|
|
@@ -186,7 +186,7 @@
|
|
|
"source": [
|
|
|
"# %load functions.py\n",
|
|
|
"def process_missing(df):\n",
|
|
|
- " \"\"\"Handle various missing values from the data set\n",
|
|
|
+ " \"\"\"Handle various missing values from the dataset\n",
|
|
|
"\n",
|
|
|
" Usage\n",
|
|
|
" ------\n",
|
|
|
@@ -439,11 +439,11 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "The `SibSp` column shows the number of siblings and/or spouses each passenger had on board, while the `Parch` columns shows the number of parents or children each passenger had onboard. Neither column has any missing values.\n",
|
|
|
+ "The `SibSp` column shows the number of siblings and/or spouses each passenger had on board, while the `Parch` column shows the number of parents or children each passenger had onboard. Neither column has any missing values.\n",
|
|
|
"\n",
|
|
|
"The distribution of values in both columns is skewed right, with the majority of values being zero.\n",
|
|
|
"\n",
|
|
|
- "You can sum these two columns to explore the total number of family members each passenger had onboard. The shape of the distribution of values in this case is similar, however there are less values at zero, and the quantity tapers off less rapidly as the values increase.\n",
|
|
|
+ "You can sum these two columns to explore the total number of family members each passenger had onboard. The shape of the distribution of values in this case is similar; however, there are fewer values at zero, and the quantity tapers off less rapidly as the values increase.\n",
|
|
|
"\n",
|
|
|
"Looking at the survival rates of the the combined family members, you can see that few of the over 500 passengers with no family members survived, while greater numbers of passengers with family members survived."
|
|
|
]
|
|
|
@@ -686,7 +686,7 @@
|
|
|
" all_y = df[\"Survived\"]\n",
|
|
|
"\n",
|
|
|
" # List of dictionaries, each containing a model name,\n",
|
|
|
- " # it's estimator and a dict of hyperparameters\n",
|
|
|
+ " # its estimator and a dict of hyperparameters\n",
|
|
|
" models = [\n",
|
|
|
" {\n",
|
|
|
" \"name\": \"LogisticRegression\",\n",
|
|
|
@@ -788,7 +788,7 @@
|
|
|
"name": "python",
|
|
|
"nbconvert_exporter": "python",
|
|
|
"pygments_lexer": "ipython3",
|
|
|
- "version": "3.8.2"
|
|
|
+ "version": "3.8.5"
|
|
|
}
|
|
|
},
|
|
|
"nbformat": 4,
|
darinbradley