From d168b5a187e2c777561b9c3da12721adf867937d Mon Sep 17 00:00:00 2001
From: acfa360755dfad8a1b8d2c7cf6b8d4b8
 <acfa360755dfad8a1b8d2c7cf6b8d4b8@app-learninglab.inria.fr>
Date: Fri, 24 Apr 2020 09:24:40 +0000
Subject: [PATCH] Read from a local file

---
 module3/exo1/analyse-syndrome-grippal.ipynb | 97 +++++++++++++++------
 1 file changed, 68 insertions(+), 29 deletions(-)

diff --git a/module3/exo1/analyse-syndrome-grippal.ipynb b/module3/exo1/analyse-syndrome-grippal.ipynb
index c502114..0617dc1 100644
--- a/module3/exo1/analyse-syndrome-grippal.ipynb
+++ b/module3/exo1/analyse-syndrome-grippal.ipynb
@@ -29,7 +29,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 28,
    "metadata": {
     "scrolled": true
    },
@@ -996,7 +996,7 @@
        "[1851 rows x 10 columns]"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 28,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1028,31 +1028,6 @@
     "La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skiprows=1`."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ValueError",
-     "evalue": "Invalid file path or buffer object type: <class 'pandas.core.frame.DataFrame'>",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-24-d645e08d553e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mraw_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_origine\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mskiprows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mraw_data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mparser_f\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)\u001b[0m\n\u001b[1;32m    707\u001b[0m                     skip_blank_lines=skip_blank_lines)\n\u001b[1;32m    708\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 709\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    710\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    711\u001b[0m     \u001b[0mparser_f\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    431\u001b[0m     \u001b[0mcompression\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_infer_compression\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcompression\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    432\u001b[0m     filepath_or_buffer, _, compression = get_filepath_or_buffer(\n\u001b[0;32m--> 433\u001b[0;31m         filepath_or_buffer, encoding, compression)\n\u001b[0m\u001b[1;32m    434\u001b[0m     \u001b[0mkwds\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'compression'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompression\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    435\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/common.py\u001b[0m in \u001b[0;36mget_filepath_or_buffer\u001b[0;34m(filepath_or_buffer, encoding, compression)\u001b[0m\n\u001b[1;32m    209\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mis_file_like\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    210\u001b[0m         \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"Invalid file path or buffer object type: {_type}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 211\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    212\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    213\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcompression\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mValueError\u001b[0m: Invalid file path or buffer object type: <class 'pandas.core.frame.DataFrame'>"
-     ]
-    }
-   ],
-   "source": [
-    "raw_data = pd.read_csv(data_origine, skiprows=1)\n",
-    "raw_data"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1062,9 +1037,73 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 29,
    "metadata": {},
-   "outputs": [],
+   "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>week</th>\n",
+       "      <th>indicator</th>\n",
+       "      <th>inc</th>\n",
+       "      <th>inc_low</th>\n",
+       "      <th>inc_up</th>\n",
+       "      <th>inc100</th>\n",
+       "      <th>inc100_low</th>\n",
+       "      <th>inc100_up</th>\n",
+       "      <th>geo_insee</th>\n",
+       "      <th>geo_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1614</th>\n",
+       "      <td>198919</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>FR</td>\n",
+       "      <td>France</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        week  indicator  inc  inc_low  inc_up  inc100  inc100_low  inc100_up  \\\n",
+       "1614  198919          3    0      NaN     NaN       0         NaN        NaN   \n",
+       "\n",
+       "     geo_insee geo_name  \n",
+       "1614        FR   France  "
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "raw_data[raw_data.isnull().any(axis=1)]"
    ]
-- 
2.18.1