
       "1.2 (2018-03-26)                0  \n",
       "1.2 (2018-03-26)                0  \n",
       "1.2 (2018-03-26)                2  \n",
       "1.2 (2018-03-26)                1  \n",
       "\n",
       "[5 rows x 372 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Working with the datafile Pt. 2\n",
    "## Looking at data: Check if the download worked, and  what the data looks like.\n",
    "\n",
    "# Show sample data by displaying the first rows\n",
    "data.head()\n",
    "\n",
    "# The rows are unique observations. In your case survey data each row is an invidual respondent, because you \n",
    "# use survey data.\n",
    "# The columns are variables, which are mostly questions in survey data. The variable names in the header show \n",
    "# which question is stored in which column, and the values show the answer each respondent gave to each \n",
    "# question.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a3a04022",
   "metadata": {},
   "outputs": [],
   "source": [
    "### Where to go from here? Pt. 2. \n",
    "\n",
    "# Another option is to use a different dataset that is published under an open access license (CC BY) that \n",
    "# does not require a login or API key.\n",
    "\n",
    "# Data citation: Kittel, Bernhard; Kritzinger, Sylvia; Boomgaarden, Hajo; Prainsack, Barbara; Eberl, \n",
    "# Jakob-Moritz; Kalleitner, Fabian; Lebernegg, Noëlle S.; Partheymüller, Julia; Plescia, Carolina; \n",
    "# Schiestl, David W.; Schlogl, Lukas, 2020, \"Austrian Corona Panel Project (OA edition)\", \n",
    "# https://doi.org/10.11587/P5YJ0O, AUSSDA, V2\n",
    "# DOI = \"doi:10.11587/P5YJ0O\"\n",
    "\n",
    "# If you want to use the Corona Panel Project instead of the Social Survey, change the DOI in the code above \n",
    "# to \"10.11587/P5YJ0O\" in Step 2. Look at the codebook or the questionnaire again to determine which variable \n",
    "# contains information on which question. \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a21780b7",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Manual Process: Specify the id of the file you want to download, and proceed with Step 1 and Step 2\n",
    "\n",
    "# If the automatic download described above does not work, you can specify the name of the file you want to \n",
    "# retrieve manually, and download it using the function get_dataframe_by_name. In order to find the name, \n",
    "# check the object files_list that you created after Step 2, or look at the landing page for the Social \n",
    "# Survey Austria in the repository at  https://doi.org/10.11587/EHJHFJ.\n",
    "# You can also download the files manually when using the Corona Panel Project in case the automatic \n",
    "# download does not work.\n",
    "\n",
    "# # Check the id numbers for each file.\n",
    "# for file in files_list:\n",
    "#     filename = file[\"dataFile\"][\"filename\"]\n",
    "#     file_id = file[\"dataFile\"][\"id\"]\n",
    "#     print(\"File name {} has id {}\".format(filename, file_id))\n",
    "# # Specify which file you want to retrieve.\n",
    "# datafile_id = 188 \n",
    "# # Step 1: Connect to API for data access at the repository\n",
    "# data_access_api = DataAccessApi(repository_url)\n",
    "# # Step 2: Retrieve data file\n",
    "# response = data_access_api.get_datafile(datafile_id)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "518fe0c2",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.11.0 64-bit",
   "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": "3.11.0"
  },
  "vscode": {
   "interpreter": {
    "hash": "ff4b1fca65a764b45acb559e482afe389d289dd599b9f8c5fd12ff5c2ea46a65"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}