Skip to content

M
mooc-rr
Commit 49ba419c authored by f82c1c4a1227cdba8ff3317d228324d6's avatar f82c1c4a1227cdba8ff3317d228324d6
Browse files
Options

7

parent 5009355d
Hide whitespace changes
Inline Side-by-side
Showing with 450 additions and 27 deletions
module3/exo3/exercice.ipynb
View file @ 49ba419c
......@@ -9,7 +9,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
......@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
......@@ -30,7 +30,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
......@@ -44,38 +44,425 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 24,
"metadata": {},
"outputs": [
{
"ename": "ParserError",
"evalue": "Error tokenizing data. C error: Expected 1 fields in line 33, saw 4\n",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mParserError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-4-ae9cd278969e>\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_file\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 453\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 454\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 455\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 456\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 457\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\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;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1067\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'skipfooter not supported for iteration'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1068\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1069\u001b[0;31m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1070\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1071\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'as_recarray'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\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;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1837\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1838\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1839\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1840\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1841\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_first_chunk\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader.read\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_low_memory\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_rows\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._tokenize_rows\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.raise_parser_error\u001b[0;34m()\u001b[0m\n",
"\u001b[0;31mParserError\u001b[0m: Error tokenizing data. C error: Expected 1 fields in line 33, saw 4\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>1958-03-29</th>\n",
" <th>316.19</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1958-04-05</td>\n",
" <td>317.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1958-04-12</td>\n",
" <td>317.69</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1958-04-19</td>\n",
" <td>317.58</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1958-04-26</td>\n",
" <td>316.48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1958-05-03</td>\n",
" <td>316.95</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1958-05-17</td>\n",
" <td>317.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>1958-05-24</td>\n",
" <td>317.99</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>1958-07-05</td>\n",
" <td>315.85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>1958-07-12</td>\n",
" <td>315.85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1958-07-19</td>\n",
" <td>315.46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>1958-07-26</td>\n",
" <td>315.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>1958-08-02</td>\n",
" <td>315.64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>1958-08-09</td>\n",
" <td>315.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>1958-08-16</td>\n",
" <td>315.09</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>1958-08-30</td>\n",
" <td>314.14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>1958-09-06</td>\n",
" <td>313.54</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1958-11-08</td>\n",
" <td>313.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>1958-11-15</td>\n",
" <td>313.26</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1958-11-22</td>\n",
" <td>313.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>1958-11-29</td>\n",
" <td>314.01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1958-12-06</td>\n",
" <td>314.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>1958-12-13</td>\n",
" <td>314.41</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>1958-12-20</td>\n",
" <td>314.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>1958-12-27</td>\n",
" <td>315.21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>1959-01-03</td>\n",
" <td>315.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>1959-01-10</td>\n",
" <td>315.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>1959-01-17</td>\n",
" <td>315.69</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>1959-01-24</td>\n",
" <td>315.86</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>1959-01-31</td>\n",
" <td>315.42</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>1959-02-14</td>\n",
" <td>316.94</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3327</th>\n",
" <td>2023-06-10</td>\n",
" <td>424.01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3328</th>\n",
" <td>2023-06-17</td>\n",
" <td>422.93</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3329</th>\n",
" <td>2023-06-24</td>\n",
" <td>422.21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3330</th>\n",
" <td>2023-07-01</td>\n",
" <td>422.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3331</th>\n",
" <td>2023-07-08</td>\n",
" <td>422.32</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3332</th>\n",
" <td>2023-07-15</td>\n",
" <td>421.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3333</th>\n",
" <td>2023-07-22</td>\n",
" <td>420.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3334</th>\n",
" <td>2023-07-29</td>\n",
" <td>420.88</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3335</th>\n",
" <td>2023-08-05</td>\n",
" <td>420.39</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3336</th>\n",
" <td>2023-08-12</td>\n",
" <td>420.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3337</th>\n",
" <td>2023-08-19</td>\n",
" <td>418.96</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3338</th>\n",
" <td>2023-08-26</td>\n",
" <td>418.84</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3339</th>\n",
" <td>2023-09-02</td>\n",
" <td>418.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3340</th>\n",
" <td>2023-09-09</td>\n",
" <td>418.28</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3341</th>\n",
" <td>2023-09-16</td>\n",
" <td>418.52</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3342</th>\n",
" <td>2023-09-23</td>\n",
" <td>417.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3343</th>\n",
" <td>2023-09-30</td>\n",
" <td>417.89</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3344</th>\n",
" <td>2023-10-07</td>\n",
" <td>418.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3345</th>\n",
" <td>2023-10-14</td>\n",
" <td>418.82</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3346</th>\n",
" <td>2023-10-21</td>\n",
" <td>418.85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3347</th>\n",
" <td>2023-10-28</td>\n",
" <td>418.62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3348</th>\n",
" <td>2023-11-04</td>\n",
" <td>419.07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3349</th>\n",
" <td>2023-11-11</td>\n",
" <td>419.41</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3350</th>\n",
" <td>2023-11-18</td>\n",
" <td>421.18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3351</th>\n",
" <td>2023-11-25</td>\n",
" <td>421.22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3352</th>\n",
" <td>2023-12-02</td>\n",
" <td>420.28</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3353</th>\n",
" <td>2023-12-09</td>\n",
" <td>421.23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3354</th>\n",
" <td>2023-12-16</td>\n",
" <td>422.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3355</th>\n",
" <td>2023-12-23</td>\n",
" <td>422.06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3356</th>\n",
" <td>2023-12-30</td>\n",
" <td>421.76</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3357 rows × 2 columns</p>\n",
"</div>"
],
"text/plain": [
" 1958-03-29 316.19\n",
"0 1958-04-05 317.31\n",
"1 1958-04-12 317.69\n",
"2 1958-04-19 317.58\n",
"3 1958-04-26 316.48\n",
"4 1958-05-03 316.95\n",
"5 1958-05-17 317.56\n",
"6 1958-05-24 317.99\n",
"7 1958-07-05 315.85\n",
"8 1958-07-12 315.85\n",
"9 1958-07-19 315.46\n",
"10 1958-07-26 315.59\n",
"11 1958-08-02 315.64\n",
"12 1958-08-09 315.10\n",
"13 1958-08-16 315.09\n",
"14 1958-08-30 314.14\n",
"15 1958-09-06 313.54\n",
"16 1958-11-08 313.05\n",
"17 1958-11-15 313.26\n",
"18 1958-11-22 313.57\n",
"19 1958-11-29 314.01\n",
"20 1958-12-06 314.56\n",
"21 1958-12-13 314.41\n",
"22 1958-12-20 314.77\n",
"23 1958-12-27 315.21\n",
"24 1959-01-03 315.24\n",
"25 1959-01-10 315.50\n",
"26 1959-01-17 315.69\n",
"27 1959-01-24 315.86\n",
"28 1959-01-31 315.42\n",
"29 1959-02-14 316.94\n",
"... ... ...\n",
"3327 2023-06-10 424.01\n",
"3328 2023-06-17 422.93\n",
"3329 2023-06-24 422.21\n",
"3330 2023-07-01 422.80\n",
"3331 2023-07-08 422.32\n",
"3332 2023-07-15 421.43\n",
"3333 2023-07-22 420.74\n",
"3334 2023-07-29 420.88\n",
"3335 2023-08-05 420.39\n",
"3336 2023-08-12 420.30\n",
"3337 2023-08-19 418.96\n",
"3338 2023-08-26 418.84\n",
"3339 2023-09-02 418.50\n",
"3340 2023-09-09 418.28\n",
"3341 2023-09-16 418.52\n",
"3342 2023-09-23 417.77\n",
"3343 2023-09-30 417.89\n",
"3344 2023-10-07 418.10\n",
"3345 2023-10-14 418.82\n",
"3346 2023-10-21 418.85\n",
"3347 2023-10-28 418.62\n",
"3348 2023-11-04 419.07\n",
"3349 2023-11-11 419.41\n",
"3350 2023-11-18 421.18\n",
"3351 2023-11-25 421.22\n",
"3352 2023-12-02 420.28\n",
"3353 2023-12-09 421.23\n",
"3354 2023-12-16 422.57\n",
"3355 2023-12-23 422.06\n",
"3356 2023-12-30 421.76\n",
"\n",
"[3357 rows x 2 columns]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"raw_data = pd.read_csv(data_file, skiprows=1)\n",
"raw_data = pd.read_csv(data_url, skiprows=44)\n",
"raw_data"
]
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 19,
"metadata": {},
"outputs": [
{
......@@ -85,7 +472,7 @@
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mParserError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-14-46808fbde0cb>\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_file\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<ipython-input-19-46808fbde0cb>\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_file\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 453\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 454\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 455\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 456\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 457\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\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;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1067\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'skipfooter not supported for iteration'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1068\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1069\u001b[0;31m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1070\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1071\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'as_recarray'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
......@@ -106,7 +493,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 20,
"metadata": {},
"outputs": [
{
......@@ -359,7 +746,7 @@
"41 indicated by the date in the first column. ... "
]
},
"execution_count": 15,
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
......@@ -369,6 +756,42 @@
"raw_data"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 316.19\n",
"1958-03-29, \n",
"1958-04-05 317.31\n",
"1958-04-12 317.69\n",
"1958-04-19 317.58\n",
"1958-04-26 316.48\n",
"1958-05-03 316.95\n"
]
}
],
"source": [
"# Cargar datos desde el archivo CSV local\n",
"file_path = \"https://scrippsco2.ucsd.edu/assets/data/atmospheric/stations/in_situ_co2/weekly/weekly_in_situ_co2_mlo.csv\" # Reemplaza con la ruta correcta a tu archivo\n",
"\n",
"data_file_co2 = \"weekly_co2_in_situ_co2.csv\"\n",
"\n",
"import os\n",
"import urllib.request\n",
"if not os.path.exists(data_file):\n",
" urllib.request.urlretrieve(file_path, data_file_co2)\n",
"\n",
"data_co2 = pd.read_csv(file_path, skiprows=44, sep=r'\\s+', engine='python', parse_dates=[0], index_col=[0])\n",
"\n",
"# Verificar los primeros registros de datos\n",
"print(data_co2.head())"
]
},
{
"cell_type": "markdown",
"metadata": {},
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment