diff --git a/HospitalCancerClassification.ipynb b/HospitalCancerClassification.ipynb
index b32dbeb..cc15719 100644
--- a/HospitalCancerClassification.ipynb
+++ b/HospitalCancerClassification.ipynb
@@ -50,7 +50,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 3,
"id": "3a05014a-200c-4bc6-9667-568898547852",
"metadata": {},
"outputs": [],
@@ -71,7 +71,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 4,
"id": "10d93e7f-9ba8-45a4-831d-7ba48046fea7",
"metadata": {},
"outputs": [
@@ -81,7 +81,7 @@
"np.int64(10)"
]
},
- "execution_count": 3,
+ "execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -95,7 +95,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 5,
"id": "3434f6bb-7cdb-4434-a948-1dc7d9e7d260",
"metadata": {},
"outputs": [
@@ -105,7 +105,7 @@
"np.int64(0)"
]
},
- "execution_count": 4,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -127,7 +127,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 6,
"id": "a8887198-0dbd-471d-bd1e-836d34def83a",
"metadata": {},
"outputs": [
@@ -195,7 +195,7 @@
"4 60 55-64"
]
},
- "execution_count": 5,
+ "execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
@@ -224,7 +224,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 7,
"id": "f9beff06-ce08-479d-b63d-56ca8aaf6338",
"metadata": {},
"outputs": [
@@ -310,7 +310,7 @@
"max 1.735732e+00 1.772241e+00"
]
},
- "execution_count": 6,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -342,7 +342,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 8,
"id": "8bc14115-e855-4233-9058-eff0ce5c9386",
"metadata": {},
"outputs": [
@@ -542,7 +542,7 @@
"4 60 no none -1.446316 0.649743 212.8 yes 5 moderate False False False False True False False False True False False False False False True"
]
},
- "execution_count": 7,
+ "execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -568,7 +568,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 9,
"id": "a5174be9-c40b-457e-afd5-1ec97c70ed0a",
"metadata": {
"scrolled": true
@@ -580,7 +580,7 @@
"((693, 23), (148, 23), (149, 23))"
]
},
- "execution_count": 8,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -621,7 +621,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 10,
"id": "c94e2161-e95d-4a84-864d-bc1388bd4d48",
"metadata": {},
"outputs": [
@@ -631,13 +631,12 @@
"(693, 21)"
]
},
- "execution_count": 9,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "\n",
"# Drop two unnecessary features/columns that aren't relevant to cancer risk evaluation and wouldn't affect if someone would be likely to have cancer.\n",
"X_train = X_train.drop(['travelled_overseas', 'number_of_children'], axis=1)\n",
"X_val = X_val.drop(['travelled_overseas', 'number_of_children'], axis=1)\n",
@@ -646,6 +645,1382 @@
"# Print the results to allow the user to determine the changes have worked\n",
"X_train.shape\n"
]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "49174e92-2e15-461a-844f-ffa90c0d7c99",
+ "metadata": {},
+ "source": [
+ "# Part 3: Train and evaluate ML model - Task 1: Train ML model 1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "b95cb28a-5312-4f55-8485-61c4e95e782e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Select an appropriate initial model size by setting the number of layers and neurons.\n",
+ "\n",
+ "\n",
+ "from sklearn.neural_network import MLPClassifier\n",
+ "\n",
+ "mlp_model_1 = MLPClassifier(\n",
+ " hidden_layer_sizes=(64, 32),\n",
+ " activation='relu',\n",
+ " solver='adam',\n",
+ " max_iter=300,\n",
+ " random_state=42\n",
+ ")\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "9a44bcdd-8605-4e21-9a7a-1a3296f46909",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "age int64\n",
+ "family_history str\n",
+ "alcohol_consumption str\n",
+ "bmi float64\n",
+ "blood_pressure float64\n",
+ "cholesterol_level float64\n",
+ "age_group_15-24 bool\n",
+ "age_group_25-34 bool\n",
+ "age_group_35-44 bool\n",
+ "age_group_45-54 bool\n",
+ "age_group_55-64 bool\n",
+ "age_group_65-74 bool\n",
+ "age_group_75-84 bool\n",
+ "age_group_85+ bool\n",
+ "smoking_history_former bool\n",
+ "smoking_history_never bool\n",
+ "diet_good bool\n",
+ "diet_poor bool\n",
+ "exercise_frequency_low bool\n",
+ "exercise_frequency_moderate bool\n",
+ "exercise_frequency_none bool\n",
+ "dtype: object"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# BUG FIXING: List any non numerical rows\n",
+ "X_train.dtypes"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "f16e2e40-e065-44ca-b944-e9a2921d89db",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/tmp/ipykernel_82/146862157.py:2: Pandas4Warning: For backward compatibility, 'str' dtypes are included by select_dtypes when 'object' dtype is specified. This behavior is deprecated and will be removed in a future version. Explicitly pass 'str' to `include` to select them, or to `exclude` to remove them and silence this warning.\n",
+ "See https://pandas.pydata.org/docs/user_guide/migration-3-strings.html#string-migration-select-dtypes for details on how to write code that works with pandas 2 and 3.\n",
+ " X_train.select_dtypes(include=['object']).head()\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " family_history \n",
+ " alcohol_consumption \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 494 \n",
+ " yes \n",
+ " none \n",
+ " \n",
+ " \n",
+ " 379 \n",
+ " yes \n",
+ " high \n",
+ " \n",
+ " \n",
+ " 220 \n",
+ " yes \n",
+ " none \n",
+ " \n",
+ " \n",
+ " 732 \n",
+ " yes \n",
+ " high \n",
+ " \n",
+ " \n",
+ " 869 \n",
+ " no \n",
+ " low \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " family_history alcohol_consumption\n",
+ "494 yes none\n",
+ "379 yes high\n",
+ "220 yes none\n",
+ "732 yes high\n",
+ "869 no low"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# BUG FIXING: Check if the text value exists\n",
+ "X_train.select_dtypes(include=['object']).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "f62a9503-664a-43d9-9afa-0029695acce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# BUG FIXING - Rayyan Hodges\n",
+ "\n",
+ "# Force all non-numeric columns to be one-hot encoded\n",
+ "X_train = pd.get_dummies(X_train)\n",
+ "X_val = pd.get_dummies(X_val)\n",
+ "X_test = pd.get_dummies(X_test)\n",
+ "\n",
+ "# Align columns so they match exactly\n",
+ "X_train, X_val = X_train.align(X_val, join=\"left\", axis=1, fill_value=0)\n",
+ "X_train, X_test = X_train.align(X_test, join=\"left\", axis=1, fill_value=0)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "cfcddd52-1a78-4c07-8f5d-036682a8cad6",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42) In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org. \n",
+ "
\n",
+ "
\n",
+ " Parameters \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " hidden_layer_sizes\n",
+ " hidden_layer_sizes: array-like of shape(n_layers - 2,), default=(100,) The ith element represents the number of neurons in the ith hidden layer. \n",
+ " \n",
+ " \n",
+ " (64, ...) \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " activation\n",
+ " activation: {'identity', 'logistic', 'tanh', 'relu'}, default='relu' Activation function for the hidden layer. - 'identity', no-op activation, useful to implement linear bottleneck, returns f(x) = x - 'logistic', the logistic sigmoid function, returns f(x) = 1 / (1 + exp(-x)). - 'tanh', the hyperbolic tan function, returns f(x) = tanh(x). - 'relu', the rectified linear unit function, returns f(x) = max(0, x) \n",
+ " \n",
+ " \n",
+ " 'relu' \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " solver\n",
+ " solver: {'lbfgs', 'sgd', 'adam'}, default='adam' The solver for weight optimization. - 'lbfgs' is an optimizer in the family of quasi-Newton methods. - 'sgd' refers to stochastic gradient descent. - 'adam' refers to a stochastic gradient-based optimizer proposed by Kingma, Diederik, and Jimmy Ba For a comparison between Adam optimizer and SGD, see :ref:`sphx_glr_auto_examples_neural_networks_plot_mlp_training_curves.py`. Note: The default solver 'adam' works pretty well on relatively large datasets (with thousands of training samples or more) in terms of both training time and validation score. For small datasets, however, 'lbfgs' can converge faster and perform better. \n",
+ " \n",
+ " \n",
+ " 'adam' \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " alpha\n",
+ " alpha: float, default=0.0001 Strength of the L2 regularization term. The L2 regularization term is divided by the sample size when added to the loss. For an example usage and visualization of varying regularization, see :ref:`sphx_glr_auto_examples_neural_networks_plot_mlp_alpha.py`. \n",
+ " \n",
+ " \n",
+ " 0.0001 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " batch_size\n",
+ " batch_size: int, default='auto' Size of minibatches for stochastic optimizers. If the solver is 'lbfgs', the classifier will not use minibatch. When set to \"auto\", `batch_size=min(200, n_samples)`. \n",
+ " \n",
+ " \n",
+ " 'auto' \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " learning_rate\n",
+ " learning_rate: {'constant', 'invscaling', 'adaptive'}, default='constant' Learning rate schedule for weight updates. - 'constant' is a constant learning rate given by 'learning_rate_init'. - 'invscaling' gradually decreases the learning rate at each time step 't' using an inverse scaling exponent of 'power_t'. effective_learning_rate = learning_rate_init / pow(t, power_t) - 'adaptive' keeps the learning rate constant to 'learning_rate_init' as long as training loss keeps decreasing. Each time two consecutive epochs fail to decrease training loss by at least tol, or fail to increase validation score by at least tol if 'early_stopping' is on, the current learning rate is divided by 5. Only used when ``solver='sgd'``. \n",
+ " \n",
+ " \n",
+ " 'constant' \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " learning_rate_init\n",
+ " learning_rate_init: float, default=0.001 The initial learning rate used. It controls the step-size in updating the weights. Only used when solver='sgd' or 'adam'. \n",
+ " \n",
+ " \n",
+ " 0.001 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " power_t\n",
+ " power_t: float, default=0.5 The exponent for inverse scaling learning rate. It is used in updating effective learning rate when the learning_rate is set to 'invscaling'. Only used when solver='sgd'. \n",
+ " \n",
+ " \n",
+ " 0.5 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " max_iter\n",
+ " max_iter: int, default=200 Maximum number of iterations. The solver iterates until convergence (determined by 'tol') or this number of iterations. For stochastic solvers ('sgd', 'adam'), note that this determines the number of epochs (how many times each data point will be used), not the number of gradient steps. \n",
+ " \n",
+ " \n",
+ " 300 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " shuffle\n",
+ " shuffle: bool, default=True Whether to shuffle samples in each iteration. Only used when solver='sgd' or 'adam'. \n",
+ " \n",
+ " \n",
+ " True \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " random_state\n",
+ " random_state: int, RandomState instance, default=None Determines random number generation for weights and bias initialization, train-test split if early stopping is used, and batch sampling when solver='sgd' or 'adam'. Pass an int for reproducible results across multiple function calls. See :term:`Glossary `. \n",
+ " \n",
+ " \n",
+ " 42 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " tol\n",
+ " tol: float, default=1e-4 Tolerance for the optimization. When the loss or score is not improving by at least ``tol`` for ``n_iter_no_change`` consecutive iterations, unless ``learning_rate`` is set to 'adaptive', convergence is considered to be reached and training stops. \n",
+ " \n",
+ " \n",
+ " 0.0001 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " verbose\n",
+ " verbose: bool, default=False Whether to print progress messages to stdout. \n",
+ " \n",
+ " \n",
+ " False \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " warm_start\n",
+ " warm_start: bool, default=False When set to True, reuse the solution of the previous call to fit as initialization, otherwise, just erase the previous solution. See :term:`the Glossary `. \n",
+ " \n",
+ " \n",
+ " False \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " momentum\n",
+ " momentum: float, default=0.9 Momentum for gradient descent update. Should be between 0 and 1. Only used when solver='sgd'. \n",
+ " \n",
+ " \n",
+ " 0.9 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " nesterovs_momentum\n",
+ " nesterovs_momentum: bool, default=True Whether to use Nesterov's momentum. Only used when solver='sgd' and momentum > 0. \n",
+ " \n",
+ " \n",
+ " True \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " early_stopping\n",
+ " early_stopping: bool, default=False Whether to use early stopping to terminate training when validation score is not improving. If set to True, it will automatically set aside ``validation_fraction`` of training data as validation and terminate training when validation score is not improving by at least ``tol`` for ``n_iter_no_change`` consecutive epochs. The split is stratified, except in a multilabel setting. If early stopping is False, then the training stops when the training loss does not improve by more than ``tol`` for ``n_iter_no_change`` consecutive passes over the training set. Only effective when solver='sgd' or 'adam'. \n",
+ " \n",
+ " \n",
+ " False \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " validation_fraction\n",
+ " validation_fraction: float, default=0.1 The proportion of training data to set aside as validation set for early stopping. Must be between 0 and 1. Only used if early_stopping is True. \n",
+ " \n",
+ " \n",
+ " 0.1 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " beta_1\n",
+ " beta_1: float, default=0.9 Exponential decay rate for estimates of first moment vector in adam, should be in [0, 1). Only used when solver='adam'. \n",
+ " \n",
+ " \n",
+ " 0.9 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " beta_2\n",
+ " beta_2: float, default=0.999 Exponential decay rate for estimates of second moment vector in adam, should be in [0, 1). Only used when solver='adam'. \n",
+ " \n",
+ " \n",
+ " 0.999 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " epsilon\n",
+ " epsilon: float, default=1e-8 Value for numerical stability in adam. Only used when solver='adam'. \n",
+ " \n",
+ " \n",
+ " 1e-08 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " n_iter_no_change\n",
+ " n_iter_no_change: int, default=10 Maximum number of epochs to not meet ``tol`` improvement. Only effective when solver='sgd' or 'adam'. .. versionadded:: 0.20 \n",
+ " \n",
+ " \n",
+ " 10 \n",
+ " \n",
+ " \n",
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " max_fun\n",
+ " max_fun: int, default=15000 Only used when solver='lbfgs'. Maximum number of loss function calls. The solver iterates until convergence (determined by 'tol'), number of iterations reaches max_iter, or this number of loss function calls. Note that number of loss function calls will be greater than or equal to the number of iterations for the `MLPClassifier`. .. versionadded:: 0.22 \n",
+ " \n",
+ " \n",
+ " 15000 \n",
+ " \n",
+ " \n",
+ " \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ "MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42)"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Train model 1 on generated data\n",
+ "mlp_model_1.fit(X_train, y_train)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "600e90f1-fc12-4300-ab60-76b4656bf5d8",
+ "metadata": {},
+ "source": [
+ "# Run the validation data through the ML model."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "4d08a5ac-93cf-4da5-a266-7052ea31ac6a",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array(['low', 'high', 'high', 'moderate', 'low', 'high', 'high', 'high',\n",
+ " 'low', 'low'], dtype='