mirror of
https://github.com/gsi-upm/sitc
synced 2024-11-05 15:31:42 +00:00
Fixed bug in substrings_in_string and set default df[AgeGroup] to np.nan
This commit is contained in:
cif2cif
parent
44aa3d24fb
commit
161cd8492b
@ -46,7 +46,7 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 11,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -209,12 +209,315 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 20,
|
||||||
"metadata": {},
|
"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>PassengerId</th>\n",
|
||||||
|
" <th>Survived</th>\n",
|
||||||
|
" <th>Pclass</th>\n",
|
||||||
|
" <th>Name</th>\n",
|
||||||
|
" <th>Sex</th>\n",
|
||||||
|
" <th>Age</th>\n",
|
||||||
|
" <th>SibSp</th>\n",
|
||||||
|
" <th>Parch</th>\n",
|
||||||
|
" <th>Ticket</th>\n",
|
||||||
|
" <th>Fare</th>\n",
|
||||||
|
" <th>Cabin</th>\n",
|
||||||
|
" <th>Embarked</th>\n",
|
||||||
|
" <th>FamilySize</th>\n",
|
||||||
|
" <th>AgeGroup</th>\n",
|
||||||
|
" <th>Deck</th>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" </thead>\n",
|
||||||
|
" <tbody>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>0</th>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>Braund, Mr. Owen Harris</td>\n",
|
||||||
|
" <td>male</td>\n",
|
||||||
|
" <td>22.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>A/5 21171</td>\n",
|
||||||
|
" <td>7.2500</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>X</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>1</th>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
|
||||||
|
" <td>female</td>\n",
|
||||||
|
" <td>38.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>PC 17599</td>\n",
|
||||||
|
" <td>71.2833</td>\n",
|
||||||
|
" <td>C85</td>\n",
|
||||||
|
" <td>C</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>C</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>2</th>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>Heikkinen, Miss. Laina</td>\n",
|
||||||
|
" <td>female</td>\n",
|
||||||
|
" <td>26.0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>STON/O2. 3101282</td>\n",
|
||||||
|
" <td>7.9250</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>X</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>3</th>\n",
|
||||||
|
" <td>4</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
|
||||||
|
" <td>female</td>\n",
|
||||||
|
" <td>35.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>113803</td>\n",
|
||||||
|
" <td>53.1000</td>\n",
|
||||||
|
" <td>C123</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>C</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>4</th>\n",
|
||||||
|
" <td>5</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>Allen, Mr. William Henry</td>\n",
|
||||||
|
" <td>male</td>\n",
|
||||||
|
" <td>35.0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>373450</td>\n",
|
||||||
|
" <td>8.0500</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>X</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",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>886</th>\n",
|
||||||
|
" <td>887</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" <td>Montvila, Rev. Juozas</td>\n",
|
||||||
|
" <td>male</td>\n",
|
||||||
|
" <td>27.0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>211536</td>\n",
|
||||||
|
" <td>13.0000</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>X</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>887</th>\n",
|
||||||
|
" <td>888</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>Graham, Miss. Margaret Edith</td>\n",
|
||||||
|
" <td>female</td>\n",
|
||||||
|
" <td>19.0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>112053</td>\n",
|
||||||
|
" <td>30.0000</td>\n",
|
||||||
|
" <td>B42</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>B</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>888</th>\n",
|
||||||
|
" <td>889</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
|
||||||
|
" <td>female</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" <td>W./C. 6607</td>\n",
|
||||||
|
" <td>23.4500</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>S</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>X</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>889</th>\n",
|
||||||
|
" <td>890</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>Behr, Mr. Karl Howell</td>\n",
|
||||||
|
" <td>male</td>\n",
|
||||||
|
" <td>26.0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>111369</td>\n",
|
||||||
|
" <td>30.0000</td>\n",
|
||||||
|
" <td>C148</td>\n",
|
||||||
|
" <td>C</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>C</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>890</th>\n",
|
||||||
|
" <td>891</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>Dooley, Mr. Patrick</td>\n",
|
||||||
|
" <td>male</td>\n",
|
||||||
|
" <td>32.0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>370376</td>\n",
|
||||||
|
" <td>7.7500</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>Q</td>\n",
|
||||||
|
" <td>0</td>\n",
|
||||||
|
" <td>3.0</td>\n",
|
||||||
|
" <td>X</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" </tbody>\n",
|
||||||
|
"</table>\n",
|
||||||
|
"<p>891 rows × 15 columns</p>\n",
|
||||||
|
"</div>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
" PassengerId Survived Pclass \\\n",
|
||||||
|
"0 1 0 3 \n",
|
||||||
|
"1 2 1 1 \n",
|
||||||
|
"2 3 1 3 \n",
|
||||||
|
"3 4 1 1 \n",
|
||||||
|
"4 5 0 3 \n",
|
||||||
|
".. ... ... ... \n",
|
||||||
|
"886 887 0 2 \n",
|
||||||
|
"887 888 1 1 \n",
|
||||||
|
"888 889 0 3 \n",
|
||||||
|
"889 890 1 1 \n",
|
||||||
|
"890 891 0 3 \n",
|
||||||
|
"\n",
|
||||||
|
" Name Sex Age SibSp \\\n",
|
||||||
|
"0 Braund, Mr. Owen Harris male 22.0 1 \n",
|
||||||
|
"1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n",
|
||||||
|
"2 Heikkinen, Miss. Laina female 26.0 0 \n",
|
||||||
|
"3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n",
|
||||||
|
"4 Allen, Mr. William Henry male 35.0 0 \n",
|
||||||
|
".. ... ... ... ... \n",
|
||||||
|
"886 Montvila, Rev. Juozas male 27.0 0 \n",
|
||||||
|
"887 Graham, Miss. Margaret Edith female 19.0 0 \n",
|
||||||
|
"888 Johnston, Miss. Catherine Helen \"Carrie\" female NaN 1 \n",
|
||||||
|
"889 Behr, Mr. Karl Howell male 26.0 0 \n",
|
||||||
|
"890 Dooley, Mr. Patrick male 32.0 0 \n",
|
||||||
|
"\n",
|
||||||
|
" Parch Ticket Fare Cabin Embarked FamilySize AgeGroup \\\n",
|
||||||
|
"0 0 A/5 21171 7.2500 NaN S 1 3.0 \n",
|
||||||
|
"1 0 PC 17599 71.2833 C85 C 1 3.0 \n",
|
||||||
|
"2 0 STON/O2. 3101282 7.9250 NaN S 0 3.0 \n",
|
||||||
|
"3 0 113803 53.1000 C123 S 1 3.0 \n",
|
||||||
|
"4 0 373450 8.0500 NaN S 0 3.0 \n",
|
||||||
|
".. ... ... ... ... ... ... ... \n",
|
||||||
|
"886 0 211536 13.0000 NaN S 0 3.0 \n",
|
||||||
|
"887 0 112053 30.0000 B42 S 0 3.0 \n",
|
||||||
|
"888 2 W./C. 6607 23.4500 NaN S 3 NaN \n",
|
||||||
|
"889 0 111369 30.0000 C148 C 0 3.0 \n",
|
||||||
|
"890 0 370376 7.7500 NaN Q 0 3.0 \n",
|
||||||
|
"\n",
|
||||||
|
" Deck \n",
|
||||||
|
"0 X \n",
|
||||||
|
"1 C \n",
|
||||||
|
"2 X \n",
|
||||||
|
"3 C \n",
|
||||||
|
"4 X \n",
|
||||||
|
".. ... \n",
|
||||||
|
"886 X \n",
|
||||||
|
"887 B \n",
|
||||||
|
"888 X \n",
|
||||||
|
"889 C \n",
|
||||||
|
"890 X \n",
|
||||||
|
"\n",
|
||||||
|
"[891 rows x 15 columns]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 20,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
"source": [
|
"source": [
|
||||||
"df['FamilySize'] = df['SibSp'] + df['Parch']\n",
|
"df['FamilySize'] = df['SibSp'] + df['Parch']\n",
|
||||||
"df.head()"
|
"df"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -303,9 +606,31 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 8,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [
|
||||||
|
{
|
||||||
|
"ename": "KeyError",
|
||||||
|
"evalue": "'Salutation'",
|
||||||
|
"output_type": "error",
|
||||||
|
"traceback": [
|
||||||
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||||
|
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
|
||||||
|
"\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m 3079\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3080\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\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 3081\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||||||
|
"\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
|
||||||
|
"\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
|
||||||
|
"\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
|
||||||
|
"\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
|
||||||
|
"\u001b[0;31mKeyError\u001b[0m: 'Salutation'",
|
||||||
|
"\nThe above exception was the direct cause of the following exception:\n",
|
||||||
|
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
|
||||||
|
"\u001b[0;32m<ipython-input-8-515fd9f54fd1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Others'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Salutation'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Salutation'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgroup_salutation\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 16\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Salutation'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\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[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 3022\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnlevels\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3023\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3024\u001b[0;31m \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\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 3025\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\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[1;32m 3026\u001b[0m \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||||||
|
"\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m 3080\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3081\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3082\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3083\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3084\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtolerance\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\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[0;31mKeyError\u001b[0m: 'Salutation'"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
"source": [
|
"source": [
|
||||||
"def group_salutation(old_salutation):\n",
|
"def group_salutation(old_salutation):\n",
|
||||||
" if old_salutation == 'Mr':\n",
|
" if old_salutation == 'Mr':\n",
|
||||||
@ -372,13 +697,13 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 12,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"# Group ages to simplify machine learning algorithms. 0: 0-5, 1: 6-10, 2: 11-15, 3: 16-59 and 4: 60-80\n",
|
"# Group ages to simplify machine learning algorithms. 0: 0-5, 1: 6-10, 2: 11-15, 3: 16-59 and 4: 60-80\n",
|
||||||
"df['AgeGroup'] = 0\n",
|
"df['AgeGroup'] = np.nan\n",
|
||||||
"df.loc[(.Age<6),'AgeGroup'] = 0\n",
|
"df.loc[(df.Age<6),'AgeGroup'] = 0\n",
|
||||||
"df.loc[(df.Age>=6) & (df.Age < 11),'AgeGroup'] = 1\n",
|
"df.loc[(df.Age>=6) & (df.Age < 11),'AgeGroup'] = 1\n",
|
||||||
"df.loc[(df.Age>=11) & (df.Age < 16),'AgeGroup'] = 2\n",
|
"df.loc[(df.Age>=11) & (df.Age < 16),'AgeGroup'] = 2\n",
|
||||||
"df.loc[(df.Age>=16) & (df.Age < 60),'AgeGroup'] = 3\n",
|
"df.loc[(df.Age>=16) & (df.Age < 60),'AgeGroup'] = 3\n",
|
||||||
@ -395,7 +720,7 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 14,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -404,8 +729,8 @@
|
|||||||
" if np.isnan(big_string):\n",
|
" if np.isnan(big_string):\n",
|
||||||
" return 'X'\n",
|
" return 'X'\n",
|
||||||
" for substring in substrings:\n",
|
" for substring in substrings:\n",
|
||||||
" if big_string.find(substring) != 1:\n",
|
" if substring in big_string:\n",
|
||||||
" return substring\n",
|
" return substring[0::]\n",
|
||||||
" print(big_string)\n",
|
" print(big_string)\n",
|
||||||
" return 'X'\n",
|
" return 'X'\n",
|
||||||
" \n",
|
" \n",
|
||||||
@ -478,6 +803,15 @@
|
|||||||
}
|
}
|
||||||
],
|
],
|
||||||
"metadata": {
|
"metadata": {
|
||||||
|
"datacleaner": {
|
||||||
|
"position": {
|
||||||
|
"top": "50px"
|
||||||
|
},
|
||||||
|
"python": {
|
||||||
|
"varRefreshCmd": "try:\n print(_datacleaner.dataframe_metadata())\nexcept:\n print([])"
|
||||||
|
},
|
||||||
|
"window_display": false
|
||||||
|
},
|
||||||
"kernelspec": {
|
"kernelspec": {
|
||||||
"display_name": "Python 3",
|
"display_name": "Python 3",
|
||||||
"language": "python",
|
"language": "python",
|
||||||
@ -493,7 +827,7 @@
|
|||||||
"name": "python",
|
"name": "python",
|
||||||
"nbconvert_exporter": "python",
|
"nbconvert_exporter": "python",
|
||||||
"pygments_lexer": "ipython3",
|
"pygments_lexer": "ipython3",
|
||||||
"version": "3.7.1"
|
"version": "3.7.9"
|
||||||
},
|
},
|
||||||
"latex_envs": {
|
"latex_envs": {
|
||||||
"LaTeX_envs_menu_present": true,
|
"LaTeX_envs_menu_present": true,
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user