Import Data

$$ Execute the cell below to load the Titanic data from Seaborn and reduce it to the meaningful variables

$$ For this analysis, the survived variable will be used as the target variable, while the rest of the variables are the input features.

$$ The goal is to predict whether a passenger survived $($survived $=1)$ or died $($survived $=0)$ the Titanic sinking

In a Markdown cell, identify the categorical and numerical features

$$ Examine the possible values each feature can assume

$$ Hint: survived is the Target. There will be four of each type.

Partition Data into Training and Testing sets

$$ Stratify on the target variable to maintain the imbalance in the data sets

$$ Extract $20\%$ for testing

$$ Print the dimensions of the Training and Testing Data sets

$$ Hint: Split into two DataFrames with the target present:

$$ The output should be df$\_$train, df$\_$test

Using the Training Data, calculate the following:

Calculate and show $()()$

$$ The probability of each target label

Calculate and show $(|)(|)$ for each of the categorical features in the Training Data

identify and show the means and standard deviations of the Continuous features

The probability of observing any value is assumed to the Normal Distribution:

$(|)=(,)(|)=(,)$ given the target label

where $$ and $$ are calculated from each feature $$ and target label $$

Construct a prediction function

This data set is of mixed types $($Categorical and Continuous$),$ so built$-$in functionality cannot work.

Recall, you are calculating:

$(|())=$argmax$$ in $\{0,1\}[()(()|)](|())=$argmax$$ in $\{0,1\}[()(()|)]$

Where yk$=0=$Died and yk$=1=$Survived

Your function should calculate the above expression for k$=0$ and k$=1,$ and return both predictions for each instance considered.

Using your function, calculate the predictions from the Training data

Then, calculate the confusion matrix and accuracy score

Using your function, calculate the predictions from the Test data

Then, calculate the confusion matrix and accuracy score